Subset (3)

conversational · 12.5k rows

Split (3)

train · 10.1k rows

id stringlengths 1 5	prompt listlengths 1 1	completion listlengths 1 1	Label stringclasses 3 values
1171	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Sleep quality in mechanically ventilated patients: comparison between NAVA and PSV modes\n\n ABSTRACT.BACKGROUND:\nMechanical ventilation seems to occupy a major source in alteration in the quality and quantity of sleep among patients in intensive care. Quality of sleep is negatively affected with frequent patient-ventilator asynchronies and more specifically with modes of ventilation. The quality of sleep among ventilated patients seems to be related in part to the alteration between the capacities of the ventilator to meet patient demand. The objective of this study was to compare the impact of two modes of ventilation and patient-ventilator interaction on sleep architecture.\n\nABSTRACT.METHODS:\nProspective, comparative crossover study in 14 conscious, nonsedated, mechanically ventilated adults, during weaning in a university hospital medical intensive care unit. Patients were successively ventilated in a random ordered cross-over sequence with neurally adjusted ventilatory assist (NAVA) and pressure support ventilation (PSV). Sleep polysomnography was performed during four 4-hour periods, two with each mode in random order.\n\nABSTRACT.RESULTS:\nThe tracings of the flow, airway pressure, and electrical activity of the diaphragm were used to diagnose central apneas and ineffective efforts. The main abnormalities were a low percentage of rapid eye movement (REM) sleep, for a median (25th-75th percentiles) of 11.5% (range, 8-20%) of total sleep, and a highly fragmented sleep with 25 arousals and awakenings per hour of sleep. Proportions of REM sleep duration were different in the two ventilatory modes (4.5% (range, 3-11%) in PSV and 16.5% (range, 13-29%) during NAVA (p = 0.001)), as well as the fragmentation index, with 40 ± 20 arousals and awakenings per hour in PSV and 16 ± 9 during NAVA (p = 0.001). There were large differences in ineffective efforts (24 ± 23 per hour of sleep in PSV, and 0 during NAVA) and episodes of central apnea (10.5 ± 11 in PSV vs. 0 during NAVA). Minute ventilation was similar in both modes.\n\nABSTRACT.CONCLUSIONS:\nNAVA improves the quality of sleep over PSV in terms of REM sleep, fragmentation index, and ineffective efforts in a nonsedated adult population.\n\nBODY.BACKGROUND:\nSleep is severely disturbed in mechanically ventilated ICU patients [1-3]. Sleep alterations are known to have deleterious consequences in healthy subjects, but the paucity of data in the literature [4-7] makes it difficult to determine the impact of sleep abnormalities in ICU patients. Intensive care unit (ICU) patients present disrupted sleep with reduced sleep efficiency and a decrease in slow wave sleep and rapid eye movement (REM) sleep [8-10]. Furthermore, polysomnographic studies performed on mechanically ventilated ICU patients have demonstrated an increase in sleep fragmentation, a reduction in slow-wave and REM sleep, and an abnormal distribution of sleep, because almost half of the total sleep time occurred during the daytime [11-13]. In the Freedman et al. study [14], noise was considered a nuisance for the patients questioned; the most annoying noises were alarms and caregivers' conversations. When the same authors simultaneously recorded noise and microarousal, they identified an association between arousal and noise in only 11-17% of the cases [11]. This percentage is confirmed by Gabor et al. [3] where 21% of the arousal interruptions were explained by loud noises and 7% to patients' care. Seventy-eight percent of the microarousals were not associated with environment noises, suggesting other causes, such as patient/ventilator asynchrony [3,14]. The effects of assist control ventilation (ACV) and pressure support ventilation (PSV) on sleep fragmentation have been examined in critically ill patients receiving mechanical ventilation [15], where PSV mode was associated with increases in the number of central apneas and subsequent sleep fragmentation compared with AVC. Furthermore, the study suggested that PSV by itself or an excess of ventilator assistance with PSV could have caused such sleep alterations. Indeed, ventilatory settings adjusted during wakefulness may become excessive during sleep, as the patients' ventilatory demand is reduced while asleep [16]. Whether these results can be explained by the ventilatory mode itself or how it was adjusted is an important issue, because hyperventilation and patient ventilator asynchrony may result from PSV as well as ACV in mechanically ventilated ICU patients [17]. Fanfulla et al. [18] compared two ventilatory settings in nine patients under long-term PSV for neuromuscular disease. The initial setting was set according to clinical parameters, and the second setting was adjusted with measurement of esophageal pressure (physiological setting) to optimize patient effort. The physiological setting improved the duration and quality of sleep, decreased episodes of apnea, and the amount of inefficient efforts for ventilator triggering [18]. The level of pressure support and PEEP tended to decrease, with a lowering of intrinsic PEEP and patient-ventilator asynchronies. A recent study by Cabello et al. [19] compared the impact of three modes of ventilation (AVC, PSV, and SmartCareTM) on the quality of sleep in alert and nonsedated patients, and no difference for the architecture, fragmentation, and duration of sleep was found among the three modes. Our hypothesis is that NAVA ventilation is superior to PSV by allowing optimal patient-ventilator synchrony and thereby decreasing sleep fragmentation.\n\nBODY.METHODS:\nThis study was approved by the Ethics Committee of the Hôpital du Sacré-Coeur de Montréal, and patients or their surrogates gave written informed consent.\n\nBODY.METHODS.PATIENTS:\nThis physiologic study was conducted in a 22-bed medical ICU during a 12-month period. The weaning phase of mechanical ventilation was chosen because patient-ventilator asynchrony is common when patients are spontaneously triggering breaths. The inclusion criteria required that the patient was conscious, free from sedation and opiate analgesia for ≥ 24 hours, and ventilated in PSV mode with an FIO2 < 60%, PEEP = 5 cmH2O, and SpO2 ≥ 90%. Exclusion criteria consisted of the presence of a central nervous system disorder, Glasgow Coma Scale score < 11, hemodynamic instability, renal and/or hepatic insufficiency, and ongoing sepsis.\n\nBODY.METHODS.METHODS:\nAll patients were ventilated through an endotracheal tube or a tracheostomy; once they met the inclusion criteria, they were connected to a Servo i ventilator (Maquet critical Care, Sölna, Sweden), equipped with a neurally adjusted ventilator assist system (NAVA). The electrical activity of the diaphragm (EAdi) is captured with the EAdi catheter (Maquet Critical Care, Sölna, Sweden) consisting of a 16-Fr gastric tube equipped with electrodes. End-tidal CO2 was monitored with the Servo-i Volumetric CO2 module. The two different ventilatory modes were delivered in a randomized order using a closed-envelope technique during four periods of 4 hours: a daytime period from 7 to 11 a.m. and 12 to 4 p.m., and a nocturnal period from 10 p.m. to 2 a.m. and 3 to 7 a.m. To prevent possible data contamination from the previous mode of ventilation, a 1-hour washout period after a ventilator change was introduced before data acquisition (Figure 1; Study Protocol). Figure 1Patients were studied for a period of 4 hours for each recording sequences and for more than 19 consecutive hours. During periods of wakefulness, PSV and NAVA were clinically adjusted by the attending physician to obtain a tidal volume of 8 mL/kg of predicted body weight and a respiratory rate ≤ 35 breaths/min. For both modes of ventilation, inspiratory triggering sensitivity was set at thresholds that would not allow auto-triggering for both modes of ventilation: 0.5 mV in NAVA and 5 in PSV. EEG was recorded from standard locations: left frontal/right mastoïd reference (F3/M2 or F3/A2), right frontal/left mastoid reference (F4/M1or F4/A1), left central/right mastoïd reference (C3/M2 or C3/A2), right central/left mastoïd reference (C4/M1 or C4/A1), left occipital/right mastoïd reference (O1/M2 or O1/A2), and right occipital/left mastoïd reference (O2/M1or O2/A1), according to the International 10-20 System for electrode placement [20]. The standard reference used was the left mastoid lead [20]. Two electro-oculogram and three chin electromyogram leads were used to score REM and non-REM sleep. The electroencephalogram, the right and left electro-oculogram, and the submental electromyogram signals were amplified and recorded in the data acquisition system (Alice 5 polysomnography system using Alice® SleepwareTM 2.5 software, Respironics, Nantes, France). Sleep recordings were manually read and scored by an independent pulmonologist blinded to the study, using the criteria of Rechtschaffen and Kales [21,22] and the criteria of the American Sleep Disorder Association for arousals and awakenings [23,24]. Diagnosis of central apnea was based on international recommendations [24]. The diagnosis of central apnea is characterized by absent breathing and respiratory effort for a period of at least 10 seconds. Arousals and awakenings were considered secondary to apnea when occurring within three cycles and/or 15 sec after a respiratory event [25,26]. Ineffective efforts were defined as an inspiratory effort observed by a peak electrical activity of the diaphragm (EAdi peak) without a simultaneously triggered ventilator cycle. Airflow, Paw, and EAdi were acquired from the ventilator through a RS232 interface at a sampling rate of 100 Hz, recorded by a dedicated software (Nava Tracker V. 2.0, Maquet Critical Care, Sölna, Sweden), and an analyzer using software Analysis V 1.0 (Maquet Critical Care) and a customized software based for Microsoft Excel. An arousal or awakening event was considered secondary to ineffective triggering when it occurred within 15 seconds after the asynchrony [19]. Noise was measured with a portable noise meter at the level of patient's head (Quest Technologies, Oconomowoc, WI). Arousals and awakenings were associated with the noise when they occurred 3 seconds after or within noise increase ≥10 dB [3,11]. Inspiratory trigger delay was calculated as the time difference between the onset of EAdi peak and Paw inspiratory swings. Cycling-off delay was calculated as the time difference between the end of the inspiratory EAdi peak deflection and the onset of expiratory flow.\n\nBODY.METHODS.STATISTICS ANALYSIS:\nStatistical analysis was performed using SPSS statistical software (SPSS 17.0). Continuous variables were expressed as median (25th-75th percentile) or mean ± SD. Data were compared using the general linear model for repeated measures (GLM). The small sample of patients led us to use Wilcoxon's t test for paired samples, and the p values for multiple comparisons were corrected for the Bonferroni inequality. A two-tailed p value < 0.05, corrected as needed, was retained to indicate statistical significance.\n\nBODY.RESULTS.PATIENTS:\nFourteen patients were selected and none were excluded during the study. Their main characteristics are shown in Table 1. Acute respiratory failure was the most frequent reason to initiate mechanical ventilation in ten patients, postoperative complications in three patients, and septic shock in one patient. Table 1 Characteristics of patients Characteristics of patients Sex (M/F) (8/6) Age (yr ± SD) 64 ± 11 SAPS II ± SD 46 ± 12 Duration of MV (days ± SD) 17 ± 9 Tracheotomy (%) 2 (14) Cause for initial MV (%) Acute respiratory failure 10 (71.5%) Postoperative complication 3 (21.5%) Septic shock 1 (7%) M = male; F = female; SAPS = Simplified Acute Physiology score; MV = mechanical ventilation. \n\nBODY.RESULTS.SLEEP RECORDINGS:\nAll patients completed the study, and recordings were well tolerated. Individual sleep data are shown in Table 2. The median total sleep time was 564 (range, 391-722) minutes. The median sleep efficiency (i.e., the percentage of sleep during the study) was 59% (range, 41-75%). The main abnormalities observed on each patient were a diminished percentage of REM sleep, counting for only 11.5% (range, 8-20%) of total sleep time, and a high fragmentation index with 25 arousals and awakenings per hour (range, 18-51). Although interindividual variability was large, the median quantity of slow-wave sleep (stages 3 and 4 or NREM3 stage) was normal, with a median of 18.5 (range, 11.5-22; Table 2). Table 2 Sleep architecture and fragmentation during the study (16 hours) Patient Stage 1 (%) Stage 2 (%) Stages 3 and 4 (%) Rapid eye movement (%) Fragmentation index 1 5 72.5 19.5 2.5 23.5 2 2.5 67 22.5 7 35.5 3 4 61 24.5 9 30.5 4 10 57 11 20 68 5 9 61 24 5.5 16.5 6 6 57 24 12.5 15 7 5 63 22 7.5 13.5 8 11 66.5 9 10.5 64.5 9 5.5 58 17.5 19 15.5 10 11 60.5 9.5 17 56.5 11 3 66 21 9 26 12 3.5 61.5 13 22 23 13 5.5 60 13 21.5 22 14 10 59 10.5 20.5 67.5 Median [25-75 th percentiles] 5.5 [4-10] 61 [59-65] 18.5 [11.5-22] 11.5 [8-20] 25 [18-51] \n\nBODY.RESULTS.VENTILATORY MODES AND SLEEP DISTRIBUTION:\nSleep efficiency and architecture appeared very different for both modes of ventilation (NAVA and PSV). Stage 1 (NREM1 stage) lasted longer during PSV compared with NAVA 7.5% (range, 4-15%) vs. 4% (range, 3-5%; p = 0.006). Stage 2 (NREM2 stage) also lasted longer in PSV than NAVA 68% (range, 66-75%) vs. 55% (range, 52-58%; p = 0.001). Stage 3-4 (NREM3 stage) was shorter in PSV as opposed to NAVA 16.5% (range, 17-20%) vs. 20.5% (range, 16-25%; p = 0.001). REM stage (R stage) was much shorter in PSV than in NAVA 4.5% (range, 3-11%) vs. 16.5% (range, 13-29%; p = 0.001). The fragmentation index was different between the two ventilation modes, with 40 ± 20 arousals and awakenings per hour in PSV and 16 ± 9 during NAVA (p = 0.001; Figure 2 Sleep stage (percent of total sleep) during two ventilatory modes; Table 3). Figure 2Sleep stages (percent of total sleep) during the two ventilator modes: pressure support ventilation (PSV), and neurally adjusted ventilatory assist (NAVA). REM = rapid eye movement. Table 3 Comparison of sleep quality between the ventilatory modes PSV NAVA \n p \n Stage 1, % 7.5 [4-15] 4 [3-5] 0.006* Stage 2, % 68 [66-75] 55 [52-58] 0.001* Stage 3 and 4, % 16.5 [17-20] 20.5 [16-25] 0.001* REM, % 4.5 [3-11] 16.5 [13-29] 0.001* Fragmentation index, (n/h) 33.5 [25-54] 17.5 [8-21.5] 0.001* Sleep efficacy, % 44 [29-73.5] 73.5 [52.5-77] 0.001* PSV = pressure support ventilation; NAVA = neurally adjusted ventilatory assist; REM = rapid eye movement; Fragmentation Index = number of arousals and awakenings per hour of sleep; Sleep efficiency = duration of sleep/total duration of recording. Values are expressed as median [interquartile range]. * p < 0.05. Minute ventilation did not significantly differ between PSV and NAVA with median values of 9.8 L/min (range, 8.0-10.9), and 9.6 L/min (range, 7.5-11.0) respectively (p = 0.51). The median respiratory rates were 17 breaths/min (range, 14-21), and 20 breaths/min (range, 15-23) during PSV and NAVA (p = 0.14). Median tidal volume was 420 mL (8.1 mL/Kg of predicted body weight; range, 375-479 mL), and 378 mL (7.3 mL/Kg of predicted body weight; range, 370-448 mL) during PSV and NAVA, respectively (p = 0.36). The mean PSV level was 15 ± 5 cmH2O, and the mean NAVA level was 1.6 ± 1.4 cmH2O/μV. Positive end-expiratory pressure was kept at 5 cmH2O for all patients.\n\nBODY.RESULTS.APNEAS AND INEFFECTIVE EFFORTS:\nTen of the 14 patients presented sleep apnea, and 11 exhibited ineffective efforts. The mean index of sleep apneas (number of apneas per hour of sleep) was 10.5 ± 11 apneas during PSV and 0 during NAVA (p = 0.005) and ineffective efforts (number of ineffective efforts per hour of sleep) was 24 ± 23 ineffective efforts during PSV and 0 during NAVA (p = 0.001). Over-assistance during sleep is sensed on the previous three cycles preceding central apnea. Tidal volume and minute ventilation increased, whereas ETCO2 and EAdi decreased over the three cycles preceding central apnea Table 4. Table 4 Oscillatory behaviour of various ventilator parameters for stages 3-4 with PSV mode of ventilation Respiratory variables Baseline Pre-apneas PSV V T (mL) 425 ± 67 585 ± 70 RR (breath/min) 13 ± 2 12 ± 1 VE (L/min) 5.2 ± 0.5 6.8 ± 0.8 ETCO 2 (mmHg) 46 ± 1.4 42 ± 1.0 EAdi (mVolt) 15 ± 4 10 ± 2 V T = tidal volume; RR = respiratory rate; VE = minute ventilation; ETCO 2 = end-tidal carbon dioxyde; PSV = pressure support ventilation. \n\nBODY.RESULTS.TRIGGER DELAY AND CYCLING-OFF DELAY:\nDuring N-REM sleep in PSV, the trigger delay increased on average by 80 ± 26 (msec) during stage 1 versus 158 ± 42 (msec) during stage 3 and 4. The expiratory trigger (cycling-off) increased in PSV by 158 ± 103 (msec) and 258 ± 87 (msec) during stage 1 and stages 3 and 4, respectively. In NAVA, the trigger delay remained stable during sleep, 68 ± 24 (msec) during stage 1 and 72 ± 32 (msec) during stages 3 and 4. The expiratory trigger also remained stable in NAVA: 39 ± 28 (msec) during stage 1 and 41 ± 34 (msec) during stages 3 and 4.\n\nBODY.RESULTS.NOISE:\nIn ICU, we recorded the average baseline ambient noise level and evaluated arousals from this baseline to a peak noise level ≥ 10 dB above ambient noise level. The mean noise level was recorded at 64 ± 8 dB, with the peak level recorded at 111 dB and the minimal level at 52 dB. No differences were observed between the two different ventilatory modes concerning the index of fragmentation associated with noise: 7.5 ± 3 during PSV and 6 ± 3.5 during NAVA (p = 0.19). These data indicate that 18% during PSV and 21% during NAVA of the fragmentation was associated with sudden increases in noise.\n\nBODY.RESULTS.SLEEP DISTRIBUTION AMONG STUDY PERIODS:\nThe cross-over pattern was balanced with an equal number of patients from each sequence initiating the rotation. Independent of the ventilatory mode, sleep efficiency and sleep architecture had a significantly different distribution based on the study period considered (Figure 3--sleep stage (percent of total sleep) during the four daily time periods). Sleep efficiency was the same in the two daytime periods (2 periods during the day): 52% (range, 26-67%) during the first day period (7 h-11 h a.m.) and 51.5% (range, 27-67%) during the second day period (12 h-4 h p.m.; p = 0.18). Sleep efficiency also did not differ between the two night periods: 65.5% (range, 37-82%) during the first night period (10 h p.m.-2 h a.m.) and 65% (range, 45-82.5%) during the second nighttime period (3 h-7 h a.m.; p = 0.11). Figure 3First daytime period (7 h-11 h a.m.), second daytime period (12 h-4 h p.m.), first nighttime period (10 h p.m. to 2 h a.m.) and second nighttime period (3 h-7 h a.m.). There was no statistical difference between stage 1 and 2 recording periods. A greater duration of slow-wave sleep (stage 3-4) was found during the first nocturnal period with a median percentage 22.5% (range, 20-33.5%) vs. 15.5% (range, 7-19.5%) during first day period (p = 0.03), vs. 15% (range, 7-18%) during second day period (p = 0.01) and vs. 18% (range, 13-21%) during second nighttime period (p = 0.001). The proportion of REM sleep was longer during the second nocturnal period, with a median percentage of 16.5% (range, 15-25%) vs. 11.5% (range, 5-15%) during first day period (p = 0.001) vs. 9% (range, 5-15%) during second day period (p = 0.001) and vs. 10.5% (range, 7-21%) during first nighttime period (p = 0.02). The fragmentation index did not differ with 26 (range, 20-65) arousals and awakenings/hour during first daytime vs. 24 (range, 19-55), 23 (range, 18-57), and 19 (range, 15-53) during the second day period and first and second night period, respectively (p = 0.08). Ineffective effort indexes per hour also were similar across the four periods.\n\nBODY.DISCUSSION:\nIn a study where spontaneously breathing patients were conscious and under mechanical ventilation, proportions of sleep fragmentation sleep architecture and sleep quality were positively influenced by NAVA. In the PSV mode, a low percentage of REM sleep and a high degree of fragmentation were present. NAVA showed a normal percentage of REM sleep with an important decrease in fragmentation. Less than 15% of the sleep fragmentations in the PSV mode were attributed to apneas and ineffective efforts, whereas in NAVA, no asynchrony (no apnea and no ineffective patient efforts) were recorded. Environmental noise is responsible for 18% of the arousals and awakenings in PSV compared with 21% in NAVA, respectively. We observed results similar to the Cabello et al. [19] study concerning the rate of fragmentation, the number of central apneas, and the number of ineffective patient efforts during PSV. Another similar finding concerned the increased percentage of REM sleep during the second nighttime period recordings. However, one major difference between our study and the Cabello study is that they did not allocate an even distribution for each of the study periods and ventilatory strategies. Also, they did not allow washout periods between the ventilatory modes, which could possibly contaminate the recordings at the beginning of the next study period. Detecting asynchronies also was different; they used the airway pressure-flow signal and the thoracoabdominal plethysmography, whereas we observed the EAdi signal. Parthasarathy and Tobin [15] found a lower rate of sleep fragmentation during ACV compared with PSV. This was explained by the central apneas induced by over-assistance during PSV. In fact, tidal volume was much greater during PSV compared with ACV. This was validated by the addition of a dead space to the 11 patients showing central apneas, which significantly decreased the number of apneas. In the Toublanc et al. study [27], no difference was found in terms of quantity, quality of sleep, and in terms of arousal index between the AC and a low level of PSV assistance for the whole night. Toublanc et al. found that ACV was superior in terms of percentage of slow-wave sleep but not during REM sleep [27]. It is very difficult to compare the results for PSV because of a lack of information on expiratory triggering with Evita 4, number of asynchronies (tidal volume, respiratory rate, and minute ventilation). In the Toublanc study, the majority of patients were affected with COPD and pressure support was adjusted to 6 cmH2O. According to Brochard et al., it is suggested that for COPD patients, the pressure support needed to overcome resistance imposed by the endotracheal tube is higher than non-COPD patients: 12 ± 1.9 vs 5.7 ± 1.5 cmH2O respectively [28]. In the Leleu et al. study, pressure support must be superior to 6 cmH2O, particularly in COPD if the intention is to compensate work of breathing imposed by the endotracheal tube, ventilator circuit, and patient effort to trigger the demand valve during pressure support [29]. A low-pressure support only allows for partial relieve of imposed work of breathing without modifying the work necessary to trigger the demand valve. In the Toublanc study, pressure support set too low in COPD patients resulted in an increase in imposed work of breathing, which can be accounted for in the decrease in SWS and REM. The Toublanc study offers no information on expiratory triggering, which is somewhat important in COPD patients. Tassaux et al. recently have evaluated the positive impact of shortening inspiratory time in PSV on patient-ventilator asynchronies and the work of breathing in COPD patients. This study also demonstrated that the increase in expiratory trigger up to 70% of peak flow improved synchrony and decreased ineffective efforts without modifying work of breathing or minute ventilation [30]. Bosma et al. evaluated the impact on sleep with other modes of ventilation, such as the proportional assist ventilation (PAV). The objective of PAV, such as NAVA, is to improve patient ventilator synchrony by delivering ventilator assist proportional to patient effort. The study by Bosma et al. shows an improvement in the quality of sleep using PAV compared with PSV during one night sleep [31]. There are similarities between the Bosma study and ours. More specifically, PAV appeared superior to PSV in terms of decrease in arousals, improvement in sleep quality, decrease in amounts of arousals, awakenings per hour, and improved SWS and REM. With NAVA, we observed a decrease in tidal volume by up to 15% during REM sleep, which increased end-tidal CO2 by approximately 4 mmHg. Bosma et al. observed a tidal volume slightly more elevated in PSV compared with PAV (despite similar offloading of the work of breathing), resulting in a higher morning PaCO2 with PAV attributed to lower tidal volume and minute ventilation [31], thus offering perhaps a protection against central apneas. Finally, fewer patient-ventilator asynchronies were observed with PAV with fewer awakenings per hour [31]. Contrary to NAVA, PAV cannot eliminate wasted or ineffective efforts. There was a nonstatistically significant difference in ineffective triggering during inspiration; 19.6 n/hr for PSV vs. 11.6 n/hr for PAV [31]. According to Thille et al. ineffective efforts and double triggering are among the most frequent asynchronies: 85 and 13% respectively [32], which is somewhat contradictory to Bosma et al. who identify auto triggering as the most frequent asynchrony in PSV. We observed that the absence of central apnea and ineffective efforts in NAVA do not totally explain the great improvement in the SWS and REM sleep. This improvement may be explained in part by a microanalysis of the sleep architecture. The microanalysis suggests an over-assistance with PSV during the N-REM stages, because 100% of the fragmentations in PSV occurred during this stage. The tidal volume decrease in NAVA follows the respiratory physiologic changes during sleep, whereas in PSV we find a tidal volume oscillatory behavior due to constant inspiratory efforts, independent of the sleep stage and produces sequential over-assistance during N-REM sleep leading to a decrease in end-tidal CO2. It is our assumption that improvement of the slow-wave sleep and REM is most probably explained by better patient comfort through better neuromechanical coupling. During sleep, the respiratory accessory muscles (intercostals, scalene, and abdominals) decrease their muscle tone and the mechanical response of the diaphragm is, in part, spent in the production of a mechanical distortion of the chest wall, secondary to a lack of synchronization between diaphragmatic contraction and the accessory muscles. NAVA improves this mechanical distortion, whereas PSV worsens this distortion by a tidal volume oscillation (overshoot) during sleep, with a constant patient effort. Patient comfort is not only directly related to inefficient efforts and central apneas; the microanalysis showed that during N-REM sleep in PSV, the trigger delay increased during stage 1 versus during stage 3 and 4. The expiratory trigger increased in PSV during stage 1 and stages 3 and 4, respectively. In NAVA, the trigger delay remained stable during stage 1 and during stages 3 and 4. The expiratory trigger also remained stable in NAVA, during stage 1 and during stages 3 and 4. NAVA allows optimizing the neuromechanical coupling and therefore patient-ventilator synchrony [33] and allows for optimized adequacy between ventilatory load and patient breathing ability, thereby providing beneficial effects on sleep in ICU patients. It appeared to us that the EAdi tracing is much more efficient than flow and pressure tracings to detect asynchronies. Our study has some limitations; one is the open space between patients. This study included only 14 patients, which could favor the possibility of a type II error. Patients' heterogeneity implies that patients required bedside care, such as suctioning or other care, which could perhaps influence sleep fragmentation. The study by Cabello found that suctioning was associated with < 1% arousals and awakenings [19]. The choice for a 15-second interval between asynchrony and the occurrence of arousal was chosen based on one previous study on the same topic [19]. Literature on this specific time interval to choose is very scarce. In one study, it was shown that the breathing response to a complete airway occlusion was 20.4 ± 2.3 sec during NREM and 6.2 ± 1.2 sec during REM [34]. The choice of a 15-second interval seems very reasonable but may need further investigation. In a sleep laboratory, it is a lot easier to control the baseline ambient noise level. In a clinical environment, such as an ICU, we recorded the average baseline ambient noise level and evaluated arousals from this baseline to a peak noise level ≥10 dB above ambient noise level. There is therefore a potential for statistical inaccuracies. The fact that we stopped sedation 24 hours before beginning the study does not imply an absence of cumulative sedation. However, every patient had a Ramsay Score of 2 or less and a Glasgow Score of 11 (the maximum score for an intubated patient).\n\nBODY.CONCLUSIONS:\nThe ventilatory mode NAVA improves the quality of sleep by increasing the slow-wave sleep and REM and by decreasing fragmentation. NAVA improves patient comfort through better neuromechanical coupling during N-REM sleep, by a shorter trigger delay, and more efficient expiratory triggering. To minimize sleep fragmentation, optimal setting of pressure support level and expiratory trigger are paramount in PSV. However, proportional assistance modes of ventilation according to patient inspiratory effort, such as NAVA, appear to be a better choice to minimize sleep fragmentation.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nSD and PO drafted the manuscript, and PB, JPT, and PA revised the manuscript.\n\nQuestion: Compared to pressure support ventilation (PSV) what was the result of neurally adjusted ventilatory assist (NAVA) on fragmentation index?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1047	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomised controlled trial to evaluate the efficacy and usability of a computerised phone-based lifestyle coaching system for primary and secondary prevention of stroke\n\n ABSTRACT.BACKGROUND:\nOne of the most effective current approaches to preventing stroke events is the reduction of lifestyle risk factors, such as unhealthy diet, physical inactivity and smoking. In this study, we assessed the efficacy and usability of the phone-based Computer-aided Prevention System (CAPSYS) in supporting the reduction of lifestyle-related risk factors.\n\nABSTRACT.METHODS:\nA single-centre two-arm clinical trial was performed between January 2013 and February 2014, based on individual follow-up periods of six months with 94 patients at high risk of stroke, randomly assigned to an intervention group (IC: 48; advised to use the CAPSYS system) or a standard care group (SC: 46). Study parameters, such as blood pressure, blood values (HDL, LDL, HbA1c, glycaemia and triglycerides), weight, height, physical activity as well as nutrition and smoking habits were captured through questionnaires and medical records at baseline and post-intervention and analysed to detect significant changes. The usability of the intervention was assessed based on the standardised System Usability Scale (SUS) complemented by a more system-specific user satisfaction and feedback questionnaire.\n\nABSTRACT.RESULTS:\nThe statistical evaluation of primary measures revealed significant decreases of systolic blood pressure (mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]), LDL (pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]) and triglyceride values (pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]) in the intervention group, while no such changes could be observed in the control group. Furthermore, we detected a statistically significant increase in self-reported fruit and vegetable consumption (pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]) and a decrease in sweets consumption (pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]) in the intervention group. The usability assessment showed that the CAPSYS system was, in general, highly accepted by the users (average SUS score: 80.1).\n\nABSTRACT.CONCLUSIONS:\nThe study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is well applicable in practice.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov Identifier: NCT02444715\n\nBODY.BACKGROUND:\nLifestyle risk factors, such as unhealthy diet, physical inactivity and smoking, have a strong influence on the personal risk of stroke. Reducing such risk factors is currently one of the most effective approaches to preventing stroke events. According to the World Health Organization (WHO), \"most cardiovascular diseases can be prevented by addressing risk factors such as tobacco use, unhealthy diet and obesity, physical inactivity, high blood pressure, diabetes and raised lipids\" [1–3]. However, many individuals have difficulties adhering to recommendations concerning a healthy lifestyle, and long-term compliance with such lifestyle changes is usually low. Early findings in behavioural research support the assumption that the mere task of self-monitoring increases habit awareness, induces reflection on habits, and thus can provoke a positive change of the monitored behaviour [4]. Furthermore, experience has shown that sustained contact is necessary in order to support people in establishing and maintaining lifestyle changes [5]. In this context, the recently developed Computer-aided Prevention System (CAPSYS) offers a cost-effective automated solution combining remote surveillance of individual cerebro-cardiovascular risk factors with tailored advice [6]. Registered patients can access CAPSYS through a phone interface, simply by dialling a landline number. In an automated dialog, patients are asked to provide information about a predefined number of risk factors (current nutrition, physical activity, smoking, weight and blood pressure) by typing in the corresponding answers using the phone keypad. Based on the patient's answers, CAPSYS issues tailored feedback aiming at motivating a positive change towards or maintenance of healthy, risk-reducing habits. The system has been designed as a multi-language tool, in which the languages German and French have already been implemented and used within the trial. Clearly, a telephone as a user interface requires sufficient hearing abilities by the patients as well as the ability to understand and follow the instructions and advice issued by the virtual lifestyle coach. Consequently, this system is not appropriate for use by persons with severe hearing impairments or cognitive limitations. In cases of doubt, a patient's cognitive abilities can be evaluated by means of the Folstein mini-mental state test [7]. On the other hand, there is no problem for patients with difficulties in articulation or speech impediments to use CAPSYS, due to the fact that patient interaction does not involve any speech input but is purely limited to pressing buttons on the telephone keypad. In order to assess the efficacy of the CAPSYS approach concerning the reduction of stroke-related risk factors as well as the usability of the system, a dedicated study was designed and carried out, the results of which are presented in this article.\n\nBODY.METHODS:\nIn 2013 and 2014, a single-centre randomised controlled trial was carried out at the Department of Neurology of the Centre Hospitalier de Luxembourg. The study was designed as a six-month, parallel-group two-arm trial involving an intervention and a control group. Within this six-month study with a relatively limited number of participants, it was not possible to focus on the registration of severe events, such as stroke or death. Instead, the study concentrates on changes in different surrogate parameters for stroke (systolic blood pressure, BMI, HDL, LDL, HbA1c, glycaemia and triglycerides). A draft of the study design has already been presented in [8].\n\nBODY.METHODS.PARTICIPANTS:\nPatients aged 20 and over were eligible for the study if they had already suffered from a stroke or were at high risk of stroke (at least two risk factors according to the criteria described in [2, 9, 10]). The eligibility criteria are summarised in Table 1. Patients' stroke risk and thus their suitability to participate in the CAPSYS study were evaluated by the treating neurologist based on the patients' individual risk factor profiles.\nTable 1Eligibility criteria for the CAPSYS studyInclusion criteriaExclusion criteriaAge: 20 and over; At high risk of stroke:Inability to fill out or to understand the informed consent;∙ Already suffered a stroke or Transient Ischemic Attack (TIA) orNo signed informed consent;∙ At least two risk factors for stroke:– High blood pressure (systolic blood pressure ≥ 140 mmHg)Dementia– Overweight (BMI ≥ 25 kg/m2)– Low physical activity (less than 30 min. of moderate-intensity physical exercise per week)– Smoking– Unhealthy diet\n\nBODY.METHODS.RECRUITMENT AND RANDOMISATION:\nPotential study participants were approached in the course of their regular consultations with their neurologist, where they were screened for eligibility. Prior to their enrolment in the study, all participants signed a written informed consent; 94 participants were randomised by lot to one of two groups: Interventional Care (IC: 48, 34 [71 %] male) or Standard Care (SC: 46, 29 [63 %] male). Participants were aged between 32 and 86 (SC: mean = 59.6; SD = 12.1; median = 59) (IC: mean = 60.7; SD = 11.3; median = 61). The major characteristics of the study cohort are summarised in Table 2. Due to the specific design of the intervention, the study had to be carried out in an only partially blinded manner. It is inherent to the CAPSYS approach that the treating neurologist performs regular reviews of the data collected in the intervention group. The need to have access to patient histories and the possibility to contact patients at any time in case of emerging situations has limited the use of blinding methods within the trial. However, in order to ensure the validity of the study, the CAPSYS study team was separated into three different groups: a) principal investigator and treating neurologist responsible for the initial eligibility check of potential study participants, b) hospital research nurse responsible for patient recruitment and randomisation, and c) healthcare researchers who performed the statistical evaluation of the collected data by using pseudonymised data sets. During the recruitment meeting, patients were informed about the purpose of the study and about the study approach. The CAPSYS study design was approved by the Luxembourg National Research Ethics Committee (CNER) (N° 201205/08) and the National Commission for Data Protection (CNPD) (T007990).\nTable 2Descriptive statistics of the study cohortSC (n = 46)IC (n = 48)Mean age [years] (±SD)59.6 (±12.1)60.7 (±11.3)Men29 (63 %)34 (71 %)Mean BMI [ kg/m2] (±SD)27 (±4.3)28 (±4.3)Smokers2 (4 %)6 (13 %)Hypertension36 (78 %)43 (90 %)Hyper-/Dyslipidemia39 (85 %)44 (92 %)Diabetes mellitus5 (11 %)8 (17 %)Previous stroke/TIA37 (80 %)31 (65 %)\n\nBODY.METHODS.INTERVENTION:\nIn addition to the usual care, participants in the IC group were advised to regularly call the phone-based prevention system CAPSYS (preferably twice a week). In the course of the recruitment process, they were carefully instructed in the proper use of the system, and they were provided a corresponding user manual in form of a leaflet. The participants could access the CAPSYS system by calling a specific land line number with their stationary or mobile phones. After choosing their preferred language (French or German) and authenticating themselves with their individual patient number and PIN code, the participants were posed the following questions: \nHow many servings of fruits and vegetables have you consumed yesterday?How many servings of whole-grain food have you consumed yesterday?How many servings of sweets have you consumed yesterday?Please enter your current weight.How many cigarettes have you smoked yesterday? [removed for non-smokers]How many minutes have you been physically active yesterday? [moderate or high intensity]Please enter your current systolic blood pressure. The participants could answer to these questions by typing in the numerical values (number of servings, weight, minutes etc.) using the phone key pad. During the recruitment meeting at the beginning of the study, participants were instructed on how to estimate the size of one portion for the relevant food groups, and they were advised to measure their current blood pressure and weight, and to write down all necessary values prior to calling the CAPSYS system. Depending on the data provided by the patient, he or she received immediate customized feedback after each answer concerning his or her progress and advice on how to proceed reducing the corresponding risk factor or motivation on maintaining some observed healthy behaviour respectively. The phone call was closed with a concluding statement summing up the feedback issued before by the system. The questions and feedback were automatically generated by CAPSYS and were issued to the patients in spoken natural language by means of a text-to-speech software (TTS). The system was implemented to run fully automatically and could be accessed at any time of day. In case of systolic blood pressure higher than 140 mmHg, the patient was advised to rest for a while and then repeat the measurement. The system also advised the patients to contact a doctor in case of constantly high blood pressure. Patients with values above 140 mmHg were also particularly marked in the web interface when the treating physician accessed the system. Apart from that, all participants have been informed that there were no direct alerts in cases of high blood pressure provided within the study. The treating neurologist could access the data provided by his patients through a web interface, offering both a numerical as well as an adaptable graphical representation of the patient data for a certain period of time. The use of CAPSYS within the study has not replaced or reduced the existing information exchange between the neurologist and the corresponding referring physicians, which was proceeded according to the practices of the Luxembourgish healthcare system. Technically, CAPSYS offers the possibility for further physicians, e.g. the treating general practitioner, to access and monitor the data gathered from their patients. However, in the scope of this study, this option was deliberately discarded in order to avoid potential bias caused by the general practitioner accessing and interpreting the CAPSYS data. In contrast to the IC group, SC participants received only the usual care including blood analyses, blood pressure controls and individual advice on healthy lifestyle during the outpatient treatment given by the neurologist, by the general practitioner and by other physicians. Information material concerning a healthy lifestyle was provided to both groups.\n\nBODY.METHODS.DATA COLLECTION:\nDemographic and medical information of each participant was recorded by the study personnel in a predefined form, including body weight and height, medical history, current medication, smoking habits, blood pressure and heart rate as well as recent blood test results (HDL, LDL, HbA1c, glycaemia and triglycerides). Furthermore, participants were asked to fill in three questionnaires exploring their nutritional habits, physical activity and quality of life. The latter was measured using the standardised EQ-5D-5L instrument provided by the EuroQol Group [11]. Six months after enrolment, participants were asked to fill in the same questionnaires again, and current medical data (weight, blood pressure, heart rate, blood test results, smoking habits and medication) were again recorded by the study personnel. In addition, IC participants were asked to share their experiences with using CAPSYS and to provide their opinions about the system in a predefined questionnaire, which encompasses the well-established System Usability Scale (SUS) [12] and some further more specific questions concerning the usage of CAPSYS and its particular features. There was also space left for open-ended comments and suggestions at the end of the questionnaire.\n\nBODY.METHODS.DEPENDENT MEASURES:\nThe impact of the intervention was assessed based on the changes of cerebro-cardiovascular risk parameters during the six-month trial period, whereby changes in the IC group were compared to those in the control group (SC). Changes in systolic blood pressure, HDL, LDL, HbA1c, glycaemia, triglycerides and BMI were considered as primary dependent measures (see Table 3). Changes in self-reported weekly consumption of fruits and vegetables, whole grain food and sweets as well as changes in self-reported weekly duration of physical activity and quality of life were analysed as secondary measures. Due to the low number of smokers among the study participants (SC: 2, IC: 6), smoking habits were not evaluated.\nTable 3Overview of baseline values and evaluation of primary dependent measures in SC and IC groupsSCICBaselineEvaluationBaselineEvaluation\nParametric data\n\nMean (±SD)\n\nT-test\n\nMean (±SD)\n\nT-test\nSystolic BP [mmHg]139.6 (±21)mean of diff. =0.19145 (±19.4)mean of diff. =−9p =0.96\np\n= 0.03\n95 % CI = [–7.5, 7.88]95 % CI = [–17.29, –0.71]Cohen's d =0.42BMI [ kg/m2]27 (±4.3)mean of diff. =0.0328 (±4.3)mean of diff. =−0.18p =0.9p =0.4395 % CI = [–0.49, 0.55]95 % CI = [–0.65, 0.28]\nNon-parametric data\n\nMedian [IQR]\n\nWilcoxon\n\nMedian [IQR]\n\nWilcoxon\nHDL [ mg/dl]57 [45, 51]pseudo-median of diff =1.553 [47, 74]pseudo-median of diff =−1.5p =0.53p =0.4495 % CI = [–2.5, 4.5]95 % CI = [–4.5, 2]LDL [ mg/dl]96 [71, 114]pseudo-median of diff =−195 [76, 117]pseudo-median of diff =−7.9p =0.76\np\n= 0.04\n95 % CI = [–10.5, 6]95 % CI = [–18.5, –0.5]r =0.24HbA1c [ %]5.8 [5.6, 5.9]pseudo-median of diff =05.9 [5.5, 6.25]pseudo-median of diff =0.1p =0.92p =0.3795 % CI = [–0.25, 0.2]95 % CI = [–0.1, 0.25]Glycaemia [ mg/dl]98 [89, 106.75]pseudo-median of diff =0.5102 [92.5, 114.5]pseudo-median of diff =2.5p =0.78p =0.1995 % CI = [–5.5, 5]95 % CI = [–2, 6]Triglycerides [ mg/dl]95 [73, 134.25]pseudo-median of diff =−6105 [78, 132.5]pseudo-median of diff =−12.5p =0.39\np\n= 0.04\n95 % CI = [–21, 10]95 % CI = [–26, –0.5]r =0.25(statistically significant values are marked in bold) Statistical analyses were carried out on an intention-to-treat basis using RStudio (Version 0.98.978) with a significance level of 0.05. Parametric data (paired and unpaired samples) were evaluated with the Student's t-test approach, and the corresponding effect size was calculated with Cohen's d. Non-parametric data were evaluated using the Wilcoxon signed-rank test (for paired samples) or the Mann-Whitney U test (for unpaired samples) respectively, and effect size was calculated as \\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym} \n\t\t\t\t\\usepackage{amsfonts} \n\t\t\t\t\\usepackage{amssymb} \n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$r = \\frac {Z}{\\sqrt {N}}$\\end{document}r=ZN. For non-parametric paired samples, the pseudo-median is computed as the Hodges-Lehmann estimate.\n\nBODY.RESULTS.EFFICACY OF THE INTERVENTION:\nFinal questionnaires on nutritional habits, physical activity and quality of life could be collected from 68 participants (SC: 36; IC: 32) at the end of the study. This results in an overall dropout rate of 28 % (SC: 22 %; IC: 33 %). Further participant data, such as blood test values, could be retrieved from medical records. Out of the 48 recruited IC participants, 11 (23 %) did not use CAPSYS at all. The remaining 37 IC subjects (77 %) called the system up to 55 times during the study period (mean = 23.32; SD = 14.1; median = 24). Within-subjects analyses of primary dependent measures showed the following statistically significant changes between baseline and post-intervention: \nDecrease of systolic blood pressure in IC group (two-sided paired-samples t-test: mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]; Cohen's d = 0.42: large effect size) (see Fig. 1), with no corresponding significant difference in SC group (p = 0.96);\nFig. 1Systolic blood pressure. Significant decrease of systolic blood pressure in IC groupDecrease of low-density lipoprotein (LDL) levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]; r = 0.24: medium effect size), with no corresponding significant difference in SC group (p = 0.76) (see Fig. 2);\nFig. 2LDL. Significant decrease of LDL levels in IC groupDecrease of triglyceride levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]; r = 0.25: medium effect size), with no corresponding significant difference in SC group (p = 0.39) (see Fig. 3);\nFig. 3Triglycerides. Significant decrease of triglyceride levels in IC groupNo statistically significant changes could be found for any of the other primary measures (BMI, HDL, HbA1c and glycaemia). In this context, it needs to be stated that, at baseline, there were no statistical differences between both groups concerning the proportions of patients taking antihypertensives (SC: 36 [78 %]; IC: 43 [90 %]; p = 0.22), antidiabetic drugs (SC: 5 [11 %]; IC: 8 [17 %]; p = 0.61) or cholesterol-lowering medication (SC: 39 [85 %]; IC: 44 [92 %]; p = 0.47). Concerning the secondary dependent measures, we could observe the following statistically significant results: \nIncrease of self-reported fruit and vegetable consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.67);Decrease of self-reported sweets consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.06);Difference between SC and IC groups concerning the change of self-reported whole-grain food consumption (Mann-Whitney U test: difference in location = 3.26 servings/week; p = 0.04; 95 % CI = [0.00006, 7]; r = 0.24: medium effect size);No statistically significant changes for self-reported physical activity and quality of life.\n\nBODY.RESULTS.USABILITY AND USER ACCEPTANCE OF THE INTERVENTION:\nAssessments of the intervention based on the System Usability Scale (SUS) were provided by 28 participants of the IC group, 2 of which were declared invalid, as these participants have demonstrably never used CAPSYS during the trial period, and consequently, they were considered unable to assess the intervention. The average SUS score for CAPSYS was 80.1 (SD = 16.22; median = 78.75; min = 37.5; max = 100; 95 % CI = [73.54, 86.65]). According to Sauro and Lewis, this average score corresponds to an \"A–\" school grade and a percentile of 85–89, meaning that CAPSYS scored better than 85 to 89 % of all systems considered in the Sauro and Lewis study (see [13], chapter 8, page 204, table 8.6). Using the simplified regression equation proposed by Lewis [14], the Likelihood to Recommend for each CAPSYS user was derived from the corresponding SUS scores as LTR = SUS/10. With these values, we could identify 10 promoters (38 %; LTR ≥ 9) and 4 detractors (23 %; LTR ≤ 6) among the 26 participants who provided valid SUS scores, which results in a positive Net Promoter Score (NPS) of 23 [15], meaning that there are 23 % more users who would recommend CAPSYS (promoters) than users who would argue against using the system (detractors). Beside the standardised SUS questionnaire, IC participants were also asked to asses the voice of the text-to-speech module applied in CAPSYS and the automatically generated utterances issued by the system. The results concerning these questions are presented in Table 4.\nTable 4Evaluation of CAPSYS's voice and utterancesScaleResultsVoice1: pleasant – 5: unpleasantmean =1.77;median =1.5;SD =0.991: difficult to understand – 5: easy to understandmean =4.28;median =5;SD =1.141: natural – 5: unnaturalmean =2.15;median =2;SD =1.121: too fast – 5: too slowmean =3.2;median =3;SD =0.5Utterances1: diversified – 5: unvariedmean =3.28;median =4;SD =1.241: inappropriate – 5: appropriatemean =3.46;median =3;SD =1.071: too short – 5: too longmean =3.2;median =3;SD =0.5 Concerning the frequency of use, the majority of the 26 IC participants who answered to the usability questionnaire indicated that they would prefer using CAPSYS once (11; 42 %) or twice (9; 35 %) per week. None of the respondents was willing to use the system more than twice a week, 2 (8 %) preferred to use it less than once a week and 4 (15 %) expressed that they would not use it at all. The approach of connecting to CAPSYS by calling the system whenever they wish was favoured by most of the respondents (18; 69 %) over the potential alternatives of being called by the system (3; 12 %) or receiving reminders to call the system (2; 8 %). Although CAPSYS does not offer speech recognition, we asked users if they prefer to have such an input option instead or in combination with the implemented keypad input. In this context, using the phone keypad was identified as the most preferred way of communication with such a system (20; 77 %) as compared to speech input (1; 4 %) or a combination of both (4; 15 %). The majority of the respondents were interested in having insight into the data history gathered by CAPSYS, either online (9; 35 %) or in a printed version (11; 42 %). Concerning a potential alternative interface for CAPSYS beside the phone interface, 10 (38 %) participants were interested in a corresponding website and 4 (15 %) fancied the idea of having a CAPSYS smartphone app. Regarding the question if the use of CAPSYS has motivated them to a healthier lifestyle, 5 (19 %) of the respondents stated that through the intervention they started eating healthier, 3 (12 %) reported to have become physically more active and 12 (46 %) claimed to have achieved both healthier eating and increased physical activity. This means that, in total, 20 (77 %; 95 % CI = [59 %, 95 %]) of the respondents expressed an improvement of their health-related lifestyle (improved nutrition or increased physical activity or both) through the use of CAPSYS.\n\nBODY.DISCUSSION:\nThe positive effects that could be observed in the IC group concerning systolic blood pressure, LDL and triglyceride levels as well as the self-reported improvements of nutritional habits can be regarded as an indicator that a computerised phone-based intervention, such as CAPSYS, can support the reduction of cerebro-cardiovascular risk when offered in addition to usual care. An average decrease in systolic blood pressure of 9 mmHg among CI participants can be regarded as clinically significant [16]. The same also holds for the observed average decreases of 7.9 mg/dl for LDL [17] and 12.5 mg/dl for triglycerides [18]. Though, the relatively wide 95 % confidence intervals retrieved in the statistical analysis indicate that the cohort size was probably too small to be able to demonstrate strong clinical effects. The evaluation of BMI, HDL, HbA1c and glycaemia values showed no significant changes in the two groups. Our results are to some extent supported by the recently published Australian CLIP study, which found that telephone coaching performed by human health care professionals can result in a significant reduction of LDL and total cholesterol values in the intervention group [19]. A systematic review by Goode et al. also underlines the efficacy of telephone-based lifestyle coaching. In 20 out of 26 studies, telephone support by health professionals have led to significant improvements concerning physical exercises and healthy nutrition [20]. However, personal telephone coaching by health experts requires intensive use of human resources and is associated with enormous costs, which limits its widespread distribution to larger patient groups. CAPSYS is a system that supports prevention initiatives by supporting individuals in daily life settings. It can be assumed that a large percentage of the total target group is not willing to perform any lifestyle changes at all, no matter which kind of support they will receive. So, it has to be taken into account that our study participants are a selected subgroup of the target population with a potentially higher motivation to change risk factors and lifestyle. However, this selection bias in general concerns all prevention initiatives, and the randomisation process should ensure that the general motivation is balanced across both study arms. Compared to therapy studies, participants in prevention studies mostly do not see any direct measurable advantages in their actual health status. Missing short-term improvements are therefore often a reason for higher dropout rates. However, compared to other studies in secondary prevention, the moderate and balanced dropout rates of both CAPSYS arms should not have significantly affected the study results. On the other hand, self-reported consumptions of fruits, vegetables or sweets have a high potential for reporting bias. Therefore, in our study, this kind of information is only considered as secondary depended measures. The improvements of nutritional habits in the IC group (5 servings of fruits and vegetables more per week; 2 servings of sweets less per week) are significant, but have to be treated with caution as they are based on self-reported values and thus less reliable. As the dropout rates were not significantly different for both groups (SC: 22 %; IC: 33 %; p = 0.31), it can be supposed that the withdrawal of IC patients from the clinical trial was not substantially influenced by the intervention itself, but it was due to common reasons, like lack of time, forgetting appointments or just lack of motivation. Furthermore, it remains open how the observed positive effects will evolve after the study period and if they actually are of a long-term nature. The usability evaluation revealed that the CAPSYS approach was well accepted by the study participants. In particular, the large proportion of respondents (77 %) expressing a positive change of health-related behaviour due to the use of CAPSYS is remarkable. One might argue that this result is strongly biased due to the fact that users who have a positive experience with a system are more likely to finish a study and provide corresponding feedback than users with negative experiences. However, even if we consider all dropout IC participants as non-beneficiaries, the success rate concerning a positive health behaviour change would still be 42 % (95 % CI = [27 %, 57 %]). Unfortunately, our cohort was not large enough to perform subgroup analyses in order to evaluate the characteristics of beneficiaries and non-beneficiaries. A follow-up study focussing on such aspects might help to identify appropriate target groups for which a system like CAPSYS might be most beneficial and most accepted. During informal interviews at the end of the study, many of the IC participants explained that they often could not find the time or simply forgot to call CAPSYS. Taking this into account, the implementation of a call reminder functionality seems beneficial, even though in the feedback questionnaire, the majority of the respondents did not favour the concepts of being called or reminded by the system. Another important issue concerning risk factor reduction in the stroke prevention context is the topic of medication adherence. In order to support users in regularly taking their antihypertensive or cholesterol-lowering medication, CAPSYS could be extended to incorporate prompts in its automatically generated feedback messages asking the users if they have taken their prescribed medication according to their individual medication plan. Concerning the technical implementation of CAPSYS, it could be observed that, on average, the artificial voice applied in CAPSYS was perceived as rather pleasant, easy to understand and natural, and the speech rate was perceived as appropriate. The length of the utterances was, on average, perceived as adequate, but the feedback text might also be shortened to some extent. The results also show that there is some space for improvement concerning the diversity and adequacy of the automatically generated feedback. The offered keypad interface for data input was highly accepted by the users, and the need for an alternative input method, such as speech, was detected to be low. Unsurprisingly, only few users were currently interested in a mobile app version of CAPSYS. However, with increasing spread of smartphones, a mobile solution will certainly gain in importance in the future. What is already important for most users is to have access to their own self-monitored data, even if due to technical reasons they might only be able to access them in a printed form.\n\nBODY.CONCLUSION:\nIn summary, the present study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is in general well accepted by the affected patients. In a next step, CAPSYS could be extended to a disease management tool, involving health professionals from different disciplines, such as neurologists, cardiologists, dieticians, physiotherapists etc., in the treatment of patients. One aspect that could be explored in future research is if the motivational effect of CAPSYS could be strengthened through an increased involvement of the treating physician and through incorporation of social interaction.\n\nQuestion:* Compared to Standard care what was the result of CAPSYS system on Self-reported consumption of fruits and vegetables?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1048	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomised controlled trial to evaluate the efficacy and usability of a computerised phone-based lifestyle coaching system for primary and secondary prevention of stroke\n\n ABSTRACT.BACKGROUND:\nOne of the most effective current approaches to preventing stroke events is the reduction of lifestyle risk factors, such as unhealthy diet, physical inactivity and smoking. In this study, we assessed the efficacy and usability of the phone-based Computer-aided Prevention System (CAPSYS) in supporting the reduction of lifestyle-related risk factors.\n\nABSTRACT.METHODS:\nA single-centre two-arm clinical trial was performed between January 2013 and February 2014, based on individual follow-up periods of six months with 94 patients at high risk of stroke, randomly assigned to an intervention group (IC: 48; advised to use the CAPSYS system) or a standard care group (SC: 46). Study parameters, such as blood pressure, blood values (HDL, LDL, HbA1c, glycaemia and triglycerides), weight, height, physical activity as well as nutrition and smoking habits were captured through questionnaires and medical records at baseline and post-intervention and analysed to detect significant changes. The usability of the intervention was assessed based on the standardised System Usability Scale (SUS) complemented by a more system-specific user satisfaction and feedback questionnaire.\n\nABSTRACT.RESULTS:\nThe statistical evaluation of primary measures revealed significant decreases of systolic blood pressure (mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]), LDL (pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]) and triglyceride values (pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]) in the intervention group, while no such changes could be observed in the control group. Furthermore, we detected a statistically significant increase in self-reported fruit and vegetable consumption (pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]) and a decrease in sweets consumption (pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]) in the intervention group. The usability assessment showed that the CAPSYS system was, in general, highly accepted by the users (average SUS score: 80.1).\n\nABSTRACT.CONCLUSIONS:\nThe study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is well applicable in practice.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov Identifier: NCT02444715\n\nBODY.BACKGROUND:\nLifestyle risk factors, such as unhealthy diet, physical inactivity and smoking, have a strong influence on the personal risk of stroke. Reducing such risk factors is currently one of the most effective approaches to preventing stroke events. According to the World Health Organization (WHO), \"most cardiovascular diseases can be prevented by addressing risk factors such as tobacco use, unhealthy diet and obesity, physical inactivity, high blood pressure, diabetes and raised lipids\" [1–3]. However, many individuals have difficulties adhering to recommendations concerning a healthy lifestyle, and long-term compliance with such lifestyle changes is usually low. Early findings in behavioural research support the assumption that the mere task of self-monitoring increases habit awareness, induces reflection on habits, and thus can provoke a positive change of the monitored behaviour [4]. Furthermore, experience has shown that sustained contact is necessary in order to support people in establishing and maintaining lifestyle changes [5]. In this context, the recently developed Computer-aided Prevention System (CAPSYS) offers a cost-effective automated solution combining remote surveillance of individual cerebro-cardiovascular risk factors with tailored advice [6]. Registered patients can access CAPSYS through a phone interface, simply by dialling a landline number. In an automated dialog, patients are asked to provide information about a predefined number of risk factors (current nutrition, physical activity, smoking, weight and blood pressure) by typing in the corresponding answers using the phone keypad. Based on the patient's answers, CAPSYS issues tailored feedback aiming at motivating a positive change towards or maintenance of healthy, risk-reducing habits. The system has been designed as a multi-language tool, in which the languages German and French have already been implemented and used within the trial. Clearly, a telephone as a user interface requires sufficient hearing abilities by the patients as well as the ability to understand and follow the instructions and advice issued by the virtual lifestyle coach. Consequently, this system is not appropriate for use by persons with severe hearing impairments or cognitive limitations. In cases of doubt, a patient's cognitive abilities can be evaluated by means of the Folstein mini-mental state test [7]. On the other hand, there is no problem for patients with difficulties in articulation or speech impediments to use CAPSYS, due to the fact that patient interaction does not involve any speech input but is purely limited to pressing buttons on the telephone keypad. In order to assess the efficacy of the CAPSYS approach concerning the reduction of stroke-related risk factors as well as the usability of the system, a dedicated study was designed and carried out, the results of which are presented in this article.\n\nBODY.METHODS:\nIn 2013 and 2014, a single-centre randomised controlled trial was carried out at the Department of Neurology of the Centre Hospitalier de Luxembourg. The study was designed as a six-month, parallel-group two-arm trial involving an intervention and a control group. Within this six-month study with a relatively limited number of participants, it was not possible to focus on the registration of severe events, such as stroke or death. Instead, the study concentrates on changes in different surrogate parameters for stroke (systolic blood pressure, BMI, HDL, LDL, HbA1c, glycaemia and triglycerides). A draft of the study design has already been presented in [8].\n\nBODY.METHODS.PARTICIPANTS:\nPatients aged 20 and over were eligible for the study if they had already suffered from a stroke or were at high risk of stroke (at least two risk factors according to the criteria described in [2, 9, 10]). The eligibility criteria are summarised in Table 1. Patients' stroke risk and thus their suitability to participate in the CAPSYS study were evaluated by the treating neurologist based on the patients' individual risk factor profiles.\nTable 1Eligibility criteria for the CAPSYS studyInclusion criteriaExclusion criteriaAge: 20 and over; At high risk of stroke:Inability to fill out or to understand the informed consent;∙ Already suffered a stroke or Transient Ischemic Attack (TIA) orNo signed informed consent;∙ At least two risk factors for stroke:– High blood pressure (systolic blood pressure ≥ 140 mmHg)Dementia– Overweight (BMI ≥ 25 kg/m2)– Low physical activity (less than 30 min. of moderate-intensity physical exercise per week)– Smoking– Unhealthy diet\n\nBODY.METHODS.RECRUITMENT AND RANDOMISATION:\nPotential study participants were approached in the course of their regular consultations with their neurologist, where they were screened for eligibility. Prior to their enrolment in the study, all participants signed a written informed consent; 94 participants were randomised by lot to one of two groups: Interventional Care (IC: 48, 34 [71 %] male) or Standard Care (SC: 46, 29 [63 %] male). Participants were aged between 32 and 86 (SC: mean = 59.6; SD = 12.1; median = 59) (IC: mean = 60.7; SD = 11.3; median = 61). The major characteristics of the study cohort are summarised in Table 2. Due to the specific design of the intervention, the study had to be carried out in an only partially blinded manner. It is inherent to the CAPSYS approach that the treating neurologist performs regular reviews of the data collected in the intervention group. The need to have access to patient histories and the possibility to contact patients at any time in case of emerging situations has limited the use of blinding methods within the trial. However, in order to ensure the validity of the study, the CAPSYS study team was separated into three different groups: a) principal investigator and treating neurologist responsible for the initial eligibility check of potential study participants, b) hospital research nurse responsible for patient recruitment and randomisation, and c) healthcare researchers who performed the statistical evaluation of the collected data by using pseudonymised data sets. During the recruitment meeting, patients were informed about the purpose of the study and about the study approach. The CAPSYS study design was approved by the Luxembourg National Research Ethics Committee (CNER) (N° 201205/08) and the National Commission for Data Protection (CNPD) (T007990).\nTable 2Descriptive statistics of the study cohortSC (n = 46)IC (n = 48)Mean age [years] (±SD)59.6 (±12.1)60.7 (±11.3)Men29 (63 %)34 (71 %)Mean BMI [ kg/m2] (±SD)27 (±4.3)28 (±4.3)Smokers2 (4 %)6 (13 %)Hypertension36 (78 %)43 (90 %)Hyper-/Dyslipidemia39 (85 %)44 (92 %)Diabetes mellitus5 (11 %)8 (17 %)Previous stroke/TIA37 (80 %)31 (65 %)\n\nBODY.METHODS.INTERVENTION:\nIn addition to the usual care, participants in the IC group were advised to regularly call the phone-based prevention system CAPSYS (preferably twice a week). In the course of the recruitment process, they were carefully instructed in the proper use of the system, and they were provided a corresponding user manual in form of a leaflet. The participants could access the CAPSYS system by calling a specific land line number with their stationary or mobile phones. After choosing their preferred language (French or German) and authenticating themselves with their individual patient number and PIN code, the participants were posed the following questions: \nHow many servings of fruits and vegetables have you consumed yesterday?How many servings of whole-grain food have you consumed yesterday?How many servings of sweets have you consumed yesterday?Please enter your current weight.How many cigarettes have you smoked yesterday? [removed for non-smokers]How many minutes have you been physically active yesterday? [moderate or high intensity]Please enter your current systolic blood pressure. The participants could answer to these questions by typing in the numerical values (number of servings, weight, minutes etc.) using the phone key pad. During the recruitment meeting at the beginning of the study, participants were instructed on how to estimate the size of one portion for the relevant food groups, and they were advised to measure their current blood pressure and weight, and to write down all necessary values prior to calling the CAPSYS system. Depending on the data provided by the patient, he or she received immediate customized feedback after each answer concerning his or her progress and advice on how to proceed reducing the corresponding risk factor or motivation on maintaining some observed healthy behaviour respectively. The phone call was closed with a concluding statement summing up the feedback issued before by the system. The questions and feedback were automatically generated by CAPSYS and were issued to the patients in spoken natural language by means of a text-to-speech software (TTS). The system was implemented to run fully automatically and could be accessed at any time of day. In case of systolic blood pressure higher than 140 mmHg, the patient was advised to rest for a while and then repeat the measurement. The system also advised the patients to contact a doctor in case of constantly high blood pressure. Patients with values above 140 mmHg were also particularly marked in the web interface when the treating physician accessed the system. Apart from that, all participants have been informed that there were no direct alerts in cases of high blood pressure provided within the study. The treating neurologist could access the data provided by his patients through a web interface, offering both a numerical as well as an adaptable graphical representation of the patient data for a certain period of time. The use of CAPSYS within the study has not replaced or reduced the existing information exchange between the neurologist and the corresponding referring physicians, which was proceeded according to the practices of the Luxembourgish healthcare system. Technically, CAPSYS offers the possibility for further physicians, e.g. the treating general practitioner, to access and monitor the data gathered from their patients. However, in the scope of this study, this option was deliberately discarded in order to avoid potential bias caused by the general practitioner accessing and interpreting the CAPSYS data. In contrast to the IC group, SC participants received only the usual care including blood analyses, blood pressure controls and individual advice on healthy lifestyle during the outpatient treatment given by the neurologist, by the general practitioner and by other physicians. Information material concerning a healthy lifestyle was provided to both groups.\n\nBODY.METHODS.DATA COLLECTION:\nDemographic and medical information of each participant was recorded by the study personnel in a predefined form, including body weight and height, medical history, current medication, smoking habits, blood pressure and heart rate as well as recent blood test results (HDL, LDL, HbA1c, glycaemia and triglycerides). Furthermore, participants were asked to fill in three questionnaires exploring their nutritional habits, physical activity and quality of life. The latter was measured using the standardised EQ-5D-5L instrument provided by the EuroQol Group [11]. Six months after enrolment, participants were asked to fill in the same questionnaires again, and current medical data (weight, blood pressure, heart rate, blood test results, smoking habits and medication) were again recorded by the study personnel. In addition, IC participants were asked to share their experiences with using CAPSYS and to provide their opinions about the system in a predefined questionnaire, which encompasses the well-established System Usability Scale (SUS) [12] and some further more specific questions concerning the usage of CAPSYS and its particular features. There was also space left for open-ended comments and suggestions at the end of the questionnaire.\n\nBODY.METHODS.DEPENDENT MEASURES:\nThe impact of the intervention was assessed based on the changes of cerebro-cardiovascular risk parameters during the six-month trial period, whereby changes in the IC group were compared to those in the control group (SC). Changes in systolic blood pressure, HDL, LDL, HbA1c, glycaemia, triglycerides and BMI were considered as primary dependent measures (see Table 3). Changes in self-reported weekly consumption of fruits and vegetables, whole grain food and sweets as well as changes in self-reported weekly duration of physical activity and quality of life were analysed as secondary measures. Due to the low number of smokers among the study participants (SC: 2, IC: 6), smoking habits were not evaluated.\nTable 3Overview of baseline values and evaluation of primary dependent measures in SC and IC groupsSCICBaselineEvaluationBaselineEvaluation\nParametric data\n\nMean (±SD)\n\nT-test\n\nMean (±SD)\n\nT-test\nSystolic BP [mmHg]139.6 (±21)mean of diff. =0.19145 (±19.4)mean of diff. =−9p =0.96\np\n= 0.03\n95 % CI = [–7.5, 7.88]95 % CI = [–17.29, –0.71]Cohen's d =0.42BMI [ kg/m2]27 (±4.3)mean of diff. =0.0328 (±4.3)mean of diff. =−0.18p =0.9p =0.4395 % CI = [–0.49, 0.55]95 % CI = [–0.65, 0.28]\nNon-parametric data\n\nMedian [IQR]\n\nWilcoxon\n\nMedian [IQR]\n\nWilcoxon\nHDL [ mg/dl]57 [45, 51]pseudo-median of diff =1.553 [47, 74]pseudo-median of diff =−1.5p =0.53p =0.4495 % CI = [–2.5, 4.5]95 % CI = [–4.5, 2]LDL [ mg/dl]96 [71, 114]pseudo-median of diff =−195 [76, 117]pseudo-median of diff =−7.9p =0.76\np\n= 0.04\n95 % CI = [–10.5, 6]95 % CI = [–18.5, –0.5]r =0.24HbA1c [ %]5.8 [5.6, 5.9]pseudo-median of diff =05.9 [5.5, 6.25]pseudo-median of diff =0.1p =0.92p =0.3795 % CI = [–0.25, 0.2]95 % CI = [–0.1, 0.25]Glycaemia [ mg/dl]98 [89, 106.75]pseudo-median of diff =0.5102 [92.5, 114.5]pseudo-median of diff =2.5p =0.78p =0.1995 % CI = [–5.5, 5]95 % CI = [–2, 6]Triglycerides [ mg/dl]95 [73, 134.25]pseudo-median of diff =−6105 [78, 132.5]pseudo-median of diff =−12.5p =0.39\np\n= 0.04\n95 % CI = [–21, 10]95 % CI = [–26, –0.5]r =0.25(statistically significant values are marked in bold) Statistical analyses were carried out on an intention-to-treat basis using RStudio (Version 0.98.978) with a significance level of 0.05. Parametric data (paired and unpaired samples) were evaluated with the Student's t-test approach, and the corresponding effect size was calculated with Cohen's d. Non-parametric data were evaluated using the Wilcoxon signed-rank test (for paired samples) or the Mann-Whitney U test (for unpaired samples) respectively, and effect size was calculated as \\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym} \n\t\t\t\t\\usepackage{amsfonts} \n\t\t\t\t\\usepackage{amssymb} \n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$r = \\frac {Z}{\\sqrt {N}}$\\end{document}r=ZN. For non-parametric paired samples, the pseudo-median is computed as the Hodges-Lehmann estimate.\n\nBODY.RESULTS.EFFICACY OF THE INTERVENTION:\nFinal questionnaires on nutritional habits, physical activity and quality of life could be collected from 68 participants (SC: 36; IC: 32) at the end of the study. This results in an overall dropout rate of 28 % (SC: 22 %; IC: 33 %). Further participant data, such as blood test values, could be retrieved from medical records. Out of the 48 recruited IC participants, 11 (23 %) did not use CAPSYS at all. The remaining 37 IC subjects (77 %) called the system up to 55 times during the study period (mean = 23.32; SD = 14.1; median = 24). Within-subjects analyses of primary dependent measures showed the following statistically significant changes between baseline and post-intervention: \nDecrease of systolic blood pressure in IC group (two-sided paired-samples t-test: mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]; Cohen's d = 0.42: large effect size) (see Fig. 1), with no corresponding significant difference in SC group (p = 0.96);\nFig. 1Systolic blood pressure. Significant decrease of systolic blood pressure in IC groupDecrease of low-density lipoprotein (LDL) levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]; r = 0.24: medium effect size), with no corresponding significant difference in SC group (p = 0.76) (see Fig. 2);\nFig. 2LDL. Significant decrease of LDL levels in IC groupDecrease of triglyceride levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]; r = 0.25: medium effect size), with no corresponding significant difference in SC group (p = 0.39) (see Fig. 3);\nFig. 3Triglycerides. Significant decrease of triglyceride levels in IC groupNo statistically significant changes could be found for any of the other primary measures (BMI, HDL, HbA1c and glycaemia). In this context, it needs to be stated that, at baseline, there were no statistical differences between both groups concerning the proportions of patients taking antihypertensives (SC: 36 [78 %]; IC: 43 [90 %]; p = 0.22), antidiabetic drugs (SC: 5 [11 %]; IC: 8 [17 %]; p = 0.61) or cholesterol-lowering medication (SC: 39 [85 %]; IC: 44 [92 %]; p = 0.47). Concerning the secondary dependent measures, we could observe the following statistically significant results: \nIncrease of self-reported fruit and vegetable consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.67);Decrease of self-reported sweets consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.06);Difference between SC and IC groups concerning the change of self-reported whole-grain food consumption (Mann-Whitney U test: difference in location = 3.26 servings/week; p = 0.04; 95 % CI = [0.00006, 7]; r = 0.24: medium effect size);No statistically significant changes for self-reported physical activity and quality of life.\n\nBODY.RESULTS.USABILITY AND USER ACCEPTANCE OF THE INTERVENTION:\nAssessments of the intervention based on the System Usability Scale (SUS) were provided by 28 participants of the IC group, 2 of which were declared invalid, as these participants have demonstrably never used CAPSYS during the trial period, and consequently, they were considered unable to assess the intervention. The average SUS score for CAPSYS was 80.1 (SD = 16.22; median = 78.75; min = 37.5; max = 100; 95 % CI = [73.54, 86.65]). According to Sauro and Lewis, this average score corresponds to an \"A–\" school grade and a percentile of 85–89, meaning that CAPSYS scored better than 85 to 89 % of all systems considered in the Sauro and Lewis study (see [13], chapter 8, page 204, table 8.6). Using the simplified regression equation proposed by Lewis [14], the Likelihood to Recommend for each CAPSYS user was derived from the corresponding SUS scores as LTR = SUS/10. With these values, we could identify 10 promoters (38 %; LTR ≥ 9) and 4 detractors (23 %; LTR ≤ 6) among the 26 participants who provided valid SUS scores, which results in a positive Net Promoter Score (NPS) of 23 [15], meaning that there are 23 % more users who would recommend CAPSYS (promoters) than users who would argue against using the system (detractors). Beside the standardised SUS questionnaire, IC participants were also asked to asses the voice of the text-to-speech module applied in CAPSYS and the automatically generated utterances issued by the system. The results concerning these questions are presented in Table 4.\nTable 4Evaluation of CAPSYS's voice and utterancesScaleResultsVoice1: pleasant – 5: unpleasantmean =1.77;median =1.5;SD =0.991: difficult to understand – 5: easy to understandmean =4.28;median =5;SD =1.141: natural – 5: unnaturalmean =2.15;median =2;SD =1.121: too fast – 5: too slowmean =3.2;median =3;SD =0.5Utterances1: diversified – 5: unvariedmean =3.28;median =4;SD =1.241: inappropriate – 5: appropriatemean =3.46;median =3;SD =1.071: too short – 5: too longmean =3.2;median =3;SD =0.5 Concerning the frequency of use, the majority of the 26 IC participants who answered to the usability questionnaire indicated that they would prefer using CAPSYS once (11; 42 %) or twice (9; 35 %) per week. None of the respondents was willing to use the system more than twice a week, 2 (8 %) preferred to use it less than once a week and 4 (15 %) expressed that they would not use it at all. The approach of connecting to CAPSYS by calling the system whenever they wish was favoured by most of the respondents (18; 69 %) over the potential alternatives of being called by the system (3; 12 %) or receiving reminders to call the system (2; 8 %). Although CAPSYS does not offer speech recognition, we asked users if they prefer to have such an input option instead or in combination with the implemented keypad input. In this context, using the phone keypad was identified as the most preferred way of communication with such a system (20; 77 %) as compared to speech input (1; 4 %) or a combination of both (4; 15 %). The majority of the respondents were interested in having insight into the data history gathered by CAPSYS, either online (9; 35 %) or in a printed version (11; 42 %). Concerning a potential alternative interface for CAPSYS beside the phone interface, 10 (38 %) participants were interested in a corresponding website and 4 (15 %) fancied the idea of having a CAPSYS smartphone app. Regarding the question if the use of CAPSYS has motivated them to a healthier lifestyle, 5 (19 %) of the respondents stated that through the intervention they started eating healthier, 3 (12 %) reported to have become physically more active and 12 (46 %) claimed to have achieved both healthier eating and increased physical activity. This means that, in total, 20 (77 %; 95 % CI = [59 %, 95 %]) of the respondents expressed an improvement of their health-related lifestyle (improved nutrition or increased physical activity or both) through the use of CAPSYS.\n\nBODY.DISCUSSION:\nThe positive effects that could be observed in the IC group concerning systolic blood pressure, LDL and triglyceride levels as well as the self-reported improvements of nutritional habits can be regarded as an indicator that a computerised phone-based intervention, such as CAPSYS, can support the reduction of cerebro-cardiovascular risk when offered in addition to usual care. An average decrease in systolic blood pressure of 9 mmHg among CI participants can be regarded as clinically significant [16]. The same also holds for the observed average decreases of 7.9 mg/dl for LDL [17] and 12.5 mg/dl for triglycerides [18]. Though, the relatively wide 95 % confidence intervals retrieved in the statistical analysis indicate that the cohort size was probably too small to be able to demonstrate strong clinical effects. The evaluation of BMI, HDL, HbA1c and glycaemia values showed no significant changes in the two groups. Our results are to some extent supported by the recently published Australian CLIP study, which found that telephone coaching performed by human health care professionals can result in a significant reduction of LDL and total cholesterol values in the intervention group [19]. A systematic review by Goode et al. also underlines the efficacy of telephone-based lifestyle coaching. In 20 out of 26 studies, telephone support by health professionals have led to significant improvements concerning physical exercises and healthy nutrition [20]. However, personal telephone coaching by health experts requires intensive use of human resources and is associated with enormous costs, which limits its widespread distribution to larger patient groups. CAPSYS is a system that supports prevention initiatives by supporting individuals in daily life settings. It can be assumed that a large percentage of the total target group is not willing to perform any lifestyle changes at all, no matter which kind of support they will receive. So, it has to be taken into account that our study participants are a selected subgroup of the target population with a potentially higher motivation to change risk factors and lifestyle. However, this selection bias in general concerns all prevention initiatives, and the randomisation process should ensure that the general motivation is balanced across both study arms. Compared to therapy studies, participants in prevention studies mostly do not see any direct measurable advantages in their actual health status. Missing short-term improvements are therefore often a reason for higher dropout rates. However, compared to other studies in secondary prevention, the moderate and balanced dropout rates of both CAPSYS arms should not have significantly affected the study results. On the other hand, self-reported consumptions of fruits, vegetables or sweets have a high potential for reporting bias. Therefore, in our study, this kind of information is only considered as secondary depended measures. The improvements of nutritional habits in the IC group (5 servings of fruits and vegetables more per week; 2 servings of sweets less per week) are significant, but have to be treated with caution as they are based on self-reported values and thus less reliable. As the dropout rates were not significantly different for both groups (SC: 22 %; IC: 33 %; p = 0.31), it can be supposed that the withdrawal of IC patients from the clinical trial was not substantially influenced by the intervention itself, but it was due to common reasons, like lack of time, forgetting appointments or just lack of motivation. Furthermore, it remains open how the observed positive effects will evolve after the study period and if they actually are of a long-term nature. The usability evaluation revealed that the CAPSYS approach was well accepted by the study participants. In particular, the large proportion of respondents (77 %) expressing a positive change of health-related behaviour due to the use of CAPSYS is remarkable. One might argue that this result is strongly biased due to the fact that users who have a positive experience with a system are more likely to finish a study and provide corresponding feedback than users with negative experiences. However, even if we consider all dropout IC participants as non-beneficiaries, the success rate concerning a positive health behaviour change would still be 42 % (95 % CI = [27 %, 57 %]). Unfortunately, our cohort was not large enough to perform subgroup analyses in order to evaluate the characteristics of beneficiaries and non-beneficiaries. A follow-up study focussing on such aspects might help to identify appropriate target groups for which a system like CAPSYS might be most beneficial and most accepted. During informal interviews at the end of the study, many of the IC participants explained that they often could not find the time or simply forgot to call CAPSYS. Taking this into account, the implementation of a call reminder functionality seems beneficial, even though in the feedback questionnaire, the majority of the respondents did not favour the concepts of being called or reminded by the system. Another important issue concerning risk factor reduction in the stroke prevention context is the topic of medication adherence. In order to support users in regularly taking their antihypertensive or cholesterol-lowering medication, CAPSYS could be extended to incorporate prompts in its automatically generated feedback messages asking the users if they have taken their prescribed medication according to their individual medication plan. Concerning the technical implementation of CAPSYS, it could be observed that, on average, the artificial voice applied in CAPSYS was perceived as rather pleasant, easy to understand and natural, and the speech rate was perceived as appropriate. The length of the utterances was, on average, perceived as adequate, but the feedback text might also be shortened to some extent. The results also show that there is some space for improvement concerning the diversity and adequacy of the automatically generated feedback. The offered keypad interface for data input was highly accepted by the users, and the need for an alternative input method, such as speech, was detected to be low. Unsurprisingly, only few users were currently interested in a mobile app version of CAPSYS. However, with increasing spread of smartphones, a mobile solution will certainly gain in importance in the future. What is already important for most users is to have access to their own self-monitored data, even if due to technical reasons they might only be able to access them in a printed form.\n\nBODY.CONCLUSION:\nIn summary, the present study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is in general well accepted by the affected patients. In a next step, CAPSYS could be extended to a disease management tool, involving health professionals from different disciplines, such as neurologists, cardiologists, dieticians, physiotherapists etc., in the treatment of patients. One aspect that could be explored in future research is if the motivational effect of CAPSYS could be strengthened through an increased involvement of the treating physician and through incorporation of social interaction.\n\nQuestion:* Compared to Standard care what was the result of CAPSYS system on Self-reported consumption of sweets?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1172	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Sleep quality in mechanically ventilated patients: comparison between NAVA and PSV modes\n\n ABSTRACT.BACKGROUND:\nMechanical ventilation seems to occupy a major source in alteration in the quality and quantity of sleep among patients in intensive care. Quality of sleep is negatively affected with frequent patient-ventilator asynchronies and more specifically with modes of ventilation. The quality of sleep among ventilated patients seems to be related in part to the alteration between the capacities of the ventilator to meet patient demand. The objective of this study was to compare the impact of two modes of ventilation and patient-ventilator interaction on sleep architecture.\n\nABSTRACT.METHODS:\nProspective, comparative crossover study in 14 conscious, nonsedated, mechanically ventilated adults, during weaning in a university hospital medical intensive care unit. Patients were successively ventilated in a random ordered cross-over sequence with neurally adjusted ventilatory assist (NAVA) and pressure support ventilation (PSV). Sleep polysomnography was performed during four 4-hour periods, two with each mode in random order.\n\nABSTRACT.RESULTS:\nThe tracings of the flow, airway pressure, and electrical activity of the diaphragm were used to diagnose central apneas and ineffective efforts. The main abnormalities were a low percentage of rapid eye movement (REM) sleep, for a median (25th-75th percentiles) of 11.5% (range, 8-20%) of total sleep, and a highly fragmented sleep with 25 arousals and awakenings per hour of sleep. Proportions of REM sleep duration were different in the two ventilatory modes (4.5% (range, 3-11%) in PSV and 16.5% (range, 13-29%) during NAVA (p = 0.001)), as well as the fragmentation index, with 40 ± 20 arousals and awakenings per hour in PSV and 16 ± 9 during NAVA (p = 0.001). There were large differences in ineffective efforts (24 ± 23 per hour of sleep in PSV, and 0 during NAVA) and episodes of central apnea (10.5 ± 11 in PSV vs. 0 during NAVA). Minute ventilation was similar in both modes.\n\nABSTRACT.CONCLUSIONS:\nNAVA improves the quality of sleep over PSV in terms of REM sleep, fragmentation index, and ineffective efforts in a nonsedated adult population.\n\nBODY.BACKGROUND:\nSleep is severely disturbed in mechanically ventilated ICU patients [1-3]. Sleep alterations are known to have deleterious consequences in healthy subjects, but the paucity of data in the literature [4-7] makes it difficult to determine the impact of sleep abnormalities in ICU patients. Intensive care unit (ICU) patients present disrupted sleep with reduced sleep efficiency and a decrease in slow wave sleep and rapid eye movement (REM) sleep [8-10]. Furthermore, polysomnographic studies performed on mechanically ventilated ICU patients have demonstrated an increase in sleep fragmentation, a reduction in slow-wave and REM sleep, and an abnormal distribution of sleep, because almost half of the total sleep time occurred during the daytime [11-13]. In the Freedman et al. study [14], noise was considered a nuisance for the patients questioned; the most annoying noises were alarms and caregivers' conversations. When the same authors simultaneously recorded noise and microarousal, they identified an association between arousal and noise in only 11-17% of the cases [11]. This percentage is confirmed by Gabor et al. [3] where 21% of the arousal interruptions were explained by loud noises and 7% to patients' care. Seventy-eight percent of the microarousals were not associated with environment noises, suggesting other causes, such as patient/ventilator asynchrony [3,14]. The effects of assist control ventilation (ACV) and pressure support ventilation (PSV) on sleep fragmentation have been examined in critically ill patients receiving mechanical ventilation [15], where PSV mode was associated with increases in the number of central apneas and subsequent sleep fragmentation compared with AVC. Furthermore, the study suggested that PSV by itself or an excess of ventilator assistance with PSV could have caused such sleep alterations. Indeed, ventilatory settings adjusted during wakefulness may become excessive during sleep, as the patients' ventilatory demand is reduced while asleep [16]. Whether these results can be explained by the ventilatory mode itself or how it was adjusted is an important issue, because hyperventilation and patient ventilator asynchrony may result from PSV as well as ACV in mechanically ventilated ICU patients [17]. Fanfulla et al. [18] compared two ventilatory settings in nine patients under long-term PSV for neuromuscular disease. The initial setting was set according to clinical parameters, and the second setting was adjusted with measurement of esophageal pressure (physiological setting) to optimize patient effort. The physiological setting improved the duration and quality of sleep, decreased episodes of apnea, and the amount of inefficient efforts for ventilator triggering [18]. The level of pressure support and PEEP tended to decrease, with a lowering of intrinsic PEEP and patient-ventilator asynchronies. A recent study by Cabello et al. [19] compared the impact of three modes of ventilation (AVC, PSV, and SmartCareTM) on the quality of sleep in alert and nonsedated patients, and no difference for the architecture, fragmentation, and duration of sleep was found among the three modes. Our hypothesis is that NAVA ventilation is superior to PSV by allowing optimal patient-ventilator synchrony and thereby decreasing sleep fragmentation.\n\nBODY.METHODS:\nThis study was approved by the Ethics Committee of the Hôpital du Sacré-Coeur de Montréal, and patients or their surrogates gave written informed consent.\n\nBODY.METHODS.PATIENTS:\nThis physiologic study was conducted in a 22-bed medical ICU during a 12-month period. The weaning phase of mechanical ventilation was chosen because patient-ventilator asynchrony is common when patients are spontaneously triggering breaths. The inclusion criteria required that the patient was conscious, free from sedation and opiate analgesia for ≥ 24 hours, and ventilated in PSV mode with an FIO2 < 60%, PEEP = 5 cmH2O, and SpO2 ≥ 90%. Exclusion criteria consisted of the presence of a central nervous system disorder, Glasgow Coma Scale score < 11, hemodynamic instability, renal and/or hepatic insufficiency, and ongoing sepsis.\n\nBODY.METHODS.METHODS:\nAll patients were ventilated through an endotracheal tube or a tracheostomy; once they met the inclusion criteria, they were connected to a Servo i ventilator (Maquet critical Care, Sölna, Sweden), equipped with a neurally adjusted ventilator assist system (NAVA). The electrical activity of the diaphragm (EAdi) is captured with the EAdi catheter (Maquet Critical Care, Sölna, Sweden) consisting of a 16-Fr gastric tube equipped with electrodes. End-tidal CO2 was monitored with the Servo-i Volumetric CO2 module. The two different ventilatory modes were delivered in a randomized order using a closed-envelope technique during four periods of 4 hours: a daytime period from 7 to 11 a.m. and 12 to 4 p.m., and a nocturnal period from 10 p.m. to 2 a.m. and 3 to 7 a.m. To prevent possible data contamination from the previous mode of ventilation, a 1-hour washout period after a ventilator change was introduced before data acquisition (Figure 1; Study Protocol). Figure 1Patients were studied for a period of 4 hours for each recording sequences and for more than 19 consecutive hours. During periods of wakefulness, PSV and NAVA were clinically adjusted by the attending physician to obtain a tidal volume of 8 mL/kg of predicted body weight and a respiratory rate ≤ 35 breaths/min. For both modes of ventilation, inspiratory triggering sensitivity was set at thresholds that would not allow auto-triggering for both modes of ventilation: 0.5 mV in NAVA and 5 in PSV. EEG was recorded from standard locations: left frontal/right mastoïd reference (F3/M2 or F3/A2), right frontal/left mastoid reference (F4/M1or F4/A1), left central/right mastoïd reference (C3/M2 or C3/A2), right central/left mastoïd reference (C4/M1 or C4/A1), left occipital/right mastoïd reference (O1/M2 or O1/A2), and right occipital/left mastoïd reference (O2/M1or O2/A1), according to the International 10-20 System for electrode placement [20]. The standard reference used was the left mastoid lead [20]. Two electro-oculogram and three chin electromyogram leads were used to score REM and non-REM sleep. The electroencephalogram, the right and left electro-oculogram, and the submental electromyogram signals were amplified and recorded in the data acquisition system (Alice 5 polysomnography system using Alice® SleepwareTM 2.5 software, Respironics, Nantes, France). Sleep recordings were manually read and scored by an independent pulmonologist blinded to the study, using the criteria of Rechtschaffen and Kales [21,22] and the criteria of the American Sleep Disorder Association for arousals and awakenings [23,24]. Diagnosis of central apnea was based on international recommendations [24]. The diagnosis of central apnea is characterized by absent breathing and respiratory effort for a period of at least 10 seconds. Arousals and awakenings were considered secondary to apnea when occurring within three cycles and/or 15 sec after a respiratory event [25,26]. Ineffective efforts were defined as an inspiratory effort observed by a peak electrical activity of the diaphragm (EAdi peak) without a simultaneously triggered ventilator cycle. Airflow, Paw, and EAdi were acquired from the ventilator through a RS232 interface at a sampling rate of 100 Hz, recorded by a dedicated software (Nava Tracker V. 2.0, Maquet Critical Care, Sölna, Sweden), and an analyzer using software Analysis V 1.0 (Maquet Critical Care) and a customized software based for Microsoft Excel. An arousal or awakening event was considered secondary to ineffective triggering when it occurred within 15 seconds after the asynchrony [19]. Noise was measured with a portable noise meter at the level of patient's head (Quest Technologies, Oconomowoc, WI). Arousals and awakenings were associated with the noise when they occurred 3 seconds after or within noise increase ≥10 dB [3,11]. Inspiratory trigger delay was calculated as the time difference between the onset of EAdi peak and Paw inspiratory swings. Cycling-off delay was calculated as the time difference between the end of the inspiratory EAdi peak deflection and the onset of expiratory flow.\n\nBODY.METHODS.STATISTICS ANALYSIS:\nStatistical analysis was performed using SPSS statistical software (SPSS 17.0). Continuous variables were expressed as median (25th-75th percentile) or mean ± SD. Data were compared using the general linear model for repeated measures (GLM). The small sample of patients led us to use Wilcoxon's t test for paired samples, and the p values for multiple comparisons were corrected for the Bonferroni inequality. A two-tailed p value < 0.05, corrected as needed, was retained to indicate statistical significance.\n\nBODY.RESULTS.PATIENTS:\nFourteen patients were selected and none were excluded during the study. Their main characteristics are shown in Table 1. Acute respiratory failure was the most frequent reason to initiate mechanical ventilation in ten patients, postoperative complications in three patients, and septic shock in one patient. Table 1 Characteristics of patients Characteristics of patients Sex (M/F) (8/6) Age (yr ± SD) 64 ± 11 SAPS II ± SD 46 ± 12 Duration of MV (days ± SD) 17 ± 9 Tracheotomy (%) 2 (14) Cause for initial MV (%) Acute respiratory failure 10 (71.5%) Postoperative complication 3 (21.5%) Septic shock 1 (7%) M = male; F = female; SAPS = Simplified Acute Physiology score; MV = mechanical ventilation. \n\nBODY.RESULTS.SLEEP RECORDINGS:\nAll patients completed the study, and recordings were well tolerated. Individual sleep data are shown in Table 2. The median total sleep time was 564 (range, 391-722) minutes. The median sleep efficiency (i.e., the percentage of sleep during the study) was 59% (range, 41-75%). The main abnormalities observed on each patient were a diminished percentage of REM sleep, counting for only 11.5% (range, 8-20%) of total sleep time, and a high fragmentation index with 25 arousals and awakenings per hour (range, 18-51). Although interindividual variability was large, the median quantity of slow-wave sleep (stages 3 and 4 or NREM3 stage) was normal, with a median of 18.5 (range, 11.5-22; Table 2). Table 2 Sleep architecture and fragmentation during the study (16 hours) Patient Stage 1 (%) Stage 2 (%) Stages 3 and 4 (%) Rapid eye movement (%) Fragmentation index 1 5 72.5 19.5 2.5 23.5 2 2.5 67 22.5 7 35.5 3 4 61 24.5 9 30.5 4 10 57 11 20 68 5 9 61 24 5.5 16.5 6 6 57 24 12.5 15 7 5 63 22 7.5 13.5 8 11 66.5 9 10.5 64.5 9 5.5 58 17.5 19 15.5 10 11 60.5 9.5 17 56.5 11 3 66 21 9 26 12 3.5 61.5 13 22 23 13 5.5 60 13 21.5 22 14 10 59 10.5 20.5 67.5 Median [25-75 th percentiles] 5.5 [4-10] 61 [59-65] 18.5 [11.5-22] 11.5 [8-20] 25 [18-51] \n\nBODY.RESULTS.VENTILATORY MODES AND SLEEP DISTRIBUTION:\nSleep efficiency and architecture appeared very different for both modes of ventilation (NAVA and PSV). Stage 1 (NREM1 stage) lasted longer during PSV compared with NAVA 7.5% (range, 4-15%) vs. 4% (range, 3-5%; p = 0.006). Stage 2 (NREM2 stage) also lasted longer in PSV than NAVA 68% (range, 66-75%) vs. 55% (range, 52-58%; p = 0.001). Stage 3-4 (NREM3 stage) was shorter in PSV as opposed to NAVA 16.5% (range, 17-20%) vs. 20.5% (range, 16-25%; p = 0.001). REM stage (R stage) was much shorter in PSV than in NAVA 4.5% (range, 3-11%) vs. 16.5% (range, 13-29%; p = 0.001). The fragmentation index was different between the two ventilation modes, with 40 ± 20 arousals and awakenings per hour in PSV and 16 ± 9 during NAVA (p = 0.001; Figure 2 Sleep stage (percent of total sleep) during two ventilatory modes; Table 3). Figure 2Sleep stages (percent of total sleep) during the two ventilator modes: pressure support ventilation (PSV), and neurally adjusted ventilatory assist (NAVA). REM = rapid eye movement. Table 3 Comparison of sleep quality between the ventilatory modes PSV NAVA \n p \n Stage 1, % 7.5 [4-15] 4 [3-5] 0.006* Stage 2, % 68 [66-75] 55 [52-58] 0.001* Stage 3 and 4, % 16.5 [17-20] 20.5 [16-25] 0.001* REM, % 4.5 [3-11] 16.5 [13-29] 0.001* Fragmentation index, (n/h) 33.5 [25-54] 17.5 [8-21.5] 0.001* Sleep efficacy, % 44 [29-73.5] 73.5 [52.5-77] 0.001* PSV = pressure support ventilation; NAVA = neurally adjusted ventilatory assist; REM = rapid eye movement; Fragmentation Index = number of arousals and awakenings per hour of sleep; Sleep efficiency = duration of sleep/total duration of recording. Values are expressed as median [interquartile range]. * p < 0.05. Minute ventilation did not significantly differ between PSV and NAVA with median values of 9.8 L/min (range, 8.0-10.9), and 9.6 L/min (range, 7.5-11.0) respectively (p = 0.51). The median respiratory rates were 17 breaths/min (range, 14-21), and 20 breaths/min (range, 15-23) during PSV and NAVA (p = 0.14). Median tidal volume was 420 mL (8.1 mL/Kg of predicted body weight; range, 375-479 mL), and 378 mL (7.3 mL/Kg of predicted body weight; range, 370-448 mL) during PSV and NAVA, respectively (p = 0.36). The mean PSV level was 15 ± 5 cmH2O, and the mean NAVA level was 1.6 ± 1.4 cmH2O/μV. Positive end-expiratory pressure was kept at 5 cmH2O for all patients.\n\nBODY.RESULTS.APNEAS AND INEFFECTIVE EFFORTS:\nTen of the 14 patients presented sleep apnea, and 11 exhibited ineffective efforts. The mean index of sleep apneas (number of apneas per hour of sleep) was 10.5 ± 11 apneas during PSV and 0 during NAVA (p = 0.005) and ineffective efforts (number of ineffective efforts per hour of sleep) was 24 ± 23 ineffective efforts during PSV and 0 during NAVA (p = 0.001). Over-assistance during sleep is sensed on the previous three cycles preceding central apnea. Tidal volume and minute ventilation increased, whereas ETCO2 and EAdi decreased over the three cycles preceding central apnea Table 4. Table 4 Oscillatory behaviour of various ventilator parameters for stages 3-4 with PSV mode of ventilation Respiratory variables Baseline Pre-apneas PSV V T (mL) 425 ± 67 585 ± 70 RR (breath/min) 13 ± 2 12 ± 1 VE (L/min) 5.2 ± 0.5 6.8 ± 0.8 ETCO 2 (mmHg) 46 ± 1.4 42 ± 1.0 EAdi (mVolt) 15 ± 4 10 ± 2 V T = tidal volume; RR = respiratory rate; VE = minute ventilation; ETCO 2 = end-tidal carbon dioxyde; PSV = pressure support ventilation. \n\nBODY.RESULTS.TRIGGER DELAY AND CYCLING-OFF DELAY:\nDuring N-REM sleep in PSV, the trigger delay increased on average by 80 ± 26 (msec) during stage 1 versus 158 ± 42 (msec) during stage 3 and 4. The expiratory trigger (cycling-off) increased in PSV by 158 ± 103 (msec) and 258 ± 87 (msec) during stage 1 and stages 3 and 4, respectively. In NAVA, the trigger delay remained stable during sleep, 68 ± 24 (msec) during stage 1 and 72 ± 32 (msec) during stages 3 and 4. The expiratory trigger also remained stable in NAVA: 39 ± 28 (msec) during stage 1 and 41 ± 34 (msec) during stages 3 and 4.\n\nBODY.RESULTS.NOISE:\nIn ICU, we recorded the average baseline ambient noise level and evaluated arousals from this baseline to a peak noise level ≥ 10 dB above ambient noise level. The mean noise level was recorded at 64 ± 8 dB, with the peak level recorded at 111 dB and the minimal level at 52 dB. No differences were observed between the two different ventilatory modes concerning the index of fragmentation associated with noise: 7.5 ± 3 during PSV and 6 ± 3.5 during NAVA (p = 0.19). These data indicate that 18% during PSV and 21% during NAVA of the fragmentation was associated with sudden increases in noise.\n\nBODY.RESULTS.SLEEP DISTRIBUTION AMONG STUDY PERIODS:\nThe cross-over pattern was balanced with an equal number of patients from each sequence initiating the rotation. Independent of the ventilatory mode, sleep efficiency and sleep architecture had a significantly different distribution based on the study period considered (Figure 3--sleep stage (percent of total sleep) during the four daily time periods). Sleep efficiency was the same in the two daytime periods (2 periods during the day): 52% (range, 26-67%) during the first day period (7 h-11 h a.m.) and 51.5% (range, 27-67%) during the second day period (12 h-4 h p.m.; p = 0.18). Sleep efficiency also did not differ between the two night periods: 65.5% (range, 37-82%) during the first night period (10 h p.m.-2 h a.m.) and 65% (range, 45-82.5%) during the second nighttime period (3 h-7 h a.m.; p = 0.11). Figure 3First daytime period (7 h-11 h a.m.), second daytime period (12 h-4 h p.m.), first nighttime period (10 h p.m. to 2 h a.m.) and second nighttime period (3 h-7 h a.m.). There was no statistical difference between stage 1 and 2 recording periods. A greater duration of slow-wave sleep (stage 3-4) was found during the first nocturnal period with a median percentage 22.5% (range, 20-33.5%) vs. 15.5% (range, 7-19.5%) during first day period (p = 0.03), vs. 15% (range, 7-18%) during second day period (p = 0.01) and vs. 18% (range, 13-21%) during second nighttime period (p = 0.001). The proportion of REM sleep was longer during the second nocturnal period, with a median percentage of 16.5% (range, 15-25%) vs. 11.5% (range, 5-15%) during first day period (p = 0.001) vs. 9% (range, 5-15%) during second day period (p = 0.001) and vs. 10.5% (range, 7-21%) during first nighttime period (p = 0.02). The fragmentation index did not differ with 26 (range, 20-65) arousals and awakenings/hour during first daytime vs. 24 (range, 19-55), 23 (range, 18-57), and 19 (range, 15-53) during the second day period and first and second night period, respectively (p = 0.08). Ineffective effort indexes per hour also were similar across the four periods.\n\nBODY.DISCUSSION:\nIn a study where spontaneously breathing patients were conscious and under mechanical ventilation, proportions of sleep fragmentation sleep architecture and sleep quality were positively influenced by NAVA. In the PSV mode, a low percentage of REM sleep and a high degree of fragmentation were present. NAVA showed a normal percentage of REM sleep with an important decrease in fragmentation. Less than 15% of the sleep fragmentations in the PSV mode were attributed to apneas and ineffective efforts, whereas in NAVA, no asynchrony (no apnea and no ineffective patient efforts) were recorded. Environmental noise is responsible for 18% of the arousals and awakenings in PSV compared with 21% in NAVA, respectively. We observed results similar to the Cabello et al. [19] study concerning the rate of fragmentation, the number of central apneas, and the number of ineffective patient efforts during PSV. Another similar finding concerned the increased percentage of REM sleep during the second nighttime period recordings. However, one major difference between our study and the Cabello study is that they did not allocate an even distribution for each of the study periods and ventilatory strategies. Also, they did not allow washout periods between the ventilatory modes, which could possibly contaminate the recordings at the beginning of the next study period. Detecting asynchronies also was different; they used the airway pressure-flow signal and the thoracoabdominal plethysmography, whereas we observed the EAdi signal. Parthasarathy and Tobin [15] found a lower rate of sleep fragmentation during ACV compared with PSV. This was explained by the central apneas induced by over-assistance during PSV. In fact, tidal volume was much greater during PSV compared with ACV. This was validated by the addition of a dead space to the 11 patients showing central apneas, which significantly decreased the number of apneas. In the Toublanc et al. study [27], no difference was found in terms of quantity, quality of sleep, and in terms of arousal index between the AC and a low level of PSV assistance for the whole night. Toublanc et al. found that ACV was superior in terms of percentage of slow-wave sleep but not during REM sleep [27]. It is very difficult to compare the results for PSV because of a lack of information on expiratory triggering with Evita 4, number of asynchronies (tidal volume, respiratory rate, and minute ventilation). In the Toublanc study, the majority of patients were affected with COPD and pressure support was adjusted to 6 cmH2O. According to Brochard et al., it is suggested that for COPD patients, the pressure support needed to overcome resistance imposed by the endotracheal tube is higher than non-COPD patients: 12 ± 1.9 vs 5.7 ± 1.5 cmH2O respectively [28]. In the Leleu et al. study, pressure support must be superior to 6 cmH2O, particularly in COPD if the intention is to compensate work of breathing imposed by the endotracheal tube, ventilator circuit, and patient effort to trigger the demand valve during pressure support [29]. A low-pressure support only allows for partial relieve of imposed work of breathing without modifying the work necessary to trigger the demand valve. In the Toublanc study, pressure support set too low in COPD patients resulted in an increase in imposed work of breathing, which can be accounted for in the decrease in SWS and REM. The Toublanc study offers no information on expiratory triggering, which is somewhat important in COPD patients. Tassaux et al. recently have evaluated the positive impact of shortening inspiratory time in PSV on patient-ventilator asynchronies and the work of breathing in COPD patients. This study also demonstrated that the increase in expiratory trigger up to 70% of peak flow improved synchrony and decreased ineffective efforts without modifying work of breathing or minute ventilation [30]. Bosma et al. evaluated the impact on sleep with other modes of ventilation, such as the proportional assist ventilation (PAV). The objective of PAV, such as NAVA, is to improve patient ventilator synchrony by delivering ventilator assist proportional to patient effort. The study by Bosma et al. shows an improvement in the quality of sleep using PAV compared with PSV during one night sleep [31]. There are similarities between the Bosma study and ours. More specifically, PAV appeared superior to PSV in terms of decrease in arousals, improvement in sleep quality, decrease in amounts of arousals, awakenings per hour, and improved SWS and REM. With NAVA, we observed a decrease in tidal volume by up to 15% during REM sleep, which increased end-tidal CO2 by approximately 4 mmHg. Bosma et al. observed a tidal volume slightly more elevated in PSV compared with PAV (despite similar offloading of the work of breathing), resulting in a higher morning PaCO2 with PAV attributed to lower tidal volume and minute ventilation [31], thus offering perhaps a protection against central apneas. Finally, fewer patient-ventilator asynchronies were observed with PAV with fewer awakenings per hour [31]. Contrary to NAVA, PAV cannot eliminate wasted or ineffective efforts. There was a nonstatistically significant difference in ineffective triggering during inspiration; 19.6 n/hr for PSV vs. 11.6 n/hr for PAV [31]. According to Thille et al. ineffective efforts and double triggering are among the most frequent asynchronies: 85 and 13% respectively [32], which is somewhat contradictory to Bosma et al. who identify auto triggering as the most frequent asynchrony in PSV. We observed that the absence of central apnea and ineffective efforts in NAVA do not totally explain the great improvement in the SWS and REM sleep. This improvement may be explained in part by a microanalysis of the sleep architecture. The microanalysis suggests an over-assistance with PSV during the N-REM stages, because 100% of the fragmentations in PSV occurred during this stage. The tidal volume decrease in NAVA follows the respiratory physiologic changes during sleep, whereas in PSV we find a tidal volume oscillatory behavior due to constant inspiratory efforts, independent of the sleep stage and produces sequential over-assistance during N-REM sleep leading to a decrease in end-tidal CO2. It is our assumption that improvement of the slow-wave sleep and REM is most probably explained by better patient comfort through better neuromechanical coupling. During sleep, the respiratory accessory muscles (intercostals, scalene, and abdominals) decrease their muscle tone and the mechanical response of the diaphragm is, in part, spent in the production of a mechanical distortion of the chest wall, secondary to a lack of synchronization between diaphragmatic contraction and the accessory muscles. NAVA improves this mechanical distortion, whereas PSV worsens this distortion by a tidal volume oscillation (overshoot) during sleep, with a constant patient effort. Patient comfort is not only directly related to inefficient efforts and central apneas; the microanalysis showed that during N-REM sleep in PSV, the trigger delay increased during stage 1 versus during stage 3 and 4. The expiratory trigger increased in PSV during stage 1 and stages 3 and 4, respectively. In NAVA, the trigger delay remained stable during stage 1 and during stages 3 and 4. The expiratory trigger also remained stable in NAVA, during stage 1 and during stages 3 and 4. NAVA allows optimizing the neuromechanical coupling and therefore patient-ventilator synchrony [33] and allows for optimized adequacy between ventilatory load and patient breathing ability, thereby providing beneficial effects on sleep in ICU patients. It appeared to us that the EAdi tracing is much more efficient than flow and pressure tracings to detect asynchronies. Our study has some limitations; one is the open space between patients. This study included only 14 patients, which could favor the possibility of a type II error. Patients' heterogeneity implies that patients required bedside care, such as suctioning or other care, which could perhaps influence sleep fragmentation. The study by Cabello found that suctioning was associated with < 1% arousals and awakenings [19]. The choice for a 15-second interval between asynchrony and the occurrence of arousal was chosen based on one previous study on the same topic [19]. Literature on this specific time interval to choose is very scarce. In one study, it was shown that the breathing response to a complete airway occlusion was 20.4 ± 2.3 sec during NREM and 6.2 ± 1.2 sec during REM [34]. The choice of a 15-second interval seems very reasonable but may need further investigation. In a sleep laboratory, it is a lot easier to control the baseline ambient noise level. In a clinical environment, such as an ICU, we recorded the average baseline ambient noise level and evaluated arousals from this baseline to a peak noise level ≥10 dB above ambient noise level. There is therefore a potential for statistical inaccuracies. The fact that we stopped sedation 24 hours before beginning the study does not imply an absence of cumulative sedation. However, every patient had a Ramsay Score of 2 or less and a Glasgow Score of 11 (the maximum score for an intubated patient).\n\nBODY.CONCLUSIONS:\nThe ventilatory mode NAVA improves the quality of sleep by increasing the slow-wave sleep and REM and by decreasing fragmentation. NAVA improves patient comfort through better neuromechanical coupling during N-REM sleep, by a shorter trigger delay, and more efficient expiratory triggering. To minimize sleep fragmentation, optimal setting of pressure support level and expiratory trigger are paramount in PSV. However, proportional assistance modes of ventilation according to patient inspiratory effort, such as NAVA, appear to be a better choice to minimize sleep fragmentation.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nSD and PO drafted the manuscript, and PB, JPT, and PA revised the manuscript.\n\nQuestion: Compared to pressure support ventilation (PSV) what was the result of neurally adjusted ventilatory assist (NAVA) on episodes of central apnea and ineffective efforts?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1050	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy and Safety of Subcutaneous Golimumab in Methotrexate‐Naive Patients With Rheumatoid Arthritis: Five‐Year Results of a Randomized Clinical Trial\n\n ABSTRACT.OBJECTIVE:\nTo evaluate the safety and efficacy of golimumab through 5 years in adults with active rheumatoid arthritis (RA) who had not previously received methotrexate (MTX).\n\nABSTRACT.METHODS:\nIn the GO‐BEFORE study, 637 MTX‐naive adult patients with active RA were randomized (1:1:1:1) to placebo + MTX (group 1), golimumab 100 mg + placebo (group 2), golimumab 50 mg + MTX (group 3), or golimumab 100 mg + MTX (group 4). Inadequate responders in groups 1, 2, and 3 entered early escape at week 28 to golimumab 50 mg + MTX, golimumab 100 mg + MTX, or golimumab 100 mg + MTX, respectively; remaining patients in group 1 could cross over to golimumab 50 mg + MTX at week 52. Assessments included the American College of Rheumatology 20%/50%/70% improvement criteria (ACR20/50/70) response, the Disease Activity Score in 28 joints (DAS28) using C‐reactive protein (CRP) level, and the modified Sharp/van der Heijde score (SHS). Efficacy was analyzed using an intent‐to‐treat (ITT) analysis. Pharmacokinetics and immunogenicity were evaluated at selected visits.\n\nABSTRACT.RESULTS:\nA total of 422 patients completed golimumab treatment through week 256. At week 256, 72.8%, 54.6%, and 38.0% of all patients in the full ITT population (n = 637) had an ACR20/50/70 response, respectively; 84.1% had a good or moderate DAS28‐CRP response; and 72.7% had a clinically meaningful improvement in physical function. Radiographic progression was minimal in all treatment groups through week 256, and the overall mean change from baseline in SHS was 1.36. Serum trough golimumab concentrations were approximately dose proportional and maintained through week 256. Antibodies to golimumab occurred in 9.6% of patients through week 256. Infections were the most common type of adverse event (AE); 204 of 616 patients (33.1%) had ≥1 serious AE.\n\nABSTRACT.CONCLUSION:\nClinical efficacy with golimumab treatment was maintained through week 256 of the GO‐BEFORE trial of MTX‐naive RA patients. No unexpected AEs occurred; safety results through 5 years are consistent with earlier reports.\n\nBODY.INTRODUCTION:\nGolimumab, a fully human anti–tumor necrosis factor (TNF) antibody, has been shown to improve the signs and symptoms of rheumatoid arthritis (RA) in adults in large, randomized, placebo‐controlled phase 3 trials 1, 2, 3. The GO‐BEFORE trial evaluated the safety and efficacy of subcutaneous (SC) golimumab in adult patients with RA who had not previously received methotrexate (MTX) therapy, and results through 2 years have been reported 1, 4. In the GO‐BEFORE trial, patients treated with golimumab (50 mg or 100 mg) + MTX had significantly greater improvements in the signs and symptoms of RA than those treated with MTX monotherapy. These improvements were observed at week 24 1 and were maintained through 2 years 4. In addition, golimumab + MTX‐treated patients had significantly less radiographic progression through 1 year when compared with those who received MTX monotherapy 5. Here we report the final efficacy and safety results of the GO‐BEFORE trial through 5 years. Box 1Significance & Innovations\nClinical response to golimumab (50 mg and 100 mg) + methotrexate (MTX) was maintained through 5 years in adult patients with moderate to severe rheumatoid arthritis who had not previously received MTX.Safety findings were consistent with previous golimumab studies and other anti–tumor necrosis factor agents; no unexpected adverse events occurred.The incidence of antibodies to golimumab was low, and the presence of antibodies to golimumab was not associated with adverse events.\n\n\nBODY.PATIENTS AND METHODS.PATIENTS AND STUDY DESIGN:\nThe detailed eligibility criteria and study design of the GO‐BEFORE trial have been previously described 1. Briefly, adult patients with active RA who had not been previously treated with MTX were randomly assigned to receive SC injections of placebo + MTX (group 1), golimumab 100 mg + placebo (group 2), golimumab 50 mg + MTX (group 3), or golimumab 100 mg + MTX (group 4); injections were administered at baseline and every 4 weeks. Active RA was defined as ≥4 swollen joints, ≥4 tender joints, and at least 2 of the following criteria: C‐reactive protein (CRP) level of ≥1.5 mg/dl or erythrocyte sedimentation rate ≥28 mm/hour using the Westergren method; morning stiffness lasting ≥30 minutes; or evidence of bone erosion radiographs or magnetic resonance imaging 1. Eligible patients also could not have a history of latent tuberculosis (TB) prior to screening and could not have any signs or symptoms of active TB. Patients were screened for TB by chest radiographs (both posteroanterior and lateral views) within 3 months before the first study drug administration and diagnostic testing (tuberculin and QuantiFERON‐TB Gold tests) within 6 weeks before the first study drug administration. Patients with a newly identified positive result (tuberculin or QuantiFERON‐TB Gold testing) could participate in the trial if they initiated appropriate treatment for latent TB. Patients were stratified by investigational site and baseline CRP level (<1.5 mg/dl or ≥1.5 mg/dl). Placebo and golimumab injections were administered at baseline and every 4 weeks. At week 28, patients in groups 1–3 with an inadequate response to treatment entered blinded early escape such that patients in group 1 switched from placebo to golimumab 50‐mg injections, patients in group 2 initiated concomitant MTX therapy while continuing golimumab 100‐mg injections, and patients in group 3 increased their golimumab dose to 100 mg; patients in groups 1 and 3 continued concomitant MTX. Patients in group 4 did not have any changes in treatment regimen, regardless of their early escape status. The active‐control period continued through week 52. The long‐term extension began with the week‐52 visit and continued through week 268 (5 years). At week 52, patients in group 1 who did not have any swollen or tender joints continued MTX monotherapy; patients with at least 1 swollen or tender joint were switched from placebo injections to golimumab 50 mg. Patients in groups 2, 3, and 4 continued the treatment they were receiving at week 52. The blind was maintained until the week‐52 database was locked, after which treatment adjustments could be made at the investigator's discretion. Patients in group 1 who were receiving MTX monotherapy could initiate treatment with golimumab 50 mg, and a 1‐time golimumab dose increase to 100 mg or decrease to 50 mg was permitted (including patients who had dose‐escalated to 100 mg). Additionally, MTX therapy could be initiated or adjusted during the long‐term extension period. Concomitant therapy with nonsteroidal antirheumatic drugs (NSAIDs), corticosteroids, or other analgesics for RA could also be adjusted at the investigator's discretion. The final study golimumab injection was at week 252. After week 256, patients transitioned to standard‐of‐care treatment for RA, including commercially available biologic agents. The GO‐BEFORE trial was conducted according to the Declaration of Helsinki. The protocol was approved by the institutional review board or ethics committee at each site, and all patients gave written informed consent before any study‐related procedures were performed.\n\nBODY.PATIENTS AND METHODS.EVALUATIONS:\nDuring the long‐term extension, clinical response was assessed every 12 weeks through week 256, with an additional assessment at week 104. Disease activity was assessed using the American College of Rheumatology (ACR) criteria 6 and the European League Against Rheumatism Disease Activity Score in 28 joints (DAS28) using CRP level 7. Post hoc efficacy assessments included the Simplified Disease Activity Index (SDAI) 8 and the Clinical Disease Activity Index (CDAI) 9. Physical function was evaluated using the Health Assessment Questionnaire (HAQ) disability index (DI) 10. Normal physical function was defined as a HAQ DI score ≤0.5, and a minimal clinically important difference (MCID) was defined as an improvement ≥0.25 11. Health‐related quality of life was evaluated using the physical component summary (PCS) and mental component summary (MCS) scores of the Short Form 36‐item (SF‐36) health survey 12. The impact of disease on productivity was assessed using a visual analog scale (0–10 cm) at baseline and at week 256. Radiographs of the hands and feet were obtained at weeks 52, 104, 208, and 256 during the long‐term extension; results through week 104 have been previously reported 1, 4. Data from patients with radiographs at baseline, week 104, and at least 1 radiograph after week 104 were included in the current analysis. As previously detailed 5, radiographs were scored by 2 independent readers and an adjudicator using the modified Sharp/van der Heijde score (SHS) 13. Patients were monitored through week 268 for adverse events (AEs). Routine laboratory analyses were performed through week 256. The incidence of each AE was summarized according to actual treatment received at the time of the event. Blood samples were collected (prior to administration of study agents) at selected visits for the analysis of pharmacokinetics and evaluation for the presence of antibodies to golimumab using validated immunoassays 14.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS:\nDescriptive statistics (e.g., counts and percentages and means/medians) were used to summarize the efficacy results of the long‐term extension by randomized treatment group. In the a priori analysis of clinical efficacy end points (ACR components and DAS28‐CRP), observed data were used through week 256 with no imputation for missing values. A more stringent post hoc intent‐to‐treat (ITT) analysis including all randomized patients was performed on the clinical efficacy measures, and these results are reported herein. This ITT analysis used the following data imputation and treatment failure rules: 1) missing baseline values for continuous variables were replaced with the median value of the corresponding baseline CRP level stratum (<1.5 mg/dl or ≥1.5 mg/dl), and the last observation carried forward (LOCF) methodology was applied to missing postbaseline values, and 2) patients who discontinued the study agent due to unsatisfactory therapeutic effect were imputed as nonresponders. The proportions of patients achieving at least a 20%, 50%, or 70% improvement in the ACR criteria (ACR20/50/70 response) 6, a moderate or good DAS28‐CRP response 7, 15, a DAS28‐CRP <2.6, a DAS28‐CRP ≤3.2, an MCID in HAQ DI score, and a HAQ DI score ≤0.5 were determined. SF‐36 and productivity outcomes were analyzed using observed data, with no missing data imputation, and included improvements from baseline in SF‐36 PCS and MCS scores and the impact of disease on productivity at week 256, as well as the proportions of patients with normal SF‐36 PCS or MCS scores (score ≥50). In the post hoc analysis, the proportions of patients who achieved remission, as defined by an SDAI score ≤3.3 16, a CDAI score ≤2.8 16, or Boolean definition 17 were also determined. Radiographic data through week 256 were summarized by randomized treatment group and included all patients who had radiographs at weeks 0, 104, and at least 1 radiograph after week 104. Changes from baseline to week 208 and week 256 in the SHS are reported; missing postbaseline values were replaced using the LOCF methodology. Among patients with an SHS score at baseline and week 256, annual rates of progression at baseline and 5 years were determined using the SHS score divided by RA duration for each patient at baseline and the change in SHS over 5 years. Cumulative safety data are reported for all patients who received at least 1 administration of golimumab through week 268. AEs and serious AEs were summarized according to the treatment received at the time of the event. As a result of early escape, placebo crossover, and golimumab dose adjustments allowed during the long‐term extension, patients could be included in more than 1 treatment group. AEs were summarized through week 268, with the exception of those that occurred after receipt of any commercial biologic agent (including commercial golimumab). Patients who received commercially available biologic treatment after discontinuing study golimumab, yet who remained in the study, had AEs reported through week 268, but these AEs were excluded from the safety summaries. The rates per 100 patient‐years and 95% confidence intervals (95% CIs) for the total numbers of serious infections, malignancies (including nonmelanoma skin cancers), and death are also reported. In addition, standardized incidence ratios (SIRs) for malignancies were determined using the Surveillance, Epidemiology and End Results (SEER) database; nonmelanoma skin cancers were excluded from this comparison because they are not reported in the SEER database.\n\nBODY.RESULTS:\nData for this report were collected from December 2005 to June 2012. As previously reported, patient demographics and disease characteristics at baseline were well‐balanced among the treatment groups 1. A total of 637 patients were randomly assigned to group 1 (n = 160), group 2 (n = 159), group 3 (n = 159), and group 4 (n = 159; see Supplementary Table 1, available on the Arthritis Care & Research web siteat http://onlinelibrary.wiley.com/doi/10.1002/acr.22759/abstract). Eighty‐nine patients (group 1, n = 28; group 2, n = 22; group 3, n = 20; and group 4, n = 19) met the early escape criteria at week 28 4. Through week 104, 140 patients discontinued the SC study agent, with AEs being the most common reason 4. A total of 215 patients (33.9%) discontinued the study agent through week 252; 111 (17.5%) discontinued due to an AE, including worsening of RA (n = 4, 0.6%), and 23 patients (3.6%) discontinued due to unsatisfactory therapeutic effect (Table 1). A total of 402 patients (63.4%) completed the safety followup through week 268. Table 1 Patients who discontinued study agent through week 252 a \n Golimumab + MTX Placebo + MTX Golimumab 100 mg + placebo 50 mg 100 mg Combined Total Patients randomized, no. 160 159 159 159 318 637 Patients treated, no. 160 157 158 159 317 634 Patients who discontinued study agent 50 (31.3) 56 (35.7) 49 (31.0) 60 (37.7) 109 (34.4) 215 (33.9) Reason for discontinuation Initiated protocol‐prohibited medication(s) 0 0 0 0 0 0 Adverse event 21 (13.1) 32 (20.4) 24 (15.2) 34 (21.4) 58 (18.3) 111 (17.5) Worsening of RA 0 3 (1.9) 0 1 (0.6) 1 (0.3) 4 (0.6) Unsatisfactory therapeutic effect 5 (3.1) 6 (3.8) 5 (3.2) 7 (4.4) 12 (3.8) 23 (3.6) Lost to followup 3 (1.9) 4 (2.5) 7 (4.4) 6 (3.8) 13 (4.1) 20 (3.2) Death 0 3 (1.9) 3 (1.9) 2 (1.3) 5 (1.6) 8 (1.3) Other 21 (13.1) 11 (7.0) 10 (6.3) 11 (6.9) 21 (6.6) 53 (8.4) a Values are the number (percentage) unless indicated otherwise. MTX = methotrexate; RA = rheumatoid arthritis. Through week 256, a total of 616 patients received at least 1 administration of golimumab. Of these, 172 received only the 50‐mg dose, 243 received only the 100‐mg dose, and 201 received at least 1 administration of each dose during the trial.\n\nBODY.RESULTS.CLINICAL EFFICACY AND PATIENT‐REPORTED OUTCOMES:\nClinical efficacy results from the ITT analysis that included all randomized patients are shown in Table 2. At week 256, 72.8% of all patients had an ACR20 response, 54.6% had an ACR50 response, and 38.0% had an ACR70 response. After the placebo crossover at week 52, ACR20 and ACR50 response rates were maintained for all treatment groups through week 256 (Figure 1). Additionally, 84.1% of all patients had either a good or moderate DAS28‐CRP response at week 256, and 43.3% of patients had a DAS28‐CRP <2.6. Approximately 28% of all patients were in remission at week 256 according to the SDAI and CDAI remission criteria, and 21.2% met the Boolean remission criteria (Table 2). Meaningful improvements in physical function were observed, with an overall mean improvement in HAQ DI score of 0.57 at week 256. Additionally, at week 256, 72.7% of all patients had an improvement from baseline ≥0.25, and 43.0% achieved normal physical function (HAQ DI ≤0.5) (Table 2) compared with 9.1% (58 of 637) who had a normal HAQ DI score at baseline. The results of the protocol‐specified efficacy analysis were consistent with this modified ITT analysis (see Supplementary Table 2, available on the Arthritis Care & Research web site at http://onlinelibrary.wiley.com/doi/10.1002/acr.22759/abstract). Figure 1The proportions of patients with A) American College of Rheumatology 20% improvement criteria (ACR20) response or B) ACR50 response through week 256. MTX = methotrexate. Table 2 Clinical efficacy, patient‐reported outcomes, and radiographic results at week 256 using the ITT analysis a \n Golimumab + MTX Placebo + MTX Golimumab 100 mg + placebo 50 mg 100 mg Combined Total Clinical efficacy b \n Patients randomized, no. 160 159 159 159 318 637 ACR20 109 (68.1) 117 (73.6) 114 (71.7) 124 (78.0) 238 (74.8) 464 (72.8) ACR50 80 (50.0) 83 (52.2) 88 (55.3) 97 (61.0) 185 (58.2) 348 (54.6) ACR70 61 (38.1) 59 (37.1) 57 (35.8) 65 (40.9) 122 (38.4) 242 (38.0) DAS28‐CRP response c \n 128 (80.0) 138 (86.8) 131 (82.4) 139 (87.4) 270 (84.9) 536 (84.1) DAS28‐CRP <2.6 67 (41.9) 65 (40.9) 70 (44.0) 74 (46.5) 144 (45.3) 276 (43.3) DAS28‐CRP ≤3.2 86 (53.8) 90 (56.6) 91 (57.2) 94 (59.1) 185 (58.2) 361 (56.7) SDAI ≤3.3 47 (29.4) 40 (25.2) 42 (26.4) 46 (28.9) 88 (27.7) 175 (27.5) CDAI ≤2.8 51 (31.9) 40 (25.2) 44 (27.7) 49 (30.8) 93 (29.2) 184 (28.9) Boolean remission 30 (18.8) 32 (20.1) 38 (23.9) 35 (22.0) 73 (23.0) 135 (21.2) Improvement from baseline in HAQ DI, mean ± SD 0.68 ± 0.69 0.70 ± 0.74 0.65 ± 0.70 0.80 ± 0.72 0.72 ± 0.71 0.70 ± 0.71 Patients with improvement in HAQ DI ≥0.25 120 (75.0) 111 (69.8) 110 (69.2) 122 (76.7) 232 (73.0) 463 (72.7) Patients with HAQ DI ≤0.5 61 (38.1) 62 (39.0) 72 (45.3) 79 (49.7) 151 (47.5) 274 (43.0) Radiographic results SHS change from baseline, mean ± SD d \n At week 208 2.18 ± 6.53 1.74 ± 6.71 0.68 ± 3.59 0.54 ± 2.72 0.61 ± 3.19 1.29 ± 5.23 At week 256 2.28 ± 6.65 1.81 ± 6.82 0.72 ± 3.67 0.60 ± 2.86 0.66 ± 3.30 1.36 ± 5.34 SHS change from week 104, mean ± SD d \n At week 208 0.68 ± 3.19 0.79 ± 4.39 0.43 ± 1.82 0.57 ± 2.36 0.50 ± 2.10 0.62 ± 3.08 At week 256 0.78 ± 3.40 0.87 ± 4.64 0.47 ± 2.05 0.64 ± 2.64 0.55 ± 2.35 0.69 ± 3.31 Patients with change in total SHS ≤0 at week 256 65 (54.2) 64 (56.6) 75 (62.5) 73 (65.2) 148 (63.8) 277 (59.6) Patients with change in total SHS ≤0.5 at week 256 78 (65.0) 82 (72.6) 92 (76.7) 89 (79.5) 181 (78.0) 341 (73.3) Estimated annual rate of progression at baseline, mean ± SD 8.44 ± 19.37 8.32 ± 27.49 9.75 ± 24.86 6.76 ± 14.73 8.31 ± 20.61 8.34 ± 22.14 Estimated annual rate of progression at week 256, mean ± SD 0.46 ± 1.34 0.36 ± 1.36 0.14 ± 0.74 0.12 ± 0.57 0.13 ± 0.66 0.27 ± 1.07 a Values are the number (percentage) unless indicated otherwise. ITT = intent‐to‐treat; MTX = methotrexate; ACR20/50/70 = American College of Rheumatology criteria for 20%/50%/70% improvement; DAS28‐CRP = Disease Activity Score in 28 joints using the C‐reactive protein level; SDAI = Simplified Disease Activity Index; CDAI = Clinical Disease Activity Index; HAQ = Health Assessment Questionnaire; DI = disability index; SHS = modified Sharp/van der Heijde score. b Modified ITT analysis in which the following rules were applied: 1) missing baseline values for continuous variables were replaced with the median value, and last observation carried forward methodology was applied to missing postbaseline values, and 2) patients who discontinued study agent due to unsatisfactory therapeutic effect were considered to be nonresponders. c Good or moderate response as defined by the European League Against Rheumatism 14 . d Includes patients who had an SHS at weeks 0 and 104 and at least 1 score after week 104. A total of 101 patients had an increase in golimumab dose from 50 mg to 100 mg during the long‐term extension (after week 52), and of these, 100 patients had ≥12 weeks of followup available. Among these patients, 84 did not have a DAS28‐CRP <2.6 immediately prior to dose escalation, and 68 did not have a score ≤3.2 prior to dose escalation. Both of these subgroups had a mean ± SD improvement in DAS28‐CRP of 1.0 ± 1.1 at 12 weeks after dose escalation. Improvements from baseline to week 256 in patient‐reported outcomes were generally similar among the treatment groups (Table 3). Mean improvements in SF‐36 PCS and MCS scores ranged from 11.3–11.9 and 4.5–7.6, respectively. Among patients with evaluable SF‐36 data at baseline and week 256, 27.9% had a normal (score ≥50) SF‐36 PCS score, and 46.9% had a normal SF‐36 MCS score at week 256 (Table 3) compared with 1.4% and 28.8% who had normal baseline SF‐36 PCS and MCS scores, respectively. Mean improvements from baseline to week 256 in the impact of disease on productivity ranged from 3.2–4.3 among the treatment groups. Table 3 Improvements in health‐related quality of life and productivity at week 256 a \n \n Golimumab + MTX \n \n Placebo + MTX \n \n Golimumab 100 mg + placebo \n \n 50 mg \n \n 100 mg \n \n Combined \n \n Total \n SF‐36 PCS score Improvement from baseline, mean ± SD 11.3 ± 10.5 11.6 ± 11.0 11.9 ± 11.1 11.9 ± 10.0 11.9 ± 10.6 11.7 ± 10.7 Patients with score ≥50, no. (%) 28 (25.7) 28 (26.9) 33 (30.6) 28 (28.3) 61 (29.5) 117 (27.9) SF‐36 MCS score Improvement from baseline, mean ± SD 4.5 ± 12.6 7.6 ± 12.0 5.7 ± 12.1 6.4 ± 11.9 6.1 ± 12.0 6.0 ± 12.2 Patients with score ≥50, no. (%) 47 (43.1) 51 (49.0) 55 (50.9) 44 (44.4) 99 (47.8) 197 (46.9) Improvement in the impact of disease on productivity, mean ± SD 3.2 ± 3.1 4.3 ± 4.3 3.9 ± 2.7 4.2 ± 2.8 4.0 ± 2.8 3.9 ± 3.3 a MTX = methotrexate; SF‐36 = Short Form 36 health survey; PCS = physical component summary; MCS = mental component summary. At week 256, 41.0% (n = 261 of 637) of all patients were receiving concomitant oral corticosteroids (mean dosage: 6.1 mg/day prednisone or equivalent) compared with 52.0% (n = 331 of 637) at baseline (mean dose: 7.4 mg/day). Likewise, 67.8% (n = 432) used concomitant NSAIDs at week 256 in comparison with 82.9% (n = 528) of patients at baseline.\n\nBODY.RESULTS.RADIOGRAPHIC PROGRESSION:\nA total of 465 patients (group 1, n = 120; group 2, n = 113; group 3, n = 120; and group 4, n = 112) had radiographic data available at baseline, week 104, and at least 1 radiograph after the week‐104 time point and were therefore included in the analysis for reading session 3. At week 256, radiographic progression was low, with a mean change from baseline in SHS for all patients of 1.36; mean changes among the treatment groups ranged from 0.60 to 2.28 (Table 2). Furthermore, approximately 60% of all patients had a change in SHS ≤0 at week 256, and 73% of patients had a change from baseline ≤0.5. At baseline, the mean estimated annual rates of radiographic progression for groups 1, 2, 3, and 4 were 8.44, 8.32, 9.75, and 6.76, respectively (mean duration of RA: group 1, 2.9 years; group 2, 4.1 years; group 3, 3.5 years, and group 4, 3.6 years). Over the 5‐year study, the mean annual rate of progression was 0.27 for all patients, and 0.46, 0.36, 0.14, and 0.12 for groups 1, 2, 3, and 4, respectively.\n\nBODY.RESULTS.AES:\nA total of 616 patients received at least 1 dose of golimumab 50 mg or 100 mg and were included in the safety analysis, and 402 patients completed the safety followup through week 268. The mean duration of followup for all golimumab‐treated patients was 205 weeks, and the mean number of golimumab administrations was 46.9 (Table 4). The most common types of AEs by the Medical Dictionary for Regulatory Activities classification were infections and infestations (n = 463, 75.2%), gastrointestinal disorders (n = 323, 52.4%), and musculoskeletal and connective tissue disorders (n = 258, 41.9%). Commonly reported AEs are listed in Table 4 and include upper respiratory tract infection (n = 181, 29.4%), nausea (n = 121, 19.6%), bronchitis (n = 102, 16.6%), and increased alanine aminotransferase (n = 99, 16.1%). Among all golimumab‐treated patients, 73 (11.9%) had at least 1 injection site reaction through week 268; none of these reactions were considered to be severe. Of the 28,866 golimumab injections administered, 258 (0.9%) were associated with an injection‐site reaction. Table 4 Adverse events through week 268 a \n 50 mg + MTX only 50 mg and 100 mg + placebo or MTX Golimumab 100 mg + placebo or MTX Total golimumab Treated patients, no. 172 201 243 616 Mean duration of followup, weeks 182.9 238.7 192.7 205.0 Mean number of administrations 41.5 54.9 44.0 46.9 Patients with ≥1 AE 161 (93.6) 187 (93.0) 234 (96.3) 582 (94.5) Patients who discontinued due to AEs 30 (17.4) 14 (7.0) 67 (27.6) 111 (18.0) Common AEs (≥10%) Upper respiratory tract infection 46 (26.7) 72 (35.8) 63 (25.9) 181 (29.4) Nausea 22 (12.8) 44 (21.9) 55 (22.6) 121 (19.6) Bronchitis 27 (15.7) 34 (16.9) 41 (16.9) 102 (16.6) Alanine aminotransferase increased 31 (18.0) 32 (15.9) 36 (14.8) 99 (16.1) Cough 19 (11.0) 29 (14.4) 37 (15.2) 85 (13.8) Patients with ≥1 injection site reaction 15 (8.7) 19 (9.5) 39 (16.0) 73 (11.9) Patients with ≥1 SAE 55 (32.0) 55 (27.4) 94 (38.7) 204 (33.1) Pneumonia 5 (2.9) 5 (2.5) 4 (1.6) 14 (2.3) Pulmonary tuberculosis 1 (0.6) 1 (0.5) 4 (1.6) 6 (1.0) Breast cancer 1 (0.6) 0 3 (1.2) 4 (0.6) Uterine leiomyoma 1 (0.6) 2 (1.0) 1 (0.4) 4 (0.6) Basal cell carcinoma 0 2 (1.0) 1 (0.4) 3 (0.5) Hodgkin's disease 0 0 2 (0.8) 2 (0.3) Non–small cell lung cancer 2 (1.2) 0 0 2 (0.3) Patients with ≥1 serious infection 17 (9.9) 25 (12.4) 33 (13.6) 75 (12.2) Incidence per 100 patient‐years (95% CI) 3.97 (2.54–5.90) 3.68 (2.55–5.15) 6.00 (4.50–7.82) 4.61 (3.80–5.55) Pneumonia 5 (2.9) 5 (2.5) 4 (1.6) 14 (2.3) Herpes zoster 0 3 (1.5) 2 (0.8) 5 (0.8) Pulmonary tuberculosis 1 (0.6) 1 (0.5) 3 (1.2) 5 (0.8) Sepsis 0 1 (0.5) 3 (1.2) 4 (0.6) Urinary tract infection 1 (0.6) 2 (1.0) 1 (0.4) 4 (0.6) Appendicitis 0 2 (1.0) 1 (0.4) 3 (0.5) Upper respiratory tract infection 1 (0.6) 0 2 (0.8) 3 (0.5) Malignancies Lymphoma 0 0 2 (0.8) 2 (0.3) Incidence per 100 patient‐years (95% CI) 0.00 (0.00–0.50) 0.00 (0.00–0.32) 0.22 (0.03–0.80) 0.08 (0.01–0.30) SIR (95% CI) b \n 0.00 (0.00–18.91) 0.00 (0.00–12.15) 9.54 (1.16–34.48) 3.26 (0.39–11.76) Nonmelanoma skin cancers 0 3 (1.5) 2 (0.8) 5 (0.8) Incidence per 100 patient‐years (95% CI) 0.00 (0.00–0.50) 0.33 (0.07–0.95) 0.22 (0.03–0.80) 0.21 (0.07–0.48) Other malignancies 8 (4.7) 2 (1.0) 4 (1.6) 14 (2.3) Incidence per 100 patient‐years (95% CI) 1.33 (0.57–2.62) 0.22 (0.03–0.78) 0.44 (0.12–1.14) 0.58 (0.32–0.97) SIR (95% CI) b \n 2.21 (0.95–4.35) 0.36 (0.04–1.28) 0.85 (0.23–2.18) 1.00 (0.55–1.68) Total malignancies 8 (4.7) 5 (2.5) 8 (3.3) 21 (3.4) Incidence per 100 patient‐years (95% CI) 1.33 (0.57–2.62) 0.54 (0.18–1.27) 0.89 (0.38–1.75) 0.87 (0.54–1.33) SIR (95% CI) b \n 2.12 (0.91–4.18) 0.34 (0.04–1.23) 1.23 (0.45–2.67) 1.10 (0.63–1.79) Deaths 6 (3.5) 0 6 (2.5) 12 (1.9) Incidence per 100 patient‐years (95% CI) 0.99 (0.36–2.16) 0.00 (0.00–0.32) 0.67 (0.24–1.45) 0.49 (0.26–0.86) a Data presented as number (percentage) unless indicated otherwise. MTX = methotrexate; AE = adverse event; SAE = serious AE; 95% CI = 95% confidence interval; SIR = standardized incidence ratio. b The SIR is in comparison with the expected number of events in the Surveillance, Epidemiology, and End Results database (2004), which does not include nonmelanoma skin cancers. Through week 268, 204 patients (33.1%) had at least 1 serious AE. Seventy‐five patients (12.2%) had a serious infection, the most common being pneumonia (n = 14; 2.3%) (Table 4). Among all golimumab‐treated patients, the incidence (95% CI) of serious infections per 100 patient‐years was 4.61 (3.80–5.55). At baseline, 106 patients (16.6%) required treatment for latent TB. Through week 268, 13 patients were diagnosed with active TB (golimumab 50 mg: n = 2; 100 mg: n = 11). The majority of these cases were in endemic countries (e.g., Philippines, Chile, and Thailand). Ten of these patients had negative tuberculin and QuantiFERON testing at screening; the remaining patients were identified as having latent TB, completed the required treatment as specified in the protocol, and developed active TB several months after completing the treatment for latent TB. Eleven TB cases occurred before week 104 and have been previously described 4. The 2 cases that occurred after week 104 were TB pleurisy and intestinal TB. There were no cases of disseminated TB or deaths resulting from TB in this study. Five opportunistic infections were reported through week 268. Two were classified as serious infections (pneumonia legionella, n = 1; Pneumocystitis jiroveci pneumonia, n = 1), and 3 were classified as nonserious infections (esophageal candidiasis, n = 2; aspergillosis, n = 1). Two patients experienced demyelination AEs (demyelination of the central nervous system and autoimmune demyelination); both patients were receiving golimumab 100 mg + MTX. Both AEs were considered to be serious, and the patients discontinued study treatment. No cases of systemic lupus erythematosus were reported. Among all patients who received golimumab, 21 reported a malignancy through week 268. The incidence (95% CI) of all malignancies per 100 patient‐years was 0.87 (0.54–1.33) (Table 4). Two cases of lymphoma were reported among golimumab‐treated patients (both patients received the 100‐mg dose); the incidence (95% CI) per 100 patient‐years for lymphoma was 0.08 (0.01–0.30). Eight deaths occurred prior to week 104 and have been previously described 1, 4. An additional 4 deaths occurred after week 104: two patients receiving golimumab 50 mg + MTX (a 71‐year‐old woman, with a history of cigarette smoking, died from myocardial infarction, and a 50‐year‐old woman, with a history of chronic lung disease, hypertension, and cigarette smoking, died from unknown causes), 1 patient receiving golimumab 100 mg + placebo (a 68‐year‐old woman died from hematemesis), and 1 patient receiving golimumab 100 mg + MTX (a 61‐year‐old woman, with a history of hyperlipidemia, hypertension, and cigarette smoking, died of sepsis). Through week 268, the incidence (95% CI) of death per 100 patient‐years for all golimumab‐treated patients was 0.49 (0.26–0.86). After discontinuing the study golimumab injections, a total of 47 patients received a commercial biologic agent (including commercial golimumab) after week 256. Six of these patients had an AE after receiving commercial golimumab; most AEs were similar to those reported during receipt of study drug during the trial. One of these 6 patients had a serious AE (cellulitis).\n\nBODY.RESULTS.GOLIMUMAB PHARMACOKINETICS AND IMMUNOGENICITY:\nSerum trough golimumab concentrations were approximately dose proportional and were generally maintained through week 256 for patients who did not have any changes in golimumab dose. Through week 256, a total of 57 golimumab‐treated patients (9.6%) tested positive for antibodies to golimumab, and of these, 46 patients (92.0%) were positive for neutralizing antibodies. Eight patients (14.0%) who were positive for antibodies to golimumab also had an injection site reaction; 1 reaction of moderate injection site erythema was classified as serious and led to discontinuation of the study agent. Among the 538 patients who tested negative for antibodies to golimumab, 78 (14.5%) had an injection site reaction; none were serious or led to study discontinuation.\n\nBODY.DISCUSSION:\nThe GO‐BEFORE trial evaluated the safety and efficacy of golimumab with and without MTX in MTX‐naive patients with active RA. Through 24 weeks, patients treated with golimumab 50 mg or 100 mg + MTX had substantial improvements in disease activity 1, and these improvements were sustained through weeks 52 and 104 4. Through 1 year, patients treated with golimumab + MTX had significantly less radiographic progression than did patients who received MTX monotherapy 5, and progression was minimal in all treatment groups at week 104, when all patients had been receiving golimumab 4. Here we report the final clinical efficacy, radiographic, and safety findings through 5 years of the GO‐BEFORE trial. Approximately 66% of patients who were randomized at baseline continued study treatment through week 252. Long‐term completion rates through 5 years were approximately 46–49% in previous trials of other SC anti‐TNF therapies in patients with RA who were MTX naive 18, 19. Among all randomized patients in the GO‐BEFORE trial, 72.8% of patients had an ACR20 response, 54.6% had an ACR50 response, and 38.0% had an ACR70 response at week 256 (when all patients were receiving golimumab), with no appreciable differences among the treatment groups. Additionally, more than 80% of golimumab‐treated patients had either a good or moderate DAS28‐CRP response at week 256. Golimumab‐treated patients also had clinically meaningful improvements in physical function as demonstrated by an overall mean improvement from baseline in HAQ DI score of 0.57, and by 72.7% of patients having an improvement ≥0.25. Radiographic progression was low through 5 years; the mean change in SHS was 0.72 and 0.60 over 5 years in patients randomized to golimumab 50 mg + MTX and 100 mg + MTX, respectively, with nearly three‐quarters of all patients having no progression (change in SHS of ≤0.5). The proportion of patients using oral corticosteroids and the median dose received decreased from baseline to week 256. The proportion of patients using NSAIDs also decreased during the trial. These observations may suggest that reduced use of these concomitant medications could be achieved with golimumab treatment. However, it should be noted that the use of these medications was solely at the discretion of the investigator. Safety findings through week 268 were generally consistent with those reported through week 104 1, 4. The majority of cases of active TB occurred in patients receiving the 100‐mg dose; however, it is difficult to compare the 2 doses (50 and 100 mg) due to the treatment changes allowed through early escape and adjustments to golimumab and concomitant medications during the long‐term extension. The incidences of serious infections, lymphoma, and deaths adjusted for patient‐years of exposure for both golimumab doses were generally consistent with long‐term data reported for other biologic anti‐TNF agents from both randomized clinical trials 18, 19, 20 and observational studies 21, 22. Throughout the trial, infections were the most common type of AE and serious AE; pneumonia was the most common type of serious infection (n = 14, 2.3%). There were a total of 13 cases of active TB. All patients were screened for TB prior to study entry and had to either have negative TB test results or initiate treatment for latent TB. The 13 cases of TB in the GO‐BEFORE trial were considered to be new, active infections and most were in areas with a high background rate of TB (e.g., Philippines, Chile, and Thailand). Given the substantial number of patients who were enrolled from regions with a high TB incidence rate, the comprehensive screening procedures utilized in this trial may have contributed to a lower than expected rate of TB 23. However, physicians should remain vigilant regarding the development of new TB infections. Five opportunistic infections were reported, including pneumonia legionella, P jiroveci pneumonia, and esophageal candidiasis. A total of 12 deaths occurred through week 268; no predominant cause of death was identified. Among golimumab‐treated patients, 21 malignancies were reported. Two cases of lymphoma occurred through week 268, both in patients receiving golimumab 100 mg, which corresponded to an SIR (95% CI) of 9.54 (1.16–34.48). A previous registry analysis of more than 6,000 patients with RA did not show an increase in lymphoma risk with increasing duration of anti‐TNF therapy 24. Throughout the trial, less than 1% of all golimumab injections were associated with an injection site reaction. The incidence of injection site reactions through week 256 was similar between patients who tested positive for antibodies to golimumab (14.0%) and those who tested negative for antibodies to golimumab (14.5%). A substantial portion of the patients (66%) who were enrolled and treated in the GO‐BEFORE trial completed treatment with golimumab through week 252. Interpretation of the long‐term efficacy and safety results is limited by selection bias over time, although our use of an ITT analysis including all randomized patients may have mitigated this effect. The results through 5 years of this study are also limited by the lack of a control group after week 52, as well as possible confounding effects of concomitant medications and golimumab dose changes that were permitted during the long‐term extension. The overall findings of the GO‐BEFORE trial indicate that the majority of patients remained in the trial through 5 years and had sustained improvements in clinical and radiographic outcomes with long‐term safety results consistent with other anti‐TNF therapies.\n\nBODY.AUTHOR CONTRIBUTIONS:\nAll authors were involved in drafting the article or revising it critically for important intellectual content, and all authors approved the final version to be submitted for publication. Dr. Emery had full access to all of the data in the study and takes responsibility for the integrity of the data and the accuracy of the data analysis.\n\nBODY.AUTHOR CONTRIBUTIONS.STUDY CONCEPTION AND DESIGN:\nEmery, Fleischmann, Park, Han, Leu, Hsia.\n\nBODY.AUTHOR CONTRIBUTIONS.ACQUISITION OF DATA:\nEmery, Fleischmann, Strusberg, Durez, Nash, Amante, Churchill, Park, Pons‐Estel, Han, Zhou, Hsia.\n\nBODY.AUTHOR CONTRIBUTIONS.ANALYSIS AND INTERPRETATION OF DATA:\nEmery, Fleischmann, Durez, Churchill, Park, Han, Gathany, Xu, Zhou, Leu, Hsia.\n\nBODY.ROLE OF THE STUDY SPONSOR:\nAuthors who are or were employees of Janssen Research & Development, LLC were involved in the study design and in the collection, analysis, and interpretation of the data, the writing of the manuscript, and the decision to submit the manuscript for publication. All authors approved the manuscript for submission. Rebecca Clemente, PhD, and Mary Whitman, PhD, of Janssen Scientific Affairs provided writing support.\n\nBODY.SUPPORTING INFORMATION:\nSupplementary Table 1. Actual treatment received through week 256Click here for additional data file. Supplementary Table 2. Clinical efficacy results at week 256 (observed data analysis).Click here for additional data file.\n\nQuestion: Compared to Placebo?plus MTX or Golimumab what was the result of Golimumab plus?MTX on ACR20/50/70 response?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1175	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Evaluation of different sodium bicarbonate regimens for the prevention of contrast medium-induced nephropathy\n\n ABSTRACT.INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease. The pathophysiology of contrast-induced nephropathy (CIN) is poorly understood, but it may include acute hypoxia-induced oxidative stress and free radicals generated within the acid environment of the renal medulla. Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN. The aim of this study was to determine whether a long-duration sodium bicarbonate regimen is more effective than a short-duration regimen in reducing CIN.\n\nABSTRACT.METHODS:\nOne hundred patients were assigned randomly to treatment with sodium bicarbonate solution using either the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) or the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). Patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergent coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at Nephrology Department (Theodor Bilharz Research Institute) were enrolled in the study. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nABSTRACT.RESULTS:\nThere was a significant increase in serum creatinine and a decrease in eGFR 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters group 2 (long regimen). Serum potassium clearly was decreased significantly post procedure in both groups.\n\nABSTRACT.CONCLUSIONS:\nThe results of our study indicated that the long regimen of bicarbonate supplementation was a more effective strategy to prevent CIN than the short regimen.\n\nBODY.1. INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease (CKD) or even end-stage renal disease (ESRD). Contrast-induced nephropathy (CIN) is a leading cause of new-onset renal failure in hospitalized patients, with the highest risk observed in patients with CKD (1, 2). It is associated with significantly increased in-hospital and long-term morbidity and mortality and acceleration of chronic renal disease (3). Since there is no specific therapy for CIN and the disease is iatrogenic, prevention is of paramount importance. The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction resulting in renal hypoperfusion, hypoxia-induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4, 5). Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN (6–11). Putting into consideration that the alkalization of urine can be used to prevent CIN, our aim was to evaluate whether a longer duration of sodium bicarbonate infusion is more beneficial than a shorter duration infusion in reducing the frequency of contrast nephropathy in patients after coronary angiography.\n\nBODY.2. MATERIAL AND METHODS:\nThe protocol of this study was approved by the Ethics Committee of Theodor Bilharz Research Institute, and written informed consent was obtained from all patients. The study complies with the Declaration of Helsinki. All adult patients, i.e., those over the age of 18 who were scheduled for coronary angiography, were screened for inclusion and exclusion criteria. Between November 2013 and November 2014, 200 patients were considered eligible for the trial. After 100 exclusions, 100 patients were assigned randomly to either the short-duration or the long duration treatment with sodium bicarbonate solution. The short-duration treatment consisted of intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before the injection of the radiocontrast, with subsequent treatment with the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. The long-duration treatment consisted of initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr before the injection of the radiocontrast, after which the patients received the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. Demographic data, current medication, and medical history were recorded at baseline. Serum creatinine (S. Cr), eGFR, and serum potassium were measured before initiating the pre-procedural hydration. Urine samples were obtained to analyze the pH of the urine one hour prior to the procedure. Two days after coronary angiography, serum creatinine, eGFR, and serum potassium were analyzed again. We calculated eGFR according to the MDRD formula (20). Change in creatinine, percent change in creatinine, percent change in eGFR, change in serum potassium, and urine pH were compared between the two groups. The side effects of the high-dose of sodium bicarbonate, such as congestive heart failure, respiratory disorder, and low potassium, were carefully evaluated during the study. CIN was defined as an increase of more than absolute 0.5 mg/dL and/or relative 25% in serum creatinine after 48 hr. Consecutive patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergency coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at our institution were enrolled. The eGFR was calculated using the MDRD formula. Patients were excluded for any of the following reasons: end-stage renal insufficiency (eGFR <15 mL/min), acute renal insufficiency, a history of reaction to contrast media, the use of potentially nephrotoxic medicines (48 h before and 24 h after the procedure), pulmonary edema, multiple myeloma, exposure to contrast media within 7 days before the procedure, pregnancy, patient non-compliance, and the use of either N-acetylcystein, dopamine, fenoldopam, or mannitol before coronary angiography. Patients were randomized to one of the two regimens of volume supplementation described below. Randomization with stratification for intra-arterial and intravenous radiographic contrast procedures were performed by using sealed envelopes, 1:1 to each group (12). The analysis was performed according to the intent-to-treat principle. All patients were hydrated with intravenous normal saline at 1 mL/kg/h for 12 hr before exposure to the contrast and 12 h after coronary angiography. The rate of infusion was reduced in patients who developed signs of pulmonary congestion. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nBODY.3. RESULTS AND DISCUSSION:\nBetween November 2013 and November 2014, 200 patients were screened, and, after 100 exclusions, 100 patients were randomly assigned to treatment either with short regimen (60 minutes) bicarbonate solution prior to contrast administration (50 patients) or with long regimen (6 hr prior to the intervention) (50 patients). Thus, the final study population was 100 patients. No side effects of sodium bicarbonate infusion were observed, and discontinuation of protocol dose of infusion was not necessary in any of the patients. Our findings showed that there were no significant differences between the two groups in age, gender, smoking, body mass index, diabetes mellitus, hypertension, percutaneous coronary intervention, and volume of contrast administered (Table 1). There were no statistical differences in baseline urine pH, baseline S. Cr., baseline eGFR by MDRD, or baseline serum potassium (S. K.) between the two groups (Table 2). There was a significant increase in S. Cr., and a significant decrease in eGFR by MDRD 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters in group 2 (long regimen). S. K clearly was decreased significantly post-procedure in both groups (short and long regimens). There was no correlation between S. K. and S. Cr. and eGFR by MDRD 48 hr post intervention in both groups. Also, a highly-significant negative correlation between s. Cr and eGFR by MDRD was reported in both groups (Table 3). Note that acute deterioration in renal function can be caused by radiographic contrast agents, but, generally, it is mild and transient. However, acute deterioration can result in lasting renal dysfunction and the need for renal replacement therapy (1). Contrast-induced nephropathy (CIN) is a leading cause of new onset renal failure in hospitalized patients, with the highest risk observed in patients with pre-existing impaired renal function (2). It is associated with significantly increased long-term morbidity and mortality, acceleration of chronic renal disease, and increased costs of medical care (13). The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction, resulting in renal hypoperfusion, hypoxia induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4). Thus, studies have begun to evaluate the effect of volume supplementation with sodium bicarbonate in prevention of CIN based on the hypothesis that alkalinizing renal tubular fluid with bicarbonate may reduce renal injury and increase medullary pH with subsequent slowing of the production of free radicals (14). Similarly, it was stated in (4) that the role of bicarbonate in protecting against CIN is attributed to buffering of subclinical acidosis-induced vasoconstriction, which is typical of acute settings and may amplify the vasoconstriction induced by the contrast itself. On the contrary, some studies have indicated that the effectiveness of sodium bicarbonate treatment to prevent CIN in high risk patients remains uncertain and that the magnitude of any benefit probably had ben overestimated (15, 16). However Klima et al. (16) explained these discrepant findings by the early termination of these studies, publication bias, small differences in the concentration, the overall amount of sodium bicarbonate applied, the type of the contrast procedure, and the patient selection. In our study we compared two procedures of CIN prevention in patients with renal dysfunction: group 1 (short regimen) in which the patients received sodium bicarbonate 20 minutes prior to the contrast administration and group 2 (long regimen) in which the patients received the same amount and concentration sodium bicarbonate but 7 hr prior to the intervention, taken into consideration that all patients in our study received non-ionic low osmolar contrast agents. We observed a significant increase in S. Cr. and significant decrease in eGFR calculated by MDRD formula in (group 1) when we compare their levels prior to contrast administration with their levels 48 hr after the intervention (S. Cr: 2.32 ± 0.41 vs. 2.42 ± 0.48) and (eGFR by MDRD: 30.22 ± 6.07 vs, 28.97 ± 6.57). Regarding group 2, the results of our study showed no statistical difference in S. Cr. and eGFR calculated by MDRD 48 hr post-procedure (S. Cr: 2.26 ± 0.47 vs. 2.26 ± 0.49) and (eGFR by MDRD: 30.97 ± 7.13 vs. 31.06 ± 7.41). Also, we demonstrated a significant inverse correlation between S. Cr. and eGFR calculated by MDRD for both group 1 and group 2 (group 1: r = −0.856, p < 0.001) and (group 2: r = −0.908, p < 0.001). In agreement with our study, Briguori et al. (17) found that the long-term regimen of sodium bicarbonate was superior to the short regimen. This was in agreement with with Recio-Mayoral et al. (18). On the contrary, Klima et al. (16) and Mueller (4) stated that both regimens (the long and the short regimens) have the same effectiveness with very high safety, even in patients with NYHA class I or II heart failure, and, thus, the short-term regimen may be the regimen of choice because it is very easy to apply, even to outpatient procedures (15–17). Our research also showed that S. K. has significantly decreased post procedure in both group 1 and group 2 (group1: 4.21 ± 0.43 vs. 3.88 ± 0.33) and (group 2: 4.16 ± 0.42 vs. 3.92 ± 0.34). Also, we demonstrated a non-significant negative correlation between S. Cr. and S. K. in both groups (group 1: r = −0.184) and (group 2: r = −0.235). This was in agreement with Walter et al. (19) who reported that the infusion of sodium bicarbonate can shift potassium from the extracellular to the intracellular space by increasing blood pH. However, this should be reserved for situations with severe educational environments (19). In contrast, Kim (20) stated that sodium bicarbonate is no longer recommended to lower potassium, although it may be appropriate in patients with severe metabolic acidosis (20). Regarding the pH of urine, we found that it was (5.95 ± 0.26) in group 1 and (5.97 ± 0.24) in group 2, showing no statistical difference and highlighting the fact that both regimen had almost the same alkalinizing efficacy with no proven extra benefit for patients with pH values greater than 6.\n\nBODY.4. CONCLUSIONS:\nWe should stress the importance of sodium bicarbonate infusion prior to the administration of the contrast medium to guard against CIN, especially in renally-impaired patients who could easily be susceptible to CIN. In addition, the results of our study indicated that the long regimen of bicarbonate supplementation was a better and more efficient strategy to prevent CIN than the short regimen.\n\nQuestion: Compared to sodium bicarbonate solution using the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). what was the result of sodium bicarbonate solution using the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) on eGFR ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1052	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Self-reported immature defense style as a predictor of outcome in short-term and long-term psychotherapy\n\n ABSTRACT.OBJECTIVE:\nIdentification of pretreatment patient characteristics predictive of psychotherapy outcome could help to guide treatment choices. This study evaluates patients' initial level of immature defense style as a predictor of the outcome of short-term versus long-term psychotherapy.\n\nABSTRACT.METHOD:\nIn the Helsinki Psychotherapy Study, 326 adult outpatients with mood or anxiety disorder were randomized to individual short-term (psychodynamic or solution-focused) or long-term (psychodynamic) psychotherapy. Their defense style was assessed at baseline using the 88-item Defense Style Questionnaire and classified as low or high around the median value of the respective score. Both specific (Beck Depression Inventory [BDI], Hamilton Depression Rating Scale [HDRS], Symptom Check List Anxiety Scale [SCL-90-Anx], Hamilton Anxiety Rating Scale [HARS]) and global (Symptom Check List Global Severity Index [SCL-90-GSI], Global Assessment of Functioning Scale [GAF]) psychiatric symptoms were measured at baseline and 3–7 times during a 3-year follow-up.\n\nABSTRACT.RESULTS:\nPatients with high use of immature defense style experienced greater symptom reduction in long-term than in short-term psychotherapy by the end of the 3-year follow-up (50% vs. 34%). Patients with low use of immature defense style experienced faster symptom reduction in short-term than in long-term psychotherapy during the first year of follow-up (34% vs. 19%).\n\nABSTRACT.CONCLUSION:\nKnowledge of patients' initial level of immature defense style may potentially be utilized in tailoring treatments. Further research on defense styles as outcome predictors in psychotherapies of different types is needed.\n\nBODY.INTRODUCTION:\nBoth short-term and long-term psychotherapies are common in the treatment of mood and anxiety disorders. Evidence-based knowledge on which treatment is most effective for whom is, however, scarce. Various patient-related variables have been suggested as being essential in the evaluation of patients' suitability for psychotherapies and thus in the prediction of their psychotherapy outcome (Blenkiron 1999; Valbak 2004; Norcross and Wampold 2011). One such variable is the initial level of defense style, that is, availability and integration of individual regulating functions, defense mechanisms, aimed at alleviating anxiety-provoking stressors and maintaining mental balance (American Psychiatric Association 1994; OPD Task Force 2001). Healthy aspects of personality, such as a well-integrated, mature defense style, are considered important predictors of positive outcome of short-term psychotherapies, not aiming to achieve structural changes in personality (Van et al. 2009). On the other hand, patients with a less integrated, immature defense style may need long-term treatments to recover. The use of defense styles as outcome predictors in individual psychotherapies has been little studied to date, only in short-term psychotherapies, and with somewhat contradictory findings (Hersoug et al. 2002; Kronström et al. 2009; Van et al. 2009). No studies comparing the prediction of outcome by defense styles in short-term versus long-term psychotherapies have so far been published. More research on the use of defense styles as predictors of psychotherapy outcomes in general and on potential differential prediction of immature defense style on short-term versus long-term psychotherapy outcome in particular is thus needed.\n\nBODY.AIMS OF THE STUDY:\nThis study examines the relationship between level of self-reported immature defense style and subsequent changes in psychiatric symptoms in individual short-term and long-term psychotherapy during a 3-year follow-up period. Our aim was to find out whether the level of immature defense style prior to therapy differentiates the outcome of short-term and long-term therapy.\n\nBODY.MATERIAL AND METHODS:\nThis study was part of the Helsinki Psychotherapy Study (HPS). The methods used have been described in detail elsewhere (Knekt and Lindfors 2004; Knekt et al. 2008, 2012) and are summarized here. Patients gave written informed consent. The study protocol was approved by the Helsinki University Central Hospital's ethics council.\n\nBODY.MATERIAL AND METHODS.PATIENTS:\nOutpatients from the Helsinki region were referred to the study by local practitioners from June 1994 to June 2000 (Knekt and Lindfors 2004; Knekt et al. 2008). Eligible patients were 20–45 years of age and had a long-standing (>1 year) disorder causing work dysfunction. Patients were required to meet the DSM-IV criteria (American Psychiatric Association 1994) for anxiety or mood disorders evaluated based on a semi-structured diagnostic interview (Knekt and Lindfors 2004) and Kernberg's criteria (Kernberg 1996) for neurosis to high-level borderline personality organization evaluated based on a psychodynamic assessment interview (Kernberg 1996). Patients with psychotic disorder or severe personality disorder (DSM-IV cluster A personality disorder and/or lower level borderline personality organization), adjustment disorder, substance-related disorder, organic brain disease, or mental retardation were excluded from the study. Patients suffering from such disorders are generally considered to be in need of a longer treatment as they are unlikely able to tolerate considerable anxiety, which is a requirement for a shorter, more anxiety-provoking treatment; therefore their randomization to short-term therapy was not considered fair (American Psychiatric Association 1985; Blenkiron 1999). Patients treated with psychotherapy within the previous 2 years, psychiatric health employees and persons known to the research team members were also excluded. Altogether 459 patients were considered eligible, of which 133 declined to participate. The remaining 326 patients were randomized according to a central computerized randomization schedule in a 1: 1: 1.3 ratio to individual solution-focused therapy (N = 97), short-term psychodynamic psychotherapy (N = 101), or long-term psychodynamic therapy (N = 128) (Knekt et al. 2008). Of the patients randomized, 33 declined to participate, and 42 of those starting treatment discontinued prematurely. The patients were followed up for 3 years after randomization. During this 3-year follow-up, the patients were provided, in accordance with the study protocol, with either short-term therapy followed by no treatment, or long-term therapy. Follow-up measurements were carried out at eight occasions (at 0, 3, 7, 9, 12, 18, 24, and 36 months). The mean dropout rates over these eight measurement occasions in the three therapy groups were similar (15% in the solution-focused, 13% in the short-term psychodynamic, and 18% in the long-term psychodynamic therapy group) (Knekt et al. 2008).\n\nBODY.MATERIAL AND METHODS.THERAPIES:\nSolution-focused therapy is a brief resource-oriented and goal-focused therapeutic approach, helping clients change by constructing solutions (Johnson and Miller 1994; Lambert et al. 1998). The orientation was based on an approach developed by de Shazer et al. (1986), de Shazer (1991). The frequency of sessions was flexible, usually one every second or third week, with a maximum of 12 sessions (90 min each) over no more than 8 months. Short-term psychodynamic psychotherapy is a brief, focal, transference-based therapeutic approach, helping patients by exploring and working through specific intrapsychic and interpersonal conflicts. The orientation was based on approaches described by Malan (1976) and Sifneos (1978). The therapy was scheduled for 20 treatment sessions (60 min each), one session a week, over 5–6 months. Long-term psychodynamic psychotherapy is an open-ended, intensive, transference-based therapeutic approach, helping patients by exploring and working through a broad area of intrapsychic and interpersonal conflicts. Therapy includes both expressive and supportive elements, the use of which depends on patient needs. The orientation followed the clinical principles of long-term psychodynamic psychotherapy (Gabbard 2004). The session frequency was 2–3 sessions a week and the duration of therapy up to 3 years.\n\nBODY.MATERIAL AND METHODS.THERAPISTS:\nAltogether 55 therapists participated in the study; six provided solution-focused therapy, 12 short-term psychodynamic psychotherapy, and 41 long-term psychodynamic psychotherapy (Knekt et al. 2008). All the therapists had been trained in the respective therapy form. The mean number of years of experience in the therapy form provided was nine (range 3–15) in solution-focused therapy, nine (range 2–20) in short-term psychodynamic psychotherapy, and 18 (range 6–30) in long-term psychodynamic psychotherapy. Additionally, the therapists providing short-term psychodynamic psychotherapy had a mean of 16 years (range 10–21) experience of long-term psychodynamic psychotherapy. None of the therapists providing solution-focused therapy had received any training in psychodynamic psychotherapy and vice versa. Only solution-focused therapy was manualized, and clinical adherence monitoring was performed. All the solution-focused therapists carried out therapy at a center for solution-focused therapy, in which group supervision was part of the institute procedures. On the contrary, all the psychodynamic therapists were private practitioners who had a variety of different arrangements with regard to (primarily individual) supervision. Both psychodynamic psychotherapies were conducted in accordance with clinical practice, where interventions can be modified to patients' needs within the psychodynamic framework.\n\nBODY.MATERIAL AND METHODS.ASSESSMENTS AT BASELINE:\nPatient defense style was assessed using a self-report questionnaire at baseline, before randomization of patients into therapies. Other baseline factors potentially confounding the relationship between the baseline defense style and psychotherapy outcome during follow-up were assessed using questionnaires and interviews.\n\nBODY.MATERIAL AND METHODS.ASSESSMENTS AT BASELINE.DEFENSE STYLE:\nPsychological defense styles were assessed as a part of personality functions assessment using the Finnish translation (Sammallahti et al. 1994) of the revised 88-item Defense Style Questionnaire (DSQ) by Andrews et al. (1989). Each item consists of an attitudinal statement describing defenses along an ordinal continuum ranging from no agreement (score 1) to total agreement (score 9). A three-factor scale, based on factor analysis (Andrews et al. 1993), has been developed to group the individual defenses into three different types of defense styles: immature, neurotic, and mature (Andrews et al. 1989). This scale has been proven to be an internally reliable instrument, the internal consistency reliabilities (Cronbach's alpha) being 0.89, 0.72, and 0.59 for factors 1, 2, and 3, respectively (Kim and Mueller 1978). Of the 88 items, 72 items are included in the calculation of defense style scores (16 items were control questions); immature, neurotic, and mature defense style scores are based on 46, 16, and 10 items, respectively. The immature defense style covers the specific defenses of acting out, autistic fantasy, denial, devaluation, displacement, dissociation, isolation, passive aggression, projection, rationalization, splitting, and somatization. A score describing the amount of defense style at present is calculated as a mean of the corresponding items, varying thus from 1.0 to 9.0. A factor analysis was carried out to investigate the internal factor structure of the DSQ in the HPS sample. The three-factor solution resembled the original solution (Kim and Mueller 1978; Andrews et al. 1989), with Cronbach's alphas 0.81, 0.68, and 0.50 for immature, neurotic, and mature defense style factors, respectively. The level of immature defense style in this study was classified as low or high around the median value of the score (3.98); a score under the median represented low use of immature defense style and a score equal to or above the median represented high use of immature defense style.\n\nBODY.MATERIAL AND METHODS.ASSESSMENTS AT BASELINE.POTENTIAL CONFOUNDING FACTORS:\nPsychiatric diagnoses at Axes I and II were assessed based on a semi-structured interview (Knekt and Lindfors 2004) according to the DSM-IV diagnostic criteria (American Psychiatric Association 1994). Sociodemographic factors (gender, age, education), psychiatric history (previous depressive states, previous psychotherapy), personality functions, including suitability for psychotherapy (SPS; median kappa coefficient for agreement 0.69 [Laaksonen et al. 2012]), quality of object relations (QORS; Azim et al. 1991), and interpersonal problems (IIP; Horowitz et al. 2000), as well as social functioning, including life orientation (LOT; Scheier and Carver 1985), sense of coherence (SOC; Antonovsky 1993), and social adjustment (SAS-SR; Weissmann and Bothwell 1976) were assessed using questionnaires.\n\nBODY.MATERIAL AND METHODS.ASSESSMENTS AT FOLLOW-UP:\nThe primary outcome measures were specific depressive and anxiety symptoms. The symptoms of depression were assessed with the 21-item self-report Beck Depression Inventory (BDI; Beck et al. 1961) and with the 17-item observer-rated Hamilton Depression Rating Scale (HDRS; Hamilton 1960). The symptoms of anxiety were assessed with the 10-item self-reported Symptom Check List Anxiety Scale (SCL-90-Anx; Derogatis et al. 1973) and with the 14-item observer-rated Hamilton Anxiety Rating Scale (HARS; Hamilton 1959). Secondary outcome measures describing general psychiatric symptoms and global functional capacity were assessed with the Symptom Check List Global Severity Index (SCL-90-GSI; Derogatis et al. 1973) and the Global Assessment of Functioning Scale (GAF; American Psychiatric Association 1994). The self-report measures (BDI, SCL-90-Anx, SCL-90-GSI) were assessed at baseline and 3, 7, 9, 12, 18, 24, and 36 months after the start of the treatment, and the observer-rated measures (HDRS, HARS, GAF) at baseline and 7, 12, and 36 months after the start of the treatment.\n\nBODY.MATERIAL AND METHODS.STATISTICAL METHODS:\nThe statistical analyses were based on linear mixed models (Verbeke and Molenberghs 1997) carried out with SAS software, version 9.1. (SAS Institute Inc 2007). The main analyses were based on the \"intention-to-treat\" (ITT) design. Complementary \"as-treated\" (AT) analyses were also performed (Härkänen et al. 2005; Knekt et al. 2008). The primary analyses were based on the assumption of ignorable dropouts (Knekt et al. 2008). In the secondary analyses, missing values were replaced by multiple imputation. The imputation was based on the Markov chain Monte Carlo methods. Model adjusted outcome means and mean differences were calculated for different measurement points (Lee 1981). The delta method was used for the calculation of confidence intervals (Migon and Gamerman 1999). The statistical significance of the model used was tested with the Wald test. In the ITT analyses, two models were used: a basic model and a complete model. The dependent variable in the analyses was each of the outcome measures (BDI, HDRS, SCL-90-Anx, HARS, SCL-90-GSI, GAF) at a time. The basic ITT model included as independent variables the immature defense style measured at baseline, therapy group, and time (i.e., measurement points), their first- and second-order interactions, a correction term (i.e., the second-order interaction of the difference between theoretical and realized date of measurement, time and immature defense style), and outcome measure at baseline. The complete ITT model further included sociodemographic variables (age, gender, education), DSM-IV diagnoses (Axes I and II, major depressive disorder, and comorbidity of mood and anxiety disorder), psychiatric history data (previous depressive states, previous psychotherapy), personality functions (SPS, QORS, IIP) and social functioning (LOT, SOC, SAS-SR). These were all measured at baseline and satisfied the criteria for confounding, that is, were related with the immature defense style and preceded and were causally related to any of the six outcome measures, without being an intermediate or latent variable (Rothman and Greenland 1998). To account for the deviations from the study protocol, an AT model was created by adding variables describing noncompliance, that is, waiting time from randomization to initiation of treatment and degree of participation (i.e., withdrawal from or discontinuation of treatment) during follow-up as main effects to the complete ITT model. All three models (ITT basic, ITT complete, AT) were carried out based on both the original data and imputed data. The independent variable of main interest was the interaction term between the immature defense style score, therapy group, and time. As no notable differences in the prediction of the immature defense style on outcome of solution-focused therapy and short-term psychodynamic psychotherapy were found during the 3-year follow-up, these two short-term therapies were combined into one short-term therapy group which was compared to the long-term therapy group. A comparison between the basic and complete ITT models demonstrated that the results were slightly different depending on whether potential confounding factors were used in the statistical model, whereas no major difference between the ITT and AT models were found (data not shown). Imputation caused the confidence intervals to widen, and accordingly resulted in statistical significance of some of the comparisons to disappear (data not shown). The results presented are based on the complete ITT model as based on the original data. The significance of the immature defense style in predicting the outcome of short-term versus long-term therapy during the 3-year follow-up was evaluated by testing the statistical significance of the interaction term between the immature defense style and the therapy group throughout the follow-up. The Wald test was used. We assessed statistical significance of the change in outcome from baseline to the different measurement points for each therapy group (short-term and long-term) and category (low and high) of immature defense style. Therapy was considered beneficial for the patients who experienced and maintained a statistically significant reduction in symptoms in comparison with the baseline during the 3-year follow-up. We measured the statistical significance of the model-adjusted difference in the outcome between the therapy groups in the immature defense style categories at the different measurement points. We considered short-term therapy to be equally or more beneficial than long-term therapy when there were no statistically significant differences between the therapy groups or greater benefit from short-term therapy, whereas long-term therapy was considered to be more beneficial when comparisons favored long-term over short-term therapy.\n\nBODY.RESULTS:\nThe study sample consisted of 326 patients ranging in age from 20 to 46 years (mean 32 years) (Table 1). Approximately 25% of the patients were men, about 50% lived alone, and 25% had an academic education. The majority (85%) of the patients suffered from mood disorder, 44% from anxiety disorder, and 18% from personality disorder. No notable differences between short-term and long-term therapy groups were found with respect to baseline sociodemographic or clinical characteristics, with the exception of significantly higher prevalence of anxiety disorder and personality disorder in the short-term therapy group. Table 1 Baseline characteristics of the 326 patients intended to treat by treatment group Treatment 1 Characteristic Short ( N = 198) Long ( N = 128) Sociodemographic variables Men (%) 25.8 21.1 Age (years) 2 32.8 (7.1) 31.6 (6.6) University degree (%) 24.2 28.1 Living alone (%) 52.5 49.2 Employed (%) 3 84.2 75.4 Psychiatric diagnoses 4 Mood disorder (%) 82.3 88.3 Anxiety disorder (%) 48.0 36.7 Comorbid mood and anxiety disorder (%) 30.3 25.0 Personality disorder (%) 21.7 12.5 Psychiatric symptoms Beck Depression Inventory (BDI) 2 18.0 (7.6) 18.8 (8.3) Hamilton Depression Rating Scale (HDRS) 2 15.6 (4.7) 15.8 (4.9) Symptom Check List, Anxiety scale (SCL-90-Anx) 2 1.3 (0.7) 1.2 (0.7) Hamilton Anxiety Rating Scale (HARS) 2 15.0 (5.3) 14.8 (5.2) Symptom Check List, Global Severity Index (SCL-90-GSI) 2 1.3 (0.5) 1.3 (0.6) Global Assessment of Functioning Scale (GAF) 2 55.1 (7.1) 55.5 (8.1) Psychiatric background Recurrent episodes of major depressive disorder (%) 64.1 69.1 Duration of primary disorder over 5 years (%) 34.3 29.7 Previous psychotherapy (%) 19.4 19.0 Psychological defenses (DSQ) Immature defense style 2 3.93 (0.76) 3.93 (0.69) Neurotic defense style 2 4.21 (0.96) 4.21 (0.94) Mature defense style 2 5.25 (0.92) 5.12 (1.01)) 1 Short, Short-term psychodynamic psychotherapy and solution-focused therapy combined; Long, Long-term psychodynamic psychotherapy. 2 . 3 Full-time/part-time work or full-time student/student at work. 4 Mood disorder: mood disorder only or comorbid mood and anxiety disorder. Anxiety disorder: anxiety disorder only or comorbid mood and anxiety disorder. Personality disorder: main diagnoses on Axis II. During the 3-year follow-up, a statistically significant symptom reduction was found in all six outcome measures (BDI, HDRS, SCL-90-Anx, HARS, SCL-90-GSI, GAF) in both short-term and long-term therapy groups (Table 2). There was no statistically significant interaction between immature defense style and therapy group in the 3-year follow-up. Numerous consistent statistically significant differences in symptom development between short-term and long-term therapies at different points of follow-up were, however, found in relation to the level of immature defense style. During the first year of the follow-up, a statistically larger symptom reduction in the short-term therapy group than in the long-term therapy group (18–45% vs. 9–31%, respectively) was found among patients with low immature defense style according to all six outcome measures. At the end of the 3-year follow-up, on the other hand, a statistically larger symptom reduction in the long-term therapy group than in the short-term therapy group (26–64% vs. 21–45%, respectively) was found among patients with high immature defense style according to five outcome measures. Table 2 Mean values and mean value differences (95% confidence intervals) between short-term and long-term therapy at baseline and at 7, 12, and 36 month follow-up according to the low and high values of the immature defense style score. 1961 Low 2 High 2 Outcome measure Therapy 0 7 12 36 0 7 12 36 P -value 3 BDI Short 18.0 10.7 10.1 10.0 18.0 9.91 9.55 10.1 0.50 Long 18.2 14.7 12.7 7.58 19.2 14.1 12.8 6.47 S-L 4 −3.96 * (−6.57, −1.35) −2.60 (−5.36, 0.15) 2.43 (−0.49, 5.35) − 4.23 * (−6.79, −1.67) − 3.26 * (−5.99, −0.52) 3.63 * (0.62, 6.65) HDRS Short 15.3 10.7 10.6 10.7 15.9 11.1 11.1 10.7 0.26 Long 15.5 13.3 13.8 10.3 16.2 12.4 11.7 7.87 S-L 4 − 2.57 * (−4.40, −0.75) − 3.23 * (−5.16, −1.29) 0.47 (−1.54, 2.47) −1.28 (−3.12, 0.57) −0.68 (−2.66, 1.30) 2.87 * (0.77, 4.97) SCL-90-Anx Short 1.20 0.81 0.81 0.75 1.27 0.94 0.85 0.83 0.18 Long 1.08 1.10 0.96 0.74 1.38 1.03 0.98 0.53 S-L 4 − 0.29 * (−0.51, −0.07) −0.15 (−0.36, 0.05) 0.01 (−0.12, 0.23) −0.10 (−0.31, 0.12) −0.13 (−0.33, 0.07) 0.30 * (0.09, 0.52) HARS Short 14.4 10.0 9.90 9.71 15.4 10.7 10.5 9.92 0.11 Long 14.5 13.0 12.5 9.08 15.5 10.9 10.5 7.56 S-L 4 − 2.97 * (−4.68, −1.27) − 2.55 * (−4.33, −0.77) 0.63 (−1.20, 2.46) −0.21 (−1.93, 1.52) 0.05 (−1.77, 1.87) 2.35 * (0.44, 4.26) SCL-90-GSI Short 1.18 0.88 0.82 0.84 1.34 0.92 0.82 0.83 0.54 Long 1.20 1.14 1.04 0.81 1.38 1.04 0.95 0.60 S-L 4 − 0.26 * (−0.43, −0.09) − 0.21 * (−0.37, −0.05) 0.03 (−0.15, 0.20) 0.12 (−0.29, 0.05) −0.13 (−0.29, 0.03) 0.23 * (0.04, 0.41) GAF Short 54.0 65.3 65.5 67.5 56.3 65.1 66.0 66.8 0.79 Long 54.3 61.3 60.4 68.4 55.8 63.3 62.9 69.9 S-L 4 4.03 * (0.59, 7.46) 5.19 * (1.56, 8.83) −0.88 (−4.28, 3.07) 1.77 (−1.70, 5.23) 3.09 (−0.62, 6.80) −3.05 (−7.18, 1.09) BDI, Beck Depression Inventory; HDRS, Hamilton Depression Rating Scale; SCL-90-Anx, Symptom Check List, Anxiety scale; HARS, Hamilton Anxiety Rating Scale; SCL-90-GSI, Symptom Check List, Global Severity Index; GAF, Global Assessment of Functioning Scale. Underlined symptoms have changed statistically significantly in comparison with baseline symptom level. * Bold values ( P < 0.05) are for comparison between short-term and long-term therapy. 1 Complete “intention-to-treat” (ITT) model: outcome measure = interaction of immature defense style score (low, high), therapy group (short, long) and time (in months) adjusted for time, the immature defense style according to the therapy group, the difference between planned and realized date of measurement, second-order interaction of the difference between planned and realized date of measurement, time and immature defense style according to the therapy group, age, gender, education, DSM-IV Axis I diagnosis, DSM-IV Axis II diagnosis, DSM-IV major depressive disorder diagnosis, comorbidity of mood and anxiety disorder, previous depressive states, previous psychotherapy, suitability for psychotherapy, quality of object relations, interpersonal problems, life orientation, sense of coherence, social adjustment, and the baseline level of the outcome measure. 2 The median score of the immature defense style in the Helsinki Psychotherapy Study sample was 3.98. Low immature defense style was categorized as values below the median (2.00–3.97) and high immature defense style as values equal to or above the median (3.98–6.04). 3 P -value for interaction between the immature defense style, the therapy group, and time throughout the follow-up. 4 Mean value difference of outcome measure between short-term and long-term psychotherapy. Imputation, carried out to study the reliability of the ignorable drop-out assumption, attenuated the results to some extent but the benefit of short-term therapy during the first year of follow-up still remained statistically significant for five of six outcome measures (excluding GAF) and the benefit of long-term therapy during the last year of follow-up for three of five outcome measures (excluding HDRS and HARS) (data not shown). Thus, according to our criteria, for patients with low use of immature defense style short-term therapy seemed to be more beneficial, whereas for patients with high use of immature defense style long-term therapy seemed more beneficial.\n\nBODY.DISCUSSION:\nIt has been suggested that healthy aspects of personality are necessary precursors for positive outcome in short-term psychotherapies which, due to the limited amount of time, in contrast to long-term psychotherapies, do not usually aim at achieving structural changes in personality (Van et al. 2009). It follows that persons with poorly functioning personality are likely to need long-term psychotherapies to recover, as long-term therapies foster capacity for growth and aim to increase self-awareness and to improve interpersonal skills through changes in personality (American Psychiatric Association 1985). A person's characteristic defenses represent one key aspect of their personality organization, manifested in the person's interpersonal behavior and personal experiences. Accordingly, the presence of immature defense style highlights the likelihood that the person is characterized also of having contradictory personality traits, low level of object relations, and an unstable sense of self and others (Kernberg 1996). An immature defense style, defined as a type of maladaptive behavior pattern in which the very occurrence of the perceived psychic threat (affect, idea, or aspect of a relationship) is denied, split-off from consciousness, or in other ways significantly distorted, thus reflects a poorly functioning, that is, more primitive, personality organization. The few previous studies on the analysis of defense styles and overall defensive functioning as predictors of treatment outcome have focused on short-term psychodynamic psychotherapy alone or in comparison to medication and have produced contradictory findings (Hersoug et al. 2002; Kronström et al. 2009; Van et al. 2009). According to Van et al. (2009), self-reported mature, but not neurotic or immature, defense style was predictive of positive symptomatic outcome in short-term psychodynamic psychotherapy. However, according to Kronström et al. (2009) and Hersoug et al. (2002), respectively, mature defense style and overall level of defenses were not predictive of psychotherapy outcome. The role of immature defense style in the prediction of long-term psychotherapy outcome or potential differential prediction of short-term versus long-term psychotherapy outcome has not been previously studied. In this study, the use of self-reported baseline immature defense style as a predictor of outcomes of short-term and long-term psychotherapies was examined for the first time. No differences in relationship between self-reported immature defense style and outcome in short-term psychodynamic psychotherapy and solution-focused therapy were found. This is in line with our previous findings on other psychotherapy suitability variables (Laaksonen et al. 2013a). The prediction, however, appeared to vary depending on the length of the treatment and follow-up. On average, patients with low use of immature defense style recovered faster in short-term than in long-term psychotherapy, whereas patients with high use of immature defense style recovered better in long-term than in short-term psychotherapy by the end of the 3-year follow-up. Our findings thus support the hypotheses presented in the literature and are also in line with our previous findings (Laaksonen et al. 2013b). This study has several strengths. First, the relatively large sample size enabled more reliable detection of possible differences. Second, the long follow-up time and frequent outcome measurements allowed a comprehensive description and comparison of the symptom development in the treatment groups. Third, use of various well-validated, both observer-rated and self-reported, outcome measures permitted evaluation of the generalizability of the phenomenon studied. The main results were found according to all these measures, indicating that the phenomenon was independent of different assessment methods. Fourth, a widely used self-report measure of defense styles, DSQ, was used. The measure has been concluded to be the best self-reported defense style assessment method based on available information on the validity and reliability of different methods (Soultanian et al. 2005). Further use also of observer-rated methods would, however, likely give a more comprehensive picture of the predictive role of defense styles, especially as defenses are automatic psychological processes that individuals often are unaware of, and therefore the self-report methods only reflect their conscious derivates and might be sensitive to the influence of the actual psychopathology (Andrews et al. 1989; Van et al. 2009). Fifth, a factor analysis was carried out to compare the internal factor structure of the DSQ in the HPS sample to the original factor solution by Andrews et al. (1989), and the DSQ was concluded to be a valid and reliable measure of immature defense style in the HPS. Sixth, comprehensive criteria, based on statistical significance, for the evaluation of different aspects of prediction of the influence of defense styles on psychotherapy outcome were applied (Laaksonen et al. 2013a,b). This study has, however, also several limitations. The general limitations related to the design of the HPS (i.e., lack of manuals and blindness of raters making follow-up assessments) are discussed in more detail elsewhere (Knekt et al. 2008, 2012), and only the limitations specific to this study are addressed here. First, although potential confounding factors were comprehensively studied and adjusted by modeling, the possibility of residual confounding cannot be fully excluded. Second, the compliance of study treatment or auxiliary treatment may potentially cause bias (Knekt et al. 2011). Results from AT analysis, adjusted for withdrawal or discontinuation and for time-dependent variables on auxiliary treatment, did not, however, notably differ from the results from ITT analysis. Third, although analyses were carried out based on both the original and imputed data, possible nonignorable dropouts may still bias the results (Härkänen et al. 2005). Some differences between the analyses based on the original and imputed data were found which also emphasizes need for further research. Fourth, a follow-up longer than 3 years is needed to be able to verify the stability of the findings in long-term therapy.\n\nBODY.CONCLUDING REMARK:\nThis study suggests that patients with low use of immature defense style may be more suitable for short-term psychotherapy, while patients with high use of immature defense style may benefit more from long-term psychotherapy. More research is, however, needed to confirm these findings and to demonstrate their usefulness in practice.\n\nBODY.SIGNIFICANT OUTCOMES:\nSymptoms of patients with high use of immature defense style prior to therapy reduced significantly more in long-term than in short-term psychotherapy.Symptoms of patients with low use of immature defense style prior to therapy reduced significantly faster in short-term than in long-term psychotherapy.Level of patient's initial immature defense style appeared to differentiate the suitability of short-term and long-term psychotherapy and may be utilized to guide treatment choices to better match patients to therapies.\n\nBODY.LIMITATIONS:\nA widely used and well-validated self-report defense style measure, DSQ, was used for the assessment of immature defense style, but use of observer-rated methods would provide a more comprehensive view of these phenomena.The possible changes in the use of immature defense style during the therapies were not analyzed and thus more research is needed to find out whether the greater benefit of long-term therapy among those with high initial use of immature defense style was due to its gradually lesser use.To be able to tailor treatments more accurately, the research on psychotherapy suitability should be expanded to include a greater variety of patient, therapist and alliance factors and their combinations as well as in the context of psychotherapies of different orientation and length.\n\nQuestion: Compared to Long-term psychotherapy what was the result of Short-term psychotherapy on Decrease in symptoms among patients with high immature defense style after 3 years?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1176	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Mirabegron for the treatment of overactive bladder: a prespecified pooled efficacy analysis and pooled safety analysis of three randomised, double-blind, placebo-controlled, phase III studies\n\n ABSTRACT.INTRODUCTION:\nTo examine pooled efficacy data from three, large phase III studies comparing mirabegron (50 and 100 mg) with placebo, and pooled safety data including additional mirabegron 25 mg and tolterodine extended release (ER) 4 mg results.\n\nABSTRACT.METHODS:\nThis prespecified pooled analysis of three randomised, double-blind, placebo-controlled, 12-week studies, evaluated efficacy and safety of once-daily mirabegron 25 mg (safety analysis), 50 or 100 mg (efficacy and safety analyses) and tolterodine ER 4 mg (safety analysis) for the treatment of symptoms of overactive bladder (OAB). Co-primary efficacy measures were change from baseline to Final Visit in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h. Key secondary efficacy end-points included mean number of urgency episodes/24 h and mean volume voided/micturitions, while other end-points included patient-reported outcomes according to the Treatment Satisfaction-Visual Analogue Scale (TS-VAS) and responder analyses [dry rate (posttreatment), ≥ 50% reduction in incontinence episodes/24 h, ≤ 8 micturitions/24 h (post hoc analysis)]. The safety analysis included adverse event (AE) reporting, laboratory assessments, ECG, postvoid residual volume and vital signs (blood pressure, pulse rate).\n\nABSTRACT.RESULTS:\nMirabegron (50 and 100 mg once daily) demonstrated statistically significant improvements compared with placebo for the co-primary end-points, key secondary efficacy variables, TS-VAS and responder analyses (all comparisons p < 0.05). Mirabegron is well tolerated and demonstrates a good safety profile. The most common AEs (≥ 3%) included hypertension, nasopharyngitis and urinary tract infection (UTI); the incidence of hypertensive events and UTIs decreased with increasing dose. For mirabegron, the incidence of the bothersome antimuscarinic AE, dry mouth, was at placebo level and of a lesser magnitude than tolterodine.\n\nABSTRACT.CONCLUSION:\nThe efficacy and safety of mirabegron are demonstrated in this large pooled clinical trial dataset in patients with OAB.\n\nBODY:\nWhat's knownOveractive bladder (OAB) is a chronic condition that is increasingly prevalent with age and represents an increasing healthcare burden to society.Antimuscarinic drugs are the current mainstay of pharmacologic treatment for OAB, but are commonly associated with adherence-limiting adverse effects including dry mouth, constipation and blurred vision.Many patients discontinue antimuscarinic therapy or seek alternative approaches to control OAB as a result of adverse effects or suboptimal efficacy.What's newMirabegron is a β3-adrenoceptor agonist, the first in a new class of drugs with a mode of action that is different from antimuscarinic agents.Mirabegron stimulates the β3-adrenoceptors in the bladder leading to detrusor relaxation and increased bladder capacity.In three international, multicentre, phase III studies, comparing mirabegron, at doses of 25, 50 and 100 mg, with placebo, mirabegron was associated with significant improvements in incontinence episodes and micturition frequency, and was well tolerated.\n\nBODY.INTRODUCTION:\nOveractive bladder (OAB) is defined by the International Continence Society as urinary urgency, with or without urinary incontinence, usually with frequency and nocturia, with no proven infection or other obvious pathology 1,2. Lower urinary tract symptoms, including those associated with OAB, are prevalent in approximately half of the general population 3, are often debilitating and have a significant impact on patients' daily routines and quality of life 3–5. OAB affects 12–16% of the adult population across Europe, the USA and Japan 6–8, and its prevalence increases with age, affecting approximately 30% of individuals > 65 years of age 9, therefore representing a substantive health problem for the ageing population. Normal bladder function is regulated by the synergistic actions of the autonomic nervous system: parasympathetic nerves stimulate contraction of the detrusor muscle via muscarinic receptors while stimulation of the sympathetic nerves leads to detrusor relaxation via β-adrenoceptors. The central pathophysiology of OAB involves involuntary contractions of the detrusor muscle as a result of increased afferent activity, decreased inhibitory control from the central nervous system, and/or increased sensitivity of the detrusor muscle to parasympathetic stimulation 10,11. Because of the role of β-adrenoceptors in relaxation of the detrusor, research was aimed at identifying an effective and well-tolerated agent directed at the β-adrenoceptor. The β3-adrenoceptor was recognised as the predominant β-receptor subtype in the human urinary bladder, representing 97% of total β-adrenoceptor mRNA expression in the human bladder 12. The importance of its role in the relaxation of the detrusor has been confirmed by in vitro pharmacological studies using human bladder strips 13–15. In animal models, activation of the β-adrenoceptor in the bladder facilitates urine storage through flattening and lengthening of the bladder base 16. Furthermore, stimulation of the β3-adrenoceptor is associated with increased bladder capacity, without change in micturition pressure, residual volume or voiding contraction 17–19. As a consequence, targeting the β3-adrenoceptor increases the storage capacity of the bladder without affecting the amplitude of the voiding contraction. Mirabegron, a β3-adrenoceptor agonist approved in Japan, the USA, Canada and Europe, for the treatment of OAB symptoms, is the first of a new class of compounds with a mechanism of action that is different from antimuscarinic agents 20. The recommended starting dose of mirabegron is 25 mg in the USA, which can be increased to 50 mg based on individual efficacy and tolerability, and 50 mg in Japan and Europe; the 100 mg dose is not approved for use. Three large-scale, 12-week, phase III studies conducted in the USA/Canada (study 047; NCT00662909) 21; Europe and Australia (study 046; NCT00689104) 22; and Europe/USA/Canada (study 074; NCT00912964)23 have demonstrated the safety, tolerability and superior efficacy of mirabegron at doses of 25 mg (NCT00912964 only), 50 mg (all three studies) and 100 mg (NCT00662909 and NCT00689104) compared with placebo for the treatment of OAB symptoms. The pooled efficacy analysis was prespecified and excluded the 25 mg mirabegron dose because it was limited to a single study. The safety analysis was an aggregate of all data from the three phase III studies and included the 25, 50 and 100 mg mirabegron doses. Pooling these data allows for additional analyses of efficacy and safety in a large dataset representative of the general OAB population in terms of demographics, previous OAB history and prevalence of comorbidities. In particular, it is important to examine the efficacy, safety and tolerability profile demonstrated in the individual studies in the pooled population for overall effect size as well as safety data reporting across the treatment groups. These pooled mirabegron data evaluations inform benefit–risk assessments and support judicious dose selection.\n\nBODY.METHODS.STUDY DESIGN:\nThis was a prespecified pooled analysis of three randomised, double-blind, placebo-controlled, 12-week studies, which evaluated the efficacy of mirabegron 50 and 100 mg, and safety of mirabegron 25 mg (NCT00912964 only), 50 mg or 100 mg for the treatment of symptoms of OAB. Each study shared a similar design, although the assessed doses of mirabegron and inclusion of an active control arm with tolterodine extended release (ER) 4 mg varied across trials (Figure 1). Male and female patients aged ≥ 18 years with OAB symptoms for ≥ 3 months were enrolled. Following a 2-week, single-blind, placebo run-in period to determine baseline symptoms and patient eligibility, patients were randomised if, during a 3-day micturition diary period, they recorded ≥ 8 micturitions/24 h and ≥ 3 urgency episodes – based on urgency grade of 3 or 4 according to the Patient Perception of Intensity and Urgency Scale [PPIUS 24] – with or without urgency incontinence. Patients were excluded with stress incontinence or mixed incontinence with stress predominance at screening or had an average total daily urine volume > 3000 ml. Figure 1Overview of the individual phase III studies included in the pooled analyses. †Screening from weeks −3 to −2; Evaluation of adverse events and concomitant medication by telephone contact or visit 30 days after Final Visit in studies 046 and 047 and 2 weeks after Final Visit in Study 074. n, number of patients randomised Patients were randomised to receive once-daily oral placebo, mirabegron 25 mg (NCT00912964 only), mirabegron 50 mg (NCT00912964/NCT00689104/NCT00662909), mirabegron 100 mg (NCT00689104/NCT00662909) or tolterodine ER 4 mg (NCT00689104 only) for 12 weeks using a computer-generated randomisation scheme; after assignment to treatment, both patient and study investigator were blinded to the identity of the study drug. Efficacy data for treatment arms that were represented in only one study (i.e. mirabegron 25 mg or tolterodine ER 4 mg) were not pooled as these data were only available from one trial. In summary, the efficacy data in these pooled analyses relate to the placebo and 50 mg mirabegron groups from all three phase III studies, and the 100 mg mirabegron group from two of the studies [NCT00662909 21/NCT00689104 22]. In contrast, the pooled 12-week phase III safety analysis includes data for the placebo, 25, 50 and 100 mg mirabegron doses and the tolterodine ER 4 mg active control arm.\n\nBODY.METHODS.EFFICACY END-POINTS:\nEfficacy measures were recorded in a patient micturition diary over a 3-day period prior to clinic visits which occurred at baseline and 4, 8 and 12 weeks/Final Visit (end of treatment, i.e. last on-treatment assessment including patients who did not complete week 12 visit) after randomisation to treatment. The co-primary end-points in all three studies were change from baseline to Final Visit in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h. Key secondary efficacy end-points in all three studies were change from baseline to Final Visit in the mean volume voided/micturition, change from baseline to week 4 in the mean number of incontinence episodes/24 h, and change from baseline to week 4 in the mean number of micturitions/24 h. Study 074 (NCT00912964) had three additional key secondary end-points – mean level of urgency (based on the PPIUS), mean number of urgency episodes (PPIUS grade 3 or 4)/24 h, and the mean number of urgency incontinence episodes/24 h – which were also included as additional secondary end-points in Study 046 (NCT00689104) and Study 047 (NCT00662909) but did not undergo the hierarchical testing procedure for multiple end-points. Further secondary end-points included change from baseline to Final Visit in mean number of nocturia episodes/24 h and patients considered 'responders' to treatment, i.e. the proportion of patients with incontinence episode(s) at baseline with zero incontinence at Final Visit, the proportion of patients with a ≥ 50% decrease from baseline in mean number of incontinence episodes/24 h, and a post hoc analysis of the proportion of patients with ≤ 8 micturitions/24 h at Final Visit. Patient-reported outcomes were assessed using the Treatment Satisfaction-Visual Analogue Scale (TS-VAS), a quantitative instrument measuring subjective improvement in patients with OAB. Complete satisfaction was indicated by a score of 10, with positive change from baseline indicating improvement.\n\nBODY.METHODS.SAFETY END-POINTS:\nThe analysis of the pooled safety data included adverse event (AE) reporting, laboratory parameters (haematology and serum chemistry), vital signs (pulse rate and blood pressure), ECG data and postvoid residual (PVR) volume. AEs of interest were based on potential or theoretical risk related to the pharmacology of β3-agonists, observed findings in non-clinical or clinical data, or recommended monitoring for specific events. The most common treatment-emergent AEs (TEAEs), according to the preferred term, are reported herein as TEAEs in ≥ 3% of the total mirabegron population. Hypertension was reported as an AE if average systolic blood pressure (SBP) was ≥ 140 mmHg and/or average diastolic blood pressure (DBP) ≥ 90 mmHg at two consecutive postbaseline visits for normotensive patients at baseline; average SBP increased ≥ 20 mmHg and/or average DBP increased ≥ 10 mmHg at two consecutive postbaseline visits for patients with hypertension at baseline; initiation or increase in antihypertensive medication; or according to clinical assessment by the investigator. Tachycardia was to be reported as an AE if average AM or PM resting pulse rate measured by the patient over 3 days was > 100 bpm (unless in the investigator's opinion this did not constitute an AE of tachycardia). Urinary retention was summarised as a reported TEAE based on spontaneous reporting by the investigator, without a prespecified definition per protocol, and assessed concurrently with changes in PVR volume (change from baseline of ≥ 150 ml).\n\nBODY.METHODS.STATISTICAL ANALYSES:\nThe safety analysis set (SAF) comprised all randomised patients who took ≥ 1 dose of double-blind study drug; the full analysis set (FAS) comprised SAF patients who had ≥ 1 micturition measurement at baseline and ≥ 1 postbaseline micturition measurement; the FAS-incontinence (FAS-I) set comprised FAS patients who reported ≥ 1 incontinence episode at baseline. Efficacy analyses were performed using the FAS except for incontinence episode end-points which used the FAS-I. Safety analyses were performed using the SAF. Descriptive statistics were used for baseline demographic and clinical characteristics. For the efficacy analysis, data for the placebo and 50 mg mirabegron groups from all three studies were pooled, and data for the 100 mg mirabegron groups from two studies were pooled. Hypothesis testing on the change from baseline in incontinence episodes was performed using a separate stratified rank analysis of covariance (ANCOVA) for each pairwise treatment group difference (mirabegron 50 and 100 mg vs. placebo). For all other efficacy end-points, hypothesis testing comparing mirabegron 50 and 100 mg vs. placebo on the change from baseline values was performed using an ANCOVA model including treatment, gender and study as fixed factors, and baseline value as a covariate. Based on the ANCOVA, least squares mean estimates and two-sided 95% confidence intervals (CIs) for mean changes from baseline were derived within treatment groups and between each mirabegron treatment group and placebo on all efficacy end-points. Multiplicity between the two primary and six key secondary efficacy end-points was controlled at the α = 0.05 type I error rate using a stepwise parallel gatekeeping procedure in which the placebo-corrected difference in mean change from baseline for each mirabegron dose had to be statistically significant to allow hypothesis testing to proceed to the next end-point step. The Hochberg procedure was performed at the α = 0.05 significance level for comparisons of the 50 and 100 mg mirabegron treatment groups with placebo to adjust for multiplicity within each stage. If only one mirabegron dose group proceeded to the next stage for any efficacy end-point, the comparison with placebo was assessed at the α = 0.025 level. Responder end-points were analysed using a logistic regression model which included treatment, gender, study and baseline value. For the pooled safety analysis, data from all three studies were included: placebo, 25, 50 and 100 mg mirabegron groups, and tolterodine ER 4 mg arm. All AEs were coded using the Medical Dictionary for Regulatory Activities version 12.1. TEAEs were defined as any AE which started, or worsened, after the first dose of study drug through 30 days after the last dose of study drug. Drug-related TEAEs included those AEs reported as probably or possibly related to study drug as assessed by the investigator or if the AE had a missing relationship. Descriptive statistics were used for measurements of laboratory parameters, ECGs and PVR volume. Change from baseline values for vital sign variables was analysed using the ANCOVA model described above.\n\nBODY.RESULTS.DEMOGRAPHIC AND BASELINE CLINICAL CHARACTERISTICS:\nOverall, there were a total of 3542 patients (placebo, n = 1328; mirabegron 50 mg, n = 1324; mirabegron 100 mg, n = 890) and 2317 patients (placebo, n = 878; mirabegron 50 mg, n = 862; mirabegron 100 mg, n = 577), respectively, in the FAS and FAS-I population for the pooled efficacy analysis. The pooled safety analysis included the additional 25 mg mirabegron dose and tolterodine active control arm and consisted of 4611 patients (mirabegron 25 mg, n = 432; mirabegron 50 mg, n = 1375; mirabegron 100 mg, n = 929; placebo, n = 1380; tolterodine, n = 495) who took at least one dose of double-blind study medication. In the FAS and SAF analyses, the disposition and reasons for discontinuation of study drug were similar for all treatment groups (Figure 2). Figure 2Patient disposition in the pooled efficacy and safety analyses Demographic and baseline characteristics were similar between the FAS and FAS-I population with the exception of gender; approximately 72% and 82% of patients were female in the FAS and FAS-I population, respectively (Table 1). Of the patients who had received prior antimuscarinic OAB medication, approximately two-thirds discontinued prior OAB treatment because of insufficient efficacy, and approximately one-quarter because of poor tolerability. The proportion discontinuing prior OAB treatment for either reason was similar across treatment groups (Table 1). Table 1 Patient demographics and baseline clinical characteristics by treatment group (FAS) Placebo ( n = 1328) Mirabegron 50 mg ( n = 1324) Mirabegron 100 mg ( n = 890) Gender, n (%) Male 362 (27.3) 382 (28.9) 241 (27.1) Female 966 (72.7) 942 (71.1) 649 (72.9) Age (years) Mean (SD) 59.2 (13.2) 59.7 (12.6) 59.8 (12.9) Range 20–95 21–91 19–90 Race, n (%) White 1227 (92.4) 1235 (93.3) 838 (94.2) Black or African American 80 (6.0) 61 (4.6) 36 (4.0) Asian 13 (1.0) 17 (1.3) 8 (0.9) Other 8 (0.6) 11 (0.8) 8 (0.9) BMI (kg/m 2 ) Mean 29.1 (6.3) 29.0 (6.1) 29.1 (6.1) Range 15.9–58.1 16.3–60.5 16.2–62.6 Type of OAB, n (%) Urgency incontinence 442 (33.3) 491 (37.1) 297 (33.4) Mixed 415 (31.3) 412 (31.1) 271 (30.4) Frequency 471 (35.5) 421 (31.8) 322 (36.2) Duration of OAB (months) Mean (SD) 86.3 (99.1) 85.2 (93.1) 88.3 (101.6) Previous OAB drug, n (%) Yes 704 (53.0) 688 (52.0) 460 (51.7) Reasons for previous OAB drug discontinuation, n (%) † Insufficient effect Yes 466 (66.2) 464 (67.4) 296 (64.3) No 238 (33.8) 224 (32.6) 164 (35.7) Poor tolerability Yes 185 (26.3) 173 (25.1) 113 (24.6) No 519 (73.7) 515 (74.9) 347 (75.4) Mean number of incontinence episodes/24 h Mean (SD) 1.8 (2.5) 1.8 (2.5) 1.8 (2.4) Range 0–26 0–18 0–15 Mean number of micturitions/24 h Mean (SD) 11.6 (3.1) 11.7 (3.2) 11.6 (3.0) Range 4–40 6–37 7–35 FAS, full analysis set; SD, standard deviation; BMI, body mass index; OAB, overactive bladder. * For BMI, placebo ( n = 1327) and mirabegron 100 mg ( n = 889). † Percentages are based on patients who had taken previous OAB medication. Patients could choose more than one reason for discontinuation. \n\nBODY.RESULTS.EFFICACY OUTCOMES:\nMirabegron at doses of 50 and 100 mg once daily demonstrated statistically significant improvement from baseline to Final Visit compared with placebo in reducing the mean number of incontinence episodes/24 h and the mean number of micturitions/24 h (p < 0.05 for all comparisons; Table 2 and Figures 3 and 4, respectively). The adjusted mean (95% CI) change from baseline to Final Visit in the mean number of incontinence episodes/24 h was −1.10 (−1.23, −0.97), −1.49 (−1.63, −1.36) and −1.50 (−1.67, −1.34) in the placebo, mirabegron 50 and 100 mg groups, respectively, and −1.20 (−1.34, −1.06), −1.75 (−1.89, −1.61), −1.74 (−1.91, −1.56) for the adjusted mean change from baseline to Final Visit in the mean number of micturitions/24. Table 2 Summary of primary and secondary efficacy end-points (FAS and FAS-I) Placebo Mirabegron 50 mg Mirabegron 100 mg Co-primary end-points Change from baseline to Final Visit in the mean number of incontinence episodes/24 h (FAS-I) Baseline 2.73 (0.09) 2.71 (0.09) 2.79 (0.10) Final Visit 1.64 (0.09) 1.23 (0.08) 1.25 (0.09) Change from baseline −1.09 (0.09) −1.48 (0.08) −1.54 (0.09) Adjusted change from baseline * (95% CI) −1.10 (−1.23, −0.97) −1.49 (−1.63, −1.36) −1.50 (−1.67, −1.34) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.58, −0.21) 3 −0.41 (−0.62, −0.19) 3 Change from baseline to Final Visit in the mean number of micturitions/24 h (FAS) Baseline 11.58 (0.09) 11.70 (0.09) 11.58 (0.10) Final Visit 10.39 (0.09) 9.93 (0.09) 9.83 (0.11) Change from baseline −1.18 (0.08) −1.77 (0.08) −1.75 (0.09) Adjusted change from baseline * (95% CI) −1.20 (−1.34, −1.06) −1.75 (−1.89, −1.61) −1.74 (−1.91, −1.56) Adjusted difference vs. placebo * (95% CI) – −0.55 (−0.75, −0.36) † −0.54 (−0.77, −0.31) † Key secondary end-points Change from baseline to Final Visit in the mean volume voided/micturition (FAS) Baseline 159.2 (1.54) 159.0 (1.55) 157.9 (1.89) Final Visit 168.6 (1.90) 180.2 (2.01) 179.9 (2.39) Change from baseline 9.4 (1.31) 21.2 (1.31) 22.0 (1.52) Adjusted change from baseline * (95% CI) 9.4 (6.9, 12.0) 21.4 (18.8, 23.9) 21.7 (18.5, 24.9) Adjusted difference vs. placebo * (95% CI) – 11.9 (8.3, 15.5) † 12.3 (8.1, 16.5) † Change from baseline to week 4 in the mean number of incontinence episodes/24 h (FAS-I) Baseline 2.73 (0.09) 2.71 (0.09) 2.79 (0.10) Week 4 2.06 (0.10) 1.59 (0.08) 1.69 (0.10) Change from baseline −0.67 (0.08) −1.12 (0.08) −1.10 (0.09) Adjusted change from baseline * (95% CI) −0.67 (−0.81, −0.54) −1.12 (−1.26, −0.98) −1.09 (−1.27, −0.92) Adjusted difference vs. placebo * (95% CI) – −0.45 (−0.64, −0.26) † −0.42 (−0.65, −0.20) † Change from baseline to week 4 in the mean number of micturitions/24 h (FAS) Baseline 11.58 (0.09) 11.71 (0.09) 11.58 (0.10) Week 4 10.82 (0.09) 10.52 (0.10) 10.26 (0.11) Change from baseline −0.76 (0.07) −1.19 (0.07) −1.32 (0.09) Adjusted change from baseline * (95% CI) −0.77 (−0.90, −0.64) −1.17 (−1.30, −1.04) −1.33 (−1.50, −1.16) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.59, −0.22) † −0.56 (−0.78, −0.35) † Mean level of urgency (FAS) Baseline 2.39 (0.02) 2.42 (0.02) 2.46 (0.02) Final Visit 2.25 (0.02) 2.15 (0.02) 2.19 (0.02) Change from baseline −0.14 (0.02) −0.27 (0.02) −0.27 (0.02) Adjusted change from baseline * (95% CI) −0.15 (−0.18, −0.12) −0.26 (−0.30, −0.23) −0.26 (−0.30, −0.22) Adjusted difference vs. placebo * (95% CI) – −0.11 (−0.16, −0.07) † −0.11 (−0.16, −0.06) † Mean number of urgency incontinence episodes/24 h (FAS−I) Baseline 2.42 (0.08) 2.42 (0.08) 2.53 (0.10) Final Visit 1.46 (0.08) 1.05 (0.07) 1.11 (0.09) Change from baseline −0.96 (0.08) −1.37 (0.07) −1.42 (0.09) Adjusted change from baseline * (95% CI) −0.98 (−1.10, −0.86) −1.38 (−1.50, −1.26) −1.38 (−1.53, −1.23) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.57, −0.23) † −0.40 (−0.60, −0.20) † Mean number of urgency episodes (PPIUS grade 3 or 4)/24 h (FAS) Baseline 5.61 (0.10) 5.80 (0.10) 5.96 (0.12) Final Visit 4.38 (0.11) 3.85 (0.11) 4.02 (0.13) Change from baseline −1.23 (0.10) −1.95 (0.10) −1.94 (0.12) Adjusted change from baseline * (95% CI) −1.29 (−1.47, −1.11) −1.93 (−2.11, −1.75) −1.89 (−2.11, −1.66) Adjusted difference vs. placebo * (95% CI) – −0.64 (−0.89, −0.39) † −0.60 (−0.89, −0.31) † Additional secondary end-points Change from baseline to Final Visit in mean number of nocturia episodes/24 h (FAS) Baseline 2.18 (0.04) 2.22 (0.04) 2.25 (0.05) Final Visit 1.78 (0.04) 1.66 (0.04) 1.71 (0.05) Change from baseline −0.41 (0.04) −0.56 (0.04) −0.54 (0.04) Adjusted change from baseline * (95% CI) −0.42 (−0.48, −0.35) −0.55 (−0.62, −0.49) −0.54 (−0.62, −0.46) Adjusted difference vs. placebo * (95% CI) – −0.14 (−0.23, −0.05) ‡ −0.12 (−0.23, −0.02) ‡ Change from baseline to Final Visit in TS-VAS (FAS) Baseline 4.87 (0.11) 4.82 (0.11) 4.43 (0.13) Final Visit 6.05 (0.10) 6.79 (0.09) 6.94 (0.11) Change from baseline 1.18 (0.11) 1.96 (0.12) 2.51 (0.14) Adjusted change from baseline * (95% CI) 1.25 (1.08, 1.42) 2.01 (1.84, 2.19) 2.33 (2.11, 2.55) Adjusted difference vs. placebo * (95% CI) – 0.76 (0.52, 1.01) ‡ 1.08 (0.80, 1.37) ‡ All values mean (SE) unless otherwise stated. * Estimates are based on an analysis of covariance model, which included treatment group, gender and study as fixed factors, and baseline as a covariate. † p < 0.05 vs. placebo with multiplicity adjustment. ‡ p < 0.05 vs. placebo without multiplicity adjustment. Figure 3Adjusted mean change from baseline (±SE) by time point in the mean number of incontinence episodes/24 h for the pooled placebo, mirabegron 50 and 100 mg groups (FAS-I). #Statistically significant treatment benefit relative to placebo (p < 0.05) with multiplicity adjustment. Statistically significant treatment benefit relative to placebo (p < 0.05) without multiplicity adjustment. SE, standard error; FAS-I, full analysis set-incontinence. Figure 4Adjusted mean change from baseline (±SE) by time point in mean number of micturitions/24 h for the pooled placebo, mirabegron 50 and 100 mg groups (FAS). #Statistically significant treatment benefit relative to placebo (p < 0.05) with multiplicity adjustment. Statistically significant treatment benefit relative to placebo (p < 0.05) without multiplicity adjustment. SE, standard error; FAS, full analysis set. The key secondary end-points, change from baseline to week 4 (first time point assessed) in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h, were significantly improved for both mirabegron doses compared with placebo (p < 0.05, all comparisons; Table 2 and Figures 3 and 4, respectively). The adjusted mean (95% CI) change from baseline to week 4 in the mean number of incontinence episodes/24 h was −0.67 (−0.81, −0.54), −1.12 (−1.26, −0.98) and −1.09 (−1.27, −0.92) in the placebo, mirabegron 50 and 100 mg groups, respectively. The adjusted mean (95% CI) change from baseline to week 4 in the mean number of micturitions/24 h was −0.77 (−0.90, −0.64), −1.17 (−1.30, −1.04) and −1.33 (−1.50, −1.16) in the placebo, mirabegron 50 and 100 mg groups, respectively. Both 50 and 100 mg mirabegron doses were associated with statistically significant improvements from baseline to Final Visit compared with placebo for the key secondary efficacy end-points of mean volume voided/micturition (p < 0.05 for all comparisons; Table 2), mean level of urgency, mean number of urgency episodes (grade 3 or 4)/24 h and mean number of urgency incontinence episodes/24 h (p < 0.05 for all comparisons; Table 2 and Figure 5). Figure 5Adjusted mean change from baseline to Final Visit (SE) in key secondary end-points: (A) mean level of urgency (FAS) (B) number of urgency episodes/24 h (FAS) and number of urgency incontinence episodes/24 h (FAS-I). #Statistically significant treatment benefit compared with placebo (p < 0.05) with multiplicity adjustment. SE, standard error; FAS, full analysis set; FAS-I, full analysis set-incontinence. Significant improvements were also evident in the pooled efficacy analysis with respect to the change from baseline to Final Visit (95% CI) in the mean number of nocturia episodes/24 h in the mirabegron 50 mg [−0.55 (−0.62, −0.49)] and mirabegron 100 mg groups [−0.54 (−0.62, −0.46)] vs. placebo [−0.42 (−0.48, −0.35)] (p < 0.05; Table 2). For the responder analyses, the percentage of patients with zero incontinence episodes at Final Visit ('dry rate') was significantly higher in the mirabegron 50 and 100 mg groups (44.1% and 46.4%, respectively) compared with placebo (37.8%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.32 (1.08, 1.61) and 1.58 (1.25, 2.00), respectively (p < 0.05). The percentage of patients with a ≥ 50% reduction from baseline to Final Visit in mean number of incontinence episodes/24 h was also significantly higher in the mirabegron 50 and 100 mg groups (69.5% and 70.5%, respectively) compared with placebo (59.6%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.54 (1.26, 1.89) and 1.64 (1.29, 2.07), respectively (p < 0.05). In the post hoc responder analysis, both 50 and 100 mg mirabegron doses were also associated with a significant improvement in 'micturition normalisation' (i.e. the percentage of patients with ≤ 8 micturitions/24 h) at Final Visit (31.6% and 34.0%) compared with placebo (24.6%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.57 (1.30, 1.89) and 1.69 (1.37, 2.09), respectively (p < 0.05). In health-related quality of life outcomes, mirabegron 50 and 100 mg was associated with a statistically significant improvement in the TS-VAS score at Final Visit compared with placebo (p < 0.05; Table 2). The adjusted mean (95% CI) changes from baseline to Final Visit were 1.25 (1.08, 1.42), 2.01 (1.84, 2.19) and 2.33 (2.11, 2.55) for the placebo, mirabegron 50 and 100 mg groups, respectively.\n\nBODY.RESULTS.EFFICACY IN PATIENTS WITH PRIOR ANTIMUSCARINIC USE AND TREATMENT-NAÏVE PATIENTS:\nBoth mirabegron 50 and 100 mg doses improved the co-primary end-points in patients who had discontinued previous antimuscarinic medication and in treatment-naïve patients. The adjusted mean difference (95% CI) from baseline to Final Visit in the mean number of incontinence episodes/24 h in patients who had discontinued previous antimuscarinic medication was −0.92 (−1.09, −0.75), −1.49 (−1.66, −1.32) and −1.42 (−.64, −1.21) in the placebo, mirabegron 50 mg and mirabegron 100 mg groups, respectively, and −1.35 (−1.55, −1.14), −1.50 (−1.71, −1.29) and −1.62 (−1.87, −1.36) in treatment-naïve patients. The adjusted mean difference (95% CI) in the mean number of micturitions/24 h from baseline to Final Visit in the placebo, mirabegron 50 and 100 mg groups, respectively, was −0.93 (−1.12, −0.74), −1.67 (−1.86, −1.48) and −1.61 (−1.85, −1.37) in patients who discontinued previous antimuscarinic therapy, and −1.51 (−1.71, −1.31), −1.84 (−2.04, −1.64) and −1.87 (−2.12, −1.63) in treatment-naïve patients. The adjusted mean difference vs. placebo in patients who discontinued previous antimuscarinic therapy was of a greater magnitude than in treatment-naïve patients because of the higher placebo response in treatment-naïve patients.\n\nBODY.RESULTS.SAFETY OUTCOMES:\nThe overall incidence of TEAEs was similar across treatment groups (Table 3) and there was no evidence of a dose–response relationship across the mirabegron treatment groups for overall rates of TEAEs: placebo (47.7%), mirabegron 25 mg (48.6%), mirabegron 50 mg (47.1%), mirabegron 100 mg (43.3%), total mirabegron (46.0%) and tolterodine ER 4 mg (46.7%). The most common TEAEs reported in ≥ 3% of the total mirabegron group were hypertension, nasopharyngitis and urinary tract infection (Table 3). The incidence of hypertension and urinary tract infection decreased as the dose of mirabegron increased from 25 to 100 mg. The most common drug-related TEAEs in the mirabegron groups were hypertension and headache, which were of similar incidence with placebo and tolterodine, with the exception of dry mouth, which was at placebo level for mirabegron but of a higher magnitude in the tolterodine group (Table 3). The majority of AEs were of mild or moderate severity across treatment groups. Table 3 Overview of treatment-emergent adverse events in the pooled safety analysis (SAF) Mirabegron Number of patients (%) Placebo ( n = 1380) 25 mg ( n = 432) 50 mg ( n = 1375) 100 mg ( n = 929) Total ( n = 2736) Tolterodine ER 4 mg ( n = 495) Any TEAE 658 (47.7) 210 (48.6) 647 (47.1) 402 (43.3) 1259 (46.0) 231 (46.7) Drug-related TEAE 232 (16.8) 87 (20.1) 256 (18.6) 172 (18.5) 515 (18.8) 131 (26.5) TEAE leading to discontinuation 46 (3.3) 17 (3.9) 53 (3.9) 34 (3.7) 104 (3.8) 22 (4.4) Drug-related TEAE leading to discontinuation 27 (2.0) 11 (2.5) 35 (2.5) 25 (2.7) 71 (2.6) 20 (4.0) SAE 29 (2.1) 7 (1.6) 29 (2.1) 26 (2.8) 62 (2.3) 11 (2.2) Drug-related SAE 6 (0.4) 3 (0.7) 7 (0.5) 3 (0.3) 13 (0.5) 6 (1.2) Common TEAEs by preferred term (reported by ≥ 3% in total mirabegron group) Hypertension 105 (7.6) 49 (11.3) 103 (7.5) 48 (5.2) 200 (7.3) 40 (8.1) Nasopharyngitis 35 (2.5) 15 (3.5) 54 (3.9) 25 (2.7) 94 (3.4) 14 (2.8) Urinary tract infection 25 (1.8) 18 (4.2) 40 (2.9) 25 (2.7) 83 (3.0) 10 (2.0) Antimuscarinic AEs of interest by preferred term (reported by ≥ 2% in any group) Headache 43 (3.1) 10 (2.3) 47 (3.4) 23 (2.5) 80 (2.9) 18 (3.6) Dry mouth 29 (2.1) 8 (1.9) 23 (1.7) 23 (2.5) 54 (2.0) 50 (10.1) Constipation 20 (1.4) 7 (1.6) 22 (1.6) 15 (1.6) 44 (1.6) 10 (2.0) Drug-related * \n TEAEs by preferred term (reported by ≥ 2% in any group) Hypertension 63 (4.6) 30 (6.9) 65 (4.7) 32 (3.4) 127 (4.6) 30 (6.1) Headache 18 (1.3) 4 (0.9) 28 (2.0) 12 (1.3) 44 (1.6) 11 (2.2) Dry mouth 22 (1.6) 7 (1.6) 13 (0.9) 20 (2.2) 40 (1.5) 47 (9.5) SAF, safety analysis set; ER, extended release; TEAE, treatment-emergent adverse event; SAE, serious adverse event. * Possible or probable, as assessed by the investigator, or records where relationship was missing. The proportion of patients discontinuing study drug because of TEAEs was low and similar across each group: placebo (3.3%), mirabegron 25 mg (3.9%), mirabegron 50 mg (3.9%), mirabegron 100 mg (3.7%), total mirabegron (3.8%) and tolterodine ER 4 mg (4.4%). The incidence of serious AEs was also low and similar between placebo and mirabegron groups: placebo (2.1%), mirabegron 25 mg (1.6%), mirabegron 50 mg (2.1%), mirabegron 100 mg (2.8%), total mirabegron (2.3%) and tolterodine ER 4 mg (2.2%). Three deaths were reported in this pooled 12-week safety analysis: in the placebo group, a 76-year-old woman died as a result of cardiac arrest 56 days after the last dose of study drug; in the mirabegron 100 mg group, a 66-year-old woman died because of metastatic colon cancer 30 days after the last dose of study drug – neither case was considered to be related to study drug – and in the tolterodine ER 4 mg group, a 74-year-old man died because of a ruptured cerebral aneurysm on day 70 (treatment-emergent), 10 days after the last dose of study drug was administered, and was considered as possibly related to study drug. In terms of vital sign measurements for blood pressure and pulse rate, the adjusted mean difference vs. placebo for change from baseline to Final Visit in SBP and DBP (AM and PM measurements) was negligible and comparable across each mirabegron group and the tolterodine ER 4 mg group. The adjusted mean difference vs. placebo for change from baseline to Final Visit in pulse rate (AM and PM measurements) increased dose-dependently by 0.6–2.3 bpm in the mirabegron groups and by 1.0–2.1 bpm in the tolterodine ER 4 mg group (Table 4). The overall occurrence of tachycardia events, either based on TEAE and/or observations of pulse rate ≥ 100 bpm captured by patient diary, was less than 5% in each treatment group and comparable with placebo (Table 4). ECG findings revealed no overt trends in central tendency or categorical outliers for QTc interval assessment across treatment groups. Changes in haematology and serum chemistry, including renal parameters, were small and comparable across treatment groups. Table 4 Summary of changes from baseline to Final Visit in blood pressure and pulse rate Placebo ( n = 1380) Mirabegron 25 mg ( n = 432) Mirabegron 50 mg ( n = 1375) Mirabegron 100 mg ( n = 929) Tolterodine ER 4 mg ( n = 495) AM PM AM PM AM PM AM PM AM PM Blood pressure (mmHg) SBP N 1329 1326 410 410 1327 1327 891 890 476 476 Baseline, mean (SE) 125.9 (0.47) 125.0 (0.41) 129.2 (0.81) 129.0 (0.71) 126.4 (0.47) 125.6 (0.43) 125.0 (0.55) 123.7 (0.49) 128.2 (0.75) 127.4 (0.64) Final Visit, mean (SE) 126.2 (0.45) 125.7 (0.41) 128.8 (0.75) 128.3 (0.67) 127.2 (0.46) 126.6 (0.41) 125.6 (0.51) 125.2 (0.46) 128.4 (0.70) 127.9 (0.63) Adjusted change from baseline, mean (SE), (95% CI) † 0.2 (0.25), (−0.3, 0.7) 0.6 (0.25), (0.1, 1.1) −0.3 (0.52), (−1.3, 0.7) −0.5 (0.53), (−1.5, 0.6) 0.8 (0.25), (0.3, 1.3) 1.1 (0.25), (0.6, 1.6) 0.6 (0.32), (−0.0, 1.2) 1.4 (0.33), (0.8, 2.1) 0.1 (0.45), (−0.8, 1.0) 0.5 (0.46), (−0.4, 1.4) Difference vs. placebo, mean (SE), (95% CI) ‡ – – −0.5 (0.57), (−1.6, 0.6) −1.0 (0.58), (−2.2, 0.1) 0.6 (0.35), (−0.1, 1.3) 0.5 (0.36), (−0.2, 1.2) 0.4 (0.41), (−0.4, 1.2) 0.9 (0.42), (0.1, 1.7) −0.1 (0.52), (−1.1, 1.0) −0.0 (0.53), (−1.1, 1.0) DBP N 1329 1326 410 410 1327 1327 890 890 476 476 Baseline, mean (SE) 77.1 (0.26) 75.3 (0.23) 78.2 (0.48) 76.1 (0.46) 77.2 (0.25) 75.4 (0.24) 77.4 (0.30) 75.3 (0.28) 76.8 (0.40) 75.4 (0.38) Final Visit, mean (SE) 77.2 (0.25) 75.7 (0.24) 77.6 (0.43) 75.7 (0.42) 77.6 (0.24) 76.2 (0.24) 77.7 (0.28) 76.3 (0.28) 77.7 (0.39) 76.6 (0.36) Adjusted change from baseline, mean (SE), (95% CI) † 0.0 (0.16), (−0.3, 0.3) 0.4 (0.16), (0.1, 0.7) −0.1 (0.33), (−0.8, 0.5) 0.1 (0.34), (−0.6, 0.7) 0.4 (0.16), (0.1, 0.7) 0.7 (0.16), (0.4, 1.1) 0.2 (0.21), (−0.2, 0.6) 0.9 (0.21), (0.5, 1.3) 0.8 (0.29), (0.2, 1.3) 1.4 (0.30), (0.8, 2.0) Difference vs. placebo, mean (SE), (95% CI) ‡ – – −0.1 (0.37), (−0.9, 0.6) −0.3 (0.37), (−1.0, 0.4) 0.4 (0.22), (−0.1, 0.8) 0.4 (0.23), (−0.1, 0.8) 0.2 (0.26), (−0.3, 0.7) 0.5 (0.27), (−0.0, 1.0) 0.7 (0.33), (0.1, 1.4) 1.0 (0.34), (0.4, 1.7) Pulse rate (bpm) N 1329 1326 410 410 1327 1327 891 890 476 476 Baseline, mean (SE) 70.5 (0.28) 75.3 (0.29) 71.0 (0.50) 75.5 (0.51) 70.4 (0.28) 74.9 (0.28) 70.4 (0.34) 74.4 (0.34) 69.8 (0.44) 73.9 (0.45) Final Visit, mean (SE) 70.9 (0.29) 74.7 (0.29) 71.7 (0.52) 75.3 (0.53) 71.8 (0.29) 75.5 (0.28) 72.9 (0.34) 76.5 (0.34) 71.4 (0.44) 76.0 (0.45) Adjusted change from baseline, mean (SE), (95% CI) † 0.4 (0.17), (0.1, 0.8) −0.4 (0.18), (−0.8, −0.1) 1.3 (0.36), (0.6, 2.0) 0.2 (0.37), (−0.6, 0.9) 1.4 (0.17), (1.1, 1.8) 0.6 (0.18), (0.2, 0.9) 2.3 (0.22), (1.9, 2.8) 1.9 (0.23), (1.4, 2.3) 1.4 (0.31), (0.8, 2.0) 1.7 (0.32), (1.1, 2.3) Difference vs. placebo, mean (SE), (95% CI) ‡ – – 0.9 (0.40), (0.1, 1.6) 0.6 (0.41), (−0.2, 1.4) 1.0 (0.24), (0.5, 1.5) 1.0 (0.25), (0.5, 1.5) 1.9 (0.28), (1.3, 2.5) 2.3 (0.29), (1.7, 2.9) 1.0 (0.36), (0.3, 1.7) 2.1 (0.37), (1.4, 2.8) Incidence of tachycardia (%) * Tachycardia events, N (%) 43 (3.1) 21 (4.9) 52 (3.8) 43 (4.6) 16 (3.2) SBP, systolic blood pressure; DBP, diastolic blood pressure. * Based on TEAE and/or observations of pulse rate ≥ 100 bpm captured by patient diary. † Adjusted change from baseline is generated from the ANCOVA model with treatment group, gender and study as fixed factors, and baseline as a covariate. ‡ Differences in the adjusted means are calculated by subtracting the adjusted mean of placebo from the adjusted mean of treatment group. With respect to other events of interest, the incidence of urinary retention was infrequent in the studies and less in mirabegron-treated patients than in placebo or tolterodine-treated patients: placebo (n = 7; 0.5%), mirabegron 25 mg (n = 0), mirabegron 50 mg (n = 1; 0.1%), mirabegron 100 mg (n = 0), total mirabegron (n = 1; < 0.1%) and tolterodine (n = 3; 0.6%). The mean change from baseline to Final Visit in PVR volume was unremarkable across treatment groups: placebo (−1.6 ml), mirabegron 25 mg (−3.0 ml), mirabegron 50 mg (−0.9 ml), mirabegron 100 mg (−0.7 ml) and tolterodine ER 4 mg (+ 0.1 ml). The proportion of patients experiencing ≥ 150 ml change from baseline in PVR volume was lower in the mirabegron groups compared with placebo and tolterodine: placebo (0.7%), mirabegron 25 mg (0%), mirabegron 50 mg (0.3%), mirabegron 100 mg (0.4%) and tolterodine ER 4 mg (0.8%).\n\nBODY.DISCUSSION:\nMirabegron, a β3-adrenoceptor agonist, is approved for the treatment of OAB symptoms in Japan, the USA, Canada and Europe, and has a different mechanism of action from the antimuscarinic agents currently available. Mirabegron facilitates detrusor relaxation during the storage phase of the micturition cycle and, in contrast with antimuscarinic agents, improves the storage capacity of the bladder without impairing the amplitude of the contraction during the voiding phase of the micturition cycle 25. In this pooled analysis of three international phase III studies 21–23, a total of 3542 OAB patients were included in the efficacy analysis, and 4611 OAB patients in the safety analysis, reflective of the general OAB population. More than half of these patients were randomised to mirabegron for 12 weeks at doses of 25, 50 and 100 mg. Furthermore, this pooled dataset included approximately 50% of OAB patients who had been previously treated with antimuscarinic agents but had discontinued either because of insufficient efficacy and/or poor tolerability. In OAB patients, mirabegron 50 and 100 mg demonstrated significant and clinically meaningful efficacy in terms of improving the symptoms of OAB, including incontinence episodes, micturition frequency and urgency, which are recognised by international guidelines as important outcome measures for OAB therapies 26. The benefit of mirabegron is evident in both treatment-naïve and previous OAB-treated patients. This is a clinically relevant observation, given the poor persistence rate associated with antimuscarinic drugs – discontinuation rates above 50% and 75% have been reported at 6 months and 1 year, respectively 27,28 – and the fact that, in addition to bothersome AEs (e.g., dry mouth), inadequate response to treatment is an underlying reason for discontinuation of antimuscarinic treatment 27,29–31. Both 50 and 100 mg doses of mirabegron demonstrated significant improvements compared with placebo for all of the key secondary end-points, including measures of urgency (the core symptom of OAB), and mean volume voided/micturition. Across primary and key secondary end-points, significant improvements with both mirabegron doses were evident at the first assessment period (week 4) and were maintained throughout the 12-week treatment period – an earlier benefit cannot be ruled out but was not assessed prior to the initial 4-week evaluation. Responder analyses showed a significant improvement with mirabegron 50 and 100 mg in terms of dry rates, ≥ 50% reduction in mean number of incontinence episodes/24 h and the proportion of patients with ≤ 8 micturitions/24 h at Final Visit. Taken together, these data demonstrate a clinically meaningful benefit with mirabegron in the objective end-points of OAB. As OAB is a symptom complex, it can be difficult to determine the efficacy of treatments using objective measures alone. Hence, patient-reported outcomes are increasingly important in the assessment of treatments for symptom-based conditions such as OAB 4. The TS-VAS scores for the 50 and 100 mg mirabegron doses were significantly better and approximately one point higher than patients receiving placebo and reflect the directional parallelism of the subjective and objective improvements in OAB symptoms. The mirabegron 100 mg dose does not appear to afford a greater efficacy benefit than the 50 mg dose for reduction in incontinence episodes or micturition frequency vs. placebo. A dose–response effect was not evident with the 50 and 100 mg doses across the co-primary and secondary end-points. Although data from the 25 mg mirabegron arm 23 were not included in the pooled efficacy analysis, 25 mg is the recommended starting dose in the USA. In the NCT00912964 phase III study, mirabegron 25 mg showed clinically significant efficacy compared with placebo for the co-primary end-points; however, for the majority of the secondary end-points it did not demonstrate significance vs. placebo 23. In terms of the safety and tolerability profile of mirabegron, the pooled analysis confirms the results of the individual phase III studies 21–23. The most common AEs (> 3% of total mirabegron group) were hypertension, nasopharyngitis and urinary tract infection. The incidence of hypertension and urinary tract infection decreased as the mirabegron dose increased and both incidences in the total mirabegron group were similar to placebo or tolterodine. The incidence of the most bothersome AE for antimuscarinic drugs, dry mouth, was at placebo level with each mirabegron dose and lower than tolterodine. This finding is consistent with previous randomised, controlled trials of other antimuscarinic therapies, which have reported even higher incidences of dry mouth (9–93%); these studies have also reported high incidences of constipation (4–21%) 32–41. Given that dry mouth is the chief cause of discontinuation because of poor tolerability with antimuscarinic drugs 27,29, the pooled safety data indicate that mirabegron may be a valuable treatment option for patients with OAB. The pooled safety analysis offers more precise estimates of certain safety parameters, such as vital signs and AEs related to cardiovascular safety, than the individual phase III studies. In this pooled analysis, mirabegron was associated with approximate increases of ≤ 1 mmHg in blood pressure and ≥ 1 bpm in pulse rate vs. placebo. The incidence of hypertension was similar among the total mirabegron group, placebo and tolterodine. The incidence of urinary retention was greater in the placebo and tolterodine groups than in mirabegron-treated patients. ECG, PVR volume and laboratory data were unremarkable across each treatment group. Overall, the data support the good safety profile of mirabegron based on this pooled phase III clinical study dataset.\n\nBODY.CONCLUSIONS:\nMirabegron, a β3-adrenoceptor agonist, and the first in its class for the treatment of OAB symptoms, has a distinct mechanism of action from antimuscarinic agents, the current pharmacological mainstay in treating OAB. In these pooled analyses of efficacy and safety, mirabegron administered at daily doses of 50 and 100 mg for 12 weeks demonstrated significant and clinically meaningful improvement in treating the symptoms of OAB, including urinary incontinence, micturition frequency and urgency. Mirabegron was beneficial in both treatment-naïve patients and in patients who used prior antimuscarinic treatment. The improvement in OAB symptoms measured objectively was reflected in the improvement in the patient-reported outcome related to treatment satisfaction. Mirabegron was well tolerated with an incidence of dry mouth at placebo level and lower than tolterodine. Mirabegron represents a new therapeutic in a new class of medication for the treatment of OAB and has demonstrable efficacy and tolerability in a large clinical trial dataset in OAB patients. In clinical practice, mirabegron will provide a valuable treatment option for OAB syndrome.\n\nQuestion: Compared to placebo what was the result of mirabegron (50 and 100 mg) on the mean number of incontinence episodes/24 h and the mean number of micturitions/24 h?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1055	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomized comparison of etoposide pharmacokinetics after oral etoposide phosphate and oral etoposide.\n\n ABSTRACT:\nEtoposide phosphate is a water-soluble prodrug of etoposide. The plasma pharmacokinetics of etoposide following oral administration of etoposide phosphate or oral etoposide were compared. Seventeen patients with solid tumours were enrolled to receive oral etoposide phosphate 125 mg m(-2) on days 1-5 every 3 weeks, with escalation to 175 mg m(-2) from course 3 when possible. Patients were randomized to receive oral etoposide phosphate or oral etoposide on day 1 of course 1 and the alternative compound on day 1 of course 2. Fifteen patients received two or more courses and were evaluable for pharmacokinetic comparisons. The median AUC(inf) (area under the concentration vs time curve from zero to infinity) of etoposide was 77.7 mg l(-1) h after etoposide phosphate (95% CI 61.3-100.5) and 62.0 mg l(-1) h after oral etoposide (95% CI 52.2-76.9). The difference in favour of etoposide phosphate was borderline significant: median 9.9 mg l(-1) h (95% CI 0.1-32.8 mg l(-1) h; P = 0.05). However, the inter-patient variability of etoposide AUC(inf) was not improved (coefficients of variation 42.3% and 48.4%). Etoposide phosphate was undetectable in plasma after oral administration. Toxicities of oral etoposide phosphate were not different from those known for etoposide. In conclusion, oral etoposide phosphate does not offer a clinically relevant benefit over oral etoposide.\n\nBODY:\n\nQuestion: Compared to Oral etoposide what was the result of Oral etoposide phosphate on Toxicity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1184	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effectiveness of a serious game for medical education on insulin therapy for diabetes: randomized controlled trial\n\n ABSTRACT:\n\n\nBODY.BACKGROUND:\nMost patients with diabetes mellitus (DM) are followed by primary care physicians, who often lack knowledge about DM care, especially on insulin. Traditional continuing medical education has little effectiveness, so new educational approaches are required.\n\nBODY.OBJECTIVES:\nTo assess the applicability, acceptance, and effectiveness of a serious game for medical education on insulin therapy for DM.\n\nBODY.METHODS:\nA serious game called InsuOnLine© was developed by experts in endocrinology, medical education, and games. Game design was based on modern adult learning theories, and recommendations were adapted from main DM guidelines. A randomized unblinded controlled trial (RCT) was performed to assess the effectiveness of the game, played in \"real-world\" conditions (in players' own computers and in their free time), compared to a traditional on-site learning activity, both with same content and duration (3-4 h). Primary care physicians from South of Brazil who were not specialists in endocrinology or diabetes were invited to participate, and randomly allocated to one of the groups. Knowledge, problem-solving skills, attitudes, and satisfaction were assessed by a questionnaire applied at baseline, immediately after interventions, and three months later.\n\nBODY.RESULTS:\nEighty-eight physicians were allocated to game group; from those, 69 (78%) finished the game, which demonstrates good applicability. Those 69 were included in final analysis. Other 65 physicians were included in control group. Both groups were similar at baseline: 49% were female, and mean age was 38. Both interventions were very well rated, regarding methodology and satisfaction. The gain of knowledge and skills was significant in both groups, with the percentage of right answers going from 52% at baseline to 85% after traditional activity (p<0.001), and to 92% after the game (p<0.001). Three months later, that percentage decreased to 76% in control and to 80% in game group, both it remained significantly higher than at baseline. Absolute increase in performance was higher in the game group (40%) than in control (34%, p=0.01). Attitudes were more significantly improved in the game group than in control. Three months after interventions, all subjects in control and 99% in game group said that the intervention had had real impact on their practice.\n\nBODY.CONCLUSION:\nThe serious game InsuOnLine© is applicable, well accepted, and very effective for medical education on insulin.\n\nQuestion: Compared to traditional on-site learning activity what was the result of serious game called InsuOnLine© on Absolute increase in performance of insulin therapy for DM.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1058	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of Neuromuscular Electrical Stimulation Combined with Exercises versus an Exercise Program on the Pain and the Function in Patients with Knee Osteoarthritis: A Randomized Controlled Trial\n\n ABSTRACT:\n\nObjectives. To investigate the effect of 8 weeks of NMES + Ex (neuromuscular electrical stimulation combined with exercises) on pain and functional improvement in patients with knee osteoarthritis (OA) compared to exercise (Ex) alone. Design. Randomized controlled trial. Setting. A specialty outpatient clinic. Participants. Patients (N = 100; women = 86, men = 14; age range, 50–75 years) with knee OA. Interventions. Participants were randomly assigned to NMES + Ex or Ex group. Outcome Measures. Numerical Rating Scale 0 to 10 (NRS) and the Timed Up and Go (TUG) test were the primary outcomes. The secondary outcomes used were the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Results. Following the interventions, a statistically significant improvement in both groups was observed in all outcomes assessed. For the comparison between the groups, no statistically significant difference was found between the NMES + Ex and the Ex groups in NRS (P = 0.52), TUG test (P = 0.12), and aspects of WOMAC: pain (P = 0.26), function (P = 0.23), and stiffness (P = 0.63). Conclusion. The addition of NMES to exercise did not improve the outcomes assessed in knee OA patients. This study was registered at the Australian Clinical Trials Registry (ACTRN012607000357459).\n\nBODY.1. INTRODUCTION:\nOsteoarthritis (OA) is the most common form of arthritis. It affects one-third of adults and tends to increase with age [1]. Knee OA is associated with symptoms of pain, swelling, instability, and reduced range of motion (ROM). These symptoms lead to functional impairment, increasing the risk of morbidity and mortality [2, 3]. The synovium is infiltrated with inflammatory cells and secretes excess synovial fluid, leading to capsular swelling [4]. Through a spinal reflex, the capsular swelling inhibits muscle activation, which, combined with disuse, may cause muscle weakness and atrophy [1]. Because the quadriceps muscle acts as shock absorber for the knee joint, weakness in the thigh muscle reduces joint protection, resulting in overload [4]. Exercises strengthen the muscles, reduce pain, improve physical function, and are therefore considered a major intervention in the conservative treatment of patients with knee OA [5]. In addition to muscle strengthening exercises, stretching exercises are commonly used to increase ROM and are often prescribed in rehabilitation protocols as part of routine warm-up to prepare the muscles and joints for other types of exercise, such as aerobic and strengthening programs [6, 7]. Stretching of the hamstring muscles may improve knee extension ROM in OA patients. Neuromuscular electrical stimulation (NMES) is defined as the application of electrical stimulation using surface electrodes placed over skeletal muscles to produce visible muscle contraction through the activation of intramuscular nerve branches [8]. This technique can also be used as a form of physical therapy in the treatment of patients with knee OA. The goals of rehabilitation protocols that include NMES are to provide additional stimulus to increase muscle strength in patients with knee OA [9]. The methods and findings of previous studies on the effectiveness of NMES in knee OA differ in the modulation of NMES parameters, choice of the outcomes used to evaluate the patients, and characteristics of the control groups. This leads to a lack of consensus regarding the effectiveness attained from including NMES in conventional rehabilitation protocols. Major flaws with regard to methodological quality were found in clinical trials testing the use of NMES in the conservative treatment of patients with knee OA. Only one of these studies reported using allocation concealment, blinded assessment, and intention-to-treat analysis [10]. Thus, the objective of this study was to conduct a randomized clinical trial following methodological criteria, including allocation concealment, blinding of the examiner, and application of intention-to-treat analysis to assess the role of NMES in improving pain and physical function in patients with knee OA. It is important to study interventions with the potential to improve functional status in this patient population [11]. \n\nBODY.2. METHODS:\nThe study was conducted at the Interlagos Specialty Outpatient Clinic, São Paulo, Brazil. Patients were referred from the Rheumatology Department according to the inclusion and exclusion criteria and randomly allocated into groups using a computer-generated randomization chart. The allocation codes were sealed in opaque envelopes by a third person not involved in the study to avoid selection bias. Written informed consent was obtained from all participants. The study was approved by the Research Ethics Committee of the Universidade Federal de São Paulo (UNIFESP), Brazil, no. 0141/07, and registered with the Australian Clinical Trials Registry, no. ACTRN012607000357459. Setting the significance level at 5% and the power of the sample at 80%, a sample size of 40 patients per group was estimated to be necessary to detect a difference of at least 1 minute ± 3 seconds in the Timed Up and Go (TUG) test, which was considered to be the minimum clinically significant difference for the present trial [12]. Paired Student's t-test and analysis of covariance (ANCOVA) were used for comparisons between groups; the covariant was obtained from a previous study [13]. One hundred patients were recruited according to inclusion and exclusion criteria. Eligibility criteria were age 50 to 75 years, OA grade 2 or greater according to the radiographic classification of OA proposed by Kellgren and Lawrence [14], and diagnosis of knee OA based on the American College of Rheumatology (ACR) criteria. Exclusion criteria were use of a pacemaker, unstable heart conditions, participation in another physical activity program, inability to exercise on a stationary bicycle ergometer, inability to walk, previous hip or knee arthroplasty, diagnosis of fibromyalgia, epilepsy, and skin tumor or lesion at the NMES application site. Patients were divided into two groups of 50 each: (1) the NMES combined with exercises (NMES + Ex) group and (2) exercise (Ex) group. Patient medication was standardized and not modified during the study period. Paracetamol was prescribed for pain, and diacerein and chloroquine for OA control. Interventions were delivered for both groups by the same physical therapist, twice a week, for 8 weeks, with each session lasting about 40 minutes. All patients received a manual including guidelines on how not to overload the knee during daily activities and instructions on the use of ice packs in case of pain and inflammation and warm compresses in case of pain without inflammation as follows. \nManual for Patients with Osteoarthritis of the Knee. The purpose of this manual is to explain osteoarthritis and to teach how you can adjust yourself to your daily activities, according to the knee symptoms. Try to seriously follow our orientations for your own benefit! \nThe Knee. The knee joint is composed of 3 bones—the femur (thigh bone), the patella (kneecap) and the tibia (leg bone). It has muscles, capsule, ligaments, meniscus, and the cartilage that lines the bones and protects them from the impact. The knee joint supports nearly the whole weight of our body. \nWhat Is Osteoarthritis? It is a disease caused by the breakdown of cartilage in the joints. The layers in the cartilage become damaged and with time they lose the function of smoothing the contact between the bone surface and the joints. The pain is a result of the attrition of one bone against the other in the absence or decreased cartilage in the joints. \nWhat Are the Signs and Symptoms? Patients with osteoarthritis may have some pain mainly when starting a movement, as in morning stiffness or after immobilization. With time, the pain might be intensified and be permanent. The presence of crepitation when moving the knees is often. \nWhat Kind of Difficulties Might I Have in My Daily Life? Difficulties found in daily live vary according to the patients' symptoms. In general, however, the patient has pain and difficulty when supporting the body weight using the affected knee, going up and down the stairs, or when walking. \nWhat Should I Do When It Is Painful? A doctor can prescribe the treatment for osteoarthritis. However, a simple form of improving the pain is to use warm to hot water bottle over the knee joint (be careful not to burn the skin, use a protection, and test the water temperature before using it. \nWhat If It Is Swollen? To manage the swollen, you can combine rest, use of ice pack, and elevating the leg above the level of the heart. The ice pack should be placed over the knee joint for 20 minutes. \nWhat Are the Other Recommendations?\nIf you are overweight, losing some kilos will reduce the stress over the joint. Wear comfortable shoes with a rubber sole and no heels.In case of pain when walking, use a cane as an aid tool.Try to have a good night sleep.\n\n\nBODY.2. METHODS.2.1. NMES COMBINED WITH EXERCISE GROUP:\nTreatment for patients in the NMES + Ex included 10 minutes on a stationary bicycle, stretching of hamstring muscles (3 repetitions of 30 seconds) with the aid of an elastic band, and loaded quadriceps strengthening exercises combined with NMES. The strengthening exercise with NMES was performed in the sitting position with the knee and hip flexed to 90 degrees; patients contracted their quadriceps at each NMES stimulus. NMES was applied using an electrical stimulator (Globus ACTIVA 600 Pro, Globus, Italia) with two 7.5 × 13 cm self-adhesive electrodes (ValuTrode electrodes, Axelgaard Manufacturing Co. Ltd., Fallbrook, CA) placed over the region of the quadriceps muscle (rectus femoris and vastus medialis). NMES parameters were as follows: pulsed current, biphasic, asymmetrical, rectangular waveform, frequency 50 Hz, pulse duration 250 μs, contraction time 10 s, rest time 30 s every 20 minutes; current intensity was the maximum tolerated by each patient [15]. \n\nBODY.2. METHODS.2.2. EXERCISE GROUP (EX):\nPatients in the Ex group performed the same exercise program as those in the NMES group but without NMES. The exercise protocol included 10 minutes of warm-up on a stationary bicycle ergometer, stretching of hamstrings muscles with the aid of an elastic band, and knee extension exercises performed for 3 sets of 15 repetitions with rest intervals of 30–45 seconds between sets. For both groups, the training load for the strengthening exercises was established based on 50–60% of the 10-repetition maximum (RM) instead of 1 RM to avoid injury by excessive muscle contraction [16].\n\nBODY.2. METHODS.2.3. OUTCOMES:\nPatients were evaluated before and after intervention by a physical therapist blinded to group assignment. The primary outcomes were the TUG test results [12] and pain walking on a flat surface in the last 72 h measured on an 11-point Numerical Rating Scale (NRS) [17]. The secondary outcomes were scores on the pain, physical function, and stiffness subscales of the culturally validated Brazilian-Portuguese version of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) [18, 19]. In this study, WOMAC pain, physical function, and stiffness scores were analyzed separately. \n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nPaired Student's t-test was performed to compare pre- and postintervention values at a significance level of 0.05 (P < 0.05). Statistical analysis was performed on an intent-to-treat (ITT) basis and included all patients who were randomized to treatment. Mixed model analysis of variance with repeated measures was used with occasion measures as within-group factors and intervention as between-group factor. Relations between the observations were analyzed using an unstructured covariance matrix. Missing-data imputation was not performed to evaluate pre- and postintervention differences between the two groups, because Chakraborty and GU [20] showed that mixed model analysis without missing-data imputation always provides equal or more power than does mixed model analysis with missing-data imputation. Effect size was calculated as the difference between the means divided by the standard deviation using Cohen's d [21]. The analyses were performed using the General Linear Model (GLM), and mixed analyses were carried out using the Statistical Analysis Software (SAS) version 9.2 for Windows [22].\n\nBODY.3. RESULTS:\nThe demographic and clinical characteristics of patients, including age, sex, side treated, and body mass index (BMI), as well as TUG test values, NRS pain scores, and WOMAC scores on the pain, physical function, and stiffness subscales, are shown in Table 1. Eighty-seven patients completed the study. Of the 13 dropouts, 6 (12%) patients were in the NMES + Ex group and 7 (14%) in the Ex group (Figure 1). \n\nBODY.3. RESULTS.3.1. PRIMARY OUTCOMES:\nNo significant differences between groups were found in NRS pain scores and TUG test time on ITT analysis. A significant decrease in pain intensity (NRS scores) and TUG test time was observed after intervention compared with baseline in the NMES + Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001) and Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001). The primary outcomes are listed in Table 2. \n\nBODY.3. RESULTS.3.2. SECONDARY OUTCOMES:\nNo significant differences between groups were found on the pain, physical function, and stiffness subscales of the WOMAC index on ITT analysis. There was a significant improvement in all WOMAC subscales in the NMES + Ex group (pain; P < 0.0001; physical function, P < 0.0001; stiffness, P < 0.0001) and in the Ex group (pain, P < 0.0001; physical function, P < 0.0001; stiffness, P = 0.0009). The secondary outcomes are listed in Table 2.\n\nBODY.3. RESULTS.3.3. ADVERSE EFFECT:\nOne patient in the NMES + Ex group exhibited a blood pressure spike, which may have resulted from the use of NMES or from the exercise program itself. The following contraindications to the use of NMES were respected: avoiding the use of NMES over areas of tumor, with open wounds, or bleeding, and in patients with pacemakers [15].\n\nBODY.4. DISCUSSION:\nIn this randomized clinical trial, the NMES combined with exercise did improve pain and physical function, but there was no evidence that it did better than exercise alone. Our results are in agreement with the findings of Rosemffet et al. [23] who conducted a pilot study comparing the treatment results of patients with knee OA (n = 26) treated with either NMES alone or exercises alone or exercises combined with NMES. The authors reported a significant improvement on the WOMAC pain subscale in the three groups, but no significant differences in WOMAC scores were found between groups [23]. The lack of difference in treatment outcome between groups in the present study might be attributed to the fact that the participants had no clinically significant muscle or functional impairment. A finding substantiating this hypothesis is that the mean TUG test values in the two groups were similar to those found in the study of Steffen et al., for elderly patients with no physical limitations categorized under the same mean age group [24]. The TUG test values reported were 8 ± 2 seconds for patients with 60–69 years old and 9 ± 3 seconds for patients with 70–79 years old. In the present study, the baseline values for TUG test were 8.27 + 1.76 for NMES + Ex group and 9.34 ± 2.47 for Ex group. Given that the greater the muscle impairment, the greater the NMES effect, patients with a more advanced stage of OA might obtain greater benefit from NMES [25–27]. With regard to evidence on the effectiveness of NMES in the rehabilitation of patients with knee OA, the Cochrane Collaboration published a systematic review evaluating the pre- and postoperative use of NMES in total knee arthroplasty [28]. The two studies that were evaluated were classified as being at high risk of bias, because randomization and allocation concealment were not described, and no data obtained from the study groups were presented in terms of means and standard deviations. It was not possible to determine whether or not the pre- and postoperative use of NMES was effective in the rehabilitation of knee arthroplasty patients, and therefore further studies are warranted. Regarding lines of evidence on the effectiveness of NMES in the treatment of other conditions, Kim et al. [29] conducted a review of the use of NMES after anterior cruciate ligament (ACL) reconstruction. Based on eight different studies, the authors concluded that the use of NMES combined with exercises can be effective in improving quadriceps strength up to four weeks after surgery. However, there was no sufficient evidence to affirm that NMES has any positive effect on the functional performance of patients who had undergone ACL reconstruction [29]. No literature review could be found on the effectiveness of NMES in patients with knee OA without indication for knee arthroplasty. A limitation of this study is that the current intensity used for electrical stimulation was not recorded. However, the maximum current intensity tolerated by each patient was applied as in previous studies [9, 24, 30]. No participant showed intolerance to electrical stimulation. The questionnaires used in this study have been translated into Brazilian Portuguese, cross-culturally adapted, and validated in previous studies [19, 31, 32]. The assessment of patient-reported pain intensity and physical function was performed according to the international consensus on outcomes measures for phase III clinical trials in OA, in which pain and physical function are identified as the most important outcome measures in randomized clinical trials [18]. The TUG test was chosen because it is a simple and inexpensive test designed to assess the functional mobility of patients based on activities of daily living [12]. Statistical analysis was performed on an intent-to-treat basis to minimize the impact of protocol violations (which may occur after randomization) on the results and conclusions and to avoid an overestimation of the treatment effect. This randomized clinical trial conforms to the Consort Statement (Consolidated Standards of Reporting Trials) [33], whose aim is to improve the quality of reports of randomized clinical trials. Given the predominance of mild and moderate OA cases among the participants, the results of this study can be generalized especially for patients with similar severity levels of OA.\n\nBODY.5. CONCLUSIONS:\nOur results revealed that the application of NMES combined with a conventional exercise program was as effective as the exercise program alone in reducing pain and improving physical function in patients with knee OA, and therefore no therapeutic benefit was observed with the use of NMES. \n\nBODY.6. CLINICAL IMPLICATIONS:\nModerate exercises, including warm-up and muscle stretching and strengthening exercises—combined or not with NMES—are recommended to reduce pain and improve physical function and quality of life in patients with knee OA.\n\nQuestion: Compared to Exercise alone what was the result of NMES plus exercise on Timed Up and Go test?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1059	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of Neuromuscular Electrical Stimulation Combined with Exercises versus an Exercise Program on the Pain and the Function in Patients with Knee Osteoarthritis: A Randomized Controlled Trial\n\n ABSTRACT:\n\nObjectives. To investigate the effect of 8 weeks of NMES + Ex (neuromuscular electrical stimulation combined with exercises) on pain and functional improvement in patients with knee osteoarthritis (OA) compared to exercise (Ex) alone. Design. Randomized controlled trial. Setting. A specialty outpatient clinic. Participants. Patients (N = 100; women = 86, men = 14; age range, 50–75 years) with knee OA. Interventions. Participants were randomly assigned to NMES + Ex or Ex group. Outcome Measures. Numerical Rating Scale 0 to 10 (NRS) and the Timed Up and Go (TUG) test were the primary outcomes. The secondary outcomes used were the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Results. Following the interventions, a statistically significant improvement in both groups was observed in all outcomes assessed. For the comparison between the groups, no statistically significant difference was found between the NMES + Ex and the Ex groups in NRS (P = 0.52), TUG test (P = 0.12), and aspects of WOMAC: pain (P = 0.26), function (P = 0.23), and stiffness (P = 0.63). Conclusion. The addition of NMES to exercise did not improve the outcomes assessed in knee OA patients. This study was registered at the Australian Clinical Trials Registry (ACTRN012607000357459).\n\nBODY.1. INTRODUCTION:\nOsteoarthritis (OA) is the most common form of arthritis. It affects one-third of adults and tends to increase with age [1]. Knee OA is associated with symptoms of pain, swelling, instability, and reduced range of motion (ROM). These symptoms lead to functional impairment, increasing the risk of morbidity and mortality [2, 3]. The synovium is infiltrated with inflammatory cells and secretes excess synovial fluid, leading to capsular swelling [4]. Through a spinal reflex, the capsular swelling inhibits muscle activation, which, combined with disuse, may cause muscle weakness and atrophy [1]. Because the quadriceps muscle acts as shock absorber for the knee joint, weakness in the thigh muscle reduces joint protection, resulting in overload [4]. Exercises strengthen the muscles, reduce pain, improve physical function, and are therefore considered a major intervention in the conservative treatment of patients with knee OA [5]. In addition to muscle strengthening exercises, stretching exercises are commonly used to increase ROM and are often prescribed in rehabilitation protocols as part of routine warm-up to prepare the muscles and joints for other types of exercise, such as aerobic and strengthening programs [6, 7]. Stretching of the hamstring muscles may improve knee extension ROM in OA patients. Neuromuscular electrical stimulation (NMES) is defined as the application of electrical stimulation using surface electrodes placed over skeletal muscles to produce visible muscle contraction through the activation of intramuscular nerve branches [8]. This technique can also be used as a form of physical therapy in the treatment of patients with knee OA. The goals of rehabilitation protocols that include NMES are to provide additional stimulus to increase muscle strength in patients with knee OA [9]. The methods and findings of previous studies on the effectiveness of NMES in knee OA differ in the modulation of NMES parameters, choice of the outcomes used to evaluate the patients, and characteristics of the control groups. This leads to a lack of consensus regarding the effectiveness attained from including NMES in conventional rehabilitation protocols. Major flaws with regard to methodological quality were found in clinical trials testing the use of NMES in the conservative treatment of patients with knee OA. Only one of these studies reported using allocation concealment, blinded assessment, and intention-to-treat analysis [10]. Thus, the objective of this study was to conduct a randomized clinical trial following methodological criteria, including allocation concealment, blinding of the examiner, and application of intention-to-treat analysis to assess the role of NMES in improving pain and physical function in patients with knee OA. It is important to study interventions with the potential to improve functional status in this patient population [11]. \n\nBODY.2. METHODS:\nThe study was conducted at the Interlagos Specialty Outpatient Clinic, São Paulo, Brazil. Patients were referred from the Rheumatology Department according to the inclusion and exclusion criteria and randomly allocated into groups using a computer-generated randomization chart. The allocation codes were sealed in opaque envelopes by a third person not involved in the study to avoid selection bias. Written informed consent was obtained from all participants. The study was approved by the Research Ethics Committee of the Universidade Federal de São Paulo (UNIFESP), Brazil, no. 0141/07, and registered with the Australian Clinical Trials Registry, no. ACTRN012607000357459. Setting the significance level at 5% and the power of the sample at 80%, a sample size of 40 patients per group was estimated to be necessary to detect a difference of at least 1 minute ± 3 seconds in the Timed Up and Go (TUG) test, which was considered to be the minimum clinically significant difference for the present trial [12]. Paired Student's t-test and analysis of covariance (ANCOVA) were used for comparisons between groups; the covariant was obtained from a previous study [13]. One hundred patients were recruited according to inclusion and exclusion criteria. Eligibility criteria were age 50 to 75 years, OA grade 2 or greater according to the radiographic classification of OA proposed by Kellgren and Lawrence [14], and diagnosis of knee OA based on the American College of Rheumatology (ACR) criteria. Exclusion criteria were use of a pacemaker, unstable heart conditions, participation in another physical activity program, inability to exercise on a stationary bicycle ergometer, inability to walk, previous hip or knee arthroplasty, diagnosis of fibromyalgia, epilepsy, and skin tumor or lesion at the NMES application site. Patients were divided into two groups of 50 each: (1) the NMES combined with exercises (NMES + Ex) group and (2) exercise (Ex) group. Patient medication was standardized and not modified during the study period. Paracetamol was prescribed for pain, and diacerein and chloroquine for OA control. Interventions were delivered for both groups by the same physical therapist, twice a week, for 8 weeks, with each session lasting about 40 minutes. All patients received a manual including guidelines on how not to overload the knee during daily activities and instructions on the use of ice packs in case of pain and inflammation and warm compresses in case of pain without inflammation as follows. \nManual for Patients with Osteoarthritis of the Knee. The purpose of this manual is to explain osteoarthritis and to teach how you can adjust yourself to your daily activities, according to the knee symptoms. Try to seriously follow our orientations for your own benefit! \nThe Knee. The knee joint is composed of 3 bones—the femur (thigh bone), the patella (kneecap) and the tibia (leg bone). It has muscles, capsule, ligaments, meniscus, and the cartilage that lines the bones and protects them from the impact. The knee joint supports nearly the whole weight of our body. \nWhat Is Osteoarthritis? It is a disease caused by the breakdown of cartilage in the joints. The layers in the cartilage become damaged and with time they lose the function of smoothing the contact between the bone surface and the joints. The pain is a result of the attrition of one bone against the other in the absence or decreased cartilage in the joints. \nWhat Are the Signs and Symptoms? Patients with osteoarthritis may have some pain mainly when starting a movement, as in morning stiffness or after immobilization. With time, the pain might be intensified and be permanent. The presence of crepitation when moving the knees is often. \nWhat Kind of Difficulties Might I Have in My Daily Life? Difficulties found in daily live vary according to the patients' symptoms. In general, however, the patient has pain and difficulty when supporting the body weight using the affected knee, going up and down the stairs, or when walking. \nWhat Should I Do When It Is Painful? A doctor can prescribe the treatment for osteoarthritis. However, a simple form of improving the pain is to use warm to hot water bottle over the knee joint (be careful not to burn the skin, use a protection, and test the water temperature before using it. \nWhat If It Is Swollen? To manage the swollen, you can combine rest, use of ice pack, and elevating the leg above the level of the heart. The ice pack should be placed over the knee joint for 20 minutes. \nWhat Are the Other Recommendations?\nIf you are overweight, losing some kilos will reduce the stress over the joint. Wear comfortable shoes with a rubber sole and no heels.In case of pain when walking, use a cane as an aid tool.Try to have a good night sleep.\n\n\nBODY.2. METHODS.2.1. NMES COMBINED WITH EXERCISE GROUP:\nTreatment for patients in the NMES + Ex included 10 minutes on a stationary bicycle, stretching of hamstring muscles (3 repetitions of 30 seconds) with the aid of an elastic band, and loaded quadriceps strengthening exercises combined with NMES. The strengthening exercise with NMES was performed in the sitting position with the knee and hip flexed to 90 degrees; patients contracted their quadriceps at each NMES stimulus. NMES was applied using an electrical stimulator (Globus ACTIVA 600 Pro, Globus, Italia) with two 7.5 × 13 cm self-adhesive electrodes (ValuTrode electrodes, Axelgaard Manufacturing Co. Ltd., Fallbrook, CA) placed over the region of the quadriceps muscle (rectus femoris and vastus medialis). NMES parameters were as follows: pulsed current, biphasic, asymmetrical, rectangular waveform, frequency 50 Hz, pulse duration 250 μs, contraction time 10 s, rest time 30 s every 20 minutes; current intensity was the maximum tolerated by each patient [15]. \n\nBODY.2. METHODS.2.2. EXERCISE GROUP (EX):\nPatients in the Ex group performed the same exercise program as those in the NMES group but without NMES. The exercise protocol included 10 minutes of warm-up on a stationary bicycle ergometer, stretching of hamstrings muscles with the aid of an elastic band, and knee extension exercises performed for 3 sets of 15 repetitions with rest intervals of 30–45 seconds between sets. For both groups, the training load for the strengthening exercises was established based on 50–60% of the 10-repetition maximum (RM) instead of 1 RM to avoid injury by excessive muscle contraction [16].\n\nBODY.2. METHODS.2.3. OUTCOMES:\nPatients were evaluated before and after intervention by a physical therapist blinded to group assignment. The primary outcomes were the TUG test results [12] and pain walking on a flat surface in the last 72 h measured on an 11-point Numerical Rating Scale (NRS) [17]. The secondary outcomes were scores on the pain, physical function, and stiffness subscales of the culturally validated Brazilian-Portuguese version of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) [18, 19]. In this study, WOMAC pain, physical function, and stiffness scores were analyzed separately. \n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nPaired Student's t-test was performed to compare pre- and postintervention values at a significance level of 0.05 (P < 0.05). Statistical analysis was performed on an intent-to-treat (ITT) basis and included all patients who were randomized to treatment. Mixed model analysis of variance with repeated measures was used with occasion measures as within-group factors and intervention as between-group factor. Relations between the observations were analyzed using an unstructured covariance matrix. Missing-data imputation was not performed to evaluate pre- and postintervention differences between the two groups, because Chakraborty and GU [20] showed that mixed model analysis without missing-data imputation always provides equal or more power than does mixed model analysis with missing-data imputation. Effect size was calculated as the difference between the means divided by the standard deviation using Cohen's d [21]. The analyses were performed using the General Linear Model (GLM), and mixed analyses were carried out using the Statistical Analysis Software (SAS) version 9.2 for Windows [22].\n\nBODY.3. RESULTS:\nThe demographic and clinical characteristics of patients, including age, sex, side treated, and body mass index (BMI), as well as TUG test values, NRS pain scores, and WOMAC scores on the pain, physical function, and stiffness subscales, are shown in Table 1. Eighty-seven patients completed the study. Of the 13 dropouts, 6 (12%) patients were in the NMES + Ex group and 7 (14%) in the Ex group (Figure 1). \n\nBODY.3. RESULTS.3.1. PRIMARY OUTCOMES:\nNo significant differences between groups were found in NRS pain scores and TUG test time on ITT analysis. A significant decrease in pain intensity (NRS scores) and TUG test time was observed after intervention compared with baseline in the NMES + Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001) and Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001). The primary outcomes are listed in Table 2. \n\nBODY.3. RESULTS.3.2. SECONDARY OUTCOMES:\nNo significant differences between groups were found on the pain, physical function, and stiffness subscales of the WOMAC index on ITT analysis. There was a significant improvement in all WOMAC subscales in the NMES + Ex group (pain; P < 0.0001; physical function, P < 0.0001; stiffness, P < 0.0001) and in the Ex group (pain, P < 0.0001; physical function, P < 0.0001; stiffness, P = 0.0009). The secondary outcomes are listed in Table 2.\n\nBODY.3. RESULTS.3.3. ADVERSE EFFECT:\nOne patient in the NMES + Ex group exhibited a blood pressure spike, which may have resulted from the use of NMES or from the exercise program itself. The following contraindications to the use of NMES were respected: avoiding the use of NMES over areas of tumor, with open wounds, or bleeding, and in patients with pacemakers [15].\n\nBODY.4. DISCUSSION:\nIn this randomized clinical trial, the NMES combined with exercise did improve pain and physical function, but there was no evidence that it did better than exercise alone. Our results are in agreement with the findings of Rosemffet et al. [23] who conducted a pilot study comparing the treatment results of patients with knee OA (n = 26) treated with either NMES alone or exercises alone or exercises combined with NMES. The authors reported a significant improvement on the WOMAC pain subscale in the three groups, but no significant differences in WOMAC scores were found between groups [23]. The lack of difference in treatment outcome between groups in the present study might be attributed to the fact that the participants had no clinically significant muscle or functional impairment. A finding substantiating this hypothesis is that the mean TUG test values in the two groups were similar to those found in the study of Steffen et al., for elderly patients with no physical limitations categorized under the same mean age group [24]. The TUG test values reported were 8 ± 2 seconds for patients with 60–69 years old and 9 ± 3 seconds for patients with 70–79 years old. In the present study, the baseline values for TUG test were 8.27 + 1.76 for NMES + Ex group and 9.34 ± 2.47 for Ex group. Given that the greater the muscle impairment, the greater the NMES effect, patients with a more advanced stage of OA might obtain greater benefit from NMES [25–27]. With regard to evidence on the effectiveness of NMES in the rehabilitation of patients with knee OA, the Cochrane Collaboration published a systematic review evaluating the pre- and postoperative use of NMES in total knee arthroplasty [28]. The two studies that were evaluated were classified as being at high risk of bias, because randomization and allocation concealment were not described, and no data obtained from the study groups were presented in terms of means and standard deviations. It was not possible to determine whether or not the pre- and postoperative use of NMES was effective in the rehabilitation of knee arthroplasty patients, and therefore further studies are warranted. Regarding lines of evidence on the effectiveness of NMES in the treatment of other conditions, Kim et al. [29] conducted a review of the use of NMES after anterior cruciate ligament (ACL) reconstruction. Based on eight different studies, the authors concluded that the use of NMES combined with exercises can be effective in improving quadriceps strength up to four weeks after surgery. However, there was no sufficient evidence to affirm that NMES has any positive effect on the functional performance of patients who had undergone ACL reconstruction [29]. No literature review could be found on the effectiveness of NMES in patients with knee OA without indication for knee arthroplasty. A limitation of this study is that the current intensity used for electrical stimulation was not recorded. However, the maximum current intensity tolerated by each patient was applied as in previous studies [9, 24, 30]. No participant showed intolerance to electrical stimulation. The questionnaires used in this study have been translated into Brazilian Portuguese, cross-culturally adapted, and validated in previous studies [19, 31, 32]. The assessment of patient-reported pain intensity and physical function was performed according to the international consensus on outcomes measures for phase III clinical trials in OA, in which pain and physical function are identified as the most important outcome measures in randomized clinical trials [18]. The TUG test was chosen because it is a simple and inexpensive test designed to assess the functional mobility of patients based on activities of daily living [12]. Statistical analysis was performed on an intent-to-treat basis to minimize the impact of protocol violations (which may occur after randomization) on the results and conclusions and to avoid an overestimation of the treatment effect. This randomized clinical trial conforms to the Consort Statement (Consolidated Standards of Reporting Trials) [33], whose aim is to improve the quality of reports of randomized clinical trials. Given the predominance of mild and moderate OA cases among the participants, the results of this study can be generalized especially for patients with similar severity levels of OA.\n\nBODY.5. CONCLUSIONS:\nOur results revealed that the application of NMES combined with a conventional exercise program was as effective as the exercise program alone in reducing pain and improving physical function in patients with knee OA, and therefore no therapeutic benefit was observed with the use of NMES. \n\nBODY.6. CLINICAL IMPLICATIONS:\nModerate exercises, including warm-up and muscle stretching and strengthening exercises—combined or not with NMES—are recommended to reduce pain and improve physical function and quality of life in patients with knee OA.\n\nQuestion: Compared to Exercise alone what was the result of NMES plus exercise on Western Ontario and McMaster Universities Osteoarthritis Index for pain?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1185	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The Effect of Breathing Exercises on the Nocturnal Enuresis in the Children with the Sleep-Disordered Breathing\n\n ABSTRACT.BACKGROUND:\nThe nocturnal enuresis is one of the most common complaints of childhood. Upper airway obstruction and nocturnal snoring affect the nocturnal enuresis in children.\n\nABSTRACT.OBJECTIVES:\nThe aim of this study was to investigate the effects of breathing exercises on the nocturnal enuresis in the children with the sleep-disordered breathing.\n\nABSTRACT.PATIENTS AND METHODS:\nThis study was conducted in year of 2011 by a semi-experimental design with the control group among 40 children, aged 6 - 12 years, who had the nocturnal enuresis. Participants were examined based on the criteria of nocturnal enuresis, oral breathing, and nocturnal snoring. Subsequently, they were randomly assigned to the case and control groups. In the case group, the breathing exercises were performed for 45 minutes, and were pursued for four weeks in the morning following and prior to sleeping, and subsequently the arterial blood gases were measured and the frequency of enuresis and the respiratory rates (RR) were recorded.\n\nABSTRACT.RESULTS:\nAfter intervention the means of PaCO2 and RR in the control group were significantly higher than the case group (P < 0.0001). Likewise, O2sat, PaO2 in the case group were higher than the control group (P < 0.0001). The nocturnal enuresis decreased significantly in the case group, compared to the control group (P < 0.0001).\n\nABSTRACT.CONCLUSIONS:\nThis study suggests that the breathing exercises may reduce the frequency of nocturnal enuresis in the patients with the oral breathing and nocturnal snore. The clinical implications of these findings should be verified in the future longitudinal studies.\n\nBODY.1. BACKGROUND:\nNocturnal enuresis is defined an accidental urination with at least, twice per week for three consecutive months, and calendar age of five years old (1). It is one of the most common complaints of childhood; children from the age of five should be able to control the urine (2, 3) because at this age, bladder capacity increases and brain nerve centers control the urinary bladder contractions during sleep (4). Many children cannot reach this stage. Therefore, children and their families face severe behavioral and social problems (1). Various methods have been proposed for the treatment of nocturnal enuresis, none of which is of a definitive efficacy (2, 3, 5). One of the findings concerning this disorder is that the nocturnal enuresis in children with the sleep-disordered breathing, whose nostrils are blocked, happens more (6-8). Relaxed muscles which help to open the airways and soft palate vibrations during sleep, will cause snoring, while in the normal condition air enters through the nose during the aspiration and slip on the edge of the soft palate. If this little edge moves and makes a barrier to the air, the sound of snoring is created (8, 9). Chang et al. (10) and Yeung et al. (11) have shown that the prevalence of nocturnal enuresis in children with the habitual snoring is four times more and 46 percent of children with the sleep- disordered breathing syndrome have the nocturnal enuresis (12). In some children, recurrent upper respiratory tract persistent infections, adenoids, habitual oral breathing, blocked Eustachian tube and nocturnal snoring can cause enuresis (13, 14). Children's physical health is dependent on how they are breathing. The natural activity of respiratory tract is controlled through the neck muscles, inter-rib muscles, abdominal muscles, and diaphragm. Some of the breathing disorders occur when the transferred messages through the brain are unable to transfer to these muscles through the spinal cord (15, 16). In children with the oral breathing, the superficial and shallow breathing create the nocturnal snore due to increasing weakness of breathing muscles. This factor causes the bladder to lose its control on urination (17, 18). Ezzat waleeda et al. have shown that opening blocked airway by the surgery will reduce the nocturnal enuresis in the children with the respiratory disorders (16). Breath control is done by the aspiration and expiration. In breathing exercises, the individual capacity will increase and the equilibrium is established between the nervous and respiratory systems and the mind will work normally (19), so that by the deep breathing, the peripheral air amount will also increase substantially. Respiratory exercises, tolerance exercises and exercise activities related to the upper and lower parts improve breathing process and create a balanced ventilation system (20). The reason is that individuals under the influence of respiratory exercises show an increase in the lung functional indices, and thus, their oxygen consumption volume rises (18, 21). A few external studies are present concerning the effect of breathing exercises improvement on the children nocturnal enuresis with the conflicting results, but we were unable to find any internal reference in this regard (15, 17, 22).\n\nBODY.2. OBJECTIVES:\nTherefore, the aim of this study was to investigate the effects of breathing exercises on the reduction of the nocturnal enuresis in the children with the sleep-disordered breathing.\n\nBODY.3. PATIENTS AND METHODS.3.1. PATIENTS:\nThis study was conducted in year of 2011 by a semi-experimental study with a control group. The control and case groups were selected based on the DSM-IV-TR criteria by the convenience sampling (23). The groups were children, who had the nocturnal enuresis, and hence; were brought to the kidney and urethra clinic affiliated to the Isfahan University of Medical Sciences by their parents. The children's problem of breathing was also diagnosed by the ear, nose and throat specialists. Both groups were consisted of 40 children (6-12 years old) with the concomitant nocturnal enuresis and oral breathing. The 40 children were classified into the two equal groups. Participants were examined based on the criteria of oral breathing, nocturnal snoring, and nocturnal enuresis two times per week and the sleep-disordered breathing confirmed by the otolaryngologists. The exclusion criteria consisted of the current drug consumption (as, tetracycline, nitrofurantoin, methicillin, acethazolamide may decrease the level of PaCO2, whereas bicarbonate, hydrocortisone, metolazone may increase the level of PaO2), (24) mental and behavioral disorders, tonsillitis, physical disability, mental retardation, allergies and cigarette smoking by the parents.\n\nBODY.3. PATIENTS AND METHODS.3.2. PROCEDURE:\nFirst nocturnal enuresis frequency and the RR were recorded in the case and control groups. The RR was measured when the children were at rest and involved counting the number of breaths for one minute by counting how many times the chest rose. In addition, the patients of both groups were analyzed for the blood arterial gases. Subsequently, breathing exercises were taught to the children and their parents in the case group by the demo games and video clips by speech therapist. The patients did not drink water/any other liquids two hours before sleep. Then breathing exercises pursued in four weeks in the morning after getting-up, and also at night before sleep. Firstly, the breathing exercises of hip, anal and neck muscles and diaphragm were performed. For the evacuation of abdominal breathing toward the spine, diaphragm was drawn to the ribs. Then, the movements of the head and spinal column spin the effective energy in the body. During these exercises, breathing was done by the right nostril. Then, breathing exercises of the nose and jaw were done with closing the right nostril and pushing the chin to the chest, while expiration was done by the left nostril. Finally, during abdominal exercises, the inspiration was retained and with mouth closing, expiration expelled through the right nostril (14, 23). Then, the frequency of nocturnal enuresis and the RR were recorded. Upon the completion of breathing exercises, the arterial blood gases were also measured.\n\nBODY.3. PATIENTS AND METHODS.3.3. COLLECTION AND HANDLING OF BLOOD SAMPLES:\nA radial arterial blood of five milliliters was drawn fasting by the air-free bubbles plastic syringes (gauge 23) containing lyophilized heparin. Subsequently, the blood samples under the condition of air-sealed were placed on the ice bag instantly, and sent in a pre-cold chamber (approximate temperature 4 ̊C) to the laboratory within 10 minutes for the blood gases analysis. The laboratory also carried out the assay within 30 minutes (24). The arterial blood gas analyzer (ABL 300, Radiometer, Copenhagen, Denmark) was employed to measure the oxygen, carbon dioxide and pH levels.\n\nBODY.3. PATIENTS AND METHODS.3.4. STATISTICAL ANALYSIS:\n Statistical analyses were performed using SPSS software, version 16.0. Data presented as mean ± SD, median [IQR] and number as appropriate. At the baseline age, weight, height, body mass index (BMI), O2sat, PaO2, PaCO2, pH and RR were compared before and after the study in the control and case groups, using the independent, paired t-tests, and repeated measurements of ANOVA. In addition, the Chi-Square test was used to assess the distribution of sex between the groups. Likewise, nocturnal enuresis frequency was compared, before and after the study within and between the groups, using the Wilcoxon Signed Rank and Mann-Whitney tests, respectively. Statistical significance was accepted at the p-value less than 0.05.\n\nBODY.3. PATIENTS AND METHODS.3.5. ETHICAL CONSIDERATION:\nThis study was approved by the Ethics Committee of the Isfahan University of Medical Sciences. Written informed consent was obtained from the parents, and that the study protocol conformed to the ethical guidelines of the 1975 Declaration of Helsinki as reflected in a priory approval by the institution's human research committee.\n\nBODY.4. RESULTS:\nTable 1 displays the total number of the case group consisted of three girls and 17 boys. The case group was between 6 to 10 years old, with a mean age of 7.09 ± 1.23. In addition, the control group was between 6 to 11 years old, with a mean age of 8.12 ± 1.74. The results showed that there was insignificant difference in gender between the two groups. In addition, there was insignificant difference in the BMI, weight, and height between the case and the control groups. Table 1. Demographic Characteristics of the Groups. Case group a Control group a P value \n Weight, kg \n 29.5 (2.81) 29.3 (2.16) 0.824 b \n Height, cm \n 127.4 (2.19) 126.9 (2.04) 0.945 b \n BMI, kg/m2 \n 15.92 (2.31) 16.04 (1.08) 0.129 b \n Age \n 6-11 7.09 (1.23) 8.12 (1.74) 0.421 c \n Gender \n Male 3 6 Female 17 14 0.189 b a Values are represented as mean (SD) b P values were calculated by the Chi Squared c P values were calculated by the independent t-test Table 2 displays the comparison of the means of the O 2 sat, PaO 2 , PaCO 2 , pH and RR between the groups before and after intervention. Before intervention, the means of O 2 sat, PaO 2 , PaCO 2 , pH and RR were similar in both groups (P > 0.05). After intervention, only pH was similar in both groups (P > 0.05) and the means of O 2 sat, PaO 2 in the case group were significantly higher than the control group (P < 0.0001). However, in the control group, the means of the PaCO 2 and RR were significantly higher than the case group (P < 0.0001). Table 2. Comparison of the O 2 sat, PaO 2 , PaCO 2 , pH and RR between the Groups. Control Group a Case Group a P value b Before After Before After \n O 2 sat, mm/Hg c \n 84.61 (1.13) 84.26 (1.21) 83.92 (3.29) 89.45 (2.17) 0.001 \n P value \n d \n 0.92 0.01 \n PaO, mm/Hg 2 , mm/Hg e \n 69.54 (1.26) 67.20 (2.14) 75.28 (2.43) 0.001 \n P value \n d \n 0.091 0.001 \n PaCO 2\n , mm/Hg \n 75.16 (1.56) 76.12 (1.23) 72.30 (1.49) 60.21 (1.28) 0.001 \n P value \n d \n 0.34 0.001 \n pH, mm/Hg \n 7.76 (1.34) 7.43 (1.23) 7.91 (2.28) 7.30 (2.19) 0.124 \n P value \n d \n 0.87 0.12 \n RR \n f \n 29.61 (1.21) 29.12 (1.61) 27.42 (1.06) 21.34 (1.16) 0.001 \n P value \n d \n 0.91 0.01 a Values are represented as mean (SD) b P-values were calculated by the repeated measurements of ANOVA c P-values were calculated by the Oxygen 2 saturation d P-values were calculated by the paired t-test. e P-values were calculated by the partial pressure of O 2 f P-values were calculated by the Respiratory Rates Figure 1.Depicts the Comparison of the Means of the O 2 sat, PaO 2 , PaCO 2 , pH and RR Between the Groups Before and After Intervention.Before intervention, there were insignificant alteration in the means of O2sat, PaO2, paCO2, pH and RR between both groups (P > 0.05). However, after intervention, the means of O2sat, PaO2 in the case group were significantly higher than the control group (P < 0.0001). Conversely, the means of the PaCO2 and RR in the control group were significantly higher than the case group (P < 0.0001). Table 3 displays the comparison of the median of nocturnal enuresis frequency between the groups before and after intervention. Before intervention, the median of nocturnal enuresis frequency was similar in both groups (P > 0.001). After intervention, the median of nocturnal enuresis frequency in the case group was significantly lower than the control group (P < 0.001). Table 3. Comparison of the Nocturnal Enuresis Frequency between the Groups. Before After P value a \n Case Group b \n 6 (4.25 – 8) 1 (0 – 2) < 0.0001 \n Control Group \n b \n 6 (4.25 – 7.75) 5.5 (4 – 8.75) 0.83 \n P value \n c \n 0.7 < 0.0001 a P-values were calculated by the Wilcoxon Signed Rank tests, b Values are represented as median (IQR). c P-values were calculated by the Mann-Whitney. \n\nBODY.5. DISCUSSION:\nThis study aimed to consider the effects of breathing exercises on the nocturnal enuresis in the children with the sleep-disordered breathing. Normally, in each breath, 500 ml of air enter the lungs, and then it goes out of the lungs after the exchange of oxygen and carbon dioxide. With deep breathing, the amount of air can be increased largely. These breathing exercises bring the air volume to 2500 ml in each breath. Therefore, by breathing exercises, more air will enter the lungs, arterial blood oxygen saturation will increase, and respiratory proper functioning will be possible, which promotes deep breathing improvement (11, 25, 26). Breathing exercises will also prevent the accumulation of secretions and atelectasis, strengthen the respiratory muscles, coordinate aspiration muscles and correct the breathing patterns. It also decreases the asthmatic attacks and eliminates the dyspnea (14). On the contrary, in children with the oral breathing during sleep, the upper airways endure vibration due to airflow, and breathing becomes difficult due to weakening of the respiratory muscles. In addition, the chronic superficial breathing causes the weakening of the inter-rib muscles and diaphragm muscle (17, 18). Many studies show that the removal of airways blockade even in case of surgery, reduces the frequency of nocturnal enuresis in children with the breathing disorders (16). There are some drugs and various behavioral to treat the nocturnal enuresis, but none of them is crucial, and each has side effects. On the other hand, the treatment of nocturnal enuresis with respect to the associated disorders, can be more effective/with less complications (2, 27, 28). The results of this study showed that in children with the nocturnal enuresis, who had the blockade of airways/abnormal breathing pattern; the breathing exercises can be used as a simple method with low expenses and more efficient than other approaches. The findings of this study also showed that there was no significant difference in the demographic characteristics between the two groups (Table 1). In addition, the findings of this study revealed that there was a significant difference in the mean frequency of nocturnal enuresis between the case and the control groups after the intervention (Table 3). These findings demonstrate that the frequency of breathing exercises reduce the nocturnal enuresis in the children with the sleep-disordered breathing. There are many studies concerning the relationship between the nocturnal enuresis and nocturnal snore/airways blockade ( 16 , 21 , 22 , 29 ). The nocturnal enuresis is more common in children with the oral breathing. It appears that the relative hypoxia in these children causes low-pressure oxygen in the distal tubes of kidney, unresponsiveness to the anti-diuretic hormone, and increased production of urine temporarily, particularly during the sleep. Both of these factors can increase the volume of urine, and consequently make the urine control more difficult and finally lead to the nocturnal enuresis ( 3 , 7 ). As far as we are concerned, there is no internal research concerning the impact of breathing exercises on the nocturnal enuresis in children. Nevertheless, Crouch et al. have shown that in subjects with the breathing disorders, the pulmonary rehabilitation programs including breathing exercises, endurance activities, upper and lower extremities exercises like purse lip breathing and diaphragmatic breathing, improve ventilation and in turn, have caused the adequate exchange of air pattern ( 19 ). Ghahri Sarabi et al. have also shown that in patients with the breathing disorders, breathing exercises increase the lung functional indices ( 27 ). In addition, another study has shown that in patients with the respiratory chronic diseases, pulmonary rehabilitation and breathing exercises increase the volume of oxygen consumption ( 20 ). The respiratory disorders cause ineffective breathing habits and shallow breathing. This chronic shallow breathing leads to the weakening of the diaphragm muscle and inter-costal muscles ( 8 , 19 ). In conclusion; these findings suggest that the breathing exercises may reduce the nocturnal enuresis in the children with the sleep-disordered breathing. The clinical implications of these findings should be verified in the future longitudinal studies.\n\nQuestion: Compared to no breathing exercises what was the result of breathing exercises were performed for 45 minutes, and were pursued for four weeks in the morning following and prior to sleeping on O2sat, PaO2?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1187	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The Effect of Breathing Exercises on the Nocturnal Enuresis in the Children with the Sleep-Disordered Breathing\n\n ABSTRACT.BACKGROUND:\nThe nocturnal enuresis is one of the most common complaints of childhood. Upper airway obstruction and nocturnal snoring affect the nocturnal enuresis in children.\n\nABSTRACT.OBJECTIVES:\nThe aim of this study was to investigate the effects of breathing exercises on the nocturnal enuresis in the children with the sleep-disordered breathing.\n\nABSTRACT.PATIENTS AND METHODS:\nThis study was conducted in year of 2011 by a semi-experimental design with the control group among 40 children, aged 6 - 12 years, who had the nocturnal enuresis. Participants were examined based on the criteria of nocturnal enuresis, oral breathing, and nocturnal snoring. Subsequently, they were randomly assigned to the case and control groups. In the case group, the breathing exercises were performed for 45 minutes, and were pursued for four weeks in the morning following and prior to sleeping, and subsequently the arterial blood gases were measured and the frequency of enuresis and the respiratory rates (RR) were recorded.\n\nABSTRACT.RESULTS:\nAfter intervention the means of PaCO2 and RR in the control group were significantly higher than the case group (P < 0.0001). Likewise, O2sat, PaO2 in the case group were higher than the control group (P < 0.0001). The nocturnal enuresis decreased significantly in the case group, compared to the control group (P < 0.0001).\n\nABSTRACT.CONCLUSIONS:\nThis study suggests that the breathing exercises may reduce the frequency of nocturnal enuresis in the patients with the oral breathing and nocturnal snore. The clinical implications of these findings should be verified in the future longitudinal studies.\n\nBODY.1. BACKGROUND:\nNocturnal enuresis is defined an accidental urination with at least, twice per week for three consecutive months, and calendar age of five years old (1). It is one of the most common complaints of childhood; children from the age of five should be able to control the urine (2, 3) because at this age, bladder capacity increases and brain nerve centers control the urinary bladder contractions during sleep (4). Many children cannot reach this stage. Therefore, children and their families face severe behavioral and social problems (1). Various methods have been proposed for the treatment of nocturnal enuresis, none of which is of a definitive efficacy (2, 3, 5). One of the findings concerning this disorder is that the nocturnal enuresis in children with the sleep-disordered breathing, whose nostrils are blocked, happens more (6-8). Relaxed muscles which help to open the airways and soft palate vibrations during sleep, will cause snoring, while in the normal condition air enters through the nose during the aspiration and slip on the edge of the soft palate. If this little edge moves and makes a barrier to the air, the sound of snoring is created (8, 9). Chang et al. (10) and Yeung et al. (11) have shown that the prevalence of nocturnal enuresis in children with the habitual snoring is four times more and 46 percent of children with the sleep- disordered breathing syndrome have the nocturnal enuresis (12). In some children, recurrent upper respiratory tract persistent infections, adenoids, habitual oral breathing, blocked Eustachian tube and nocturnal snoring can cause enuresis (13, 14). Children's physical health is dependent on how they are breathing. The natural activity of respiratory tract is controlled through the neck muscles, inter-rib muscles, abdominal muscles, and diaphragm. Some of the breathing disorders occur when the transferred messages through the brain are unable to transfer to these muscles through the spinal cord (15, 16). In children with the oral breathing, the superficial and shallow breathing create the nocturnal snore due to increasing weakness of breathing muscles. This factor causes the bladder to lose its control on urination (17, 18). Ezzat waleeda et al. have shown that opening blocked airway by the surgery will reduce the nocturnal enuresis in the children with the respiratory disorders (16). Breath control is done by the aspiration and expiration. In breathing exercises, the individual capacity will increase and the equilibrium is established between the nervous and respiratory systems and the mind will work normally (19), so that by the deep breathing, the peripheral air amount will also increase substantially. Respiratory exercises, tolerance exercises and exercise activities related to the upper and lower parts improve breathing process and create a balanced ventilation system (20). The reason is that individuals under the influence of respiratory exercises show an increase in the lung functional indices, and thus, their oxygen consumption volume rises (18, 21). A few external studies are present concerning the effect of breathing exercises improvement on the children nocturnal enuresis with the conflicting results, but we were unable to find any internal reference in this regard (15, 17, 22).\n\nBODY.2. OBJECTIVES:\nTherefore, the aim of this study was to investigate the effects of breathing exercises on the reduction of the nocturnal enuresis in the children with the sleep-disordered breathing.\n\nBODY.3. PATIENTS AND METHODS.3.1. PATIENTS:\nThis study was conducted in year of 2011 by a semi-experimental study with a control group. The control and case groups were selected based on the DSM-IV-TR criteria by the convenience sampling (23). The groups were children, who had the nocturnal enuresis, and hence; were brought to the kidney and urethra clinic affiliated to the Isfahan University of Medical Sciences by their parents. The children's problem of breathing was also diagnosed by the ear, nose and throat specialists. Both groups were consisted of 40 children (6-12 years old) with the concomitant nocturnal enuresis and oral breathing. The 40 children were classified into the two equal groups. Participants were examined based on the criteria of oral breathing, nocturnal snoring, and nocturnal enuresis two times per week and the sleep-disordered breathing confirmed by the otolaryngologists. The exclusion criteria consisted of the current drug consumption (as, tetracycline, nitrofurantoin, methicillin, acethazolamide may decrease the level of PaCO2, whereas bicarbonate, hydrocortisone, metolazone may increase the level of PaO2), (24) mental and behavioral disorders, tonsillitis, physical disability, mental retardation, allergies and cigarette smoking by the parents.\n\nBODY.3. PATIENTS AND METHODS.3.2. PROCEDURE:\nFirst nocturnal enuresis frequency and the RR were recorded in the case and control groups. The RR was measured when the children were at rest and involved counting the number of breaths for one minute by counting how many times the chest rose. In addition, the patients of both groups were analyzed for the blood arterial gases. Subsequently, breathing exercises were taught to the children and their parents in the case group by the demo games and video clips by speech therapist. The patients did not drink water/any other liquids two hours before sleep. Then breathing exercises pursued in four weeks in the morning after getting-up, and also at night before sleep. Firstly, the breathing exercises of hip, anal and neck muscles and diaphragm were performed. For the evacuation of abdominal breathing toward the spine, diaphragm was drawn to the ribs. Then, the movements of the head and spinal column spin the effective energy in the body. During these exercises, breathing was done by the right nostril. Then, breathing exercises of the nose and jaw were done with closing the right nostril and pushing the chin to the chest, while expiration was done by the left nostril. Finally, during abdominal exercises, the inspiration was retained and with mouth closing, expiration expelled through the right nostril (14, 23). Then, the frequency of nocturnal enuresis and the RR were recorded. Upon the completion of breathing exercises, the arterial blood gases were also measured.\n\nBODY.3. PATIENTS AND METHODS.3.3. COLLECTION AND HANDLING OF BLOOD SAMPLES:\nA radial arterial blood of five milliliters was drawn fasting by the air-free bubbles plastic syringes (gauge 23) containing lyophilized heparin. Subsequently, the blood samples under the condition of air-sealed were placed on the ice bag instantly, and sent in a pre-cold chamber (approximate temperature 4 ̊C) to the laboratory within 10 minutes for the blood gases analysis. The laboratory also carried out the assay within 30 minutes (24). The arterial blood gas analyzer (ABL 300, Radiometer, Copenhagen, Denmark) was employed to measure the oxygen, carbon dioxide and pH levels.\n\nBODY.3. PATIENTS AND METHODS.3.4. STATISTICAL ANALYSIS:\n Statistical analyses were performed using SPSS software, version 16.0. Data presented as mean ± SD, median [IQR] and number as appropriate. At the baseline age, weight, height, body mass index (BMI), O2sat, PaO2, PaCO2, pH and RR were compared before and after the study in the control and case groups, using the independent, paired t-tests, and repeated measurements of ANOVA. In addition, the Chi-Square test was used to assess the distribution of sex between the groups. Likewise, nocturnal enuresis frequency was compared, before and after the study within and between the groups, using the Wilcoxon Signed Rank and Mann-Whitney tests, respectively. Statistical significance was accepted at the p-value less than 0.05.\n\nBODY.3. PATIENTS AND METHODS.3.5. ETHICAL CONSIDERATION:\nThis study was approved by the Ethics Committee of the Isfahan University of Medical Sciences. Written informed consent was obtained from the parents, and that the study protocol conformed to the ethical guidelines of the 1975 Declaration of Helsinki as reflected in a priory approval by the institution's human research committee.\n\nBODY.4. RESULTS:\nTable 1 displays the total number of the case group consisted of three girls and 17 boys. The case group was between 6 to 10 years old, with a mean age of 7.09 ± 1.23. In addition, the control group was between 6 to 11 years old, with a mean age of 8.12 ± 1.74. The results showed that there was insignificant difference in gender between the two groups. In addition, there was insignificant difference in the BMI, weight, and height between the case and the control groups. Table 1. Demographic Characteristics of the Groups. Case group a Control group a P value \n Weight, kg \n 29.5 (2.81) 29.3 (2.16) 0.824 b \n Height, cm \n 127.4 (2.19) 126.9 (2.04) 0.945 b \n BMI, kg/m2 \n 15.92 (2.31) 16.04 (1.08) 0.129 b \n Age \n 6-11 7.09 (1.23) 8.12 (1.74) 0.421 c \n Gender \n Male 3 6 Female 17 14 0.189 b a Values are represented as mean (SD) b P values were calculated by the Chi Squared c P values were calculated by the independent t-test Table 2 displays the comparison of the means of the O 2 sat, PaO 2 , PaCO 2 , pH and RR between the groups before and after intervention. Before intervention, the means of O 2 sat, PaO 2 , PaCO 2 , pH and RR were similar in both groups (P > 0.05). After intervention, only pH was similar in both groups (P > 0.05) and the means of O 2 sat, PaO 2 in the case group were significantly higher than the control group (P < 0.0001). However, in the control group, the means of the PaCO 2 and RR were significantly higher than the case group (P < 0.0001). Table 2. Comparison of the O 2 sat, PaO 2 , PaCO 2 , pH and RR between the Groups. Control Group a Case Group a P value b Before After Before After \n O 2 sat, mm/Hg c \n 84.61 (1.13) 84.26 (1.21) 83.92 (3.29) 89.45 (2.17) 0.001 \n P value \n d \n 0.92 0.01 \n PaO, mm/Hg 2 , mm/Hg e \n 69.54 (1.26) 67.20 (2.14) 75.28 (2.43) 0.001 \n P value \n d \n 0.091 0.001 \n PaCO 2\n , mm/Hg \n 75.16 (1.56) 76.12 (1.23) 72.30 (1.49) 60.21 (1.28) 0.001 \n P value \n d \n 0.34 0.001 \n pH, mm/Hg \n 7.76 (1.34) 7.43 (1.23) 7.91 (2.28) 7.30 (2.19) 0.124 \n P value \n d \n 0.87 0.12 \n RR \n f \n 29.61 (1.21) 29.12 (1.61) 27.42 (1.06) 21.34 (1.16) 0.001 \n P value \n d \n 0.91 0.01 a Values are represented as mean (SD) b P-values were calculated by the repeated measurements of ANOVA c P-values were calculated by the Oxygen 2 saturation d P-values were calculated by the paired t-test. e P-values were calculated by the partial pressure of O 2 f P-values were calculated by the Respiratory Rates Figure 1.Depicts the Comparison of the Means of the O 2 sat, PaO 2 , PaCO 2 , pH and RR Between the Groups Before and After Intervention.Before intervention, there were insignificant alteration in the means of O2sat, PaO2, paCO2, pH and RR between both groups (P > 0.05). However, after intervention, the means of O2sat, PaO2 in the case group were significantly higher than the control group (P < 0.0001). Conversely, the means of the PaCO2 and RR in the control group were significantly higher than the case group (P < 0.0001). Table 3 displays the comparison of the median of nocturnal enuresis frequency between the groups before and after intervention. Before intervention, the median of nocturnal enuresis frequency was similar in both groups (P > 0.001). After intervention, the median of nocturnal enuresis frequency in the case group was significantly lower than the control group (P < 0.001). Table 3. Comparison of the Nocturnal Enuresis Frequency between the Groups. Before After P value a \n Case Group b \n 6 (4.25 – 8) 1 (0 – 2) < 0.0001 \n Control Group \n b \n 6 (4.25 – 7.75) 5.5 (4 – 8.75) 0.83 \n P value \n c \n 0.7 < 0.0001 a P-values were calculated by the Wilcoxon Signed Rank tests, b Values are represented as median (IQR). c P-values were calculated by the Mann-Whitney. \n\nBODY.5. DISCUSSION:\nThis study aimed to consider the effects of breathing exercises on the nocturnal enuresis in the children with the sleep-disordered breathing. Normally, in each breath, 500 ml of air enter the lungs, and then it goes out of the lungs after the exchange of oxygen and carbon dioxide. With deep breathing, the amount of air can be increased largely. These breathing exercises bring the air volume to 2500 ml in each breath. Therefore, by breathing exercises, more air will enter the lungs, arterial blood oxygen saturation will increase, and respiratory proper functioning will be possible, which promotes deep breathing improvement (11, 25, 26). Breathing exercises will also prevent the accumulation of secretions and atelectasis, strengthen the respiratory muscles, coordinate aspiration muscles and correct the breathing patterns. It also decreases the asthmatic attacks and eliminates the dyspnea (14). On the contrary, in children with the oral breathing during sleep, the upper airways endure vibration due to airflow, and breathing becomes difficult due to weakening of the respiratory muscles. In addition, the chronic superficial breathing causes the weakening of the inter-rib muscles and diaphragm muscle (17, 18). Many studies show that the removal of airways blockade even in case of surgery, reduces the frequency of nocturnal enuresis in children with the breathing disorders (16). There are some drugs and various behavioral to treat the nocturnal enuresis, but none of them is crucial, and each has side effects. On the other hand, the treatment of nocturnal enuresis with respect to the associated disorders, can be more effective/with less complications (2, 27, 28). The results of this study showed that in children with the nocturnal enuresis, who had the blockade of airways/abnormal breathing pattern; the breathing exercises can be used as a simple method with low expenses and more efficient than other approaches. The findings of this study also showed that there was no significant difference in the demographic characteristics between the two groups (Table 1). In addition, the findings of this study revealed that there was a significant difference in the mean frequency of nocturnal enuresis between the case and the control groups after the intervention (Table 3). These findings demonstrate that the frequency of breathing exercises reduce the nocturnal enuresis in the children with the sleep-disordered breathing. There are many studies concerning the relationship between the nocturnal enuresis and nocturnal snore/airways blockade ( 16 , 21 , 22 , 29 ). The nocturnal enuresis is more common in children with the oral breathing. It appears that the relative hypoxia in these children causes low-pressure oxygen in the distal tubes of kidney, unresponsiveness to the anti-diuretic hormone, and increased production of urine temporarily, particularly during the sleep. Both of these factors can increase the volume of urine, and consequently make the urine control more difficult and finally lead to the nocturnal enuresis ( 3 , 7 ). As far as we are concerned, there is no internal research concerning the impact of breathing exercises on the nocturnal enuresis in children. Nevertheless, Crouch et al. have shown that in subjects with the breathing disorders, the pulmonary rehabilitation programs including breathing exercises, endurance activities, upper and lower extremities exercises like purse lip breathing and diaphragmatic breathing, improve ventilation and in turn, have caused the adequate exchange of air pattern ( 19 ). Ghahri Sarabi et al. have also shown that in patients with the breathing disorders, breathing exercises increase the lung functional indices ( 27 ). In addition, another study has shown that in patients with the respiratory chronic diseases, pulmonary rehabilitation and breathing exercises increase the volume of oxygen consumption ( 20 ). The respiratory disorders cause ineffective breathing habits and shallow breathing. This chronic shallow breathing leads to the weakening of the diaphragm muscle and inter-costal muscles ( 8 , 19 ). In conclusion; these findings suggest that the breathing exercises may reduce the nocturnal enuresis in the children with the sleep-disordered breathing. The clinical implications of these findings should be verified in the future longitudinal studies.\n\nQuestion: Compared to no breathing exercises what was the result of breathing exercises were performed for 45 minutes, and were pursued for four weeks in the morning following and prior to sleeping on PaCO2 and Respiratory rates ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1188	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The evaluation of effects two different doses of hydrocortisone on the intensity of perioperative shivering in elective surgery under spinal anesthesia: A double-blind randomized controlled trial study\n\n ABSTRACT.BACKGROUND:\nPost- and intra-operative shivering is one of the most complications of spinal anesthesia so recommend a suitable drug with at least complications for prevention and control of postoperative shivering. This current study aimed to compare the preventive effect of hydrocortisone on intra- and post-operative shivering in patients undergoing surgery with spinal anesthesia.\n\nABSTRACT.MATERIALS AND METHODS:\nIn a clinical trial study, ninety patients who candidate for surgery with spinal anesthesia were selected and randomly divided into three groups. The first and second groups were received 1 mg/kg and 2 mg/kg hydrocortisone, respectively, and the third group was received normal saline, and postoperative shivering was compared between the three groups.\n\nABSTRACT.RESULTS:\nThe investigation of the incidence of inter- and post-operative shivering in patients in the three groups revealed that within the study period, 31 patients suffered from shivering among which 9, 5, and 17 cases were in 1 mg/kg hydrocortisone group, 2 mg/kg hydrocortisone group, and placebo group, respectively, and according to the Chi-square test, the difference among the three groups was significant (P = 0.004).\n\nABSTRACT.CONCLUSION:\nAccording to the obtained results, the overall conclusion of the study is that using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of intra- and post-operative shivering with spinal anesthesia.\n\nBODY.INTRODUCTION:\nThe reactions of the immune system to temperature loss include activities of skin vasomotor, thermogenesis, sweating, and shivering, which is indeed the last immune mechanism, is produced in associated with muscular activities with a frequency of 4–8 Hz, and reinforces the temperature metabolism to 600% compared to the base level.[123456] Some processes can lead to central hypothermia. General and regional anesthesia are the same and in both the distribution of heat is from the center to the initial process environment that in spinal and epidural, the process does not reach to the balance because the environmental vasoconstriction is lost and shivering and low temperature are produced by a small volume of muscles above the block level.[78] Shivering occurs in 50% of patients with the core temperature of 35.5°C and in 90% of cases with the core temperature of 34.5°C.[9] Postoperative shivering is a common complication of spinal anesthesia which has different incidence in various studies and has been expressed up to 40–56.7% depending on the type and consumed drug.[1011] To treatment and prevent postoperative shivering, different drugs can be used that among from opioid drugs, pethidine, fentanyl, and tramadol and out of nonopioid drugs, dexamethasone, ondansetron, clonidine, pentazocine, ketamine, and magnesium sulfate can be mentioned.[7] Hydrocortisone is corticosteroids similar to the natural hormone produced by the adrenal gland that causes to remove inflammation (sweating, heat, redness, and pain) and its intravenous injection controls postoperative shivering with general anesthesia. The mechanism of hydrocortisone effect is applied through anti-inflammatory mechanism, core temperature gradient, and skin.[11] Since it is tried to recommend a suitable drug with at least side complications for the prevention and control of postoperative shivering, most conducted studies emphasize on the treatment of shivering, and prophylaxis has been studied less; on the other hand, until now, such study has not been conducted on people with spinal anesthesia and given the prevalence and increase of surgeries with spinal anesthesia, the current study aimed to compare the preventive effect of hydrocortisone on the incidence and intensity of shivering in patients undergoing surgery with spinal anesthesia.\n\nBODY.MATERIALS AND METHODS:\nThis is a randomized, double-blind clinical trial study conducted in an educational hospital (Kashani Hospital) of Isfahan University of Medical Sciences in Isfahan, Iran on 2013–2014. Patients were selected from those who were referred for elective orthopedic operation. Inclusion criteria were the age range of 18–60-year-old, patients undergoing lower extremity orthopedic operation with spinal anesthesia (knee arthroplasty, hip arthroplasty, femoral fracture...) American Society of Anesthesiologists physical status I–II,[2] no having hypothyroidism, hyperthyroidism, cardiopulmonary diseases, psychological disorders, no alcohol and drugs, lack of using vasodilator or drugs affecting the body's temperature settings, and patient's consent to participate in the study. It was also decided that patients requiring blood transfusions during operation, with the base temperature more than 38°C and <36°C or change in the techniques of anesthesia were excluded from the study. We assumed the incidence of shivering in the case and control group 10% and 40%, respectively, due to previous studies[56] with respect to α =0.05 and β =0.2. We calculated 29 patients in each group as the sample size. The method was in a way that after the approval of proposal and adoption of consent of Medical Ethics Committee, ninety patients with inclusion criteria were selected and divided into three 30-case equal groups by using random allocation software. Exactly, 1 mg/kg hydrocortisone + 2 cc normal saline, 2 mg/kg hydrocortisone + 2 cc normal saline, and the same normal saline (2 cc) were injected to patients in M, P, and C (control) groups, respectively. The volume of each syringe was maximally 2 cc. The syringe was similar with respect to the shape and color. The study drugs were administered 10 min before spinal anesthesia. Fluid therapy and anesthesia method were the same in all three groups. All patients were NPO for 8 h and during this time, the fluid therapy was done according to 4-2-1 formula of serum (4 ml/kg/h for the first 10 kg of body weight, 2 ml/kg/h for the second 10 kg of body weight, and 1 ml/kg/h for the third 10 kg of body weight) and then intravenous midazolam 0.05 mg/kg was injected to all patients 5 min before the onset of anesthesia. Before the onset of anesthesia, 10 cc/kg of Ringer Lactate was injected to all patients within 30 min, and patients were routinely monitored including pulse oximetry, automatic control blood pressure, central and peripheral temperature, and 3-lead electrocardiogram. Oxygen was given to the patients via a face mask as 5 l/min until the end of the operation. Spinal anesthesia was performed at L4–L5 or L3–L4 of the spinal needle of 24-gauge, midline, and at sitting position. After leaving transparent and cerebrospinal fluid, 2.5 cc bupivacaine of 0.5% was injected within 10 s for the anesthesia. Then, the patient was immediately placed at supine position and the patient's head was put 15–20°C above the horizon and no analgesic drug was injected into the patient. The level of sensory block was determined using bilateral pin-prick test in midclavicular line. When the level of block reached to the desired level, the lower limb operation was started. The temperature of the operating room had been maintained at 21–22° and nonoperative parts were covered by a layer of cloth. After the operation, the whole parts of the body were covered by a layer of cotton blanket and then, the patients were transferred to the recovery room. The temperature of recovery room was similar for all patients, and no heating device was individually used for patients. The baseline level of the central and peripheral temperatures was measured. Moreover, immediately before anesthesia (on operating table), immediately after the anesthesia, 5 min after anesthesia, before and after drug injection, every 10 min during the operation, at the onset of entrance to the recovery room, and after recovery at 10, 20, 30, 40, 50, and 60 min, central and peripheral temperatures were measured by tympanic thermometer (OMRON Medizintechnik GmbH, Mannheim, Germany) and an axillary thermometer (BMEcenter.ir, Iran). If the peripheral temperature was below 36°C, hypothermia would be considered. In hypothermic patients, if they had shivering with grade = 4. Meperidine 0.4 mg/kg was administered. To ensure that the study was double-blinded (both patients and physician who recorded the data), drugs were encoded by an operating room staff. All patients received postoperative routine nursing care and in all cases, basic rate of parameters including blood pressure, respiratory rate, heart rate, shivering score (0, no shivering; 1, piloerection or peripheral vasoconstriction but no visible shivering; 2, muscular activity in only one muscle group; 3, muscular activity in more than one muscle group but not generalized; and 4, shivering involving the whole body), pain score, drowsiness score, and vomiting was recorded. The incidence and intensity of shivering was evaluated during intra- and post-operative periods. Hypotension (low systolic pressure below 100 mmHg or 25% reduction in systolic blood pressure compared to patients' baseline pressure) was treated by intravenous Ringer lactate serum and 5 mg intravenous ephedrine. If the heart rate drops below 55 rates, the patients would receive 0.01 mg intravenous atropine per kg of body weight and if necessary, it would be repeated up to a maximum dose of 0.04 mg per kg of body weight. You should declare that as the ephedrine and atropine could alter the body temperature these nausea and vomiting were treated by 10 mg intravenous metoclopramide. All the received drugs, the number of frequency, and their dose were recorded. If patients had shivering Grade 4, meperidine 0.4 mg/kg was administered. The degree of sedation was evaluated as 1, fully awake and oriented; 2, drowsy; 3, eyes closed but rousable to command; 4, eyes closed but rousable to mild physical stimulation; and 5, eyes closed but unrousable to mild physical stimulation. The study data were entered into the computer after collecting and were analyzed using SPSS software version 20. Chi-square test (for comparison of qualitative data between groups), one-way analysis of variance (ANOVA) (for comparison of quantitative date between groups), and repeated measure ANOVA (for comparison of trend of quantities date between groups) with repeated observations, and median test were run to analyze the data.\n\nBODY.RESULTS:\nIn this study, ninety patients undergoing surgery with spinal anesthesia were investigated and assessed that during the study, no patient excluded from the study due to the incidence of unwanted complications such as hemodynamic and in the anesthesia method and all ninety patients were present in the study until the end of the study. In Table 1, the distribution of demographic and general variables of patients in the three groups has been shown. Table 1 Distribution of demographic and general variables in three study groups The investigation of the incidence of shivering in patients in the three groups revealed that within the study period, 31 patients suffered from shivering among which 9, 5, and 17 cases were in the 1 mg/kg hydrocortisone group, 2 mg/kg hydrocortisone group, and placebo group, respectively, and according to the Chi-square test, the difference among the three groups was significant (P = 0.004). Moreover, the intensity of shivering had no significant difference among the three groups (P = 0.046). The distribution of the frequency of the incidence and intensity of shivering in the three groups are given in Table 2. Comparing the incidence and intensity of shivering in binary groups indicated that the two groups of hydrocortisone of 1 mg/kg and 2 mg/kg had no significant difference in terms of the incidence and intensity of shivering (P = 0.23 and P = 0.2, respectively), while the incidence and intensity of shivering had a significant difference between the two groups of hydrocortisone of 1 mg/kg and placebo group (P = 0.039 and P = 0.018, respectively). Moreover, the incidence and intensity of shivering had a significant difference between the two groups of hydrocortisone of 2 mg/kg and placebo group (P = 0.0001 and P = 0.001, respectively). The score of sedation in patients in the three groups had no significant difference from the onset of the induction of anesthesia to 60 min of recovery in none of the studied periods. Within the study period, no patient suffered from drug allergy, whereas out of hydrocortisone group 2 mg/kg, one patient suffered from bradycardia and one patient suffered from hypotension. One of the hydrocortisone 1 mg/kg group and 1 case of hydrocortisone 2 mg/kg group suffered from postoperative nausea and vomiting, while no significant difference was observed among the three groups (P = 0.6). Table 2 Distribution of the frequency of the incidence and intensity of shivering in the three groups Figures 1 and 2 shown the mean central and peripheral temperatures in the three studied groups from the onset of the operation until 60 min of recovery. According to the one-way ANOVA test, the mean central and peripheral temperatures had no significant difference between the three groups in any of the study periods. Furthermore, repeated measure ANOVA indicated that the process of changes in the central and peripheral temperatures had no significant difference among the three groups (P = 0.64 and P = 0.31, respectively). The lowest core and peripheral temperatures were 35.75°C and 35.70°C, respectively, which occurred 90 min after spinal anesthesia. Figures 3 and 4 shown the Mean blood pressure from 0 to 60 min recovery in the three groups (P = 0.82) and Mean heart rate from 0 to 60 min recovery in the three groups (P = 0.77). Repeated measure ANOVA indicated that had no significant difference among the three groups (P = 0.82 and P = 0.77). Figure 1Mean central temperature from 0 to 60 min recovery in the three groups (P = 0.64) Figure 2Mean peripheral temperature from 0 to 60 min recovery in the three groups (P = 0.31) Figure 3Mean blood pressure from 0 to 60 min recovery in the three groups (P = 0.82) Figure 4Mean heart rate from 0 to 60 min recovery in the three groups (P = 0.77)\n\nBODY.DISCUSSION:\nShivering is the involuntary movements of one or several muscle groups and generally occurs in the initial phase of recovery after anesthesia. The incidence of this condition varies between 6.3% and 66% depending on the type and duration of operation, anesthesia technique, and patient's age and gender[12345678910] and has minimum incidence to 40% in patients operation with spinal anesthesia.[1011] With regard to the incidence and clinical significance, shivering has been known as the sixth major problem among from 33 clinical cases with the low rate of morbidity in clinical anesthesiology.[12] Of postoperative complications, the increase in oxygen consumption at the rate of 200–500%, production of CO2, heart rate and stroke volume, and blood pressure can be pointed out that their suppression reduces the metabolic need and myocardial function.[131415161718] Other complications include the increase of intraocular pressure and intracranial pressure, creation of problem in monitoring the patient, and interference with the surgical cares, especially in cases requiring immobilization, for example, secular or nerve anastomosis.[141516] According to the results of our study, three studied groups had no significant difference in terms of demographic variables and operation features such as duration of operation and anesthesia and sensory block level and no confounding effect of the above-mentioned factors was observed on the incidence and intensity of shivering and therefore it may pertain to the fact that the difference in the incidence of postoperative shivering is related to the type and rate of preventive consuming drug. According to the results of our study, the incidence of shivering in the group receiving hydrocortisone including a dose of 1 mg/kg or 2 mg/kg was considerably and significantly less than the control group. On the other hand, patients receiving hydrocortisone had lower shivering; however, no significant difference was observed between the two doses of the drug. A number of pharmaceutical interventions for the treatment and prophylaxis of shivering including clonidine, ketamine, doxapram, tramadol, pethidine, and other opioids have so far been examined (14, 17, and 18). In the study by Pawar et al., in 2011, the effectiveness of hydrocortisone for the prevention of shivering was approved so that the incidence of shivering was 32% in patients receiving hydrocortisone and 82% in the control group.[18] In their study, Yousef and Johnson showed that using hydrocortisone as a preventive drug reduced the incidence of hypothermia; consequently, it reduced the incidence of shivering in patients undergoing an operation.[19] Therefore, according to the obtained results, the overall conclusion of the study is that using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of shivering with spinal anesthesia. However, because limitations of our study such as small sample size, to highly ensure the effect of dose-response of the drug, further studies are recommended.\n\nBODY.CONCLUSION:\nAccording to this study using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of intra- and post-operative shivering with spinal anesthesia.\n\nBODY.CONCLUSION.FINANCIAL SUPPORT AND SPONSORSHIP:\nAnesthesiology and Critical Care Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.\n\nBODY.CONCLUSION.CONFLICTS OF INTEREST:\nThe authors have no conflicts of interest.\n\nBODY.AUTHORS’ CONTRIBUTION:\nMRS has planned the study and finalized it; FK, AH, MN, HS, and MRS did the statistical analysis and prepared the first version of the manuscript for publish. All authors read and approved the final manuscript.\n\nQuestion: Compared to received normal saline what was the result of received 1 mg/kg and 2 mg/kg hydrocortisone on incidence and intensity of shivering?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1190	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on mean daily number of moderate to severe hot flushes at week 4?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1066	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The efficacy of duloxetine: A comprehensive summary of results from MMRM and LOCF_ANCOVA in eight clinical trials\n\n ABSTRACT.BACKGROUND:\nA mixed-effects model repeated measures approach (MMRM) was specified as the primary analysis in the Phase III clinical trials of duloxetine for the treatment of major depressive disorder (MDD). Analysis of covariance using the last observation carried forward approach to impute missing values (LOCF_ANCOVA) was specified as a secondary analysis. Previous research has shown that MMRM and LOCF_ANCOVA yield identical endpoint results when no data are missing, while MMRM is more robust to biases from missing data and thereby provides superior control of Type I and Type II error compared with LOCF_ANCOVA. We compared results from MMRM and LOCF_ANCOVA analyses across eight clinical trials of duloxetine in order to investigate how the choice of primary analysis may influence interpretations of efficacy.\n\nABSTRACT.METHODS:\nResults were obtained from the eight acute-phase clinical trials that formed the basis of duloxetine's New Drug Application for the treatment of MDD. All 202 mean change analyses from the 20 rating scale total scores and subscales specified a priori in the various protocols were included in the comparisons.\n\nABSTRACT.RESULTS:\nIn 166/202 comparisons (82.2%), MMRM and LOCF_ANCOVA agreed with regard to the statistical significance of the differences between duloxetine and placebo. In 25/202 cases (12.4%), MMRM yielded a significant difference when LOCF_ANCOVA did not, while in 11/202 cases (5.4%), LOCF_ANCOVA produced a significant difference when MMRM did not. In 110/202 comparisons (54.4%) the p-value from MMRM was lower than that from LOCF_ANCOVA, while in 69/202 comparisons (34.2%), the p-value from LOCF_ANCOVA was lower than that from MMRM. In the remaining 23 comparisons (11.4%), the p-values from LOCF_ANCOVA and MMRM were equal when rounded to the 3rd decimal place (usually as a result of both p-values being < .001). For the HAMD17 total score, the primary outcome in all studies, MMRM yielded 9/12 (75%) significant contrasts, compared with 6/12 (50%) for LOCF_ANCOVA. The expected success rate was 80%.\n\nABSTRACT.CONCLUSIONS:\nImportant differences exist between MMRM and LOCF_ANCOVA. Empirical research has clearly demonstrated the theoretical advantages of MMRM over LOCF_ANCOVA. However, interpretations regarding the efficacy of duloxetine in MDD were unaffected by the choice of analytical technique.\n\nBODY.BACKGROUND:\nTreatment effects are often evaluated by comparing change over time in outcome measures. However, valid analyses of longitudinal data can be problematic, particularly if some data are missing for reasons related to the outcome measure [1,2]. Since the problem of missing data is almost ever-present in clinical trials, numerous methods for handling missingness have been proposed, examined, and implemented [3]. A common method of analyzing clinical trial data is to use analysis of variance or analysis of covariance (ANOVA or ANCOVA) with missing data imputed by the last observation carried forward approach (LOCF_ANCOVA). The popularity of LOCF_ANCOVA may be due to its simplicity, and also the belief that violations of the restrictive assumptions inherent to LOCF_ANCOVA lead to a conservative analysis [4]. Considerable advances in statistical methodology, and in our ability to implement these methods, have been made in recent years. Thus, methods that require less restrictive assumptions than LOCF_ANCOVA are now readily implemented. For example, likelihood-based repeated measures approaches have a number of theoretical and practical advantages for analysis of longitudinal data with dropout [4]. One such method, termed MMRM (Mixed Model Repeated Measures [5]), has been studied extensively in the context of neuropsychiatric clinical trials [6-9]. In these studies, MMRM was found to be more robust to biases from missing data than LOCF_ANCOVA, and thereby provided superior control of Type I and Type II errors. The LOCF_ANCOVA method was shown to underestimate treatment group differences in some scenarios, while overestimating differences in others. When no data were missing, the two methods yielded identical results. The MMRM approach was specified as the primary analysis in the Phase III clinical trials of duloxetine for the treatment of major depressive disorder (MDD), while LOCF_ANCOVA was specified as a secondary analysis. In the present investigation, we provide a comprehensive summary of results from MMRM and LOCF_ANCOVA in the eight acute-phase clinical trials that formed the basis for duloxetine's New Drug Application (NDA) for MDD. The primary objective of this investigation was to determine whether differences in results between MMRM and LOCF_ANCOVA influenced conclusions regarding the efficacy of duloxetine.\n\nBODY.METHODS.DATA:\nThe data source for this investigation was the eight acute-phase clinical trials in which duloxetine was compared with placebo in the treatment of MDD. Relevant details of these studies are highlighted in Table 1. Table 1 Summary of studies included in the comparisons between MMRM and LOCF_ANCOVA Study Treatment Duration Drug Number of Patients Drug Dose & Design 1 9 weeks Placebo 122 - Duloxetine 123 60 mg/d (QD) 2 9 weeks Placebo 139 - Duloxetine 128 60 mg/d (QD) 3 8 weeks Placebo 70 - Duloxetine 70 40–120 mg/d (20 mg-60 mg BID) Fluoxetine 33 20 mg/d (QD) 4 8 weeks Placebo 75 - Duloxetine 82 40–120 mg/d (20 mg-60 mg BID) Fluoxetine 37 20 mg/d (QD) 5 8 weeks Placebo 90 - Duloxetine 91 40 mg/d (20 mg BID) Duloxetine 84 80 mg/d (40 mg BID) Paroxetine 89 20 mg/d (QD) 6 8 weeks Placebo 89 - Duloxetine 86 40 mg/d (20 mg BID) Duloxetine 91 80 mg/d (40 mg BID) Paroxetine 87 20 mg/d (QD) 7 8 weeks Placebo 93 - Duloxetine 95 80 mg/d (40 mg BID) Duloxetine 93 120 mg/d (60 mg BID) Paroxetine 86 20 mg/d (QD) 8 8 weeks Placebo 99 - Duloxetine 93 80 mg/d (40 mg BID) Duloxetine 103 120 mg/d (60 mg BID) Paroxetine 97 20 mg/d (QD) Results are summarized from all rating scale total scores, subscales, and global assessments that were specified a priori in the various protocols to be analyzed for mean change from baseline to endpoint, and were collected at more than one postbaseline time point (Table 2). Efficacy measures that were assessed only at baseline and endpoint were not included in this summary because repeated measures analyses were not possible for these outcomes. Thus, the present investigation included every rating scale total score and subscale from every clinical trial relevant to duloxetine's NDA for an indication in major depression. In total, 20 efficacy and health outcome variables were included in the summary of MMRM and LOCF_ANCOVA. Some of the eight trials included multiple dose arms; therefore, some outcomes were assessed in as many as 12 comparisons with placebo. Table 2 Outcomes included in the summary of results. 17-item Hamilton Rating Scale for Depression (HAMD 17 ) Total score [24] Core subscale (items 1, 2, 3, 7, 8) (not published) Maier subscale (items 1, 2, 7, 8, 9, 10) [25] Anxiety/Somatization subscale (items 10, 11, 12, 13, 15, 17) [26] Retardation subscale (items 1, 7, 8, 14) [27] Sleep subscale (items 4, 5, 6) [27] Montgomery-Asberg Depression Rating scale [28] Hamilton Anxiety Rating Scale total score [29] Clinical Global Impression of Severity [26] Patient Global Impression of Improvement [26] Visual Analog Scale for pain [30] Overall pain severity Headaches Back pain Shoulder pain Time in pain while awake Interference with daily activities Somatic Symptom Inventory [31] 26 Item total score 28 Item total score (includes 2 additional questions on painful physical symptoms) Quality of Life in Depression Scale total score [32] Comparisons of MMRM and LOCF_ANCOVA focused on contrasts between duloxetine and placebo. However, six of the studies also included known effective antidepressants approved for marketing in the United States and other countries. Contrasts between duloxetine and the active comparators are not included in this summary since these results may draw attention to the drug versus drug results and detract from the primary focus of comparing MMRM with LOCF_ANCOVA.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThis summary makes no attempt to provide formal statistical comparisons of results from MMRM and LOCF_ANCOVA. Previous research has demonstrated conclusively that in the absence of missing data the two methods yield identical endpoint contrasts, while differences do exist in the presence of subject dropout [6-9]. Furthermore, formal statistical comparisons are typically applied to random samples obtained from larger populations in order to assess the uncertainty associated with the sampling. However, the eight studies included in this summary are not a sample, but rather represent all of the acute-phase, double-blind, placebo-controlled trials of duloxetine. Thus, there is no uncertainty associated with sampling. Consequently, results from the two methods need only be summarized in order to assess how differences between the methods may influence overall conclusions regarding the efficacy of duloxetine. Three overall summary measures were used to compare results from the two analytic techniques: 1) With regard to statistical significance of the difference between duloxetine and placebo, the proportion of outcomes showing agreement between MMRM and LOCF_ANCOVA was compared with the proportion of outcomes for which MMRM and LOCF_ANCOVA yielded disparate results; 2) The proportion of outcomes for which MMRM yielded the lowest p-value was compared with the corresponding proportion for LOCF_ANCOVA; 3) The number of outcomes for which \"substantial evidence of efficacy\" was demonstrated. In regulatory settings, the criterion for substantial evidence of efficacy is frequently the demonstration of a statistically significant advantage over placebo in two or more studies. This criterion was utilized here to define substantial evidence of efficacy for a particular outcome. The frequency of lower p-values provides a \"fine-tuned\" measure of sensitivity of the two analytic methods. However, in certain cases such an assessment may actually be misleading. For example, to distinguish between p= .800 and p = .810, or between p =. 002 and p =. 003, implies that the methods yielded different results when in fact the similarities far outweigh the differences. Hence, it is equally appropriate to simply categorize based upon the presence or absence of a significant difference. Furthermore, given the large number of outcomes assessed across the eight studies, it would not be surprising to see the two methods disagree with regard to statistical significance on at least a small number of outcomes. Therefore, perhaps the most clinically meaningful summary measure is the number of outcomes for which substantial evidence of efficacy was demonstrated. Three outcomes were selected for more detailed presentation of results: the 17-item Hamilton Rating Scale for Depression (HAMD17) total score, the HAMD17 Maier subscale, and the Visual Analog Scale (VAS) for overall pain severity. The HAMD17 total score was an obvious choice as it was the primary outcome in all studies. The other outcomes were selected since they are frequently focal points in manuscripts and presentations regarding duloxetine's efficacy. Finally, we provide case studies to help explain how and why results from MMRM and LOCF_ANCOVA may differ. MMRM and LOCF_ANCOVA analyses were specified in the Phase III duloxetine protocols as follows. In LOCF_ANCOVA analyses, change from baseline to the last observation was the dependent variable. Treatment and investigative site were included as categorical independent variables, and baseline severity was included as a covariate. In MMRM analyses, change from baseline to all postbaseline times was the dependent variable. Independent variables included the fixed, categorical effects of investigative site, treatment, time, and the treatment-by-time interaction, along with the continuous covariates of baseline severity and the baseline severity by time interaction. Parameters were estimated using Restricted Maximum Likelihood with the Newton-Raphson algorithm. The protocols specified an algorithm for choosing the best fitting covariance structure. In all cases an unstructured matrix provided the best fit. Hence, within-patient errors were modeled using an unstructured covariance matrix.\n\nBODY.RESULTS:\nThe protocols for the eight studies in the duloxetine NDA specified a priori a total of 202 mean change analyses for the 20 rating scale total scores or subscales. The frequency of significant outcomes and the frequency of higher/lower p-values for each analytic technique are summarized in Table 3. MMRM and LOCF_ANCOVA agreed with regard to substantial evidence of efficacy for 18 of the 20 outcomes, with each analysis yielding substantial evidence for 15 outcomes. That is, MMRM and LOCF_ANCOVA both found substantial evidence of efficacy for 14 outcomes; both methods did not find substantial evidence for four outcomes; and each method found substantial evidence when the other did not for one outcome (Table 3). Table 3 Summary of results from MMRM and LOCF_ANCOVA in duloxetine clinical trials. Outcome Frequency of significant outcomes 1 MMRM LOCF_ANCOVA P-value lower with MMRM LOCF_ANCOVA Outcome significant with MMRM but not LOCF_ANCOVA Outcome significant with LOCF_ANCOVA but not MMRM HAMD 17 Total score 9\\12 6\\12 9\\12 1\\12 3\\12 0\\12 Core subscale 9\\12 8\\12 5\\12 3\\12 2\\12 1\\12 Maier subscale 10\\12 9\\12 6\\12 2\\12 2\\12 1\\12 Anxiety subscale 6\\12 5\\12 7\\12 3\\12 2\\12 1\\12 Retardation subscale 8\\12 6\\12 6\\12 3\\12 4\\12 2\\12 Sleep subscale 1\\12 1\\12 10\\12 2\\12 0\\12 0\\12 MADRS Total score 5\\10 3\\10 7\\10 2\\10 2\\10 0\\10 HAMA Total score 3\\10 3\\10 4\\10 5\\10 0\\10 0\\10 CGI-Severity 6\\12 6\\12 8\\12 2\\12 0\\12 0\\12 CGI-Improvement 1\\2 1\\2 2\\2 0\\2 0\\2 0\\2 PGI-Improvement 9\\12 7\\12 8\\12 2\\12 2\\12 0\\12 Somatic Symptom Inventory 26-item Average score 2\\10 2\\10 7\\10 3\\10 0\\10 0\\10 28-item Average score 3\\10 2\\10 7\\10 3\\10 1\\10 0\\10 VAS Pain Severity Overall pain 3\\10 4\\10 2\\10 8\\10 1\\10 2\\10 Headaches 1\\10 0\\10 5\\10 5\\10 1\\10 0\\10 Back pain 2\\10 2\\10 6\\10 4\\10 1\\10 1\\10 Shoulder pain 2\\10 1\\10 3\\10 6\\10 2\\10 1\\10 Daily activities 1\\10 0\\10 2\\10 8\\10 1\\10 0\\10 Pain while awake 2\\10 2\\10 5\\10 5\\10 1\\10 1\\10 QLDS Total score 1\\4 2/4 1\\4 2\\4 0\\4 1\\4 Totals 84\\202 70\\202 110\\202 69\\202 25\\202 11\\202 1. Some of the eight trials included more than one dose arm. Therefore, an individual outcome could be assessed in as many as 12 comparisons with placebo. In 166/202 outcomes (82.2%), MMRM and LOCF_ANCOVA agreed with regard to the statistical significance of the difference between duloxetine and placebo. In 25 cases (12.4%) MMRM yielded a significant difference whereas LOCF_ANCOVA did not, while in 11 cases (5.4%) LOCF_ANCOVA yielded a significant difference when MMRM did not. Both methods tended to yield significance more frequently in depression rating scales and subscales than in outcomes related to somatic and painful physical symptoms. The studies were generally underpowered for these secondary somatic and pain outcomes owing to the greater variance in changes score for these outcomes. For example, the variance in VAS overall pain severity was approximately nine-fold greater than the variance in HAMD17 total scores, leading to a three-fold greater standard error. In 110 of the 202 outcomes (54.4%) the p-value from MMRM was lower than that from LOCF_ANCOVA, while in 69 cases (34.2%) the p-value from LOCF_ANCOVA was lower than that from MMRM. In the remaining 23 cases (11.4%) the p-values from LOCF_ANCOVA and MMRM were equal when rounded to the 3rd decimal place (usually as a result of both p-values being < .001). More detailed results from the three focus outcomes (HAMD17 total score, HAMD17 Maier subscale, and VAS overall pain) are presented in Table 4. In the case of the HAMD17 total score, the advantage of duloxetine over placebo in mean change from baseline to endpoint from MMRM analyses was greater than the corresponding advantage from LOCF_ANCOVA in 9/12 comparisons (Table 4). In 9/12 comparisons the p-value from MMRM was lower than that from LOCF_ANCOVA, while LOCF_ANCOVA yielded a smaller p-value in one case, and p-values were identical in the two remaining cases. In 3/12 comparisons, MMRM yielded a significant difference when LOCF_ANCOVA did not, but in no instance did LOCF_ANCOVA produce a significant difference when MMRM did not. When averaging results across all eight studies, the advantage of duloxetine over placebo in HAMD17 total score was 2.4 from MMRM analyses compared with 2.0 from LOCF_ANCOVA. Thus, the advantage of duloxetine over placebo, based on LOCF_ANCOVA results, was approximately 83% as large as the advantage from MMRM. Table 4 MMRM and LOCF_ANCOVA analysis of three focus outcomes from duloxetine clinical trials. Study 1 Study 2 Study 3 Study 4 Study 5 Study 6 Study 7 Study 8 Dose 60 mg QD 60 mg QD 60 mg BID 60 mg BID 20 mg BID 40 mg BID 20 mg BID 40 mg BID 40 mg BID 60 mg BID 40 mg BID 60 mg BID Δ p Δ p Δ p Δ p Δ p Δ p Δ p Δ p Δ p Δ p Δ p Δ p HAMD 17 Total Score MMRM 4.9 < .001 2.2 .024 3.1 .009 0.9 .415 1.4 .143 1.5 .116 2.4 .034 3.6 .002 2.2 .001 3.3 < .001 1.4 .045 1.6 .014 LOCF 3.8 < .001 1.7 .048 2.1 .066 0.4 .681 1.2 .222 1.5 .138 2.4 .022 3.1 .003 2.2 .007 3.0 < .001 0.9 .253 1.5 .054 HAMD 17 Maier Subscale MMRM 2.8 < .001 1.6 .003 2.0 .005 0.7 .282 1.2 .037 1.4 .012 1.1 .068 1.7 .005 1.4 < .001 2.0 < .001 0.9 .022 1.2 .002 LOCF 2.3 < .001 1.4 .007 1.0 .030 0.6 .481 1.0 .058 1.3 .012 1.5 .028 1.8 .004 1.4 .001 1.9 < .001 0.7 .090 1.0 .014 VAS Overall Pain Severity MMRM 5.9 .055 4.4 .135 NA NA 0.3 .931 1.2 .731 1.0 .771 7.4 .035 5.5 .085 6.3 .050 5.6 .044 1.3 .625 LOCF 6.9 .019 5.2 .037 NA NA 3.5 .573 3.5 .647 3.2 .710 7.1 .048 6.1 .063 5.6 .086 7.8 .014 5.5 .066 NA = not assessed Similar results were obtained for the Maier subscale. Thus, the advantage of duloxetine over placebo in mean change from baseline to endpoint from MMRM was greater than that from LOCF_ANCOVA in 9/12 comparisons (Table 4). The p-value from MMRM was lower than that from LOCF_ANCOVA in 6/12 comparisons, while LOCF_ANCOVA produced a lower p-value in 2 cases, and p-values were identical in the remaining four cases. In 2/12 comparisons MMRM yielded a significant difference when LOCF_ANCOVA did not, while there was one instance in which LOCF_ANCOVA yielded a significant difference when MMRM did not. Averaged over all eight studies, the advantage of duloxetine over placebo in mean Maier subscale score was 1.5 from MMRM analyses compared with 1.3 from LOCF_ANCOVA. Thus, the advantage of duloxetine over placebo based on LOCF_ANCOVA results was approximately 87% as large as the advantage from MMRM. For VAS overall pain severity, the advantage of duloxetine over placebo from MMRM analyses was greater than the corresponding advantage from LOCF_ANCOVA in 2/10 comparisons (Table 4). The p-value from MMRM was lower than that from LOCF_ANCOVA in 2/10 comparisons, while in the remaining 8 comparisons the p-value from LOCF_ANCOVA was lower than that from MMRM. In 1 comparison MMRM yielded a significant difference when LOCF_ANCOVA did not, while in 2 comparisons LOCF_ANCOVA yielded a significant difference when MMRM did not. Over all eight studies, the average advantage of duloxetine over placebo in VAS overall pain severity was 3.9 from MMRM analyses compared with 5.4 from LOCF_ANCOVA. Thus, the advantage of duloxetine based on LOCF_ANCOVA results was approximately 138% as large as the advantage from MMRM.\n\nBODY.RESULTS.CASE STUDIES:\nMean changes in HAMD17 total score and VAS overall pain severity from two studies (Studies 1 and 2) are used to further illustrate MMRM and LOCF_ANCOVA (analysis of variance with missing data imputed via last observation carried forward) results. Results from these studies were originally reported by Detke et al [10,11]. In both studies the advantage of duloxetine over placebo in HAMD17 total score tended to increase over time whereas duloxetine's advantage in VAS overall pain was greatest at intermediate visits (Tables 5 and 6). Table 5 MMRM and LOCF_ANCOVA analyses of HAMD 17 total score in Studies 1 and 2. STUDY 1 STUDY 2 MMRM THERAPY Week N Mean change Std.error p-value N Mean change Std.error p-value DULOX 1 121 -2.89 0.36 .435 123 -2.89 0.38 .601 PLACEBO 1 115 -2.50 0.37 136 -2.64 0.36 DULOX 2 112 -5.72 0.49 < .001 109 -5.54 0.48 .071 PLACEBO 2 110 -3.39 0.50 129 -4.43 0.45 DULOX 3 105 -7.37 0.53 < .001 108 -6.82 0.55 .287 PLACEBO 3 103 -4.58 0.54 122 -6.06 0.52 DULOX 5 100 -8.76 0.60 < .001 98 -8.58 0.66 .116 PLACEBO 5 101 -5.74 0.60 111 -7.20 0.62 DULOX 7 91 -9.93 0.64 < .001 89 -10.14 0.69 .008 PLACEBO 7 93 -5.82 0.65 97 -7.69 0.65 DULOX 9 84 -10.91 0.70 < .001 81 -10.46 0.71 .024 PLACEBO 9 89 -6.05 0.69 90 -8.29 0.67 LOCF_ANCOVA DULOX LOCF_ANCOVA 121 -9.47 0.63 < .001 123 -8.75 0.71 .048 PLACEBO LOCF_ANCOVA 115 -5.67 0.66 136 -7.02 0.68 Table 6 MMRM and LOCF_ANCOVA analyses of VAS overall pain severity in Studies 1 and 2. STUDY 1 STUDY 2 MMRM THERAPY Week N Mean change Std.error p-value N Mean change Std.error p-value DULOX 1 120 -2.69 1.97 .181 121 -2.02 1.89 .157 PLACEBO 1 113 1.04 2.04 134 1.38 1.79 DULOX 2 113 -8.20 1.87 .003 108 -6.95 2.04 .003 PLACEBO 2 108 -0.42 1.93 127 0.91 1.90 DULOX 3 105 -10.46 1.95 .005 106 -9.81 1.90 < .001 PLACEBO 3 101 -2.56 2.01 119 -1.59 1.78 DULOX 5 99 -8.68 2.20 .028 95 -9.70 2.05 .011 PLACEBO 5 99 -1.85 2.24 108 -2.92 1.92 DULOX 7 91 -10.25 2.34 .016 87 -8.91 2.12 .254 PLACEBO 7 92 -2.26 2.38 94 -5.76 2.01 DULOX 9 83 -8.68 2.18 .055 80 -10.05 2.24 .135 PLACEBO 9 88 -2.80 2.20 88 -5.65 2.12 LOCF_ANCOVA DULOX LOCF_ANCOVA 121 -8.31 2.09 .019 121 -10.39 2.05 .037 PLACEBO LOCF_ANCOVA 114 -1.40 2.18 134 -5.22 1.94 In the case of the HAMD17 total score, advantages for duloxetine over placebo at endpoint (Week 9) from MMRM in Studies 1 and 2 were 4.86 (p < .001) and 2.17 (p = .024), respectively. The corresponding advantages from LOCF_ANCOVA were 3.80 (p < .001) and 1.73 (p = .048). Although the differences were significant for both methods in both studies, MMRM yielded treatment contrasts that were approximately 25% greater than LOCF_ANCOVA. For VAS overall pain, the advantage of duloxetine over placebo at endpoint from MMRM in Studies 1 and 2 were 5.88 (p = .055) and 4.40 (p = .135), respectively. The corresponding advantages from LOCF_ANCOVA were 6.91 (p = .019) and 5.17 (p = .037). In both studies, the endpoint differences were significant from LOCF_ANCOVA, but not from MMRM. The LOCF_ANCOVA treatment contrasts were approximately 15% greater than those from MMRM. Standard errors from LOCF_ANCOVA were approximately 5% smaller than the Week 9 standard errors from MMRM for both the HAMD17 total score and VAS overall pain.\n\nBODY.DISCUSSION:\nIn many areas of clinical research, the impact of missing data can be profound [2,12-14]. Traditional approaches to analyses of data from clinical trials with dropouts, such as LOCF_ANCOVA, have focused on ease of implementation and interpretation. However, simple methods rely upon assumptions that are often unrealistic. For example, LOCF_ANCOVA assumes that patient dropout is completely random, i.e. it is unrelated to the outcome being analyzed. Hence, in an analysis of efficacy data, LOCF_ANCOVA assumes that patients do not drop out due to lack of efficacy. The LOCF_ANCOVA approach also assumes that, for those patients who drop out, their observations would not have changed had they stayed in the trial. When these assumptions do not hold true, estimates of treatment effects and associated standard errors may be biased [2-4,6,7,15-17]. Considerable advances in statistical methodology, and in our ability to implement these methods, have been made in recent years. Methods such as MMRM, which require less restrictive assumptions regarding missing data, may now be easily implemented with standard software [4,5,18,19]. No universally superior approach to analysis of longitudinal data exists. However, a series of studies [6-9] demonstrated empirically what may have been anticipated from statistical theory – namely that the MMRM approach, while providing no guarantee of immunity from bias due to subject dropout, was a sensible analytic choice for many clinical trial scenarios. MMRM has repeatedly been shown to provide adequate control of Type I (false positive) and Type II (false negative) errors in a wide variety of situations modeled after neuropsychiatric clinical trials. In these head-to-head comparisons involving 456,000 data sets, the LOCF_ANCOVA approach did not perform as well as MMRM. We therefore specified MMRM as the primary analysis and LOCF_ANCOVA as a secondary analysis in the Phase III clinical trials of duloxetine in the treatment of MDD. Similar results regarding control of Type I and Type II error for LOCF_ANCOVA and mixed-effects model analyses have been obtained independently [16,20-22]. Furthermore, following an independent investigation of data from two placebo- and active-comparator controlled duloxetine trials, in which treatments were coded A, B, C, etc. to blind analysts to the treatment names, Molenberghs et al [4] concluded that MMRM analysis was a sensible choice for those data. The theoretical differences between MMRM and LOCF_ANCOVA have been summarized [5,18], established empirically [6-9], and proven mathematically [4]. However, we are unaware of any previous investigations of how these differences manifest themselves in efficacy assessments of a new medicinal product. The VAS pain results highlight a limitation of endpoint analyses of any type, namely that they provide only a snapshot view of the response profile. From LOCF_ANCOVA analysis, one can only conclude that drug was superior to placebo at endpoint. However, MMRM analysis reveals that drug had a significant effect early in the trials, but that advantage was somewhat transitory as the placebo group tended to \"catch up\" over time. In order to understand the response profile of a drug, the entire longitudinal profile should be considered [2]. From MMRM, the entire profile can be assessed from the same analysis that provided the primary result (the contrast at endpoint). In the duloxetine database, results from MMRM and LOCF_ANCOVA were in general agreement regarding substantial evidence of efficacy and frequency of significant differences. However, MMRM tended to be more sensitive to drug-placebo differences for outcomes related to overall depressive symptoms and core emotional symptoms of depression, with mean advantages over placebo that were 10% to 20% greater than LOCF_ANCOVA. However, MMRM did not universally increase duloxetine's advantage over placebo in comparison to results from LOCF_ANCOVA. For example, in somatic and painful physical symptom outcomes, results from LOCF_ANCOVA showed mean advantages over placebo that were approximately 40% greater than that from MMRM. Therefore, while the overall conclusions regarding the efficacy of duloxetine were unaffected by the choice of analytic method, this should not mask the important differences between MMRM and LOCF_ANCOVA. The advantages of MMRM and similar methods over LOCF_ANCOVA have been conclusively demonstrated in many studies and are evident in the duloxetine data. Khan et al [23] compiled a database from FDA summaries of efficacy for all antidepressants approved between 1985 and 2000. Less than half of the studies – which were analyzed using LOCF_ANCOVA as the primary analysis – found significant advantages for drug over placebo. These studies were generally anticipated to have at least 80% power and, if the analysis worked as expected, the success rate would be 80%. Therefore, LOCF_ANCOVA was less sensitive to the drug effects than anticipated. In the duloxetine database, MMRM yielded a 75% success rate for the primary outcome measure (HAMD17 total score), while LOCF_ANCOVA produced a 50% success rate, in comparison to the expected rate of 80%. While many factors may reduce the success rate in Phase III clinical trials, the use of a statistical method with known inflation of Type II error (false negative results) is an obvious suspect. An unduly high rate of false negative results could be especially problematic in early phases of drug development where only one or two chances exist to make the correct decision regarding the efficacy of a drug. It is noteworthy that one of the instances when MMMRM yielded a significant difference on the primary outcome (HAMD17 total score) when LOCF did not was in the Phase II study (Study 3). Also consider that across all therapeutic areas only about 50% of the molecules that enter Phase III testing receive regulatory approval. Many factors may reduce the success rate of Phase III development. However, the use in Phase II of a statistical method with known inflation of Type I error (false positive results) is an obvious suspect. Thus, the unexpectedly low success rate in Phase III is consistent with the conclusion that LOCF_ANCOVA inflates Type I error (as a result of an unduly high rate of false positive results in Phase II). Hence, results from the duloxetine NDA are consistent with research suggesting a move away from LOCF_ANCOVA and other simple analytic techniques to methods such as MMRM that are more robust to the biases from missing data.\n\nBODY.CONCLUSION:\nImportant differences exist between MMRM and LOCF_ANCOVA. Research has clearly demonstrated the advantages of MMRM over LOCF_ANCOVA. However, interpretations regarding the efficacy of duloxetine in MDD were unaffected by the choice of analytical technique.\n\nBODY.COMPETING INTERESTS:\nDrs. Mallinckrodt, Raskin, Wohlreich, Watkin, and Detke are employees of Eli Lilly and Company.\n\nBODY.AUTHOR'S CONTRIBUTIONS:\nCHM designed the statistical analyses, and participated in interpretation of data and drafting of the manuscript. JR, MMW, JGW, and MJD participated in interpretation of data and drafting of the manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\nQuestion: Compared to analysis of covariance (ANOVA or ANCOVA) with missing data imputed by the last observation carried forward approach (LOCF_ANCOVA) what was the result of A mixed-effects model repeated measures approach (MMRM) on HAMD17 total score,?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1194	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on increase from baseline in the mean proportion of intermediate cells?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1196	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on improvement in the women's most bothersome vulvovaginal atrophy symptoms?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1070	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Core Decompression and Autologous Bone Marrow Concentrate for Treatment of Femoral Head Osteonecrosis: A Randomized Prospective Study\n\n ABSTRACT:\nThe aim of this study was to investigate the safety of injection of bone marrow aspirate concentrate during core decompression and to study its clinical (visual analogue scale; Harris-Hip-score) and radiological outcomes (magnetic resonance imaging). In this prospective and randomized clinical trial we evaluated 24 consecutive patients with non-traumatic femoral head necrosis (FHN) during a period of two years after intervention. In vitro analysis of mesenchymal stem cells was performed by evaluating the fibroblast colony forming units (CFU-Fs). Postoperatively, significant decrease in pain associated with a functional benefit lasting was observed. However, there was no difference in the clinical outcome between the two study groups. Over the period of two years there was no significant difference between the head survival rate between both groups. In contrast to that, we could not perceive any significant change in the volume of FHN in both treatment groups related to the longitudinal course after treating. The number of CFU showed a significant increase after centrifugation. This trial could not detect a benefit from the additional injection of bone marrow concentrate with regard to bone regeneration and clinical outcome in the short term.\n\nBODY.INTRODUCTION:\nAseptic non-traumatic avascular osteonecrosis of the femoral head is a multi-factorial disease, the etiology of which is not entirely clear. Femoral head necrosis (FHN) most commonly affects young patients, often leading to femoral head collapse and resulting secondary osteoarthritis.1 Around 10% of all THA are performed due to FHN.2 In the early stages of the disease [Association Research Circulation Osseous (ARCO) stage I - II] the treatment aims to preserve the joint and to prevent the collapse of the femoral head. One of the most widely used treatment options is the core decompression by retrograde drilling into the necrotic zone. Systematic reviews verified the significantly better head survival rates compared to non-operative treatment options.2 Based on the data by Mont et al., core decompression leads to clinical success in 53-71% of treated patients leaving room for further therapy improvement. Mesenchymal stem cells and osteoblasts that could potentially induce bone formation have been shown to be decreased in both number and activity in afflicted bone. Therefore the local application of autologous mesenchymal stem cells (MSC) into the necrotic region could stimulate the regeneration of the affected bone. MSCs can be isolated from the mononuclear cell fraction of bone marrow and expanded in-vitro to high-cell numbers using laboratory equipment and then injected into the necrotic zone.3 Bone marrow expansion is subject to restricted regulatory laws in many countries.Introduction of a single-use closed system would allow the surgical team to carry out the concentration procedure in the operating room.4 Hernigou et al. introduced the technique of intra-osseous injection of autologous concentrated bone marrow for the treatment of femoral osteonecrosis and pseudarthrosis.5 They reported on the results of core decompression with additional bone marrow grafting in 145 hips with early stage osteonecrosis (ARCO I - II). At 5 years after surgery, the head survival rate in their study was 93%, which would appear to be a considerable improvement over previous studies. Although this prospective study included an impressive number of patients, a control group and a randomized study protocol were missing. The aim of this study was i) to investigate the safety of additional injection of bone marrow aspirate concentrate (BMAC) during core decompression and ii) to study the clinical (visual analogue scale, VAS; Harris-Hip-Score, HHS) and radiological outcome (magnetic resonance tomography, MRI) in comparison to core decompression only. In addition, in vitro analysis of MSCs was performed by evaluating the fibroblast colony forming units (CFU-F's).\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nIn this prospective and randomized clinical trial we evaluated 24 consecutive patients (25 hips) with non-traumatic FHN during a period of two years after intervention. All patients signed the informed consent, the institutional review board of the hospital approved the study; all procedures were performed in accordance with the Declaration of Helsinki. The inclusion criteria for this study were age over 18 years and the presence of stage II femoral head osteonecrosis according to the Association of Research Circulation Osseous (ARCO) classification. Before inclusion into the study all patients were evaluated with two plane radiographs and an MRI of the affected hip. At the day of the procedure patients were randomized in two groups using a simple randomization method based upon sequential patient allocation: core decompression only vs. core decompression with the application of BMAC. For clinical outcome the VAS and HHS were measured. For radiological outcome the volume of the necrotic zone and the stage according to ARCO classification was evaluated with an MRI. The subsequent course of osteonecrosis was evaluated at 12 and 24 months postoperatively. This study was approved by the ethics committee of University of Heidelberg, Germany.\n\nBODY.MATERIALS AND METHODS.CORE DECOMPRESSION PROCEDURE:\nIn all patients a core decompression procedure was performed under general anesthesia. Under the guidance of an image intensifier in two planes, three 2.0 mm K-wires (Kirschner wires) were drilled through the major trochanter and along the femoral neck axis into the femoral head, reaching the subchondral necrotic area (2-3 mm from the articular cartilage). The most centrally placed K-wire in the necrotic zone was over drilled using 5 mm trephine as has been previously described in the literature.\n\nBODY.MATERIALS AND METHODS.BONE MARROW ASPIRATION, PROCESSING AND INSTILLATION:\nThe harvesting of autologous bone marrow was performed by percutaneous aspiration from the ventral iliac crest (both sides) using a bone marrow biopsy device. The initial volume of harvested marrow was 200 to 220 mL. Intra-operative processing and concentration of stem cells was performed using a Sepax centrifugation device from Biosafe SA (Eysins, Switzerland) with a volume reduction protocol that isolates the nucleated cell (NC) fraction in the buffy coat. After cell segregation, the erythrocytes, nucleated cells and plasma were automatically decanted. 12 mL of bone marrow concentrate suspension was isolated. 2 mL of the final cell concentrate volume (BMAC) was collected for further experimental investigations. 10 mL of BMAC was instilled into the necrotic zone through the canulated trephine drill after removal of the central k-wire.\n\nBODY.MATERIALS AND METHODS:\nThe number of MSCs within the native bone marrow and the bone marrow concentrate was analyzed using the CFU-F's. Assuming that each adherent MSC is able to form a fibroblast colony, the number of MSCs within a cell culture could be estimated. Per donor, 2×106 mononucleated cells (MNC) out of the native bone marrow and the BMAC were seeded into three T25 tissue culture flasks each and cultured in standard medium consisting of high glucose DMEM, 20% fetal calf serum (FCS), 1% penicillin/streptomycin, 10 ng/mL recombinant human epidermal growth factor (EGF) and 10 ng/mL recombinant human platelet-derived growth factor (PDGF). After seven days of culturing, cells were washed with phosphate buffered saline (PBS), fixed with 70 % ethanol stained with toluidin blue. Fibroblast colonies were counted manually using a microscope at 25th magnification. (Modified protocol from Castro-Malaspina et al; 1980).6\n\nBODY.STATISTICS:\nData were expressed as mean or mean ± SEM. The nominal data of patients' characteristics were tested using the test and χ2 Fisher exact test. The distribution of continuous data was determined using the Kolmogorov-Smirnov test and the appropriate parametric or non-parametric test was selected. Differences within the groups for radiological and clinical outcome data were compared with the Wilcoxon test and between the groups – with Mann-Whitney test. A P<0.05 was considered statistically significant. For radiological evaluation MRI scans of 25 hips before surgery, 20 hips at 1 year and 15 hips at 2 years after operation were available due to the presence of endoprosthesis and other reasons. For longitudinal and transverse comparison of the volume of the osteonecrosis, only data of patients with full radiological observation was analyzed. Calculation of FHN volume was performed using GE Healthcare RIS/PACS software (Milan, Italy). SPSS (SPSS Inc., Chicago, IL, USA) and Graph Pad Prism software (Graph Pad, La Jolla, CA, USA) were used for statistical analysis.\n\nBODY.RESULTS:\nTwenty-five hips of 24 patients with femoral head osteonecrosis were included into this study between 2008 and 2010 and assigned by random to the treatment method (14 in control group, 11 in verum group). All 25 hips were fully evaluated clinically (VAS: preoperatively, 3 months postoperatively, 1 and 2 years after treatment; HHP: preoperatively, 3 months, 1 and 2 years after treatment) and if feasible evaluated radiographically (MRI preoperatively, 1 and 2 years after treatment). Both study populations did not significantly differ in age, gender, side of FHN and risks factors for osteonecrosis (steroid therapy in the patients' history) as shown in Table 1. According to the inclusion criteria all patients suffered from an ARCO II FHN and had no prior trauma. No side effects (hematoma, infection, nerve injury and others) either from the bone marrow aspiration from the pelvic rim or from the injection into the femoral head were observed during the entire study period.\n\nBODY.RESULTS.CLINICAL AND FUNCTIONAL OUTCOME:\nThe clinical and functional outcome was measured using standardized scores (VAS; HHS). At the time of inclusion into the study there was no significant difference between the two groups regarding pain and function. Postoperatively, significant decrease in pain associated with a functional benefit lasting the entire observation period was observed. However, there was no difference in the clinical outcome between the two study groups (Figures 1 and 2).\n\nBODY.RESULTS.RADIOLOGICAL OUTCOME:\nBefore treatment there was no significant difference between the mean volumes of the osteonecrosis in both groups. In contrast to the clinical outcome, we could not perceive any significant change in the volume of FHN in both treatment groups related to the longitudinal course after treating (Figure 3). Again no statistically significant difference was detected between the groups. FHN progressing to ARCO III or IV was defined as failure of the treatment. This includes all patients with joint replacement (total hip arthroplasty) due to the FHN within two years in both groups. Over the period of two years there was no significant difference between the head survival rate of 8/14 (57%) in the control group, and 7/11 (64%) in the verum group. There was no difference between the two groups with regard to the interval between core decompression with or without BMAC application and THA.\n\nBODY.RESULTS.BONE MARROW:\nThe bone marrow was analyzed before and after the centrifugation procedure using the Sepax centrifugation device. Table 2 shows the significant increase in the number of nucleated cells due to the centrifugation step. Additionally, the number of CFU that best represents the number of MSC shows a significant increase (Table 2).\n\nBODY.DISCUSSION:\nFemoral head necrosis is a painful disease usually afflicting young male patients and the natural course of this disease tends to be progressive and ends in secondary osteoarthritis.7 In late stage osteonecrosis (ARCO III and IV), total hip arthroplasty (THA) currently seems to be the best treatment with good functional restoration. However, the young patient age and subsequent expected life span is substantially longer than the currently expected longevity of primary THA. Early recognition of FHN and lastly established less invasive treatment modalities open new possibilities to treat this disease for preservation of the spherical femoral head shape indicating a better outcome and finally,8 avoiding THA. One of these operations is the core decompression procedure9-11 and the literature indicates that it is superior to non-operative therapy.12,13 It has been shown that core decompression leads to significant post-operative pain reduction in early stage FHN.2,14 Nevertheless, in postoperative MRI and patho-morphologic trials it could be shown that no significant repair process in the necrotic area of FHN could be achieved with core decompression alone,15 making it a controversial procedure and calling for additional alternative treatment options. The long term results of this procedure are mainly influenced from the initial stage of the osteonecrosis with best prognosis for ARCO I and worst for ARCO III and IV. The outcome of the non-reversible early stage ARCO II is still under discussion. Therefore we included ARCO II hips in this study only. The injection of mesenchymal progenitor cells into the osteonecrosis seems to improve the outcome of FHN as shown by Hernigou et al.16 The application of ex vivo cultivated stem cells for treatment of diseases of the musculoskeletal system is possible, but currently requires advanced laboratory and technical effort. In addition, this two-step procedure is associated with a higher risk of complications and higher costs. On the other hand, cell therapy systems using centrifugation steps were recently developed which permit intra-operative enrichment of mesenchymal progenitor cells from BMAC simultaneously at the time of core decompression followed by application of the BMAC into the necrotic area of FHN at the end of the same procedure. Simultaneous application of BMAC is praised as an encouraging approach. Hernigou et al. (2002, 2005) inaugurated this treatment option and published a large patient series, that demonstrates an obvious improvement in the head survival rate compared to other literature data with core decompression only.5,16 Lastly, Civinini et al. showed good results of treating early stage femoral head necrosis using injectable calcium and sulphate/calcium bioceramic with bone marrow concentrate.17 The first aim of our investigation was to evaluate the safety of the additional aspiration and injection of autologous bone marrow. In our study we did not encounter any complications resulting from this method of bone marrow transplantation. In particular, there were no infections, excessive new bone formation or tumor induction and there were no local complications at the harvesting side. These findings are in line with published data showing the very low risk of this one step procedure.18 The second aim of our study is the effect of the additional injection of BMAC into the femoral head on the clinical and radiological outcome. We found that significant pain relief and functional improvement could be achieved in both groups at the 2 year follow up independent of the operative procedure (core decompression or core decompression with BMAC application). There are a limited number of studies evaluating pain and functional gain after core decompression, and a direct comparison with these studies is difficult. Rajagopa et al. performed a systematic review of four studies evaluating core decompression of femoral head necrosis and its effect on pain and function of the hip over a minimum of two years postoperatively.19 The results of their analysis showed a variable gain of function after core decompression procedure. One of the articles quoted demonstrated a significant improvement in hip function,20 a second one just moderate improvement21 and two other studies only minor, or no improvement.22,23 Our study supports the latter. We did not note any significant differences relating to pain or functional state of patients between both groups, supporting the hypothesis, that additional BMAC application after core decompression provides no benefit to patients with FHN at this time. This finding seems to be in contrast to the studies of Hernigou et al. However, the study presented here was set up as a randomized controlled trial with restrictive inclusion criteria (ARCO II only). The rejection of ARCO I patients with a better prognosis might, at least in part, explain differences to the results of Hernigou et al. and other studies. Table 3 shows a comparison of head survival rate of this study and recently published studies using BMAC or similar bone marrow treatment options in femoral head necrosis. Because of different study protocols, meaningful comparison of these research findings is limited. A study with a protocol similar to ours was published by Gangji et al.24 They presented the results of a randomized and prospective clinical trial of ARCO I-II patients treated with core decompression only vs. core decompression with autologous bone marrow application. Femoral head survival rate of this study is also mentioned in Table 3. Gangji et al. also describe an increased head survival rate in the BMAC group. Although this is a randomized controlled prospective trial, there are some principal limitations to this study: there is a short follow-up period (two years) and there are a small number of patients in both study groups. The small study population is a result of the prospective design and very restrictive inclusion criteria of FHN patients (ARCO II only). In comparison to the study presented by Hernigou et al.,16 the major advantage of this study is the comparison of a BMAC group with a control group, thereby increasing explanatory power.\n\nBODY.CONCLUSIONS:\nFemoral head necrosis with a spherical head and irreversible necrosis of the bone (ARCO II) profits from core decompression. In contrast to previous series the current study excluded ARCO I stages of FHN which can regenerate on its own, and inclusion of ARCO I makes interpretation of drilling of this stage difficult. This trial of 25 hips could not detect a benefit from the additional injection of bone marrow concentrate with regard to bone regeneration and clinical outcome in the short term. Further studies of BMAC properties with a larger sample size and longer follow-up are needed to better validate our results and possibly modify our procedure.\n\nQuestion: Compared to core decompression only what was the result of core decompression with the application of bone marrow aspirate concentrate on femoral head necrosis (FHN)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1071	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Core Decompression and Autologous Bone Marrow Concentrate for Treatment of Femoral Head Osteonecrosis: A Randomized Prospective Study\n\n ABSTRACT:\nThe aim of this study was to investigate the safety of injection of bone marrow aspirate concentrate during core decompression and to study its clinical (visual analogue scale; Harris-Hip-score) and radiological outcomes (magnetic resonance imaging). In this prospective and randomized clinical trial we evaluated 24 consecutive patients with non-traumatic femoral head necrosis (FHN) during a period of two years after intervention. In vitro analysis of mesenchymal stem cells was performed by evaluating the fibroblast colony forming units (CFU-Fs). Postoperatively, significant decrease in pain associated with a functional benefit lasting was observed. However, there was no difference in the clinical outcome between the two study groups. Over the period of two years there was no significant difference between the head survival rate between both groups. In contrast to that, we could not perceive any significant change in the volume of FHN in both treatment groups related to the longitudinal course after treating. The number of CFU showed a significant increase after centrifugation. This trial could not detect a benefit from the additional injection of bone marrow concentrate with regard to bone regeneration and clinical outcome in the short term.\n\nBODY.INTRODUCTION:\nAseptic non-traumatic avascular osteonecrosis of the femoral head is a multi-factorial disease, the etiology of which is not entirely clear. Femoral head necrosis (FHN) most commonly affects young patients, often leading to femoral head collapse and resulting secondary osteoarthritis.1 Around 10% of all THA are performed due to FHN.2 In the early stages of the disease [Association Research Circulation Osseous (ARCO) stage I - II] the treatment aims to preserve the joint and to prevent the collapse of the femoral head. One of the most widely used treatment options is the core decompression by retrograde drilling into the necrotic zone. Systematic reviews verified the significantly better head survival rates compared to non-operative treatment options.2 Based on the data by Mont et al., core decompression leads to clinical success in 53-71% of treated patients leaving room for further therapy improvement. Mesenchymal stem cells and osteoblasts that could potentially induce bone formation have been shown to be decreased in both number and activity in afflicted bone. Therefore the local application of autologous mesenchymal stem cells (MSC) into the necrotic region could stimulate the regeneration of the affected bone. MSCs can be isolated from the mononuclear cell fraction of bone marrow and expanded in-vitro to high-cell numbers using laboratory equipment and then injected into the necrotic zone.3 Bone marrow expansion is subject to restricted regulatory laws in many countries.Introduction of a single-use closed system would allow the surgical team to carry out the concentration procedure in the operating room.4 Hernigou et al. introduced the technique of intra-osseous injection of autologous concentrated bone marrow for the treatment of femoral osteonecrosis and pseudarthrosis.5 They reported on the results of core decompression with additional bone marrow grafting in 145 hips with early stage osteonecrosis (ARCO I - II). At 5 years after surgery, the head survival rate in their study was 93%, which would appear to be a considerable improvement over previous studies. Although this prospective study included an impressive number of patients, a control group and a randomized study protocol were missing. The aim of this study was i) to investigate the safety of additional injection of bone marrow aspirate concentrate (BMAC) during core decompression and ii) to study the clinical (visual analogue scale, VAS; Harris-Hip-Score, HHS) and radiological outcome (magnetic resonance tomography, MRI) in comparison to core decompression only. In addition, in vitro analysis of MSCs was performed by evaluating the fibroblast colony forming units (CFU-F's).\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nIn this prospective and randomized clinical trial we evaluated 24 consecutive patients (25 hips) with non-traumatic FHN during a period of two years after intervention. All patients signed the informed consent, the institutional review board of the hospital approved the study; all procedures were performed in accordance with the Declaration of Helsinki. The inclusion criteria for this study were age over 18 years and the presence of stage II femoral head osteonecrosis according to the Association of Research Circulation Osseous (ARCO) classification. Before inclusion into the study all patients were evaluated with two plane radiographs and an MRI of the affected hip. At the day of the procedure patients were randomized in two groups using a simple randomization method based upon sequential patient allocation: core decompression only vs. core decompression with the application of BMAC. For clinical outcome the VAS and HHS were measured. For radiological outcome the volume of the necrotic zone and the stage according to ARCO classification was evaluated with an MRI. The subsequent course of osteonecrosis was evaluated at 12 and 24 months postoperatively. This study was approved by the ethics committee of University of Heidelberg, Germany.\n\nBODY.MATERIALS AND METHODS.CORE DECOMPRESSION PROCEDURE:\nIn all patients a core decompression procedure was performed under general anesthesia. Under the guidance of an image intensifier in two planes, three 2.0 mm K-wires (Kirschner wires) were drilled through the major trochanter and along the femoral neck axis into the femoral head, reaching the subchondral necrotic area (2-3 mm from the articular cartilage). The most centrally placed K-wire in the necrotic zone was over drilled using 5 mm trephine as has been previously described in the literature.\n\nBODY.MATERIALS AND METHODS.BONE MARROW ASPIRATION, PROCESSING AND INSTILLATION:\nThe harvesting of autologous bone marrow was performed by percutaneous aspiration from the ventral iliac crest (both sides) using a bone marrow biopsy device. The initial volume of harvested marrow was 200 to 220 mL. Intra-operative processing and concentration of stem cells was performed using a Sepax centrifugation device from Biosafe SA (Eysins, Switzerland) with a volume reduction protocol that isolates the nucleated cell (NC) fraction in the buffy coat. After cell segregation, the erythrocytes, nucleated cells and plasma were automatically decanted. 12 mL of bone marrow concentrate suspension was isolated. 2 mL of the final cell concentrate volume (BMAC) was collected for further experimental investigations. 10 mL of BMAC was instilled into the necrotic zone through the canulated trephine drill after removal of the central k-wire.\n\nBODY.MATERIALS AND METHODS:\nThe number of MSCs within the native bone marrow and the bone marrow concentrate was analyzed using the CFU-F's. Assuming that each adherent MSC is able to form a fibroblast colony, the number of MSCs within a cell culture could be estimated. Per donor, 2×106 mononucleated cells (MNC) out of the native bone marrow and the BMAC were seeded into three T25 tissue culture flasks each and cultured in standard medium consisting of high glucose DMEM, 20% fetal calf serum (FCS), 1% penicillin/streptomycin, 10 ng/mL recombinant human epidermal growth factor (EGF) and 10 ng/mL recombinant human platelet-derived growth factor (PDGF). After seven days of culturing, cells were washed with phosphate buffered saline (PBS), fixed with 70 % ethanol stained with toluidin blue. Fibroblast colonies were counted manually using a microscope at 25th magnification. (Modified protocol from Castro-Malaspina et al; 1980).6\n\nBODY.STATISTICS:\nData were expressed as mean or mean ± SEM. The nominal data of patients' characteristics were tested using the test and χ2 Fisher exact test. The distribution of continuous data was determined using the Kolmogorov-Smirnov test and the appropriate parametric or non-parametric test was selected. Differences within the groups for radiological and clinical outcome data were compared with the Wilcoxon test and between the groups – with Mann-Whitney test. A P<0.05 was considered statistically significant. For radiological evaluation MRI scans of 25 hips before surgery, 20 hips at 1 year and 15 hips at 2 years after operation were available due to the presence of endoprosthesis and other reasons. For longitudinal and transverse comparison of the volume of the osteonecrosis, only data of patients with full radiological observation was analyzed. Calculation of FHN volume was performed using GE Healthcare RIS/PACS software (Milan, Italy). SPSS (SPSS Inc., Chicago, IL, USA) and Graph Pad Prism software (Graph Pad, La Jolla, CA, USA) were used for statistical analysis.\n\nBODY.RESULTS:\nTwenty-five hips of 24 patients with femoral head osteonecrosis were included into this study between 2008 and 2010 and assigned by random to the treatment method (14 in control group, 11 in verum group). All 25 hips were fully evaluated clinically (VAS: preoperatively, 3 months postoperatively, 1 and 2 years after treatment; HHP: preoperatively, 3 months, 1 and 2 years after treatment) and if feasible evaluated radiographically (MRI preoperatively, 1 and 2 years after treatment). Both study populations did not significantly differ in age, gender, side of FHN and risks factors for osteonecrosis (steroid therapy in the patients' history) as shown in Table 1. According to the inclusion criteria all patients suffered from an ARCO II FHN and had no prior trauma. No side effects (hematoma, infection, nerve injury and others) either from the bone marrow aspiration from the pelvic rim or from the injection into the femoral head were observed during the entire study period.\n\nBODY.RESULTS.CLINICAL AND FUNCTIONAL OUTCOME:\nThe clinical and functional outcome was measured using standardized scores (VAS; HHS). At the time of inclusion into the study there was no significant difference between the two groups regarding pain and function. Postoperatively, significant decrease in pain associated with a functional benefit lasting the entire observation period was observed. However, there was no difference in the clinical outcome between the two study groups (Figures 1 and 2).\n\nBODY.RESULTS.RADIOLOGICAL OUTCOME:\nBefore treatment there was no significant difference between the mean volumes of the osteonecrosis in both groups. In contrast to the clinical outcome, we could not perceive any significant change in the volume of FHN in both treatment groups related to the longitudinal course after treating (Figure 3). Again no statistically significant difference was detected between the groups. FHN progressing to ARCO III or IV was defined as failure of the treatment. This includes all patients with joint replacement (total hip arthroplasty) due to the FHN within two years in both groups. Over the period of two years there was no significant difference between the head survival rate of 8/14 (57%) in the control group, and 7/11 (64%) in the verum group. There was no difference between the two groups with regard to the interval between core decompression with or without BMAC application and THA.\n\nBODY.RESULTS.BONE MARROW:\nThe bone marrow was analyzed before and after the centrifugation procedure using the Sepax centrifugation device. Table 2 shows the significant increase in the number of nucleated cells due to the centrifugation step. Additionally, the number of CFU that best represents the number of MSC shows a significant increase (Table 2).\n\nBODY.DISCUSSION:\nFemoral head necrosis is a painful disease usually afflicting young male patients and the natural course of this disease tends to be progressive and ends in secondary osteoarthritis.7 In late stage osteonecrosis (ARCO III and IV), total hip arthroplasty (THA) currently seems to be the best treatment with good functional restoration. However, the young patient age and subsequent expected life span is substantially longer than the currently expected longevity of primary THA. Early recognition of FHN and lastly established less invasive treatment modalities open new possibilities to treat this disease for preservation of the spherical femoral head shape indicating a better outcome and finally,8 avoiding THA. One of these operations is the core decompression procedure9-11 and the literature indicates that it is superior to non-operative therapy.12,13 It has been shown that core decompression leads to significant post-operative pain reduction in early stage FHN.2,14 Nevertheless, in postoperative MRI and patho-morphologic trials it could be shown that no significant repair process in the necrotic area of FHN could be achieved with core decompression alone,15 making it a controversial procedure and calling for additional alternative treatment options. The long term results of this procedure are mainly influenced from the initial stage of the osteonecrosis with best prognosis for ARCO I and worst for ARCO III and IV. The outcome of the non-reversible early stage ARCO II is still under discussion. Therefore we included ARCO II hips in this study only. The injection of mesenchymal progenitor cells into the osteonecrosis seems to improve the outcome of FHN as shown by Hernigou et al.16 The application of ex vivo cultivated stem cells for treatment of diseases of the musculoskeletal system is possible, but currently requires advanced laboratory and technical effort. In addition, this two-step procedure is associated with a higher risk of complications and higher costs. On the other hand, cell therapy systems using centrifugation steps were recently developed which permit intra-operative enrichment of mesenchymal progenitor cells from BMAC simultaneously at the time of core decompression followed by application of the BMAC into the necrotic area of FHN at the end of the same procedure. Simultaneous application of BMAC is praised as an encouraging approach. Hernigou et al. (2002, 2005) inaugurated this treatment option and published a large patient series, that demonstrates an obvious improvement in the head survival rate compared to other literature data with core decompression only.5,16 Lastly, Civinini et al. showed good results of treating early stage femoral head necrosis using injectable calcium and sulphate/calcium bioceramic with bone marrow concentrate.17 The first aim of our investigation was to evaluate the safety of the additional aspiration and injection of autologous bone marrow. In our study we did not encounter any complications resulting from this method of bone marrow transplantation. In particular, there were no infections, excessive new bone formation or tumor induction and there were no local complications at the harvesting side. These findings are in line with published data showing the very low risk of this one step procedure.18 The second aim of our study is the effect of the additional injection of BMAC into the femoral head on the clinical and radiological outcome. We found that significant pain relief and functional improvement could be achieved in both groups at the 2 year follow up independent of the operative procedure (core decompression or core decompression with BMAC application). There are a limited number of studies evaluating pain and functional gain after core decompression, and a direct comparison with these studies is difficult. Rajagopa et al. performed a systematic review of four studies evaluating core decompression of femoral head necrosis and its effect on pain and function of the hip over a minimum of two years postoperatively.19 The results of their analysis showed a variable gain of function after core decompression procedure. One of the articles quoted demonstrated a significant improvement in hip function,20 a second one just moderate improvement21 and two other studies only minor, or no improvement.22,23 Our study supports the latter. We did not note any significant differences relating to pain or functional state of patients between both groups, supporting the hypothesis, that additional BMAC application after core decompression provides no benefit to patients with FHN at this time. This finding seems to be in contrast to the studies of Hernigou et al. However, the study presented here was set up as a randomized controlled trial with restrictive inclusion criteria (ARCO II only). The rejection of ARCO I patients with a better prognosis might, at least in part, explain differences to the results of Hernigou et al. and other studies. Table 3 shows a comparison of head survival rate of this study and recently published studies using BMAC or similar bone marrow treatment options in femoral head necrosis. Because of different study protocols, meaningful comparison of these research findings is limited. A study with a protocol similar to ours was published by Gangji et al.24 They presented the results of a randomized and prospective clinical trial of ARCO I-II patients treated with core decompression only vs. core decompression with autologous bone marrow application. Femoral head survival rate of this study is also mentioned in Table 3. Gangji et al. also describe an increased head survival rate in the BMAC group. Although this is a randomized controlled prospective trial, there are some principal limitations to this study: there is a short follow-up period (two years) and there are a small number of patients in both study groups. The small study population is a result of the prospective design and very restrictive inclusion criteria of FHN patients (ARCO II only). In comparison to the study presented by Hernigou et al.,16 the major advantage of this study is the comparison of a BMAC group with a control group, thereby increasing explanatory power.\n\nBODY.CONCLUSIONS:\nFemoral head necrosis with a spherical head and irreversible necrosis of the bone (ARCO II) profits from core decompression. In contrast to previous series the current study excluded ARCO I stages of FHN which can regenerate on its own, and inclusion of ARCO I makes interpretation of drilling of this stage difficult. This trial of 25 hips could not detect a benefit from the additional injection of bone marrow concentrate with regard to bone regeneration and clinical outcome in the short term. Further studies of BMAC properties with a larger sample size and longer follow-up are needed to better validate our results and possibly modify our procedure.\n\nQuestion: Compared to core decompression only what was the result of core decompression with the application of bone marrow aspirate concentrate on the head survival rate?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1197	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on reduction in the incidence of dyspareunia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1076	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The effect of hip abduction on the EMG activity of vastus medialis obliquus, vastus lateralis longus and vastus lateralis obliquus in healthy subjects\n\n ABSTRACT.STUDY DESIGN:\nControlled laboratory study.\n\nABSTRACT.OBJECTIVES:\nThe purposes of this paper were to investigate (d) whether vastus medialis obliquus (VMO), vastus lateralis longus (VLL) and vastus lateralis obliquus (VLO) EMG activity can be influenced by hip abduction performed by healthy subjects.\n\nABSTRACT.BACKGROUND:\nSome clinicians contraindicate hip abduction for patellofemoral patients (with) based on the premise that hip abduction could facilitate the VLL muscle activation leading to a VLL and VMO imbalance\n\nABSTRACT.METHODS AND MEASURES:\nTwenty-one clinically healthy subjects were involved in the study, 10 women and 11 men (aged X = 23.3 ± 2.9). The EMG signals were collected using a computerized EMG VIKING II, with 8 channels and three pairs of surface electrodes. EMG activity was obtained from MVIC knee extension at 90° of flexion in a seated position and MVIC hip abduction at 0° and 30° with patients in side-lying position with the knee in full extension. The data were normalized in the MVIC knee extension at 50° of flexion in a seated position, and were submitted to ANOVA test with subsequent application of the Bonferroni multiple comparisons analysis test. The level of significance was defined as p ≤ 0.05.\n\nABSTRACT.RESULTS:\nThe VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196). There were no statistically significant differences in the VLL EMG activity among the three sets of exercises tested.\n\nABSTRACT.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC hip abduction at 0° and 30° of abduction and MVIC knee extension at 90° of flexion in both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nBODY.INTRODUCTION:\nPatellofemoral pain syndrome (PFPS) presents one of the most perplexing pathologic conditions in orthopedic and sports medicine clinics, as well as in rehabilitation departments, and it was referred to by Dye [1] as the \"black hole of orthopedics\" because of the lack of clarity regarding the etiological factors that contribute to dysfunction or to specific treatment protocols and the causative mechanisms remain imprecisely defined [2]. Dysfunction of the quadriceps muscle has been hypothesized as a cause of patellofemoral pain syndrome (PFPS) with great emphasis placed on the role of VMO and VL muscular imbalance [3,4]. Quadriceps dysfunction in PFPS patients has been assessed in various ways including decreased magnitude of the electromyographic (EMG) activity of the quadriceps [5,6], diminished EMG activity of the VMO in relation to that of the VL [7-9], and the delayed onset of VMO activation in relation to the VL [10-12] caused by the inhibition of pain, effusion and atrophies[13]. Improved control of patella tracking is necessary for symptomatic relief [14] and the recovery of quadriceps function is essential to the resolution of the problem [15]. Consequently, there have been numerous studies that have sought to identify exercises to selectively recruit the VMO in an effort to retrain this muscle [7,16-18]. However, Mirzabeigi et al. [19] suggested that the VMO muscle cannot be significantly isolated during nine sets of different exercises. Since fibers of the VMO attach to the adductor magnus muscle, it has been hypothesized that activation of the VMO may be enhanced by combining active knee extension with volitional hip adduction [4,16,20]. Research in clinical studies on the treatment of PFPS has reported that VL activity may also be enhanced by combining knee extension exercises with hip abduction [21,22]. Fulkerson [23] noted retinacular tenderness in patients with patellofemoral pain, including some who demonstrated histological changes within the perineural tissues of the lateral retinaculum on examination of surgical biopsy specimens. Bevilaqua-Grossi et al. [24] in their anatomical study dissected the thighs of 32 human cadavers and showed that the distal fibers of the Vastus Lateralis Obliquus (VLO) were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, were subsequently joined in a common tendon with the VLL on the superolateral border of the patella (Figure 1) and that tightness of lateral retinaculum could potentially alter the tracking of the patella in the trochlear groove. Based on this anatomic correlation, Hip abduction exercises are often contraindicated by physical therapists because some group of patient with patellofemoral problems may have tight lateral structures and hip abduction exercises would enhance VMO and VL muscular imbalance [21]. Figure 1Lateral view of the right thigh showing the origin of the obliquus portion of the vastus lateralis muscle (vastus lateralis obliquus – VLO) in the lateral intermuscular septum (LIS) and its insertion in the superior -lateral border of the patella (P). VLL – vastus lateralis longus. Bevilaqua-Grossi et al. (2004) 46. Considering that previous few studies have investigated the EMG relationship VMO and VLO with other structures of the lateral compartment (lateral retinaculum and iliotibial tract) and hip abduction strengthening exercises, the aim of this paper was to analyze the EMG activity of the VMO, VLL and VLO muscles and verify whether any difference in activity between these portions occurred during MVIC: 1) knee extension at 90° of flexion, 2) hip abduction at 0° of abduction and 3) hip abduction at 30° of abduction. The data reported in this paper should be useful in future functional studies aimed at a clearer understanding of rehabilitation protocols in PFPS patients.\n\nBODY.METHODS.SUBJECTS:\nTwenty-one healthy volunteers (11 males and 10 females), aged from 19 to 28 (X = 23.3 ± 2.9), participated in this study. They were recruited from Piracicaba Methodist University and all reported no history of orthopedic disorders, surgical procedures, knee pain or other major musculoskeletal injuries. Prior to participation, all subjects read, accepted and signed a consent form that was approved by the Human Research Ethics Committee at the State University of Campinas.\n\nBODY.METHODS.INSTRUMENTATION:\nSilver/silver chloride surface electrodes placed in a bipolar configuration, with a 10 mm contact area and an inter-electrode distance of 2 cm, were used to assess the level of electromyographic activity of the VMO, VLL and VLO muscles. Before the electrode placement the sites were prepared by shaving, abrading and cleaning with isopropyl alcohol to reduce the surface impedance to less than 5 and 10 kΩ for men and women, respectively. A quadriceps line was drawn from the anterior superior iliac spine to the center of the patella for the quadriceps portion placement [24]. A surface electrode for the VMO was placed with a medial inclination of 55° from the quadriceps line [25,26]. The VLL electrode was placed 15 cm from the superior edge of patella at a lateral inclination of 13.6° and the VLO shows its superficial part around 2.2 cm of the lateralis epicondyle with a superficial length of around 8.9 cm with a 50.4° of lateral inclination[27]. A ground electrode was placed over the tibial tubercle of the tested lower limb. The same investigator performed all electrode placements. A calibrated Viking II with eight channels (Nicolet Biomedical Instruments) and a computer were used to collect all EMG data (CMRR of 110 dB, sampling 1000 Hz, gain 200, band pass filter of 10 to 1000 Hz). All signals were viewed on a display screen prior to collection to ensure that there were no visible artifacts.\n\nBODY.METHODS.PROCEDURES:\nFollowing EMG preparation, the subjects were instructed to perform 3 repetitions of the following three sets of exercises: 1) MVIC knee extension at 90° of flexion in a seated position; 2) MVIC hip abduction at 0° of abduction, with patients in side-lying position with the knee in full extension; 3) MVIC hip abduction at 30° of abduction, with patients in side-lying position with the knee in full extension During the MVIC knee extension test, the subjects were positioned seated in a leg extension machine (Queens, São Paulo, BRA) with the knee and hip at 90° of flexion and the ankle in a neutral position (figure 2). For the MVIC hip abduction (0° and 30°) tests, the subjects were positioned on their sides lying on a divan with the test lower limb placed above and with both lower limbs positioned at neutral hip and knee flexions, as measured by the investigator. For the maintenance of these positions the thighs were stabilized with padding and the calves were fixed with a belt applied immediately distal to the knees (Figure 3 and 4). Figure 2Maximum voluntary isometric contraction at 90 degrees of knee extension. Figure 3Maximum voluntary isometric contraction of hip abduction in neutral in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Figure 4Maximum voluntary isometric contraction at 30 degrees of hip abduction in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Before data collection procedures began, each subject received a verbal explanation and a demonstration of the testing activities and practice trials were performed to ensure the subject's comprehension and safety. After familiarization, the subjects randomly performed three MVIC for 5 seconds with a 2 minute rest between repetitions and 10 minutes between each set of exercises to prevent muscle exhaustion. EMG signals were collected throughout each MVIC and verbal encouragement was provided throughout the testing.\n\nBODY.METHODS.DATA ANALYSIS:\nThe normalization of the VMO, VLL and VLO EMG signals for the three exercises (knee extension at 90° of flexion, MVIC hip abduction at 0° of abduction, MVIC hip abduction at 30° of abduction) were obtained dividing the highest EMG value of the MVIC trials by the EMG value of a MVIC knee extension at 50° of flexion in a seated position and multiplied by 100 [16]. The normalization procedure performed at 50° of knee flexion in a seated position followed the same protocol of positioning for the test at 90° of knee flexion in a seated position. Normalized EMG readings were analyzed by two-way analysis of variance with repeated measurements. Post hoc comparisons within the values obtained for each of the muscles were realized by the Bonferroni multiple comparisons analysis. Significance was defined as p ≤ 0.05.\n\nBODY.RESULTS:\nMaximum voluntary isometric contractions for knee extension at 90° of flexion resulted in a significantly higher EMG activity for the VMO muscle compared with hip abduction at 0° and 30° of abduction for both male (p < 0.008) and female (p < 0.0005) subjects (Table 1, Figure 5). Table 1 Summarized results of normalized EMG values of VMO, VLL and VLO muscles during MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction (N = 21) The results are shown as a percentage of MVIC at 50° of knee flexion in a seated position Test procedure VMO (%) VLL (%) VLO (%) Hip abduction at 30° Male 53.70 88.31 75.70 Female 96.07 119.61 103.98 Hip abduction at 0° Male 69.05 110.62 90.25 female 87.09 100.13 92.30 MIVC at 90° of knee flexion Male 144.91 c 115.31 146.72 d female 165.97 b 141.30 162.61 a p ≤ 0,05 Letters demonstrate higher EMG activity of the same muscle in which there were statistically significantly differences between the three exercises a p = 0,02196 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° of abduction b p = 0,008 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction c p = 0,000055 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction d p = 0,000761 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction Figure 5Normalized EMG activity expressed as RMS values from healthy subjects performing MVIC knee extension at 90° of flexion, MVIC hip abduction at 0° and 30° of abduction. A) Significantly higher VMO activity for both male and female subjects performing MVIC knee extension at 90° of flexion when compared to MVIC hip abduction at 0° and 30° of abduction. B) VLL EMG activity without significant differences among the three exercises tested. C) Significantly higher VLO activity for male subjects was observed in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction and for female subjects performing MVIC knee extension at 90° of flexion when compared with MVIC hip abduction at 0° and 30° of abduction. There were no statistically significant differences in the VLL EMG activity among the three types of exercise tested (Table 1, Figure 5). The VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and with MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196) (Table 1, Figure 5). There were no significant differences between gender with respect to the EMG activity of the VMO, VLL and VLO muscles among the three types of exercise tested. No selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction for both male and female subjects.\n\nBODY.DISCUSSION:\nThe primary purpose of this article was to investigate whether VMO, VLL and VLO EMG activity can be influenced by hip abduction. The results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion or MVIC hip abduction at 0° and 30° of abduction for both male and female subjects. These results are in agreement with Hertel et al. [4] who investigated the EMG activity of the VMO, VLL and gluteus medius in eight healthy young adult volunteers with no history of knee injury while performing uniplanar knee extension, knee extension/hip adduction, knee extension/hip abduction and found no significant differences in the VMO/VL ratio between the exercises. It is well established in the literature that the isolation of any of the quadriceps components or selective strengthening is unlikely, especially concerning the VMO/VLL muscles [28,29]. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO in healthy subjects performing maximum voluntary isometric contraction. We are unaware of any studies which have demonstrated the characteristics of EMG activity between VMO, VLL and VLO in subjects performing hip abduction in different positions. The secondary purpose of the present work was investigating the EMG activity of the VMO, VLL and VLO while performing the three exercises tested. The results showed that the VLO presents a significantly different behavior compared with the VLL, whereas the VLO showed a similar motor unit recruitment to the VMO, producing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction. No significant differences were found in the EMG activity of the VLL among the three exercises tested, thus verifying that the VLL and VLO demonstrate not only anatomical but distinct motor unit recruitment characteristics. Bevilaqua-Grossi et al. [27] investigated the EMG activity of the VMO, VLL and VLO muscles in 21 healthy subjects performing open kinetic chain knee extension at 15° and 90° of flexion. The results showed that the VLO and VMO were more active at 90° of flexion compared with the higher activity of the VLL at 15° of flexion, demonstrating that the VMO and VLO muscle have the same behavior suggesting a synchronic antagonist stability role of the patella in healthy people. The striking difference between VLL and VLO behavior concerning the EMG activity observed, could be because the VLL fiber alignment tends to traction the patella, offering greater contribution to knee extension than patella stabilization, different from the VLO which spirally and inclination fibers in relation to femoral dyaphisis promotes patella alignment associated with the VMO [24] Hertel et al. [4] reported that both the VMO and VL are more activated in uniplanar knee extension when compared with knee extension/hip adduction or abduction. These results are not entirely supported by our results, in which the VLL showed no significant differences between MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30°. These conflicting results concerning the VLL recruitment pattern may be because these authors tested the exercises in closed kinetic chain while the three exercises tested in the current work were performed in open kinetic chain. Possible limitations of this study may be related to the non collection of gluteus medius EMG activity during the three exercises tested. Normalization methods using other types of muscle contractions or other angles of the knee joint may result in different VMO/VLL/VLO ratios between studies that use different methods of normalization. The absence of increased EMG activity with hip abduction could have been due limitations in EMG recordings from MVCs. Results might be different when studying submax voluntary contractions. Although normalized EMG data are useful in measuring relative levels of activity between muscles, such information is not indicative of muscular strength or muscular balance [58]. Future studies of this research group will focus on subjects with patellofemoral pain and investigate the recruitment patterns provided from such subjects performing the same task.\n\nBODY.DISCUSSION.CLINICAL IMPLICATIONS:\nBevilaqua-Grossi et al. [24] dissected the thighs of 32 human cadavers and determined the anatomical organizations of the VLL and VLO muscles. The distal fibers of the VLO were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, which subsequently joined in a common tendon with the VLL on the superolateral border of the patella. These results agree with previous anatomical studies which describe the origin [30-34] and insertion of these muscles [35,36]. Thus, tightness of the lateral retinaculum, perhaps as a result of increased tension in the iliotibial tract, could potentially alter the tracking of the patella in the trochlear groove, becoming an important factor in the etiology of patellofemoral pain [37]. Following this theory, some clinicians contraindicate rehabilitation exercises using hip abduction in patients with patellofemoral complaints based on the premise of avoiding excessive tightness of the lateral structures or a VLL and VMO imbalance, since the anatomical origin of the iliotibial tract has a close relation with the iliotibial band and the gluteus medius muscles [21,38]. This theory is not supported by recent works which investigated the role of pelvic control as a contributing factor in the development of anterior knee pain [39-42]. Ireland et al. [39], using hand held dynamometers, investigated hip abduction and external rotation isometric strength in 15 female patients with patellofemoral pain compared with a control group. They found significant weakness of the hip abductors and external rotators of the patellofemoral pain group. It is postulated that in the absence of pelvic control due to hip abductor and external rotator weakness, the femur may adduct and internally rotate, further increasing lateral patellar contact pressure [43]. These findings suggest that hip abduction exercises may be indicated and necessary for patients with patellofemoral pain who present absence of satisfactory pelvic control.\n\nBODY.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC at 30° and 0° of hip abduction and 90° of knee flexion for both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nQuestion: Compared to hip abduction at 0° and 30° what was the result of knee extension at 90° of flexion on vastus lateralis obliquus (VLO) EMG activity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1204	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Antioxidative and antiatherogenic effects of flaxseed, α-tocopherol and their combination in diabetic hamsters fed with a high-fat diet\n\n ABSTRACT:\nOxidative stress has previously been shown to play a role in the pathogenesis of diabetes mellitus (DM) and its complications. In the present study, the effects of supplementation with dietary antioxidants, flaxseed and α-tocopherol were investigated in diabetic golden Syrian hamsters fed with a high-fat diet. Thirty-five golden Syrian hamsters were randomly divided into a control group (C) and four diabetic groups (DM, DM + flax, DM + E and DM + Flax + E). The hamsters received four different diets for a 20-week period, as follows: i) Groups C and DM received a high-fat diet (40% energy as fat), deficient in α-linolenic acid (ALA); ii) the DM + Flax group received a high-fat diet enriched with ground flaxseed 15 g/100 g of food, rich in ALA; iii) the DM + E group received a high-fat diet enriched with vitamin E, 40 mg α-tocopherol/100 g of food; and iv) the DM + Flax + E group received a high-fat diet enriched with flaxseed and vitamin E. The results of serum lipid and oxidative stress analysis suggested that the antiatherogenic effect of flaxseed, α-tocopherol and their combination added to a high-fat diet in diabetic hamsters was based primarily on their antioxidative role, demonstrated by decreased serum lipid peroxidation and increased liver glutathione content. Improvements of serum glucose and non-high-density lipoprotein cholesterol (HDL-C) levels were observed and may have contributed to the prevention of diabetic macroangiopathy evidenced in the histopathological examination. The antioxidant effect of flaxseed was similar to that of α-tocopherol in diabetic hamsters fed a high-fat diet and combined supplementation did not appear to bring more benefits than flaxseed alone. Moreover, the high dose of ground flaxseed alone may have a better cardioprotective effect than α-tocopherol in diabetic hamsters by reducing total cholesterol and non-HDL-C levels and increasing HDL-C levels.\n\nBODY.INTRODUCTION:\nOxidative stress is considered to be significant in the pathogenesis of diabetes-induced cardiovascular disease (CVD), which is associated with an abnormal blood lipid profile, insulin resistance and metabolic syndrome (1). Oxidative stress occurs due to a disturbance of the balance between antioxidant defense mechanisms and the levels of reactive oxygen species (ROS) (2,3). Numerous studies have identified significant alterations in plasma antioxidant vitamins (including vitamins C, E and A), antioxidant enzyme systems [superoxide dismutase (SOD), catalase (CAT) and glutathione peroxidase (GSH-Px)] and in lipid peroxidation in diabetes (4,5). In chronic diabetes mellitus (DM), the stability and reactive capacity of antioxidants seriously affect the long-term complications caused by oxidative stress (6,7). Antioxidants have been shown to reduce complications in DM by preventing free radical-mediated damage (4,8). Dietary supplementation with antioxidants, including vitamins and phenolic compounds obtained from plants, may help to maintain a desirable pro-oxidative/antioxidative balance (9,10). A variety of dietary sources are presently of considerable interest due to their potential health benefits in relation to numerous diseases, including diabetic disorders (11,12). Flaxseed (also known as linseed and Linum usitatissimum), an edible oil seed/grain from a traditional arable crop, has been acknowledged as a functional food (13), and is the focus of considerable attention due to its unique nutrient components and its potential to prevent CVD (14). In addition of being one of the richest plant sources of α-linolenic acid (ALA; ~22% of whole flaxseed), flaxseed is an essential source of lignans (in particular, secoisolariciresinol diglucoside, SDG) (15). SDG has demonstrated extreme radical scavenging activity, thereby protecting polyunsaturated fatty acids from oxidation (16–18). Despite the beneficial effects of SDG, flaxseed consumption has been found to significantly reduce α- and γ-tocopherol concentrations in rats (19) and only vitamin E supplementation was able to restore the plasma concentrations (20). α-tocopherol supplementation has previously been demonstrated to be beneficial in increasing the levels of antioxidant enzymes such as SOD and GSH-Px, and of reduced GSH in diabetes (21–23); however, little is known about the effect of adding vitamin E to a flaxseed-enriched diet on oxidative stress and aortic atherosclerotic lesions in diabetes. In the present study, the effects of dietary flaxseed, α-tocopherol and their combination were investigated on atherosclerotic progression in diabetic hamsters fed a high-fat diet by examining serum lipid concentrations, oxidative stress markers, aortic cholesterol content and aortic histological aspects.\n\nBODY.MATERIALS AND METHODS.ANIMALS:\nA total of 35 male Golden Syrian hamsters were used in the study. The hamsters were purchased from the Cantacuzino National Institute for Research and Development in Microbiology and Immunology (Bucharest, Romania). This study was approved by the Laboratory Animal Care Committee of Grigore T. Popa University of Medicine and Pharmacy (Iaşi, Romania), and the hamsters were maintained in accordance with the general guidelines for the care and use of laboratory animals recommended by the Council of European Communities (24). The hamsters were caged singly and kept in standard laboratory conditions with a controlled temperature (20±2°C) and a 12 h light/12 h dark cycle. Diabetes was induced in the hamsters using streptozotocin (STZ; catalog no. S0130; Sigma-Aldrich, St. Louis, MO, USA) (25). STZ, at a dose of 50 mg/kg body weight, freshly solved in citrate buffer (50 mM, pH 4.5), was administered intraperitoneally, as a single dose in the morning, following a night of fasting. Citrate buffer (50 mM) was prepared from sodium citrate and citric acid (S.C. Chemical Company, Iaşi, Romania) dissolved in distilled water, with adjustment of the pH to 4.5. The control group (C) received an equivalent quantity of citrate buffer (50 mM), administered intraperitoneally. All animals having a blood glucose level >126 mg/dl (7 mmol/l) were considered to be diabetic.\n\nBODY.MATERIALS AND METHODS.GROUPING AND DIETS:\nEach hamster received 15 g food/day and tap water ad libitum. The animals were randomly divided into a control group (C) and four diabetic groups (DM, DM + flax, DM + E and DM + Flax + E). The hamsters received four different diets for a 20-week period, as follows: i) Groups C and DM received a high-fat diet (40% energy as fat), that was deficient in ALA; ii) the DM + Flax group received a high-fat diet enriched with ground flaxseed (Linum usitatissimum; 15/100 g of food), that was rich in ALA; Flaxseed of the Olin variety was provided by the Department of Phytotechny of the Faculty of Agronomy (Iaşi, Romania). iii) the DM + E group received a high-fat diet enriched with vitamin E (40 mg α-tocopherol/100 g of food; Sigma-Aldrich); and iv) the DM + Flax + E group received a high-fat diet enriched with a combination of flaxseed and vitamin E. All four diets had similar carbohydrate, total fiber, protein and fat contents (Table I).\n\nBODY.MATERIALS AND METHODS.ANIMAL NECROPSY AND PROCESSING OF SAMPLES:\nAt the end of the experiment, the animals were sacrificed by cardiac puncture under ketamine anesthesia (100 mg/kg body weight). Blood samples were collected without anticoagulant. Aliquots of serum were frozen and kept at −80°C for subsequent analysis. The liver was immediately removed, rinsed with ice-cold saline, placed in a sealed container, homogenized for biochemical analysis and stored at −20°C until analyzed. The aortas were dissected, rinsed with cold saline and preserved in a phosphate buffer (pH 7.2).\n\nBODY.MATERIALS AND METHODS.SERUM GLUCOSE:\nSerum glucose was measured by enzymatic colorimetric methods on a Tecan microplate reader (Tecan SunriseTM Touchscreen, Männedorf, Switzerland) using the AD1A716 commercially available kits (Audit Diagnostics, Cork, Ireland).\n\nBODY.MATERIALS AND METHODS.SERUM LIPID PROFILE:\nSerum total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C) and triglyceride (TG) levels were measured by enzymatic colorimetric methods on a Tecan microplate reader using the AD1A704, AD1A602 and AD1A306 commercially available kits (Audit Diagnostics). Non-HDL-C levels were calculated by subtracting the level of HDL-C from that of TC.\n\nBODY.MATERIALS AND METHODS.EVALUATION OF CHOLESTEROL CONTENT IN THE AORTA:\nThe aortas of the hamsters in each group were removed. A section of the aortic arch of each animal was soaked in a 10% (v/v) formal saline solution and was stored on ice prior to being stained and fixed. The remainder of the aorta was soaked in phosphate-buffered saline (PBS) and homogenized for biochemical analysis. The lipid content was extracted by treatment with chloroform and methanol followed by centrifugation (26). The extracted lipid was dissolved in ethanol and measured using a AD1A704 cholesterol assay kit (Audit Diagnostics) utilizing absorbance spectrophotometry (Microlab 300, Vital Scientific, Spankeren, Netherlands) at 500 nm wavelength, and the amount quantified as μg/mg wet tissue.\n\nBODY.MATERIALS AND METHODS.PARAMETERS OF OXIDATIVE STRESS:\nSerum and liver thiobarbituric acid reactive substances (TBARS) are indices of lipid peroxidation and oxidative stress. TBARS were determined using the method described by Phelps and Harris (27). The quantity of the TBARS was measured using a Tecan microplate reader at a wavelength of 540 nm. Liver levels of reduced GSH were determined by an enzymatic reaction, based on the oxidation of GSH by 5,5′-dithiobis(2-nitrobenzoic acid) (DTNB), in the presence of GSH reductase and methylenetetrahydrofolate reductase, monitored at a wavelength of 405 nm (28). Liver SOD levels were determined using the method described by Minami and Yoshikawa (29).\n\nBODY.MATERIALS AND METHODS.MORPHOLOGICAL STUDY OF THE AORTA:\nFor evaluation of aortic atherosclerotic lesions by light microscopy, frozen sections of 10 μm thickness were taken from the region of the proximal aorta. The extent of atherosclerosis was visually assessed after cutting the frozen sections at a size of 8–10 mm, fixing them in formalin, briefly washing them with running tap water for 1–10 mins and rinsing with 60% isopropanol prior to staining the sections with Oil Red O (3 mg/ml Oil Red O in 60% acetone and 40% water; Sigma-Aldrich). The samples were then counterstained with hematoxylin and the samples were examined under a light microscope (Olympus BX40, Olympus, Tokyo, Japan).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nData are expressed as the mean ± standard deviation (SD). Univariate statistical analysis was performed using the Student's t-test and Bonferroni's multiple comparison test (Statistical Software Package SPSS®, version 13, SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS.SERUM GLUCOSE:\nThe addition of flaxseed or/and vitamin E to the high-fat diet led to significant reductions of serum glucose levels compared with those in the DM group (Table II).\n\nBODY.RESULTS.SERUM LIPID PROFILE PARAMETERS:\nDiabetes resulted in significant increases in the serum concentrations of TC, TG and non-HDL-C, and a significant reduction of HDL-C concentrations compared with those in the control group. Flaxseed supplementation significantly decreased serum TC and non-HDL-C levels and increased HDL-C levels (Table II) compared with those in the unsupplemented DM group. The addition of vitamin E to the flaxseed-rich diet significantly decreased TC, non-HDL-C and TG levels but did not improved the HDL-C level in diabetic hamsters.\n\nBODY.RESULTS.CHOLESTEROL CONTENT OF THE AORTA:\nAortic cholesterol contents were significantly increased in the DM group fed with a standard diet compared with those in the control group (Table II). Flaxseed or/and vitamin E supplementation of the diet significantly decreased the aortic cholesterol content in the hamsters with DM (Table II).\n\nBODY.RESULTS.PARAMETERS OF OXIDATIVE STRESS:\nThe main findings are summarized in Table III. Serum and liver TBARS, as indices of lipid peroxidation, were significantly increased in the DM group compared with those in the control group, while the addition of flaxseed or a combination of flaxseed and α-tocopherol to the high-fat diet of the hamsters with DM significantly decreased these two markers compared with those in the unsupplemented DM group. Liver GSH levels were significantly diminished in the DM group compared with those in the control group. Flaxseed, α-tocopherol and their combination added to the high-fat diet significantly increased the liver GSH levels in the diabetic hamsters. The increased in liver GSH content was significantly higher in the DM + Flax + E group compared with that in the DM + Flax group. No significant differences of SOD activity in the liver were identified between groups.\n\nBODY.RESULTS.HISTOLOGICAL CHANGES IN AORTIC TISSUES.CONTROL GROUP:\nThe histologic examination of aortal fragments with O-Rd staining revealed discrete thickening of the aortic intimal layer (Fig. 1A).\n\nBODY.RESULTS.HISTOLOGICAL CHANGES IN AORTIC TISSUES.DIABETIC GROUPS:\nThe histologic examination of aortic fragments with O-Rd staining from diabetic hamsters revealed morphologic changes specific to diabetic macroangiopathy (Fig. 1B). Intimal thickening, endothelial discontinuities, lipid drops in the subintimal space, and alterations to the middle layer of the arterial wall were observed. The addition of flaxseed and/or vitamin E to the high-fat diet in diabetic hamsters improved the histological aspects of aortic atherosclerosis described in the diabetic hamsters fed an unsupplemented diet. The aortal tissue in the supplemented groups was characterized by slightly swollen endothelium, with moderate intimal thickening and moderate lipid infiltration of the intima (Fig. 2).\n\nBODY.DISCUSSION:\nIn DM, oxidative stress occurs, primarily due to the increased production of oxygen free radicals and/or a reduction in the antioxidant defense. Numerous studies have demonstrated that an increase in oxidative stress is implicated in the pathogenesis and progression of diabetic vascular lesions (1,4,6). In the present study, the antioxidative and antiatherosclerotic effects of supplementation with flaxseed (15 g Linum usitatissimum/100 g food), α-tocopherol (40 mg α-tocopherol/100 g food), and their combination were investigated in an animal model that replicates human atherosclerotic lesions. Golden Syrian hamsters appear more predisposed to develop atherosclerotic lesions than rats (30), and present many similarities with the lipoprotein metabolism in humans (31). In hamsters, a 15% flaxseed-supplemented diet is similar in energetic load to the 40 g/day dosage used in human trials. In humans, high doses of 40–50 g flaxseed/day, which corresponds to ~10% of total energy intake have been used in trials (32). In the present study, it was hypothesized that adding vitamin E to the flaxseed diet would lead to improved results for oxidative stress and the prevention of atherosclerotic lesions as there is evidence that the consumption of flaxseed reduces vitamin E (19), and only vitamin E supplementation is able to restore the plasma concentration (20). The present study demonstrated that all three diets (flaxseed, α-tocopherol or their combination) had an antiatherogenic effect in diabetic hamsters, suggested by the prevention of histological lesions (reduced intimal lipid infiltration and discrete alterations to the middle layer of the arterial wall) and by the decreased aortic cholesterol content in supplemented diabetic hamsters compared with those in the unsupplemented diabetic group. The antiatherogenic mechanism of the diets used in our experiment may be associated with changes in metabolic parameters, particularly in glucose concentrations and the lipid profile, and oxidative stress. Flaxseed, α-tocopherol, and the combination of flaxseed and α-tocopherol added to the high-fat diet resulted in similar reductions in serum lipid peroxidation in the diabetic hamsters. Liver lipid peroxidation was significantly diminished by supplementation of the diet by flaxseed alone or in combination with α-tocopherol, but not by α-tocopherol supplementation alone. Moreover, all three diets increased the liver GSH content and the highest concentrations were obtained with the combined diet. These results suggest that the higher antioxidant effects of flaxseed plus vitamin E are due to their synergic antioxidant actions. Flaxseed is the richest source of the lignan SDG. SDG isolated from flaxseed has oxygen radical-scavenging properties that have been demonstrated in vitro by direct hydroxyl radical-scavenging activity (18) or by inhibition of lipid peroxidation (16). Vitamin E is known as a major antioxidant in the cellular antioxidant defense system, which acts by interrupting the propagation of free radical chain reactions. The effect of vitamin E against the prooxidant status associated with DM has been demonstrated by the suppression of diabetes-induced increases in ROS and diminishment of lipid peroxidation (33,34). The synergistic effect of flaxseed oil and vitamin E on oxidative stress has also been observed by Deng et al (35) in male Wistar rats fed a high-fat diet. Similar to the findings of previous studies (36), the diabetic hamsters had higher serum concentrations of serum glucose, TC, TG and non-HDL-C, and lower HDL-C concentrations compared with the control group. The addition of flaxseed, α-tocopherol or their combination to the high-fat diet reduced serum concentrations of glucose, TC and non-HDL in diabetic male hamsters (37,38). The hypocholesterolemic effects of flaxseed may be attributed to ALA, lignans (SDG) or the fiber content (39). In agreement with other studies (40), vitamin E significantly reduced serum TG levels in diabetic hamsters fed an atherogenic diet. In the present study, the addition of vitamin E alone or in combination with flaxseed to the high-fat diet resulted in lower serum concentrations of TC, non-HDL and TG but failed to correct the HDL-C concentrations in diabetic hamsters. Another study has reported that in hamsters with experimental STZ-induced DM fed high a saturated fat and cholesterol diet, supplementation with α-tocopherol increased TC and did not change HDL-C (40). The results of the present study suggest that the antiatherogenic effect of flaxseed, α-tocopherol and their combination added to a high-fat diet in diabetic hamsters is based primarily on the antioxidative role of these components. The improvement of serum glucose and non-HDL were evident and could contribute to the prevention of diabetic macroangiopathy. The antioxidant effect of flaxseed was similar to that of α-tocopherol in diabetic hamsters fed a high-fat diet and the combined diet (Flax + E) did not seem to confer more benefits than flaxseed alone. Moreover, the high dose of ground flaxseed alone may have a better cardioprotective effect than α-tocopherol in diabetic hamsters due to the reduction of TC and non-HDL levels and increase in HDL-C levels. Oxidative stress has been proposed as a pathogenic mechanism of diabetic macrovascular complications, and dietary strategies that ameliorate oxidative stress may represent a promising approach to the prevention of atherosclerosis. The flaxseed-enriched diet may regulate the generation of reactive oxygen species and the metabolism of glucose and lipids, and could consequently play a role in the prevention of major cardiovascular complications in diabetic states. Ground flaxseed combined with α-tocopherol does not appear to confer a clear advantage compared with flaxseed alone in the reduction of oxidative stress and vascular lesion formation in experimental diabetes.\n\nQuestion: Compared to received a high-fat diet (40% energy as fat), deficient in ?-linolenic acid (ALA) what was the result of high-fat diet enriched with ground flaxseed 15 g/100 g of food, rich in ALA; on serum TC and non-HDL-C levels ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1078	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Attenuating effect of \n\n ABSTRACT.BACKGROUND/OBJECTIVES:\nLactobacillus brevis G101 suppresses the absorption of monosodium glutamate (MSG) from the intestine into the blood in mice. Therefore, the attenuating effect of orally administered G101 on monosodium glutamate (MSG) symptom complex was investigated in humans.\n\nABSTRACT.MATERIALS/METHODS:\nCapsules (300 mg) containing Lactobacillus brevis G101 (1×1010 CFU/individual) or maltodextrin (placebo) was orally administered in 30 respondents with self-recognized monosodium glutamate (MSG) symptom complex for 5 days and the rice with black soybean sauce containing 6 g MSG (RBSM) was ingested 30 min after the final administration. Thereafter, the MSG symptom complex (rated on a 5-point scale: 1, none; 5, strong) was investigated in a double blind placebo controlled study. The intensity of the MSG symptom complex was significantly reduced in respondents of the G101 intake group (2.87 ± 0.73) compared to that in those treated with the placebo (3.63 ± 1.03) (P = 0.0016). Respondents in the placebo group exhibited more of the various major conditions of the MSG symptom complex than in the G101 intake group. Although there was no significant difference in the appearance time of the MSG symptom complex between subjects orally administered G101 and those administered the placebo, its disappearance in < 3 h was observed in 69.9% of subjects in the G101 treatment group and in 38.0% of subjects in the placebo group (P = 0.0841).\n\nABSTRACT.CONCLUSIONS:\nOral administration of Lactobacillus brevis G101 may be able to reduce the intensity of the MSG symptom complex.\n\nBODY.INTRODUCTION:\nMonosodium glutamate (MSG), the sodium salt of glutamate, is used worldwide as a flavor enhancer in various processed foods [123]. MSG was extracted from seafood and has been as the source of the umami taste [4]. The Food and Drug Administration (FDA) has classified MSG as a generally recognized as safe (GRAS) substance and no limitation is placed on its use as a food additive. Nevertheless, Kwok first described a complex of symptoms, including numbness at the back of the neck and arms, weakness, and palpitation, after ingestion of a Chinese meal and suggested that MSG was one of the possible causes [5]. These symptoms were referred to collectively as Chinese Restaurant Syndrome (CRS). In 1995, the Federation of American Societies for Experimental Biology (FASEB) proposed the term MSG symptom complex to denote the reactions that occur following ingestion of MSG [6]. When > 5 g may be ingested, it is characterized by unpleasant reactions such as numbness, tingling, headaches, muscle tightness, general weakness, and flushing [7]. Lactic acid bacteria are found in yogurt, cheese, kimchi, and in the gut microbiota [8]. Upon ingestion, lactic acid bacteria confer beneficial effects on the health of the host [9]. Of these lactic acid bacteria, some convert MSG to gamma-aminobutyric acid (GABA), which has been reported to possess various physiological functions that act via the decarboxylation of glutamic acid by glutamate decarboxylase [1011]. Therefore, lactic acid bacteria have been used as initiators to produce GABA-rich foods [12]. We previously isolated Lactobacillus brevis G-101, a kimchi-derived lactic acid bacterium that potently converted MSG to GABA [13]. Lactobacillus brevis G101 reduces the concentration of MSG in the blood of mice fed oral administration in mice: G101 suppresses the absorption of MSG from the intestine into the blood rather than mediating the biotransformation of MSG to GABA [14]. In the present study, to investigate the ability of orally administered Lactobacillus brevis G101 to attenuate the MSG symptom complex, we orally administered G101 or a placebo (maltodextrin) to respondents presenting with self-recognized MSG symptom complex, following ingestion of rice with black soybean sauce (Jajangbap) containing 6 g MSG (RBSM), and then investigated the intensity of the MSG complex in them. This experiment was performed as a double-blind, placebo-controlled study.\n\nBODY.SUBJECTS AND METHODS.SUBJECTS:\nThe study subjects consisted of 30 healthy Korean individuals (average age, 23.57 ± 2.36 yrs; 10 male subjects, 23.00 ± 3.46 yrs; 20 female subjects, 23.85 ± 1.60 yrs) who self-identified as MSG-sensitive. Exclusion criteria included consumption of any current medication. The recruitment of subjects was approved by the Committee for the Care and Use of Clinical Study at Kyung Hee University (KHSIRB-14-004) and performed according to CONSORT 2010 guidelines.\n\nBODY.SUBJECTS AND METHODS.EXPERIMENTAL PLAN:\nAll 30 subjects participated in an orientation session for this study. The subjects were evenly divided into 2 groups (A and B). In the first week, group A subjects were orally administered one capsule (Lactobacillus brevis G101) at 11:00 am for 5 days and group B subjects took the placebo capsule every day (Table 1). RBSM was ingested 30 min after the final administration of G101, and the intensity and variety of the MSG symptom complex over 6 h were described. In the second week, group A switched with group B and the test was performed for 5 days. The intensity of the MSG symptom complex was rated according to a 5-point scale (1 = none, 5 = strong). Capsules (300 mg) containing 1 × 1010 CFU Lactobacillus brevis G101 or maltodextrin (placebo) were prepared by CTCBIO Inc. RBSM was prepared by mixing steamed rice (180 g) and MSG-contained black soybean sauce. The ingredients of the MSG-contained black soybean sauce (one serving) were as follows: 40 g pork, 40 g onion, 40 g zucchini, 30 g carrot, 50 g cabbage, 1 Tsp black soybean sauce without MSG, 1/2 Tsp soybean oil, 6 g MSG, 1 tsp starch, and 1 2/3 Tsp water. MSG was purchased from a local market.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSIS:\nThe results obtained through this experiment were analyzed using the statistical analysis system (SAS) 9.3 program. The significance of each sample was established using χ2-test and t-test, as appropriate.\n\nBODY.RESULTS.EFFECT OF LACTOBACILLUS BREVIS G101 ON THE INTENSITY OF RBSM-INDUCED MSG SYMPTOM COMPLEX:\nTo evaluate the attenuating effect of Lactobacillus brevis G101 against the MSG symptom complex, we orally administered G101 to volunteers who then ingested RBSM, and after which we evaluated the MSG symptom complex for 6 h in a double-blind, placebo-controlled study (Table 2). The intensity of MSG symptom complex was measured using a 5-point scale (1 = none, 5 = strong). Oral administration of G101 significantly attenuated the intensity of the MSG symptom complex (P = 0.0016). When treated with the placebo, 43.3% of respondents presented with more than a slightly strong MSG symptom complex, but when treated with G101, only 20.0% of respondents exhibited more than a slightly strong response. A significant difference was observed among female subjects, but not among male subjects, indicating that female respondents were more sensitive to the MSG symptom complex than male (Table 3).\n\nBODY.RESULTS.EFFECT OF LACTOBACILLUS BREVIS G101 ON RBSS-INDUCED MSG SYMPTOM VARIETY:\nThe effects of orally administered G101 on RBSM-induced self-recognized MSG symptoms (variety) experienced by the respondents were investigated (Table 4). After ingestion of RBSM, the most frequently observed self-recognized symptoms associated with the MSG symptom complex were thirstiness (81.7%) and drowsiness (70.0%), followed by weakness (26.7%), tightness (11.7%), headache (10.0%), nausea (10.0%), dizziness (8.3%), palpitation (1.7%), flushing (1.7%), and indigestion (1.7%). No significant difference was observed between the varieties of self-recognized symptoms experienced by respondents who were orally administered G101 and those administered the placebo.\n\nBODY.RESULTS.EFFECT OF LACTOBACILLUS BREVIS G101 ON THE APPEARANCE AND DISAPPEARANCE TIME OF RBSS-INDUCED MSG SYMPTOM COMPLEX:\nThe effect of orally administered G101 on the time at which the RBSM-induced MSG symptom complex appeared was also evaluated (Table 5). There was no significant difference in the appearance time of the MSG symptom complex observed between subjects orally administered G101 and those administered the placebo. When subjects were treated with G101, the appearance for the MSG symptoms complex was less than 1 h for 70.0% of the respondents in the group, and in subjects treated with the placebo, the appearance time was for 76.6% of the group. Next, we investigated the effect of orally administered G101 on the disappearance time for the RBSM-induced MSG symptoms complex (Table 6). There was no significant difference in the appearance time for the MSG symptom complex between subjects orally administered G101 and those administered the placebo. Disappearance of the MSG symptom complex in less than 3 h was observed in 69.9% of subjects in the G101 treatment group and in 38.0% of subjects in the placebo group (P = 0.0841).\n\nBODY.DISCUSSION:\nMSG is frequently used in various canned foods and in food from Chinese restaurant. MSG has been associated with various side effects, including numbness, headaches, migraines, palpitations, tightness, weakness, aching, flushing, sweating, fasciculation, lacrimation, syncope, dizziness, shudder attacks, paresthesia, arrhythmia and tachycardia [1]. Although the oral threshold range for minimal MSG-induced symptoms in humans is considerably variable, in the previous study, the oral threshold range for minimal MSG-induced symptoms in 36 subjects was found to be 1.5 to 12 g, and increased intensity of the MSG symptom response was related to an increase in the oral dose [15]. In this study, we found that oral administration of RBSM, which is containing 6 g of MSG, showed various side effects including thirstiness (56.7%), drowsiness (23.3%), weakness (6.7%), indigestion (6.7%), headache (3.3%), and nausea (3.3%). It was previously shown that the elimination of all food sources containing MSG resulted in a decreased frequency of headaches [3]. These results suggest that the side effects of MSG are dependent on the daily intake amount of MSG, and the oral intake of more than 6 g of MSG may cause its side effect. Therefore, Xiong et al. suggested possible ways to reduce the side effects of MSG, such as taking vitamin C or pre-exposure to a low dose of MSG that may either prevent or reduce the side effects of MSG [3]. Nevertheless, it is not sufficient to reduce only the side effects of MSG. Therefore, we investigated the ability of Lactobacillus brevis G101 to reduce the side effects of MSG. Oral administration of Lactobacillus brevis G101 significantly attenuated the MSG symptom complex. Although G101 did not reduce the variety of side effects, it shortened the disappearance time of the MSG symptom complex. In conclusion, this study suggests that orally administration of Lactobacillus brevis G101 may be able to reduce the intensity of the MSG symptom complex and shorten its disappearance time.\n\nQuestion: Compared to maltodextrin (placebo) what was the result of Capsules (300 mg) containing Lactobacillus brevis G101 (1×1010 CFU/individual) on the appearance time of the MSG symptom complex?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1083	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Laser Peripheral Iridotomy versus Trabeculectomy as an Initial Treatment for Primary Angle-Closure Glaucoma\n\n ABSTRACT.PURPOSE:\n To compare laser peripheral iridotomy (LPI) with trabeculectomy as an initial treatment for primary angle-closure glaucoma (PACG) with peripheral anterior synechiae (PAS) ≥ 6 clock hours. \n\nABSTRACT.METHODS:\n Patients were drawn from two randomized controlled trials. 38 eyes of 38 patients (PAS ≥ 6 clock hours) were treated with LPI (group 1) while 111 eyes of 111 PACG patients (PAS ≥ 6 clock hours) underwent primary trabeculectomy (group 2). All patients underwent a comprehensive ophthalmic examination at baseline and at postoperative visits and were followed up for a minimum of one year. \n\nABSTRACT.RESULTS:\n Group 2 had higher baseline IOP (45.7 ± 14.8 mmHg versus 34.3 ± 14.3 mmHg) than group 1 and more clock hours of PAS (10.4 ± 1.9 versus 9.0 ± 2.2). IOPs at all postoperative visits were significantly lower in group 2 than in group 1 (p = 0.000). Five eyes in group 1 required trabeculectomy. 17 of the 38 eyes in group 1 (44.7%) required IOP-lowering medications as compared to seven of the 111 eyes in group 2 (6.3%). Cataract progression was documented in 2 eyes (5.3%) in group 1 and 16 eyes (14.4%) in group 2. \n\nABSTRACT.CONCLUSIONS:\n Primary trabeculectomy for PACG (PAS ≥ 6 clock hours) is more effective than LPI in lowering IOP.\n\nBODY.1. INTRODUCTION:\nPrimary angle-closure glaucoma (PACG) is the major type of primary glaucoma in China [1–4]. The management of PACG in China is different from the recommendations of the American Academy of Ophthalmology Preferred Practice Patterns (PPP) and other published guidelines [5–7]. For primary angle closure (PAC) and PACG, the PPP recommends laser peripheral iridotomy (LPI) to eliminate pupillary block followed by a treatment strategy \"similar to that for POAG\" [8]. Accordingly, LPI is used as the first-line treatment for all patients with PAC or PACG, medication is added as needed, and surgery is considered when the intraocular pressure (IOP) cannot be controlled with maximum tolerated medications. In China, however, trabeculectomy is considered a primary option for PACG and is generally undertaken if peripheral anterior synechiae (PAS) are greater than 6 clock hours [9, 10]. To the best of our knowledge, there is no comparative study of LPI versus primary trabeculectomy in PACG to support such an approach. Using data from patients enrolled in two separate randomized controlled trials [11, 12], we compared the IOP-lowering efficacy and safety of LPI versus trabeculectomy as an initial treatment for PACG with PAS ≥ 6 clock hours.\n\nBODY.2. METHODS:\nPatients included in this study had participated in 2 randomized clinical trials (RCTs) for PACG. Both trials were conducted in accordance with the tenets of the Declaration of Helsinki and approved by the ethics committee of the Tongren Eye Centre, Capital Medical University. Written informed consent was obtained from all subjects for participation in the original trials. Patients undergoing primary trabeculectomy for PACG had participated in a multicenter RCT (registration number: ChiCTR-TCR-00000218) [12]. This RCT was conducted in four clinical collaborative centers of Beijing Tongren Hospital: Handan 3rd Hospital (Hebei Province, China), Anyang Eye Hospital (Henan Province, China), Fushun Eye Hospital (Liaoning Province, China), and the Chenzhou Eye and Optometry Center (Hunan Province, China). PACG was defined as primary angle closure with glaucomatous optic neuropathy and corresponding visual field defects, and patients were recruited from the four centers between April 2006 and November 2007. The primary purpose of the trial was to report the efficacy and complications of trabeculectomy with or without releasable sutures in PACG. Patients who underwent LPI as an initial treatment were part of another RCT (registration number: ChiCTR-TRC-00000034, http://www.chictr.org.cn) conducted at the Handan 3rd Hospital [11]. The purpose of this RCT was to investigate the role of laser iridotomy (with or without iridoplasty) in patients with synechial PAC or PACG. The definition of PACG was the same as that used in the trial mentioned above; consecutive cases of PAC and PACG presenting to the hospital between October 1, 2005, and October 31, 2006, were recruited for this trial.\n\nBODY.2. METHODS.2.1. PATIENT SELECTION:\nThe inclusion criteria for the current study were as follows:\nPACG: defined as primary angle closure with glaucomatous optic neuropathy and visual field defects [13]Age 40 years or morePAS ≥ 6 clock hoursMinimum follow-up of one year. Patients with acute angle-closure glaucoma were excluded. As part of the original clinical trial, all patients had undergone a comprehensive ophthalmic examination including refraction, Goldmann applanation tonometry, static and dynamic gonioscopy (manipulation) using a one-mirror Goldmann gonioscope [14, 15], slit-lamp examination, fundus examination, and automated perimetry (Humphrey Field Analyzer 750i, Carl Zeiss Meditec; Sita Fast strategy; and 24–2 threshold test). These examinations were performed at baseline and at postoperative visits scheduled at month 1, month 3, month 6, month 12, and month 18. Postoperative visits were scheduled on day 1, day 3, week 1, week 2, month 1, month 3, month 6, month 12, and month 18 following the LPI or trabeculectomy.\n\nBODY.2. METHODS.2.2. LASER PERIPHERAL IRIDOTOMY:\nAll laser procedures were performed by one of two senior glaucoma specialists. 2% pilocarpine was applied, and iridotomy was performed under topical anesthesia using a Nd:YAG laser (YL-1600; NIDEK Co. Ltd., Japan) using an Abraham contact lens (Ocular Instruments Inc., Bellevue, USA). A treatment site was selected in the superior nasal iris or in a crypt where present. The treatment was initiated with a single 4 mJ pulse, the power was adjusted, and the treatment was continued to obtain a 0.2 mm opening; patency was determined by direct visualization of the posterior chamber. In accordance with local practice, IOP-lowering medication was initiated if the IOP was greater than 21 mmHg following laser and confirmed by a repeat reading on the same day [11].\n\nBODY.2. METHODS.2.3. TRABECULECTOMY:\nSurgery was performed under topical or peribulbar anesthesia using a standard surgical technique. The eye was prepared using a standard aseptic technique and draped to isolate the lashes. A lid speculum was inserted and a 7/0 superior rectus muscle traction suture was placed. A limbus-based conjunctival flap was created using a 10 mm incision through the conjunctiva and Tenon's capsule approximately 8–10 mm from the limbus. The flap was dissected forwards and hemostasis achieved with monopolar diathermy. A half-thickness 4 × 3 mm2 rectangular scleral flap was fashioned, and cellulose sponges soaked in MMC (0.3 mg/ml) were applied under the scleral flap, conjunctiva, and Tenon's capsule for a duration determined by the surgeon based on an assessment of risk factors. Irrigation with balanced salt solution was performed to wash out residual MMC solution. A paracentesis was created, a 2 × 1.5 mm trabeculectomy block excised, and an iridectomy performed. The scleral flap was sutured with 10-0 monofilament, BSS was injected into the anterior chamber to assess flow, and the conjunctiva was closed with a single running 8/0 vicryl suture [12]. Visual acuity was recorded with a decimal chart and converted to the logarithm of minimum angle of resolution (LogMAR) format. Finger counting, hand movement, and light perception were recorded as 1.5, 2.0, and 2.5 on the LogMAR scale. At each postoperative visit, a trained technician measured the IOP twice using an applanation tonometer and recorded the average. If the difference between the two measurements was more than 2 mmHg, a third measurement was performed, and the average of the two closer results was recorded. All IOP measurements were performed between 8 am and 12 am. At each site, trained observers used standard LOCS III photographs to assess the lens. Cataract progression was defined as an increase of 2 or more units greater than baseline in any LOCS III category (nuclear, cortical, or posterior capsular opacity). Progression was analyzed in all eyes with a minimum follow-up of 12 months; for those whose longer follow-up was available, it was determined at the 18-month visit. The shallow anterior chamber (AC) was categorized as grade I = peripheral iris-cornea touch; grade II = midiris-cornea touch; and grade III = central cornea-lens touch [16]. Hypotony was defined as IOP ≤ 5 mmHg [17]. At each visit, other complications and interventions, if undertaken, were recorded.\n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nOne eye of each patient was randomly selected for the analysis. Statistical analysis was carried out using SPSS 15.0 (SPSS Inc., Chicago, USA). Independent t-test was used to compare the difference between the groups, and the chi-square test was used to compare the difference in IOP-lowing medication and cataract progression between the groups. A p value < 0.05 was considered significant.\n\nBODY.3. RESULTS:\n38 eyes of the 38 patients with PACG that underwent primary iridotomy comprised group 1 while group 2 consisted of 111 eyes of the 111 PACG patients who had undergone trabeculectomy. The baseline characteristics of the two groups are summarized in Table 1. Patients in group 2 were slightly younger and had higher baseline IOP and more clock hours of PAS. \nTable 2 shows the postoperative IOP and visual acuity. At each visit, the IOP was significantly lower in group 2 (p < 0.001). Five eyes in group 1 required trabeculectomy: 1 eye at 6 months, 2 eyes at 12 months, and 2 eyes at 18 months. 17 of the 38 eyes (44.7%, CI: 28.9%–60.5%) in group 1 required a mean of 1.8 IOP-lowering medications while seven of the 111 eyes (6.3%, CI: 1.8%–10.8%) in group 2 required a mean of 1.1 medications (Pearson's chi-square value = 30.940, p < 0.001). 19 eyes in group 2 developed a transient shallow anterior chamber (AC), but there was no instance of lens-cornea touch. 16 eyes (including 13 eyes with shallow AC) experienced transient hypotony. Hypotony lasted one day in 14 eyes and one week in 2 eyes and all recovered spontaneously. One eye developed hypotony maculopathy at one month after surgery that was resolved after IOP increased 3 weeks later. In one eye, the IOP increased to 60 mmHg at 3 months postsurgery and required cyclophotocoagulation. Best-corrected visual acuity at 18 months was 0.5 ± 0.5 in group 1 and 0.6 ± 0.7 in group 2. Four eyes (10.5%) in group 1 lost one line of vision, 3 eyes (7.9%) lost 2 lines, and 3 (7.9%) lost more than 2 lines. In group 2, thirteen eyes (11.7%) lost 1 line, 9 eyes (8.1%) lost 2 lines, and 11 eyes (9.9%) lost more than 2 lines. Six eyes in group 1 and 20 eyes in group 2 lost ≥2 lines (Pearson's chi-square value 0.098, p = 0.755). The absolute risk for ≥2 lost lines of vision in the trabeculectomy group was 18% (20 of 111) compared to 16% (6 of 38) in the LPI group. The absolute risk increased with trabeculectomy is 2% and the number needed to harm (NNH) is 50. Cataract progression as defined was documented in 2 eyes (5.3%, CI: −1.8%–12.4%) in group 1 and 16 eyes (14.4%, CI: 7.9%–20.9%) in group 2 (Pearson's chi-square value = 2.232, p = 0.135). The absolute risk increased in cataract formation with trabeculectomy is 9% and translates into a NNH of 11.\n\nBODY.4. DISCUSSION:\nThe PACG treatment strategy formulated by the glaucoma group of the Chinese Ophthalmology Society is different from that formulated by other published guidelines. As per Chinese guidelines, LPI is suggested for \"patients with PAS < 180° without optic disc and visual field damage\" (an indication endorsed without data by a recent publication), while primary trabeculectomy is recommended for PACG with PAS ≥ 180° [9, 18]. A 2005 survey of clinical practice in PACG diagnosis and treatment found that 73% of Chinese glaucoma specialists preferred trabeculectomy as the initial treatment for PACG with PAS ≥ 180° [10]. Evidence for such an approach is however lacking, and to the best of our knowledge, our study is the first study to compare primary LPI with primary trabeculectomy for PACG. LPI is considered a noninvasive, simple, and safe intervention in PACS, PAC, and PACG [19]. The effect of a LPI would depend on the amount of angle that is available for filtration, and this can be estimated clinically by the extent of PAS [18, 20]. IOP control following LPI as reported in the literature varies considerably, and the therapeutic effect seems to decrease over time [21, 22]. In a retrospective analysis of 131 cases (251 eyes) in China, 18 eyes with PACS, 98 eyes with PAC, and 129 eyes with PACG that underwent LPI were followed up for 9.2 ± 3.7 years [23]. Eyes with PAC and PACG had PAS < 6 clock hours. At the final follow up, 16/18 PACS, 38/98 PAC, and 814/129 of PACG eyes were controlled (defined as IOP less than 21 mmHg) without medications. 60% of cases required additional medications and 13% needed filtering surgery. A study from India evaluated the long-term outcome of PACG following laser iridotomy [24]. 70 consecutive patients with PACG whose IOP remained >21 mmHg despite a patent iridotomy had their IOP controlled by medications or trabeculectomy and were followed up over a 6-year period. A trabeculectomy without antimetabolites was performed if IOP was >21 mmHg on maximal tolerable medical therapy, if there was evidence of progression of the disc/visual field, or if the patient was noncompliant. 46 (65.7%) eyes were controlled medically with 26 (57%) eyes requiring two topical medications. 24 (34.3%) eyes required trabeculectomy at various times during follow-up. The extent of PAS was not reported in this study, but reports suggest that the therapeutic effect of LPI decreases over time and many cases need filtering surgery. The results seem consistent with the biologically plausible hypothesis that LPI is more successful in those with relatively undamaged trabecular meshwork [18]. The literature seems to suggest that, despite the presence of a patent LPI, eyes with established PACG and a certain (currently undefined) extent of PAS require further treatment to control IOP and that medical therapy fails in a significant number of cases necessitating filtering surgery [18, 25]. In the current investigation, the IOP during follow-up was significantly lower in the trabeculectomy group. Furthermore, a larger number of patients who underwent LPI needed medical treatment as compared to those who underwent trabeculectomy. In this developing country, setting patients may not be able to afford medical treatment or are generally not adherent or persistent with it. To simulate a real-world condition, we did not provide free IOP-lowering medication and found that 24% of patients could not afford long-term medication. Moreover, 5 eyes (13.2%) of patients who underwent LPI with baseline PAS ≥ 6 clock hours (group 1) had to undergo trabeculectomy during the follow-up period. The poor effectiveness of IOP lowering following LPI for PACG with ≥6 hours of PAS would seem important in selecting treatment within the well-known constraints of a developing country, including a possible one shot at treatment. We therefore suggest that 6 clock hours of PAS can be considered a provisional clinical threshold for LPI in PACG, as this is likely to change with further research and will be different for individual cases. Our findings lend credence to a recently published algorithm for the management of angle-closure disease that recommended a ≥6 clock hour threshold for PAS; that algorithm was based mainly on biological plausibility [18]. Considering the problems of medical treatment in developing countries, a policy of primary trabeculectomy for PACG with ≥6 clock hours of PAS might merit consideration. In fact, even eyes with <6 clock hours of PAS may be considered for a trabeculectomy if the socioeconomic situation so dictates [23]. The choice of initial treatment must also consider the issue of complications. Consistent with most other publications, we did not encounter any significant complications in the LPI group [11]. While complications with trabeculectomy are more frequent, the incidence of severe sight-threatening complications is now less than what it was 20 years ago; we encountered mainly transient shallow chamber and hypotony. It must be kept in mind that in our study, trabeculectomy was undertaken by glaucoma specialists in the context of a clinical trial and the potential for sight-threatening complications remains. Importantly, even in the context of a clinical trial, 18% of eyes undergoing trabeculectomy lost 2 or more lines of vision. However, the number needed to harm for ≥2 lost lines of vision is an acceptable 50. Incision-induced astigmatism as well as progression of cataract was the major reason for visual loss, but both would be considered treatable. 19% of patients in undergoing trabeculectomy had astigmatism of >1D at 6-month visit, and 14.4% had obvious progression of lens opacity. The NNH for progression of cataract with trabeculectomy was 11. While successful intervention is available for cataracts, this low NNH that could lead to an increase in the burden of cataract is a disadvantage with trabeculectomy. The choice for the initial intervention for PACG in China and other developing countries must weigh up effectiveness versus complications as well as the need for additional medications and further interventions. While LPI is safe and easy, there is a more need for intensive medications and surgical intervention. The role of cataract extraction in primary angle-closure disease is evolving but is again more likely to be useful for those with angles less compromised by PAS [18, 26]. Trabeculectomy is better than LPI for lowering the IOP, but it does have the potential for more loss of visual acuity and for serious complications. Accordingly, it is probably best to reserve primary surgical intervention for established PACG with ≥6 clock hours as these are unlikely to do well with laser alone. While not statistically significant in this study, the higher chances for progression of cataract following trabeculectomy raise the question of combining filtration with cataract surgery, an issue not addressed in this study. In addition to clinical factors, any decision will also depend on the availability of lasers and surgeons and costs. One of the limitations in our study is the small sample size in group 1 and the relatively short follow-up time. As few patients progressed during this time, we could not analyze the relationship between IOP and the visual field progression, but IOP would usually be considered an acceptable surrogate. Also, our results are derived from patients enrolled in RCTs, and the effectiveness in the real world is likely to be different. Furthermore, as it was not part of this study, we cannot comment on the increasingly popular role of phacoemulsification or its combination with trabeculectomy in the management of PACG [18]. The low NNH for cataracts with trabeculectomy could however be used as an argument for combining the two surgical procedures. Finally, while the definition of PACG used in both trials was the same, patients for this study were drawn from two separate trials that asked different questions. This could introduce significant bias. The original LPI RCT (registration number: ChiCTR-TRC-00000034, http://www.chictr.org.cn) [11] that randomized patients into two different treatment groups (iridotomy or iridotomy plus iridoplasty) found no significant difference in IOP, medications, need for surgery, or visual function between groups at the 1-year visit. This RCT showed that in eyes with PACG, both iridotomy alone and iridotomy combined with iridoplasty provide a significant and similar reduction in IOP. For the trabeculectomy RCT (registration number: ChiCTR-TCR-00000218) [12], patients were randomly allocated to permanent or releasable sutures. This study too did not demonstrate any significant differences between the groups. Accordingly, we felt that analyzing patients from either arm of the two trials for the current study was acceptable but acknowledge that the possibility of unknown differences does exist and could affect interpretation. However, as the baseline IOP was higher and PAS more extensive in the trabeculectomy group, the conclusion in favor of trabeculectomy is likely to stand. In conclusion, our results support the Chinese guidelines for management of PACG. In PACG with ≥6 clock hours of PAS, primary trabeculectomy is more effective than LPI in lowering IOP and significantly requires less medication but with more progression of cataract and more loss visual acuity. In developing countries, such as China, trabeculectomy can be considered a primary option for PACG with this degree of PAS.\n\nQuestion: Compared to primary trabeculectomy group 2 what was the result of laser peripheral iridotomy (LPI) group 1 on intraocular pressure (IOP)-lowering medications?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1087	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Changes in proprioception and pain in patients with neck pain after upper\nthoracic manipulation\n\n ABSTRACT:\n[Purpose] The purpose of this study was to conduct cervical stability training and upper\nthoracic manipulation for patients with chronic neck pain and then investigate the changes\nof cervical proprioception and pain. [Subjects and Methods] Subjects were 30 workers with\nmechanical neck pain, who were randomly divided into an upper thoracic manipulation group\nand a cervical stability training group. Upper thoracic manipulation after cervical\nstability training was conducted for the upper thoracic manipulation group, and only\nstability training was conducted for the cervical stability training group. The\nintervention period was six weeks, and consisted of three sessions a week, each of which\nlasted for 30 minutes. For proprioception measurement, an electro-goniometer was used to\nmeasure reposition sense before and after the intervention. The visual analogue scale was\nused to assess pain. [Results] After the intervention, the error angle was significantly\nsmaller in flexion and right left side-bending, and pain was significantly reduced in the\nupper thoracic manipulation group. According to the post intervention comparison of the\ntwo groups, there were significant differences in the proprioception and pain values.\n[Conclusion] Conducting both cervical stability training and upper thoracic manipulation\nfor patients with chronic neck pain was more helpful for the improvement of proprioception\nand pain than cervical stability training alone.\n\nBODY.INTRODUCTION:\nNeck pain is a disease that most people experience at least once in their life time. Neck\npain is the main cause of an increase in economic and social health costs. To treat neck\npain, physical therapists often use therapeutic exercise, traction, joint mobilization, and\nmanipulation1, 2). In the case of the patients with chronic neck pain, because of overuse, repetitive trauma,\nserious trauma and muscle weakness, the range of elasticity of the non-contractile tissues\nbecomes enlarged, and stablize the neutral position, and contractile tissues become weak. As\na result, instability increases in the spinal segments, resulting in failure to maintain the\nneutral position. Joint instability is accompanied by loss of somatosensory system function.\nIn addition, joint instability causes hyper-mobility of cervical segments, and restricts the\nmovement of the thoracic segments, which ultimately leads to functional restriction2). Manipulation and mobilization are clinically employed often to improve cervical instability\nand functional movement. Thoracic manipulation and joint mobilization help to increase the\nrestricted mobility of the spinal segments, to improve cervical mobility and stability, and\nto recover functional movement and proprioception, and ultimately reducing pain and\nfunctional disorder3, 4). In order to recover cervical proprioception in patients with chronic neck pain, a\ntherapeutic approach is conducted to improve cervical instability, joint mobility, and\nneuromuscular control. Cranio-cervical flexor (CCF) training aims at recovery of control of\nthe muscular system around the cervical spine and the recovery of cervical proprioception.\nFor improvement in cervical joint mobility, manipulation and mobilization are performed5). Previous studies have reported that direct cervical manipulation is a dangerous cervical\ntreatment, because it can reduce the function of the spinal artery. For that reason, CCF\ntraining is widely employed to improve proprioception, pain and range of motion (ROM), and\nreduce the neck disability index (NDI) score of patients with neck pain4, 6). Recently, indirect thoracic manipulation and mobilization have frequently been used to\ntreat patients with neck pain, because it is safer than direct manipulation. Spinal\nmanipulation elicits immediate effects on recovery of function, such as pain alleviation and\nROM improvement, than conservative physical therapy. In addition, according to previous\nstudies, manipulation is more effective at reducing pain than conservative muscle\ntraining7). Nevertheless, there is still a lack of research evidence supporting the efficacy of\nmanipulation. Therefore, the purpose of this study was to conduct cervical stability\ntraining (CST) and upper thoracic manipulation (UTM) for patients with chronic neck pain and\ninvestigate the changes in cervical proprioception and pain.\n\nBODY.SUBJECTS AND METHODS:\nThe subjects were 30 subjects with chronic mechanical neck pain who agreed to participate\nin this study. The inclusion criteria were: unilateral or bilateral pain in the posterior\nneck or shoulder region, and pain in the cervical region when moving or palpating the\ncervical region, which had lasted for more than 12 weeks, and was rated higher than four on\na visual analogue scale (VAS). The exclusion criteria were: a diagnosis of cervical\nradiculopathy, previous experience of spinal manipulation, a history of fracture or\ndislocation of the cervical or thoracic spine, a history of surgical operation on the\ncervical or thoracic spine, hypertension, heart disease, or pregnancy. The research protocol was approved by the Research Ethics Committee for Human Research of\nKonyang University, Korea. UTM comprised 2 methods. Method 1: Upper thoracic lift manipulation. The subjects were\nasked to lock their fingers together, put their hands on the back of the neck, and sit in a\nchair without a back support. Then, a rolled towel was placed over the target spinal\nsegment. A therapist stood behind the subject, and leant forward toward the rolled towel, or\nthe target spinal segment. The therapist held the forearm of the subject, and flexed the\nsubject's neck and upper thoracic completely up to the spinal segment, creating a force\nagainst the rolled towel using the subject's forearm, and held the subject's elbow in a\nhorizontal adduction motion while lifting the subject toward the therapist in the\nposterior-anterior direction; and then applied thrust manipulation to the subject along with\nhorizontal adduction and expiration4). Method 2: Thoracic manipulation in the supine position. The therapist stood next to the\nsubject. And placed a hand on the subject's transverse process on the inferior segment of\nthe target spinal segment. The subject puts his/her arms on the chest or locked their\nfingers at the back of the head and neck. The therapist held the subject's arms to keep the\nsubject close, then put the manipulation hand on the target spinal segment and used the\nsupporting hand to fix the subject's elbows with the therapist's forearm. After performing\nflexion up to the subject's target segment, the therapist applied thrust manipulation in the\nanterior-to-posterior direction while the subject inhaled and exhaled. The target segments\nwere T1 to T44). CTS consisted of static stability training for re-education and dynamic stability training\nfor muscle endurance and power8). The\nstatic stability training used a pressure biofeedback unit (PBU), and it was based on CCF\ntraining for activating the deep muscles such as the longus colli and longus capitis. In\ndynamic stability training, the subjects maintained cervical flexion, and active assistive\nand active methods were conducted. After they had maintained cervical stability, the\nsubjects performed dynamic training through extremity movement. The subjects were asked to\npay attention to the cervical stability during training9). To measure the cervical proprioception of the patients with chronic neck pain, the cervical\nreposition test was conducted using an electro-goniometer (Mobee, Bitburg, 2013, Germany).\nThe study subjects were asked to sit in an upright position comfortably in a chair. The\ntarget position was randomly chosen from among 30%, 60%, and 90% of the maximal ROM. The\nsubjects kept the target position for 3 seconds, repeated it 5 times10). For measurement, the reposition test was conducted at the\nset angle 3 times. The rest time between measurements was 15 seconds. Measurement directions\nwere set to flexion, extension, right and left side-bending. The subjects were asked to sit\nupright and wear black sunglasses to inhibit their vision, and to move actively toward the\ntarget position in a random order. The difference between the target angle and the actual\nangle was used in the analysis11). All\nsubjects were asked to mark on a VAS scale ranging from 0 to 10 for the subjective\nassessment of pain. VAS is a simple way for the subjects to express their level of pain and\nhas high reproducibility. It is also an evaluation method with high validity (r=0.77) and\nreliability (r=0.99)12) (Table 1Table 1.Comparison of proprioception and pain within groups and between groups\n(N=30)Manipulation group (n=15)Control group (n=15)Flexion (angle)Pre6.07 (2.02)5.67 (2.06)Post2.47 (1.55)†4.27 (1.44)†,‡ExtensionPre4.87 (1.81)4.87 (2.48)Post3.27 (0.96)†3.53 (1.81)†Rt sidebendPre6.20 (1.79)6.73 (2.55)Post1.87 (1.30)†5.00 (2.14)†,‡Lt sidebendPre6.60 (1.55)6.53 (1.89)Post1.00 (1.20)†4.67 (1.88)†,‡VASPre7.13 (0.83)6.93 (1.44)Post1.93 (0.70)†3.40 (0.74)†,‡Values are expressed as mean (SD). p<0.05, p<0.01, †Within group\ncomparison, ‡Between group comparison). For data analysis, SPSS version 18.0 (SPSS, Inc., Chicago, USA) was used. Frequency\nanalysis and descriptive statistics were employed to compare the general characteristics of\nthe subjects. The independent t-test was conducted to compare the thoracic manipulation\ngroup and the CST group. The paired t-test was performed to compare the pre- and post\nintervention results of the UTM and the CST. The level of statistical significance was\nchosen as 0.05.\n\nBODY.RESULTS:\nThere were 8 male and 7 female in the manipulation group, and 7 male and 8 female in the\ncontrol group. The mean age of the subjects was 30.80 years in the manipulation group and\n28.07 years in the control group. The average weight, height and BMI were 63.23 kg,\n164.87 cm and 23.20 kg/m2, respectively in the manipulation group, and 62.89 kg,\n168.13 cm and 21.93 kg/m2, respectively in the control group. The UTM showed\nsignificantly smaller repositioning error in flexion and right and left side-bending and\ngreater reduction in pain than the CST group (p<0.01). Both the UTM and CST groups showed\nsignificant differences in proprioception and pain after the intervention (p<0.01).\n\nBODY.DISCUSSION:\nIn this study, CST was conducted for the patients with chronic neck pain, followed by UTM\nfor six weeks. After that, the changes in proprioception and pain were analyzed. After the\ninterventions, the UTM group showed significant reductions in error angles which were less\nthan those in the CST group, and the pain level of the UTM group was also significantly\nreduced. Proprioception receptors, such as mechanoreceptors and free nerve endings, are found in the\nskin, facial, muscles, tendons, joint capsules, and ligaments. When active or passive\nmovement occurs, receptors transmit the movement information to the central nervous system\n(CNS)13). High velocity low amplitude\nmanipulation stimulates mechanoreceptors located in the muscles, ligaments, and joint\ncapsules improving their responses in transmitting to the CNS; thus, helping the recovery of\nproprioception. It is known that manipulation mechanically stimulates joint capsules and\nthus leading to increased mobility of the spinal segments and increases ROM, which lessens\nthe fear of movement by smoothly transmitting movement information to the CNS, thereby\nreducing pain1, 14). According to many previous studies, the combined approach of a therapeutic exercise program\nand manipulation is more effective at recovering the proprioception of patients with neck\npain and their functions through pain reduction than any other kind of intervention15). Cassidy et al.16) independently conducted\nboth manipulation and joint mobilization for patients with mechanical neck pain, and\nreported the two groups showed significant improvements in pain and ROM after the\ninterventions. Joint mobilization conducted for the patients with chronic RA helped to increase their pain\nthreshold17). Another hypothesis\nregarding pain reduction after manipulation is that beta-endorphins are expressed and that\nthis alleviates pain18). According to\nVernon et al.19), after manipulation,\nbeta-endorphins increased for five minutes, but 15 minutes later, their level had returned\nto its original state. According to the results of the present study, proprioception and\npain were significantly reduced after UTM, a result that is consistent with the empirical\nevidence of previous studies. Another proposal is that spine manipulation activates type I (static movement) and type II\n(dynamic movement) mechanoreceptors, which are distributed in passive and active structures,\nsending signals through the CNS to the periaqueductal grey area, the pain control system\naround the cerebral aqueduct of mid-brain, which increases the pain threshold to control\npain20). The results of this study show that the thoracic manipulation group displayed more\nsignificant differences in pain reduction than the cervical stability group, and that CST\nalso improved proprioception and pain. According to the study of Panjabi21), cervical stability is maintained by the\nstability passive and active tissues and the capability of neuromuscular control. The\npurpose of the passive system is to use the elasticity of passive tissues including\nligaments, joint capsules, and tendons to stabilize the neutral position. The purpose of the\nactive system is to use the force generated by active tissues like muscles to maintain the\nneutral position. In addition, the neuromuscular control system controls and amplitude of\nthe overall range and mobility. The CST result was consistent with the theory that training\nimproves the stability the neutral position and its maintenance through the activation of\nthe active tissues of muscles. Despite these results, this study had several limitations. For example, the number of study\nsubjects small, and there was no long-term intervention of manipulation or CST. Therefore,\nwe consider that it will be necessary to increase the number of study subjects and lengthen\nthe intervention period to prove the effects of manipulation. In the present study, the\nrepositioning test was conducted to measure the propriocetive deficit. However, this is an\nindirect method, not a direct one, of measuring proprioception. For that reason, it is\nimpossible to generalize the results. Therefore, we think that a more objective tool and\nmeasurement method will be needed to investigate proprioception. In summary, the UTM group showed significant improvements in cervical proprioception, and\nsignificant reduction in pain, which were larger than those of the CST group. The findings\nof this study indicate that combine stability training and thoracic manipulation for\npatients with neck pain improves proprioception and reduces pain level.\n\nQuestion:* Compared to cervical stability training (CST) what was the result of upper thoracic manipulation (UTM) on reduction in pain?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1088	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: A single consumption of curry improved postprandial endothelial function in healthy male subjects: a randomized, controlled crossover trial\n\n ABSTRACT.BACKGROUND:\nCurry, one of the most popular foods in Japan, contains spices that are rich in potentially antioxidative compounds, such as curcumin and eugenol. Oxidative stress is thought to impair endothelial function associated with atherosclerosis, a leading cause of cardiovascular events. The aim of this study was to determine whether a single consumption of curry meal would improve endothelial function in healthy men.\n\nABSTRACT.METHODS:\nFourteen healthy male subjects (BMI 23.7 ± 2.7 kg/m2; age 45 ± 9 years) were given a single serving of curry meal or spice-free control meal (180 g of curry or control and 200 g of cooked rice; approximately 500 kcal in total) in a randomized, controlled crossover design. Before and 1 hr after the consumption, fasting and postprandial flow-mediated vasodilation (FMD) responses and other parameters were measured.\n\nABSTRACT.RESULTS:\nThe consumption of the control meal decreased FMD from 5.8 ± 2.4% to 5.1 ± 2.3% (P = 0.039). On the other hand, the consumption of the curry meal increased FMD from 5.2 ± 2.5% to 6.6 ± 2.0% (P = 0.001), and the postprandial FMD after the curry meal was higher than that after the control meal (P = 0.002). Presence of spices in the curry did not alter significantly the systemic and forearm hemodynamics, or any biochemical parameters including oxidative stress markers measured.\n\nABSTRACT.CONCLUSIONS:\nThese findings suggest that the consumption of curry ameliorates postprandial endothelial function in healthy male subjects and may be beneficial for improving cardiovascular health.\n\nABSTRACT.TRIAL REGISTRATION:\nUMIN Clinical Trials Registry\n000012012.\n\nBODY.BACKGROUND:\nCurry originated in Indian traditional diet, and has become widely eaten throughout the world, especially in Asia\n[1]. In fact, curry is one of the most popular foods in Japan\n[1]. Japanese curry is often milder in flavor and thicker in consistency than the traditional Indian curry, and usually is served with cooked rice\n[1]. With a good amount of meat and vegetables in it, Japanese curry can make a convenient and nutritious meal for people of all ages\n[1]. While being mild in flavor, Japanese curry still contains an abundant amount of spices, some of which are high in antioxidants. For example, turmeric contains antioxidant yellow pigment, curcumin, which is known to have many health benefits such as vasoprotective, antiinflammatory, anticarcinogenic, and neuroprotective effects\n[2,3]. Clove contains antioxidant aromatic oil, eugenol, which is also known to have some health benefits such as vasoprotective and pulmonary protective effects\n[4,5]. Epidemiologic studies have shown that curry improves pulmonary function in Asian elderly adults\n[6] and curry consumption improved cognitive performance of nondemented elderly Asians\n[7]. However, few intervention studies about curry have been reported. It is well known that postprandial hyperglycemia is a contributing factor to the development of atherosclerosis and is a risk factor for cardiovascular events. A meta-regression analysis showed that the progressive relationship between glucose levels and cardiovascular risk extends even in subjects with normal glucose tolerance below the diabetic threshold\n[8]. Although mechanism by which postprandial hyperglycemia induces vascular dysfunction is not fully understood, a review by Mar and Bruno points out that oxidative stress-mediated disruptions in nitric oxide homeostasis have been implicated as key events leading to vascular dysfunction\n[9]. Glucose loading produced a decrease in endothelial function and an increase in a marker of oxidative stress in normal and diabetic subjects\n[10,11]. Hyperglycemia in response to oral glucose loading rapidly suppressed endothelium-dependent vasodilation, probably through increased production of oxygen free radicals\n[11-13]. Accumulating evidence suggests that endothelial dysfunction plays a crucial role in the development and progression of atherosclerosis. The endothelium is suggested to be a target of damage in the postprandial state\n[14-16]. The aim of this study was to determine whether a single consumption of a dish of Japanese curry and rice would improve postprandial endothelial function in healthy men.\n\nBODY.METHODS.SUBJECTS:\nIn December 2012, 18 healthy males aged 33 to 64 years were recruited for the study. We selected healthy male subjects who do not have any history of hypertension, diabetes mellitus, and dyslipidemia, to avoid the possibility of any influence on the endothelial function by these factors as well as by menstrual cycle. The study protocol was approved by Tana Orthopedic Surgery Institutional Review Board. Informed consent for participation in the study was obtained from all subjects.\n\nBODY.METHODS.STUDY DESIGN:\nThe study was performed at House Foods Corporation during the period from January 2013 to February 2013. Subjects were randomized into a control-first group and a curry-first group. Each subject was given a single serving of test meal (control meal or curry meal) in a crossover manner with more than one week in between the two test meals. Fasting and postprandial measurements were taken by the primary investigator under blinded condition as follows. Subjects were asked not to take any nutritional supplements on the day before the test and were fasted for at least 12 hours overnight prior to the fasting measurements. No other instructions were given to the subjects. After the fasting measurements, subjects were given 180 g of either control (198 kcal) or curry (187 kcal) and 200 g of cooked rice (294 kcal) by a support staff, and one hour afterwards, postprandial measurements were taken. A preliminary test which we had made before this study showed that a measurement one hour after the intake of the control meal showed low endothelial function in healthy subjects but this effect was not observed two hours after the intake of the control meal. For this reason, we thought that the single point measurement one hour after meal was appropriate for studying curry effects on postprandial endothelial dysfunction in healthy subjects. The curry consisted of ground beef, tomato, tomato puree, some seasonings, and a blend of spices (Table \n1). The control was prepared as the curry except that all the spices were removed from the formula; it tasted like a meat sauce for spaghetti. The nutritional compositions of the control meal and curry meal both with 200 g of cooked rice were essentially the same as shown in Table \n2. Table 1 Composition of the spice blend used in a single serving portion of the curry meal Spice Amount Clove (g) 0.9 Coriander (g) 1.8 Cumin (g) 0.9 Garlic (g) 3.6 Ginger (g) 2.7 Onion (sautéed) (g) 9 Red pepper (g) 0.09 Turmeric (g) 4.5 Table 2 Composition of a single serving portion of the test meal with 200 g of rice Component Control Curry Energy (kcal) \n a \n 492 481 Protein (g) \n b \n 15 16 Fat (g) \n c \n 11 10 Carbohydrate (g) \n d \n 82 82 Dietary fiber (g) \n e \n 3 3 Sodium (g) \n f \n 1 1 \n a \n Modified Atwater methods. \n b \n Kjeldahl nitrogen determination method (conversion factor: 6.25). \n c \n Ether extraction method. \n d \n Carbohydrate was calculated from protein, fat, ash (direct ashing), and moisture (oven drying at 105°C for 16 hours). \n e \n Modified Prosky method. \n f \n Inductively coupled plasma emission spectrometry. Single serving portions (180 g) of both the curry and the control were packed and sterilized in retort pouches and were stored at room temperature until use. They were heated in boiling water for five minutes just before serving with 200 g of cooked rice.\n\nBODY.METHODS.FMD AND HEMODYNAMIC MEASUREMENTS:\nAll measurements were taken in the morning, in a quiet, air-conditioned room maintained at 24°C and 50% relative humidity. The subjects rested quietly in the supine position for 20 min before and during each FMD measurement. Just before the cuff inflation, systolic and diastolic blood pressure was measured on the left arm. FMD was measured on the right arm as described previously\n[17] with a UNEXEF18G ultrasound imaging system programmed specifically for FMD measurements with the autocuff (UP310), the semi-automatic vessel tracking (X-link), and the flow mode (uFFLOW) options (UNEX Co., Nagoya, Japan). After the brachial artery diameter was determined for the baseline arterial diameter from a longitudinal image of the artery acquired 5 to 10 cm above elbow, reactive hyperemia was induced by 5 min of distal lower arm occlusion by a blood pressure cuff inflated to 50 mm Hg above systolic pressure. Subsequently, the longitudinal image of the artery was recorded continuously until 2 min after the cuff deflation for the maximal brachial artery diameter determination. Pulsed Doppler velocity signals were acquired for 20 seconds before cuff inflation and for 10 seconds after cuff deflation for the hyperemic flow (% increase in blood flow) determination. We have already estimated the reproducibility and accuracy of the measurement by a preliminary test using 10 subjects. The same person, who performed the FMD measurement of this study, had measured FMD of each subject twice at one hour interval. The interclass correlation coefficient was 0.98 and systematic error across these two measurements was 0.1%.\n\nBODY.METHODS.SERUM MEASUREMENTS:\nWhole blood samples were collected from the left arm, just after the FMD and hemodynamic measurements. They were separated immediately by centrifugation (1,200 g, 10 min) and were stored at -80°C until use. Glucose, triglycerides, and total cholesterol were measured by enzymatic procedures (Mitsubishi Chemical Medience Corporation, Tokyo, Japan). High-density lipoprotein cholesterol (HDL-C) and low-density lipoprotein cholesterol (LDL-C) were measured by enzymatic procedures (Kyowa Medex Co., Ltd., Tokyo, Japan). Insulin was measured by Chemiluminescent immunoassay (ABBOTT JAPAN Co., Ltd, Tokyo, Japan). High-sensitivity C-reactive protein (hs-CRP) was measured by nephelometry using N-latex CRP-2 (Siemens Healthcare Japan, Tokyo, Japan). Malondialdehyde-modified LDL (MDA-LDL) was measured by two step ELISA (SEKISUI MEDICAL Co., Ltd., Tokyo, Japan) which uses monoclonal antibody recognizing MDA residues (ML25) and monoclonal antibody against apoB (AB16) to make the assay specific to MDA-LDL as described previously\n[18].\n\nBODY.METHODS.URINE MEASUREMENT:\nFor the urine 8-isoprostane determinations, a single voided urine sample was collected from each subject just after the blood sampling and was stored at -80°C until use. To 1000 μl (Creatinine < 50 mg/dl) or 500 μl (Creatinine ≥ 50 mg/dl) urine sample, 3H-8epi PGF2α (20 dpm/μL) 50 μL and 4% acetic acid 3 ml were added. After being stirred for 30 min, the sample was applied on an OASIS HLB solid phase extraction column (Nihon Waters K.K., Tokyo, Japan) preconditioned with 2 ml each of Ethylacetate and Acetonitryl and 3 ml of 4% acetic acid). After being washed with 15% acetonitry in Ehylacetate: hexane: 1-butanol = 15: 85: 1, the column was eluted with 2 ml ethylacetate:hexane = 85: 1. The eluted sample was dried under nitrogen, dissolved in 1 ml EIA buffer, and stirred for 30 min before being subjected to EIA assay (Cayman Chemical, Michigan, United States) as described previously\n[19]. The urine creatinine for normalization of 8-isoprostane concentration was measured by enzymatic procedures (Mitsubishi Chemical Medience Corporation, Tokyo, Japan).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA power analysis for two-way within subjects ANOVA was performed as described\n[20] and showed that a total sample size of 12 subjects was required to detect an interaction between meals and prandial status with an α error of 0.05 and a power of 0.80. Data are presented as means ± standard deviations. Baseline characteristics were compared between the curry-first and the control-first group by unpaired t-test. Statistical analyses about the effects of curry on FMD and other parameters were performed by using two-way within subjects ANOVA (control/curry and fasting/postprandial). If the interaction was significant, post hoc Student's paired t-test was performed. Statistical significance was assumed if a null hypothesis could be rejected at P = 0.05. All analyses were performed with SPSS (version 22; IBM Japan, Ltd., Tokyo, Japan).\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nOf the 18 subjects enrolled in the study, 4 subjects were excluded from the analysis for the follwoing reasons. One subject canceled after the first participation. The ultrasound images of another subject were technically unsuitable for the analysis, Another subjects had a sleeping problem on the night before the test day, and the other subject showed very low postprandial glucose level (<50 mg/dL). Table \n3 summarizes the baseline characteristics of the remaining 14 subjects. All baseline characteristics did not differ significantly between the control-first and the curry-first group. Table 3 Baseline characteristics Parameters Total (n = 14) Control-first (n = 7) Curry-first (n = 7) Age (years) 45 ± 9 42 ± 7 48 ± 10 Body mass index (kg/m 2 ) 23.7 ± 2.7 23.0 ± 1.9 24.4 ± 3.3 Systolic blood pressure (mm Hg) 112 ± 8 112 ± 5 112 ± 11 Diastolic blood pressure (mm Hg) 75 ± 7 76 ± 5 74 ± 9 Heart rate (beats/min) 60 ± 10 59 ± 7 61 ± 13 Total cholesterol (mg/dL) 196 ± 34 194 ± 34 199 ± 37 Triglycerides (mg/dL) 97 ± 44 99 ± 53 96 ± 38 HDL-cholesterol (mg/dL) 58 ± 15 58 ± 14 57 ± 17 LDL-cholesterol (mg/dL) 118 ± 28 114 ± 29 121 ± 28 Glucose (mg/dL) 90 ± 7 88 ± 6 91 ± 8 Insulin (μU/mL) 4.1 ± 1.9 3.9 ± 1.5 4.3 ± 2.4 hs-CRP (mg/dL) 0.122 ± 0.179 0.094 ± 0.176 0.149 ± 0.192 MDA-LDL (U/L) 88 ± 20 83 ± 20 93 ± 21 8-isoprostane (pg/mg Cr) 285 ± 81 276 ± 95 294 ± 70 Values are means ± SD. Abbreviations : HDL high-density lipoprotein, LDL low-density lipoprotein, hs-CRP high-sensitivity C-reactive protein, MDA malondialdehyde-modified, Cr creatinine. \n\nBODY.RESULTS.EFFECTS OF CURRY CONSUMPTION ON FMD AND OTHER HEMODYNAMIC PARAMETERS:\nTable \n4 summarizes the brachial and hemodynamic parameters with significance probability values (P values) from the ANOVA results. Table 4 Vascular function and Systemic Hemodynamics Control Curry \n P \n values \n \n a \n \n Parameters Fasting Postprandial Fasting Postprandial Meal effects Interaction Prandial effects FMD (%) 5.8 ± 2.4 5.1 ± 2.3 5.2 ± 2.5 6.6 ± 2.0 0.20 < 0.001 0.25 Systolic blood pressure (mm Hg) 110 ± 7 110 ± 10 111 ± 8 113 ± 7 0.07 0.57 0.33 Diastolic blood pressure (mm Hg) 73 ± 8 67 ± 7 75 ± 7 70 ± 7 0.07 0.32 < 0.001 Heart rate (beats/min) 60 ± 10 66 ± 11 59 ± 9 66 ± 10 0.56 0.55 < 0.001 Baseline arterial diameter (mm) 4.00 ± 0.47 4.12 ± 0.49 3.96 ± 0.47 4.02 ± 0.46 0.12 0.07 < 0.001 Peak hyperemic flow (%) 595 ± 259 536 ± 157 609 ± 217 571 ± 170 0.60 0.76 0.22 Values are means ± SD. Abbreviations : FMD flow-mediated vasodilation. \n a \n P values were calculated by using two-way within subjects ANOVA (control/curry and fasting/postprandial). Only on FMD, the interaction effect between meals (control/curry) and prandial status (fasting/postprandial) was significant (P < 0.001). Post hoc Student's paired t-tests revealed that the consumption of the control significantly decreased the FMD from 5.8 ± 2.4% to 5.1 ± 2.3% (Figure \n1, P = 0.039). On the other hand, the consumption of the curry increased FMD from 5.2 ± 2.5% to 6.6 ± 2.0% (P = 0.001), and the postprandial FMD after the curry meal was higher than that after the control meal (5.1 ± 2.3% vs. 6.6 ± 2.0%, P = 0.002). Figure 1Effects of a single consumption of curry on flow-mediated vasodilation (FMD), n = 14. Because the interaction between meals (control/curry) and prandial status (fasting/postprandial) was found significant (P = 0.002) by using two-way within subjects ANOVA, P values were calculated by post hoc Student's paired t-test. Abbreviations: FMD flow-mediated vasodilation. After consumption of the test meals, heart rate and baseline arterial diameter increased significantly, and diastolic blood pressure decreased significantly. Other than these, no main effects of the meals, the prandial status, or no interaction effects on systemic and forearm hemodynamics were significant.\n\nBODY.RESULTS.EFFECTS OF CURRY CONSUMPTION ON BIOCHEMICAL PARAMETERS:\nTable \n5 summarizes the biochemical parameters with P values from the ANOVA results. Table 5 Biochemical parameters Control Curry \n P \n values \n \n a \n \n Parameters Fasting Postprandial Fasting Postprandial Meal effects Interaction Prandial effects Total cholesterol (mg/dL) 203 ± 36 195 ± 34 197 ± 32 191 ± 28 0.40 0.36 0.001 Triglycerides (mg/dL) 107 ± 59 114 ± 59 97 ± 44 103 ± 43 0.23 0.96 0.025 HDL-cholesterol (mg/dL) 58 ± 16 56 ± 16 59 ± 15 56 ± 15 0.55 0.53 < 0.001 LDL-cholesterol (mg/dL) 122 ± 30 118 ± 28 118 ± 27 112 ± 23 0.36 0.42 0.001 Glucose (mg/dL) 89 ± 7 113 ± 24 90 ± 7 117 ± 29 0.25 0.44 0.001 Insulin (μU/mL) 3.9 ± 2.0 26.0 ± 11.7 4.3 ± 1.9 25.5 ± 9.9 0.98 0.68 < 0.001 hs-CRP (mg/dL) 0.107 ± 0.159 0.104 ± 0.158 0.089 ± 0.145 0.087 ± 0.143 0.66 0.87 0.038 MDA-LDL (U/L) 94 ± 24 85 ± 24 95 ± 26 85 ± 21 0.93 0.91 0.027 8-isoprostane (pg/mg Cr) 273 ± 76 283 ± 89 277 ± 69 324 ± 67 0.23 0.17 0.047 Values are means ± SD. Abbreviations : HDL high-density lipoprotein, LDL low-density lipoprotein, hs-CRP high-sensitivity C-reactive protein, MDA malondialdehyde-modified, Cr creatinine. \n a \n P values were calculated by using two-way within subjects ANOVA (control/curry and fasting/postprandial). While the main effects of meals and the interaction effects between meals (control/curry) and prandial status (fasting/postprandial) were not significant, the main effects of prandial status were significant for all parameters measured.\n\nBODY.DISCUSSION:\nIn the present study, we demonstrated that a single consumption of a dish of curry and rice improved the postprandial FMD in healthy men. We believe the significant interaction effect on FMD between meals and prandial status was due to the antioxidant components in the curry, although consumption of the curry meal did not change the two oxidative stress parameters (MDA-LDL and urine 8-isoprostane) measured in our study. Many researchers reported that FMD was improved by some antioxidant consumption (long term and short term) without 8-isoprostane decrease\n[21-23]. Few intervention studies using antioxidants report serum MDA-LDL levels. Pfeuffer et al. reported that consumption of 150 mg/d quercetin for 8 weeks affected neither oxidized LDL nor 8-isoprostane\n[24]. These reports suggest that no change in MDA-LDL and urine 8-isoprostane does not necessarily mean that improvement in FMD is not attributable to decrease in oxidative stress. On the other hand, it has been reported that administration of glucose in oral glucose tolerance test (OGTT) impaired endothelial function with concomitant increase in postprandial oxidative stress\n[11]. It is also reported that the postprandial serum glucose after rice is lower than that after the equivalent amount of glucose consumption\n[25]. In our study, we found that the test meals containing 82 g carbohydrate, which is nearly equivalent to the amount of glucose administered in 75-g OGTT, increased postprandial serum glucose and a consumption of the control meal resulted in decrease in FMD suggesting impairment of endothelial function. We speculate that the presence of spice antioxidants in the curry would have prevented the increase in the oxidative stress induced by postprandial serum glucose increase, but the change in the oxidative stress parameters after our test meal was too small to be detected, because the postprandial serum glucose level after our test meals (113 mg/dL after control or 117 mg/dL after curry) was much lower than that normally encountered after 75-g oral glucose loading\n[26]. Curcumin, eugenol and quercetin in curry could have contributed to our results suggesting that spices improved postprandial endothelial function. It was reported that curcumin alleviates an endothelium-dependent vasodilator dysfunction induced by high glucose in rat aortic rings and increased heme oxygenase-1 activity, and that stimulation of guanylyl cyclase may be involved in the protective effects of curcumin\n[27]. Eugenol was reported to produce smooth muscle relaxation resulting from the blockade of both voltage-sensitive and receptor-operated channels that are modulated by endothelial-generated nitric oxide\n[4]. It has been also suggested that qurcetin, which is a main polyphenol of onion and is also contained in curry, is known as a selective modulator of cyclic GMP-dependent relaxations\n[28]. Future studies are needed for elucidating the mechanism of our findings. After consumption of the test meals, baseline arterial diameter increased significantly. Similar increase in baseline arterial diameter after a fatty meal consumption has been reported\n[29,30]. Although many researchers reported that increase in baseline diameter would decrease FMD\n[31,32], the increase did not appear to have diminished the effect of spices on FMD, because significant interaction effect between meals and prandial status on baseline diameter was not found, and because the postprandial FMD after curry even increased despite that the increase of baseline diameter should decrease FMD. It is reported that a single consumption of a high antioxidant spice blend attenuated postprandial insulin and triglyceride responses and increased some plasma measures of antioxidant activities\n[33]. The results of the present study, however, showed that no interaction effects (i.e., the effects due to spices) on biochemical data between meals (control/curry) and prandial status (fasting/postprandial) were significant. In the previous study, the subjects were given a test meal with different composition, and with different kind of spices. Moreover, they collected blood samples at 30-min intervals for 3.5 h. These differences in experimental conditions may have affected the results. We found that postprandial diastolic blood pressure decreased and postprandial heart rate increased significantly, but postprandial systolic blood pressure did not change significantly. Berry et al. reported that glucose solution with ground beef (i.e., solid food), when fed to human subjects, caused higher postprandial systolic blood pressure than glucose solution alone (i.e., liquid food)\n[34]. They also reported that diastolic blood pressure fell and heart rates increased, without significant (observable) effects from the ground beef\n[34]. Although the mechanisms were not fully understood, the results of our study in which participants consumed solid meal, agree with their findings. There are some limitations in the current study. The first limitation is our small sample size (n = 14). Follow-up work using a larger sample size may be needed. The second limitation is that because of the unique flavor and color of spices used in the curry, the curry meals were readily distinguishable from the control meals by the subjects. Although we cannot exclude the possibility entirely that this feature of our study had some influence on our results, it is more likely that the presence of spices in the curry reduced the impact of the postprandial state on the endothelium after the meal.\n\nBODY.CONCLUSION:\nCurry consumption ameliorates postprandial endothelial dysfunction and may be beneficial for preventing cardiovascular events. Lifestyle-related diseases such as atherosclerosis and diabetes mellitus have become serious health problems in the modern world. Curry may be helpful in the fight against those lifestyle-related diseases.\n\nBODY.ABBREVIATIONS:\nFMD: Flow-mediated vasodilation; HDL-C: High-density lipoprotein-cholesterol; LDL-C: Low-density lipoprotein-cholesterol; hs-CRP: High-sensitivity C-reactive protein; MDA-LDL: Malondialdehyde-modified LDL; OGTT: Oral glucose tolerance test; Cr: Creatinine.\n\nBODY.COMPETING INTERESTS:\nThis study was supported by House Foods Corporation. HN, SY and SS are employees of House Foods Corporation. NT, HS, and NM are employees of House Foods Group Inc. YH has no competing interest.\n\nBODY.AUTHORS’ CONTRIBUTION:\nHN designed the research, performed measurements and statistical analysis, and wrote the manuscript. NT conducted the research. HS provided statistical consultation and critically revised the manuscript. NM provided much consultation about the study design and conducted the research. SY designed and prepared test meals. SS provided much consultation about the study design. YH provided much consultation about the study design, conducted the research, provided consultation about the discussion of the test results, and critically revised the manuscript. All authors read and approved the final manuscript.\n\nQuestion: Compared to spice-free control meal what was the result of single serving of curry meal on flow-mediated vasodilation (FMD)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1091	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: A randomized, double-blind comparison of OROS\n\n ABSTRACT.BACKGROUND:\nLong-acting opioid formulations are advocated for maintaining pain control in chronic cancer pain. OROS® hydromorphone is a sustained-release formulation of hydromorphone that requires dosing once daily to maintain therapeutic concentrations. The objective of this study was to demonstrate the clinical equivalence of immediate-release and sustained-release formulations of hydromorphone and morphine for chronic cancer pain.\n\nABSTRACT.METHODS:\n200 patients with cancer pain (requiring ≤ 540 mg/d of oral morphine) participated in this double-blind, parallel-group trial. Patients were randomized to receive hydromorphone or morphine (immediate-release for 2–9 days, sustained-release for 10–15 days). Efficacy was assessed with the Brief Pain Inventory (BPI), investigator and patient global evaluations, Eastern Cooperative Oncology Group performance status, and the Mini-Mental State Examination. The primary endpoint was the 'worst pain in the past 24 hours' item of the BPI, in both the immediate-release and sustained-release study phases, with treatments deemed equivalent if the 95% confidence intervals (CI) of the between-group differences at endpoint were between -1.5 and 1.5. No equivalence limits were defined for secondary endpoints.\n\nABSTRACT.RESULTS:\nLeast-squares mean differences (95% CI) between groups were 0.2 (-0.4, 0.9) in the immediate-release phase and -0.8 (-1.6, -0.01) in the sustained-release phase (intent-to-treat population), indicating that the immediate-release formulations met the pre-specified equivalence criteria, but that the lower limit of the 95% CI (-1.6) was outside the boundary (-1.5) for the sustained-release formulations. BPI 'pain now PM' was significantly lower with OROS® hydromorphone compared with controlled-release morphine (least-squares mean difference [95% CI], -0.77 [-1.49, -0.05]; p = 0.0372). Scores for other secondary efficacy variables were similar between the two sustained-release treatments. At endpoint, > 70% of investigators and patients rated both treatments as good to excellent. The safety profiles of hydromorphone and morphine were similar and typical of opioid analgesics.\n\nABSTRACT.CONCLUSION:\nEquivalence was demonstrated for immediate-release formulations of hydromorphone and morphine, but not for the sustained-release formulations of OROS® hydromorphone and controlled-release morphine. The direction of the mean difference between the treatments (-0.8) and the out-of-range lower limit of the 95% CI (-1.6) were in favor of OROS® hydromorphone.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov: NCT0041054\n\nBODY.BACKGROUND:\nOpioid analgesics are highly effective for the treatment of pain, enabling 85% to 95% of patients to gain functional control of their lives [1,2]. Opioid therapy is typically initiated after the failure of maximum doses of non-opioid analgesics [3] and is titrated to attain the best balance between pain relief and side effects for each patient. The European Association for Palliative Care [4] and the American Pain Society [5] advocate the use of long-acting oral agents for maintaining analgesia once individual dose requirements have been established. For these reasons, long-acting opioids have become the mainstay of chronic cancer pain therapy. OROS® hydromorphone is a unique long-acting opioid formulation that utilizes Push-PullTM active osmotic technology developed by ALZA Corporation (Mountain View, CA, USA). The Push-PullTM system maintains consistent hydromorphone plasma concentrations throughout the 24-hour dosing interval, providing long-lasting analgesia [6-8]. Release of the drug from the system is actively controlled by the dosage form itself, and is not significantly influenced by environmental factors such as the surrounding pH or gastric motility [9,10]. There is a minimal effect of food on the rate and extent of absorption of hydromorphone from OROS® hydromorphone; in one study the mean geometric ratios of fed and fasted subjects for peak plasma concentration (Cmax) and area under the concentration-time curve (AUC) were within 20%; the median time to peak plasma concentration (Tmax) was lower under fed conditions (12 versus 16 hours), but mean plasma concentration profiles generally overlapped, especially up to 6 hours after dosing [11]. The pharmacokinetics of OROS® hydromorphone are also minimally affected by alcohol; one study found that plasma hydromorphone concentrations were slightly higher after alcohol (240 mL solutions of 4%, 20%, and 40% alcohol and orange juice) compared with no alcohol, but there was no clear alcohol dose-response relationship and no dose dumping of hydromorphone occurred [12]. The primary objective of the current study was to demonstrate the clinical equivalence of hydromorphone and morphine (immediate-release [IR] and sustained-release [SR] formulations) using the 'worst pain in the past 24 hours' item of the Brief Pain Inventory (BPI). Morphine was selected as the active comparator since it is the gold standard for pain control. Controlled-release (CR) morphine is available in twice-daily and once-daily formulations and is widely used to alleviate cancer pain; in this study the twice-daily formulation (dosing every 12 hours) was used.\n\nBODY.METHODS.PATIENTS:\nThis study was a multicenter, phase III, randomized, double-blind (double-dummy), active-controlled, parallel-group, equivalence trial. It was conducted at 37 centers in Belgium, Canada, France, Germany, The Netherlands, Spain, Sweden, and the United Kingdom. The study enrolled inpatients, outpatients, and day-patients ≥ 18 years of age who had moderate to severe chronic cancer pain requiring 60 to 540 mg of oral morphine (or equivalent) every 24 hours. The criteria used for patient selection are listed in Table 1. Concomitant chemotherapy or radiotherapy was permitted. All patients who entered the trial were informed of the nature of the study, and provided written informed consent for participation. The study was conducted in accordance with the principles of the Declaration of Helsinki. Table 1 Criteria for patient selection Inclusion criteria Exclusion criteria • Age ≥ 18 years • Pain not considered potentially responsive to opioids • Presence of chronic cancer pain: • Pain present only upon movement ◦ currently receiving strong oral or transdermal opioid analgesics (60–540 mg oral morphine or equivalent every 24 hours) • Need for other opioid analgesics (except study medication and breakthrough pain medication) after randomization ◦ appropriate candidate for strong oral or transdermal opioid analgesics (anticipated requirement, 60–540 mg oral morphine or equivalent every 24 hours) • Current or recent (within 6 months) history of drug and/or alcohol abuse • Pain suitable for treatment with a once-daily formulation • Women of childbearing potential who are pregnant or lactating, seeking pregnancy, or failing to take adequate contraceptive precautions • Intolerance of, or hypersensitivity to, hydromorphone or other opioids • Presence of GI disease of sufficient severity to likely interfere with oral analgesia (e.g., dysphagia, vomiting, no bowel movement or bowel obstruction due to impaction within 5 days of study entry, severe gut narrowing that may affect analgesic absorption or transit) • Use of monoamine oxidase inhibitors within 2 weeks prior to study entry • Investigational drug use within 4 weeks of study entry • Presence of conditions for which risks of opioid use outweigh potential benefits (e.g., raised intracranial pressure, hypotension, hypothyroidism, asthma, reduced respiratory reserve, prostatic hypertrophy, hepatic impairment, renal impairment, elderly and debilitated, convulsive disorders, Addison's disease) Abbreviation: GI, gastrointestinal \n\nBODY.METHODS.DRUGS AND DOSAGES:\nPatients were randomized 1:1, with a central computer-generated randomization list, to receive hydromorphone or morphine for up to 24 days (Figure 1). This study consisted of 2 phases: an initial IR phase and a subsequent SR phase. In the IR phase, patients received IR formulations of either hydromorphone [Dilaudid®, Abbott Laboratories] or morphine (morphine sulfate IR [Sevredol®, Napp Laboratories]) every 4 hours (6 times daily) for 2 to 9 days. Patients underwent conversion from previous therapy to 1 of 6 possible initial dose levels, based on individual patient characteristics and generally accepted morphine equivalent conversion factors. Doses were selected according to the available tablet strengths and a working conversion ratio of 1:5 (1 hydromorphone:5 morphine equivalents), in the ranges hydromorphone IR 12–108 mg/day and morphine IR 60–540 mg/day. The dose was titrated to the next higher dose level if the patient had more than 3 breakthrough pain episodes requiring breakthrough pain medication within the previous 24 hours. Daily doses were titrated up to the next higher dose level, with no dose levels skipped, at most once a day. Dose titration was continued until dose-stable pain control was achieved. Patients who experienced 2 consecutive days with no more than 3 breakthrough pain episodes requiring rescue medication per day were considered to have achieved dose-stable pain control and could begin the SR phase of the study. Patients who did not achieve dose stable pain control by day 9 were withdrawn from the study, and end-of-study evaluations were carried out. Figure 1Study design. BID, twice daily; CR, controlled-release; IR, immediate-release; QD, once-daily; q4h, every 4 hours. The duration of the SR phase was 10 to 15 days. In this phase, patients continued to receive the same study drug but in an SR formulation: OROS® hydromorphone once-daily or CR morphine (morphine sulfate SR [MST Continus®, Napp Laboratories]) twice-daily. They were started on the same dose level number on which they had achieved dose-stable pain control in the preceding IR phase, which was then adjusted as required, at most every 2 days, in single steps so that no dose level was skipped. Doses were selected according to the available tablet strengths and a working conversion ratio of approximately 1:5 (hydromorphone:morphine), in the ranges OROS® hydromorphone 16–96 mg/day and CR morphine 60–520 mg/day. The SR phase was completed after a minimum of 10 days (maximum of 15 days) on OROS® hydromorphone or CR morphine if pain was controlled and the dose was stable for at least the previous 2 days. In the IR phase, the dosing regimen was the same for both drugs: patients received a dose of study medication 6 times a day, every 4 hours, at 0600, 1000, 1400, 1800, 2200, and 0200. In this phase, all treatments were over-encapsulated resulting in identical capsules. In the SR phase, dosing was done twice each day at 1000 and 2200. To maintain the blind in this phase, matching placebo tablets and capsules were used: patients in the OROS® hydromorphone group took OROS® hydromorphone and placebo CR morphine in the morning and placebo CR morphine in the evening; patients in the CR morphine group took CR morphine and placebo OROS® hydromorphone in the morning and CR morphine in the evening. In both study phases, patients could also receive breakthrough pain medication as needed, either hydromorphone or morphine, supplied as the IR formulation. A single dose of breakthrough pain medication contained approximately one-sixth of the patient's daily dose.\n\nBODY.METHODS.ASSESSMENTS:\nBaseline efficacy assessments were done before dosing on day 1 of the IR phase and included: the BPI (12-item instrument to assess pain intensity [from 0 = no pain to 10 = pain as bad as you can imagine], pain relief [0% to 100%], and pain interference with various aspects of the patient's life [from 0 = no interference to 10 = complete interference]) [13], the Mini-Mental State Examination (MMSE; 0–30, higher scores indicate better cognitive performance) [14], and the Eastern Cooperative Oncology Group (ECOG) performance status score (0–4, higher scores indicate poorer performance) [15]. Primary equivalence of efficacy was assessed using the BPI assessment of 'worst pain in the past 24 hours' on an 11-point scale ranging from 0 (no pain) to 10 (worst pain imaginable). This was selected as the primary efficacy measure because evidence suggests that severely intense pain is what interferes most significantly with activities of daily life [13]. Secondary endpoints included other assessments of pain from the BPI (completed by the investigator in consultation with the patient); investigator and patient global assessments of treatment effectiveness (1 = poor, 2 = fair, 3 = good, 4 = very good, 5 = excellent); MMSE; ECOG; time to dose stabilization; and usage and dose of breakthrough pain medication. Patients rated BPI 'worst pain in the past 24 hours' once daily (just before taking the mid-morning dose of study medication) and 'pain now' twice daily (AM and PM; just before taking the mid-morning and evening doses) throughout the study and recorded responses in daily diaries. The other BPI assessments, plus investigator and patient global evaluations of treatment effectiveness, MMSE, and ECOG, were evaluated at the end of both phases. Adverse events (AEs) and concomitant medications were recorded throughout the study. Physical examinations were carried out at baseline and at the end of each study phase. Blood and urine samples were collected for laboratory analysis (hematology, serum biochemistry, and urinalysis) at baseline and at the end of the SR phase. Patients were contacted daily during the IR phase and every 3 to 4 days during the SR phase (preferably by home or clinic visit, or by telephone if appropriate). Contact was also made 3 days after the last dose of study drug to determine the patient's AE status.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nAssuming variability (standard deviation, SD) in the primary efficacy variable of 2.0 [16] and a 30% dropout/non-evaluable rate, a sample size of approximately 70 patients per treatment group was required (140 total). This would provide 90% power to detect equivalence with an equivalence limit of 1.5. A planned blinded re-estimation of the optimal sample size was done by an appointed independent person after 55 patients had completed the study, the variability for the primary efficacy measure was estimated using their data, and the sample size was increased to 170 patients. Subsequently, an unplanned, blinded re-estimation of the variability of the primary variable for both phases was done after 120 patients had completed the study, and as a result, the sample size was increased to 200 patients. All statistical analyses were pre-specified. All efficacy variables were analyzed using the intent-to-treat (ITT) population, which included all patients who took at least 1 dose of study medication and had at least 1 assessment from each study phase. A per-protocol (PP) analysis, excluding data from patients with major protocol deviations, was also done. All patients taking at least 1 dose of study medication were included in the analysis of safety. All efficacy analyses included a pre-specified adjustment for baseline value and country to control for potentially confounding variables. The primary efficacy analysis used the mean of the last 2 post-baseline recorded values (or the last value if only 1 was available) for BPI 'worst pain in the past 24 hours'. The primary measure was calculated separately for the IR and SR phases (there were therefore two primary outcomes). An analysis of covariance (ANCOVA) was used to calculate the 95% two-sided confidence interval (CI) for the difference between the adjusted means for the 2 treatments at endpoint of each phase. An equivalence test was used to compare the mean scores of the primary efficacy measure at the end of each phase [17-19]. The 2 treatments, within a phase, were considered equivalent if the 95% two-sided CI for the treatment difference was within a -1.5 and 1.5 point difference on the BPI scale. This particular CI range was selected prospectively because it was considered clinically relevant through consultation with physicians who specialize in analgesia. For secondary endpoints (including BPI 'pain at its least in past 24 hours', 'pain on average pain', 'pain now' (AM and PM), 'pain relief in past 24 hours', 'pain interference in past 24 hours', MMSE, and ECOG) an ANCOVA model was used to calculate 95% two-sided CIs for the difference between the adjusted treatment means at the end of the IR and SR phases. The adjusted means were estimated by the same approach used for the primary endpoint, with the baseline score designated as a covariate; however, no equivalence limits were specified for the secondary endpoints. Time to dose stabilization during both study phases was analyzed by the log-rank test. Summary statistics with 95% CIs were produced for investigator and patient global evaluations of treatment effectiveness and to assess the number of medication doses taken for breakthrough pain in the last 2 days of each phase. P values (not adjusted for multiple comparisons) are reported for secondary endpoints. Statistical significance was declared at the α = 0.05 level.\n\nBODY.RESULTS.STUDY POPULATION:\n202 patients were enrolled into the study (Belgium, n = 29; Canada, n = 10; France, n = 7; Germany, n = 15; Netherlands, n = 29; Spain, n = 41; Sweden, n = 11; UK, n = 60). 200 patients were randomized and took study medication. 163 patients (81.5%) completed the IR phase and 133 (66.5%) completed the SR phase. Figure 2 is a flow diagram of patient entry and completion and the reasons for premature discontinuation. Withdrawal from the study owing to lack of efficacy was more common in patients randomized to hydromorphone (n = 11) compared with morphine (n = 4). The mean age of participants overall was 59.8 years. 98.5% of patients were Caucasian and 51% were female. The most common types of cancer were breast (28%), lung (20%), and gastrointestinal (16%). For 133 (67%) patients, the predominant pain location was bone or soft tissue; 34 (17%) others had mixed pain, and 33 (17%) had visceral pain. No patient had neuropathic pain. The most common pain medications used at study entry were morphine (n = 124 [62%]) and tramadol (n = 38 [19%]). The baseline demographics and clinical characteristics were similar for both treatment groups (Table 2). Table 2 Demographic and baseline clinical characteristics Characteristic Hydromorphone (N = 99) Morphine (N = 101) Mean (SD) age, years 60.7 (12.50) 59.0 (11.36) Gender, % male 46.5 51.5 Race, % Caucasian/Black/Asian/Other 100/0/0/0 97/0/2/1 Mean (SD) height, cm 166.7 (9.33) 167.3 (10.47) Mean (SD) weight, kg 66.3 (15.33) 67.4 (13.33) Mean (SD) BMI, kg/m 2 23.8 (5.14) 24.2 (5.06) Cancer type, n (%) Breast 23 (23.2) 33 (32.7) Lung 20 (20.2) 19 (18.8) Genitourinary 18 (18.2) 12 (11.9) Gastrointestinal 17 (17.2) 15 (14.9) Oral cavity 3 (3.0) 3 (3.0) Lymphoma 3 (3.0) 0 Leukemia 1 (1.0) 2 (2.0) Bone 1 (1.0) 1 (1.0) Other 13 (13.1) 16 (15.8) Predominant pain type, n (%) Bone or soft tissue 61 (61.6) 72 (71.3) Mixed 19 (19.2) 15 (14.9) Visceral 19 (19.2) 14 (13.9) Mean (SD) MMSE score* 28.5 (2.3) 28.8 (2.0) Mean (SD) ECOG score 1.6 (0.8) 1.6 (0.9) Abbreviations: BMI, body mass index; ECOG, Eastern Cooperative Oncology Group; MMSE, Mini-Mental State Examination; SD, standard deviation Hydromorphone, n = 75; morphine, n = 73 Figure 2Patient disposition. IR, immediate-release; SR, sustained-release.\n\nBODY.RESULTS.EFFICACY.BPI 'WORST PAIN IN THE PAST 24 HOURS' (PRIMARY ENDPOINT):\nIn each study phase, mean values for BPI 'worst pain in the past 24 hours' decreased with both hydromorphone and morphine treatments (Table 3). The least-squares (LS) mean (95% CI) differences between the hydromorphone and morphine groups were 0.2 points (-0.4, 0.9) in the IR phase and -0.8 points (-1.6, -0.01) in the SR phase (ITT population). In the IR phase, the 95% CI was within the -1.5 to 1.5 equivalency range (-0.4 to 0.9), indicating that IR hydromorphone and IR morphine were equivalent in this primary efficacy outcome measure. In the SR phase, the upper limit of the 95% CI was within the 1.5 boundary (-0.01), but the lower limit was less than -1.5 (-1.6), indicating that the SR formulations were not equivalent but that the negative direction of the mean difference was in favor of OROS® hydromorphone (Figure 3). Results of the analysis of the primary efficacy variable were similar when using data from the PP population. Table 3 BPI scores at baseline, end of IR phase, and end of SR phase (ITT population) Variable Baseline Mean (SD) End of IR phase † LS mean (SE) End of SR phase ‡ LS mean (SE) Worst pain Hydromorphone 6.3 (2.7) 5.0 (0.3) 3.5 (0.3) Morphine 6.2 (2.5) 4.8 (0.3) 4.3 (0.3) Least pain Hydromorphone 2.7 (2.5) 1.8 (0.2) 1.8 (0.2) Morphine 2.9 (2.7) 2.2 (0.2) 1.8 (0.2) Average pain Hydromorphone 5.0 (2.1) 3.6 (0.2) 3.4 (0.3) Morphine 5.1 (2.1) 3.6 (0.2) 3.2 (0.3) Pain now AM Hydromorphone 4.0 (2.7) 3.3 (0.3) 2.4 (0.3) Morphine 4.1 (2.4) 3.4 (0.3) 2.8 (0.3) Pain now PM Hydromorphone 4.8 (3.0) 3.6 (0.3) 2.6 (0.3) § Morphine 4.2 (2.5) 3.7 (0.3) 3.4 (0.3) Abbreviations: BPI, Brief Pain Inventory; CR, controlled-release; IR, immediate-release; LS, least-squares; SD, standard deviation; SE, standard error; SR, sustained-release Hydromorphone, n = 99; morphine, n = 101 †IR hydromorphone, n = 99; IR morphine, n = 101 ‡OROS ® hydromorphone, n = 77; CR morphine, n = 86 §p = 0.0372 versus CR morphine Figure 3Least-squares mean differences and 95% confidence intervals between the OROS® hydromorphone and controlled-release (CR) morphine groups at end of the sustained-release (SR) phase.\n\nBODY.RESULTS.EFFICACY.SECONDARY ENDPOINTS:\nAt the end of the IR phase, mean scores for the secondary efficacy variables (other assessments of pain from the BPI [Table 3 and Figure 4], and MMSE and ECOG scores [data not shown]) were similar for IR hydromorphone and IR morphine, except for BPI 'pain interference with normal work', which favored IR hydromorphone (Figure 4; p = 0.0386). Figure 4Mean Brief Pain Inventory (BPI) interference scores at baseline, end of immediate-release (IR) phase, and end of sustained-release (SR) phase. Values at baseline represent means; values at other time points represent least-squares means. At baseline: hydromorphone, n = 99; morphine, n = 101. In IR phase: IR hydromorphone, n = 99; IR morphine, n = 101. In SR phase: OROS® hydromorphone, n = 77; controlled-release (CR) morphine, n = 86. At the end of the SR phase, scores were similar between treatment groups for BPI items 'least pain', 'average pain', and 'pain now AM'; however, 'pain now PM' was significantly lower in the OROS® hydromorphone group compared with the CR morphine group (LS mean [SE] scores, 2.6 [0.3] versus 3.4 [0.3], respectively; p = 0.0372) (Table 3). LS mean differences (95% CI) between treatment groups were 0.06 (-0.51, 0.64), 0.15 (-0.49, 0.79), -0.38 (-1.03, 0.27), and -0.77 (-1.49, -0.05) for least, average, morning, and evening pain, respectively (Figure 3). Figures 5 and 6 show the consistency of response to both OROS® hydromorphone and morphine throughout the SR phase, during both the morning and evening assessments of BPI 'pain now' scores. Figure 5Mean (standard error, SE) pain now scores in the morning during the sustained-release (SR) phase. Pain was rated using the 11-point Brief Pain Inventory (BPI), ranging from 0 (no pain) to 10 (worst pain imaginable). CR, controlled-release. Figure 6Mean (standard error, SE) pain now scores in the evening during the sustained-release (SR) phase. Pain was rated using the 11-point Brief Pain Inventory (BPI), ranging from 0 (no pain) to 10 (worst pain imaginable). CR, controlled-release. LS mean BPI 'pain relief' at endpoint was 69.7% for the OROS® hydromorphone group and 70.0% for the CR morphine group (95% CI for treatment difference, -8.11, 7.54). BPI 'pain interference' scores were also similar between treatment groups at endpoint, (Figure 4), as were LS mean ECOG performance status scores (1.8 versus 1.7 in the OROS® hydromorphone and CR morphine groups, respectively; 95% CI for treatment difference, -0.13, 0.26), and LS mean MMSE scores (28.9 versus 29.2; 95% CI for treatment difference, -1.19, 0.51). The majority of both investigators and patients (> 70%) rated the treatments as good, very good, or excellent at the end of each study phase (Figure 7). Mean ± SD patient global assessment scores at the end of the SR phase were 3.2 ± 1.14 for the OROS® hydromorphone group and 3.3 ± 0.98 for the CR morphine group (p = 0.6696); mean ± SD investigator global assessment scores were 3.2 ± 1.07 and 3.3 ± 0.91, respectively (p = 0.4760). Figure 7Patient (A) and investigator (B) global evaluations of treatment effectiveness at the end of the sustained-release (SR) phase. CR, controlled-release. In both treatment phases, patients in the hydromorphone group took longer than those in the morphine group to achieve stable doses (p < 0.001). The number of patients requiring dose-level changes during the SR phase was similar for both groups (19 of 77 [24.7%] OROS® hydromorphone recipients and 23 of 86 [26.7%] CR morphine recipients). Comparison of dosage levels at the end of the SR phase generally showed that similar proportions of patients received OROS® hydromorphone or CR morphine at each of the 5 (approximate 1:5 hydromorphone to morphine) lower dosage levels, although more patients in the OROS® hydromorphone group (10% versus 2% in the CR morphine group) received the highest dosage level evaluated in this study (Table 4). Table 4 Dose levels at end of SR phase OROS ® hydromorphone (N = 77) CR morphine (N = 86) Dose level Dose (mg) every 24 hours Number of subjects (%) Dose (mg) every 12 hours Number of subjects (%) 1 16 22 (28.6) 30 25 (29.1) 2 24 14 (18.2) 60 23 (26.7) 3 32 18 (23.4) 90 15 (17.4) 4 48 10 (13.0) 120 13 (15.1) 5 72 5 (6.5) 175 8 (9.3) 6 96 8 (10.4) 260 2 (2.3) Abbreviations: CR, controlled-release; SR, sustained-release In the IR phase, 61.6% of patients taking IR hydromorphone and 52.5% of those receiving IR morphine required medication for breakthrough pain on the last 2 days of the phase. In the SR phase, the corresponding percentages in the OROS® hydromorphone and CR morphine groups were 48.1% and 48.8%, respectively. The mean (SD) numbers of breakthrough pain medication doses taken on the last 2 days were as follows: IR phase, 1.8 (2.2) and 1.3 (1.8) for the IR hydromorphone and IR morphine groups, respectively; SR phase, 1.6 (2.2) and 1.4 (1.9) for the OROS® hydromorphone and CR morphine groups, respectively. The mean total doses of breakthrough pain medication as a percentage of the mean daily consumption were 39.4% and 27.1% for hydromorphone and morphine in the IR phase, and 13.8% and 10.3% for OROS® hydromorphone and CR morphine in the SR phase. There were no statistically significant treatment differences in the numbers of patients who took breakthrough pain medication or in the amount of medication taken in either phase.\n\nBODY.RESULTS.SAFETY:\nThe overall safety profiles of hydromorphone and morphine were comparable, with a similar number of patients in each group reporting AEs. Overall, irrespective of study phase, 81 of 99 (81.8%) hydromorphone-treated patients and 90 of 101 (89.1%) morphine-treated patients reported at least 1 AE. The most commonly reported AEs during the IR and SR phases of the study are listed in Table 5. The types of AEs were typical of those generally associated with opioid use. The incidence of constipation was higher with hydromorphone than morphine in both phases of the study (23.2% versus 10.9% in the IR phase and 39.0% versus 22.1% in the SR phase). In the SR phase, the incidences of vomiting, nausea, and somnolence were higher with CR morphine than with OROS® hydromorphone (22.1% versus 9.1%, 29.1% versus 19.5%, and 14.0% versus 10.4%, respectively). Most AEs were mild or moderate in severity and no clear treatment difference was seen in the relative severity of the most commonly reported AEs. Approximately 30% of patients with AEs reported events that were considered unlikely to be related or not related to study therapy. Table 5 Adverse events reported by at least 5% of patients in any group during the IR or SR phase IR phase SR phase Adverse event Hydromorphone (N = 99) Morphine (N = 101) OROS ® hydromorphone (N = 77) CR morphine (N = 86) Constipation 23 (23.2%) 11 (10.9%) 30 (39.0%) 19 (22.1%) Nausea 18 (18.2%) 23 (22.8%) 15 (19.5%) 25 (29.1%) Vomiting 16 (16.2%) 19 (18.8%) 7 (9.1%) 19 (22.1%) Somnolence 11 (11.1%) 11 (10.9%) 8 (10.4%) 12 (14.0%) Dizziness 8 (8.1%) 6 (5.9%) 4 (5.2%) 8 (9.3%) Headache 8 (8.1%) 6 (5.9%) 3 (3.9%) 2 (2.3%) Diarrhea 8 (8.1%) 1 (1.0%) 7 (9.1%) 2 (2.3%) Pruritus 4 (4.0%) 5 (5.0%) 3 (3.9%) 5 (5.8%) Asthenia 5 (5.1%) 1 (1.0%) 6 (7.8%) 4 (4.7%) Fatigue 3 (3.0%) 3 (3.0%) 4 (5.2%) 6 (7.0%) Confusion 2 (2.0%) 2 (2.0%) 7 (9.1%) 2 (2.3%) Anemia 2 (2.0%) 1 (1.0%) 3 (3.9%) 6 (7.0%) Anorexia 1 (1.0%) 4 (4.0%) 2 (2.6%) 5 (5.8%) Insomnia 1 (1.0%) 2 (2.0%) 5 (6.5%) 4 (4.7%) Peripheral edema 0 3 (3.0%) 1 (1.3%) 8 (9.3%) Pyrexia 2 (2.0%) 1 (1.0%) 4 (5.2%) 2 (2.3%) Anxiety 1 (1.0%) 1 (1.0%) 5 (6.5%) 1 (1.2%) Abbreviations: CR, controlled-release; IR, immediate-release; SR, sustained-release Serious AEs were reported for 24 patients during the double-blind period (by 5 patients in each treatment group in the IR phase, and by 7 patients in the OROS® hydromorphone group and 9 in the CR morphine group in the SR phase [2 patients had serious AEs in both phases]). Many of the serious AEs were associated with the underlying disease, although approximately one third were considered definitely or probably related to study therapy. Three patients in the morphine group died during the study (2 during the IR phase, 1 during the SR phase). None of the deaths was considered related to the study medication. Twenty-six patients withdrew prematurely from the study because of AEs, 16 during the IR phase (9 hydromorphone, 7 morphine) and 10 during the SR phase (6 OROS® hydromorphone, 4 CR morphine). There was no statistically significant difference between treatment groups in the time to withdrawal, irrespective of phase (IR phase, p = 0.6537; SR phase, p = 0.2827). The use of concomitant medications, including the use of non-opioid analgesics, was similar for both treatment groups in both the IR and SR phases.\n\nBODY.DISCUSSION:\nThis was a short-term, randomized, double-blind comparative study testing the clinical equivalence of IR and SR formulations of hydromorphone and morphine in patients with chronic cancer pain. In each study phase (IR and SR), mean values for BPI 'worst pain in the past 24 hours' (the primary efficacy endpoint) decreased with both hydromorphone and morphine. In the IR phase, the LS mean difference between the treatment groups was 0.2 points, and the 95% CI (-0.4, 0.9) was within the pre-specified equivalency range of -1.5 to 1.5. In the SR phase, the LS mean difference was -0.8 points in favor of OROS® hydromorphone. The upper limit of the 95% CI (-0.01) was within the 1.5 boundary, but the lower limit (-1.6) was less than the -1.5 limit. Therefore, according to the pre-specified criteria, equivalence was not demonstrated; the direction of the difference was in favor of OROS® hydromorphone. The BPI item 'worst pain in the past 24 hours' was selected as the primary endpoint of the trial based on previous studies showing it to be the most sensitive BPI measure in the clinical trial setting [13,20-22]. The results of the present study further suggest that OROS® hydromorphone provides consistent pain relief over 24 hours, and that pain levels in the evening were significantly lower after OROS® hydromorphone compared with CR morphine treatment. This finding reflects the 'pain now PM' measure being scored at the end of morphine dosing (i.e. trough levels) but at the midpoint of hydromorphone dosing. The comparable results between groups for the other secondary efficacy variables (including assessments of pain interference with physical activity and social function, performance status, and cognition) support similarity in the treatment efficacy. Withdrawal from the study owing to lack of efficacy was more common in patients randomized to hydromorphone (n = 11) compared with morphine (n = 4). This is a potentially negative finding for hydromorphone; however, the numbers are too low to draw any definite conclusions. Results of the dose analysis were generally consistent with those of previous reports, which indicate that most cancer pain can be controlled with ≤ 240 mg of oral morphine daily [23]. In the present study, 83% of the OROS® hydromorphone group and 88% of the CR morphine group received the equivalent of morphine 240 mg/day or less. The frequency of breakthrough medication use remained stable throughout both phases in the morphine group (52.5% in the IR phase, 48.8% in the SR phase), but decreased from the IR phase to the SR phase in the OROS® hydromorphone group (from 61.6% to 48.1%). At the end of the SR phase, there was no significant difference between the groups in use of breakthrough medication. The occurrence of 3 deaths and 23 serious AEs during the study was not unexpected, given the severity of the patients' conditions and the progressive nature of the disease. In fact, many of the serious AEs were associated with the underlying disease. The participants in this study are representative of the overall population afflicted with chronic cancer pain. The mean baseline BPI score for 'worst pain in the past 24 hours' was 6.3 on an 11-point scale, a score indicative of moderate to severe pain [16]. This is comparable to baseline values in other studies of cancer pain, for which the mean score was 6.99 [24]. Baseline cognition was similar to that of healthy controls (mean MMSE score, 28.3) [25], and the lack of change observed in both treatment groups probably reflects the fact that the MMSE was designed to measure cognition in Alzheimer's disease [14] and was not intended to measure cognition in non-demented subjects. The major positive aspect of this study was the robust design: it was multicenter, randomized, double-blind, and active controlled. It also used a widely utilized and well validated primary outcome measure, the BPI. On the negative side, there was a relatively poor completion rate, with only 60 out of 99 patients (60.6%) randomized to hydromorphone and 73 out of 101 patients (72.3%) randomized to morphine completing both treatment phases. However, this completion rate was reasonably good when taking into consideration that this study was carried out in patients with cancer which was advanced enough to require strong opioid analgesics. In addition, a dropout rate of at least 30% was anticipated. Furthermore, the duration of the study was relatively short (up to 24 days), so it was not possible to make evaluations of the sustained efficacy of the formulations. Two previous randomized, double-blind, crossover studies have compared CR formulations of hydromorphone and morphine in patients with cancer pain [26,27]. Moriarty et al (N = 100) found no significant differences between treatment groups for any outcome measure, and AEs were mild and infrequent [27]. In the other study (N = 87), patients treated with hydromorphone had significantly higher pain scores and required more doses of rescue analgesia than patients receiving morphine [26]. In addition, more patients in the hydromorphone group withdrew owing to AEs or inadequate analgesia (n = 16 versus n = 2 on morphine). Although it is difficult to directly compare the results of these studies with those of the current study, the observed differences may reflect, at least in part, the more consistent delivery of hydromorphone with the OROS® formulation relative to the dosing used in those studies. The consistent release of hydromorphone over 24 hours has been demonstrated in previous studies, in which steady-state plasma concentrations were achieved by 48 hours and sustained throughout the dosing interval [8,28]. Practicing clinicians are acutely aware of the need for multiple pain management alternatives, because it is clear that the response to a particular opioid agent varies among individuals. Although our understanding of the causes of individual differences remains incomplete, receptor and receptor-binding studies suggest that they may result not only from differences in the class of opioid receptors to which each agent binds (morphine binds to mu [primary] and kappa [lesser extent] [29]; hydromorphone binds to mu [primary] and delta [lesser extent] [30]), but also from inter-individual differences in opioid receptors (several receptor subtypes have been identified [mu 1, mu 2, mu 3, delta 1, delta 2, kappa 1, kappa 2, kappa 3]) and the location of these variants within the nervous system [31-33]. Therefore, clinicians may need to utilize different opioids to achieve maximum efficacy for each patient. In addition, some studies have supported the use of opioid rotation, switching from one opioid to another when treatment-limiting toxicity results in reduced responsiveness [34-37]. Based on numerous observations that individual response varies greatly from opioid to opioid, changing to a different drug may provide an improved balance between analgesia and adverse effects; as a result, there is a need for additional long-acting opioids on the market. Long-acting opioid formulations such OROS® hydromorphone have the potential to improve the overall management of chronic pain. Such formulations provide more consistent opioid plasma concentrations, avoiding the peaks and troughs associated with short-acting agents, and result in well-tolerated, around-the-clock pain control with fewer daily doses [38,39].\n\nBODY.CONCLUSION:\nThis study demonstrates that while IR hydromorphone is equivalent to IR morphine for relieving chronic cancer pain, equivalence was not demonstrated for OROS® hydromorphone and CR morphine in the SR phase of the study. The direction of the mean difference between the treatments, and the out-of-range lower limit of the 95% CI was in favor of OROS® hydromorphone on the primary endpoint 'worst pain'. 'Pain now PM' scores were also significantly lower for those taking OROS® hydromorphone at the end of the SR phase (although the timing of this measure coincided with a trough in the dosing levels for the twice-daily morphine compared with the once-daily OROS® hydromorphone), and BPI 'interference with normal work' scores were significantly lower for IR hydromorphone. None of the other secondary efficacy analyses showed significant treatment differences in either phase. The overall safety profiles of the 2 treatments were generally similar and most AEs were typical of opioid analgesic therapy.\n\nBODY.COMPETING INTERESTS:\nMH was a paid advisor for Janssen-Cilag.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nMH was an investigator in this study and was involved in revising this manuscript for important intellectual content. JT contributed to the analysis of the study and reviewed the manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\nQuestion:* Compared to morphine what was the result of hydromorphone on Mean ± SD patient global assessment scores at the end of the SR phase?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
972	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The implementation of a community-based aerobic walking program for mild to moderate knee osteoarthritis (OA): a knowledge translation (KT) randomized controlled trial (RCT): Part I: The Uptake of the Ottawa Panel clinical practice guidelines (CPGs)\n\n ABSTRACT.BACKGROUND:\nThe implementation of evidence based clinical practice guidelines on self-management interventions to patients with chronic diseases is a complex process. A multifaceted strategy may offer an effective knowledge translation (KT) intervention to promote knowledge uptake and improve adherence in an effective walking program based on the Ottawa Panel Evidence Based Clinical Practice Guidelines among individuals with moderate osteoarthritis (OA).\n\nABSTRACT.METHODS:\nA single-blind, randomized control trial was conducted. Patients with mild to moderate (OA) of the knee (n=222) were randomized to one of three KT groups: 1) Walking and Behavioural intervention (WB) (18 males, 57 females) which included the supervised community-based aerobic walking program combined with a behavioural intervention and an educational pamphlet on the benefits of walking for OA; 2) Walking intervention (W) (24 males, 57 females) wherein participants only received the supervised community-based aerobic walking program intervention and the educational pamphlet; 3) Self-directed control (C) (32 males, 52 females) wherein participants only received the educational pamphlet. One-way analyses of variance were used to test for differences in quality of life, adherence, confidence, and clinical outcomes among the study groups at each 3 month assessment during the 12-month intervention period and 6-month follow-up period.\n\nABSTRACT.RESULTS:\nShort-term program adherence was greater in WB compared to C (p<0.012) after 3 months. No statistical significance (p> 0.05) was observed for long-term adherence (6 to 12 months), and total adherence between the three groups. The three knowledge translation strategies demonstrated equivalent long-term results for the implementation of a walking program for older individuals with moderate OA. Lower dropout rates as well as higher retention rates were observed for WB at 12 and 18 months.\n\nABSTRACT.CONCLUSION:\nThe additional knowledge translation behavioural component facilitated the implementation of clinical practice guidelines on walking over a short-term period. More studies are needed to improve the long-term walking adherence or longer guidelines uptake on walking among participants with OA. Particular attention should be taken into account related to patient's characteristic and preference. OA can be managed through the implementation of a walking program based on clinical practice guidelines in existing community-based walking clubs as well as at home with the minimal support of an exercise therapist or a trained volunteer.\n\nABSTRACT.TRIAL REGISTRATION:\nCurrent Controlled Trials IRSCTNO9193542\n\nBODY.BACKGROUND:\nRising healthcare costs, limited resources, and the aging population have created new and growing challenges in the management of osteoarthritis (OA). The challenges associated with the management of OA are numerous as the prevalence of the population continues to increase while healthcare resources remain limited \n[1-7]. It is therefore necessary to determine the most effective methods of integrating research evidence in order to optimize health outcomes. The purpose of this randomized controlled trial (RCT) was to compare 1) improvements in quality of life (QoL) and clinical outcomes such as pain, mobility and endurance); 2) adherence rates; and 3) confidence and self-efficacy after the implementation of a 12-month supervised community-based aerobic walking program (SCAWP) based on the Ottawa Panel clinical practice guidelines (CPG) among three knowledge translation (KT) intervention arms. QoL, confidence, and self-efficacy were compared at 12- months (end of treatment) and at 18-months (6-months post-intervention). Adherence was compared during the intervention period at 3, 6, 9 and 12 months. The first part of this manuscript introduces each KT intervention and demonstrates the impact of knowledge (CPG) uptake of each by comparing outcomes influenced by the KT intervention such as adherene and behaviour change (confidence and self-efficacy). Knowledge application of each KT intervention is explained through the use a theoretical framework: Knowledge-To-Action Cycle (KTAC) \n[8,9]. The second part of this manuscript focuses on outcome evaluation, a specific phase in the KTAC framework used to guide this study. Part II demonstrates the effect of each intervention involving a walking program on outcomes which were influenced by the SCAWP including QoL (primary outcome) and other clinical outcomes such as pain, mobility, and endurance. These outcomes are exhibited in part II. Therefore, both parts of this manuscript were split according to the ''Evaluate outcomes\" phase of the KTAC framework. Part I focused on KT outcomes which measured the success of CPG uptake through participants' adherence and behavioural change while part II focused on clinical outcomes which measured the positive effect of SCAWP due to the indirect CPG uptake/implementation/adoption by individuals with OA of the knee.\n\nBODY.BACKGROUND.KNOWLEDGE TRANSLATION:\nA major issue in health research today is finding effective and efficient ways to exchange knowledge between researchers, clinicians and the general public. Potential benefits to health which could be accrued through the application of research findings are not realized due to challenges in research uptake and knowledge translation \n[10]. KT is defined by Estabrooks et al. \n[11] as \"the process by which specific research-based knowledge (science) is implemented in practice.\" The available evidence suggests that with an effective KT strategy, uptake of evidence-based clinical practice guidelines (EBCPGs) can be effective in improving patient health outcomes \n[12].\n\nBODY.BACKGROUND.PHYSICAL ACTIVITY AND OSTEOARTHRITIS:\nThe promotion of physical activity (PA) is a priority for health organizations serving the general population \n[13,14] and is highly recommended for subgroups affected by chronic diseases \n[15-19]. Community-based PA combined with a behavioural modification and self-management interventions can reduce the risk of disability and negative consequences of inactivity related to OA \n[20,21]. The challenge is to develop PA programs that will encourage OA patients to initiate and maintain improvements in exercise behaviour over a long-term period \n[22]. The available evidence suggests that with an effective KT strategy, uptake of evidence-based clinical practice guidelines (CPGs) can be effective in improving patient health outcomes \n[12].\n\nBODY.BACKGROUND.SELECTING AN EFFECTIVE KT STRATEGY:\nMultifaceted interventions combining more than one KT strategy have tended to be more effective than using a single KT strategy alone \n[23,24] and have shown to have the greatest impact on CPG adherence and PA performance \n[25]. Behavioural interventions have been used for other chronic conditions to improve long-term adherence and maintenance of PA regimens with varying success. The efficacy of different behavioural interventions including patient education, health counselling, goal setting, and social/peer support, delivered separately and or in combination, have been examined in the management of arthritis \n[26-31].\n\nBODY.METHODS:\nThe following methodology is in full agreement with the Consolidated Standards of Reporting Trials (CONSORT) 2010 Statement criteria for reporting RCTs \n[32].\n\nBODY.METHODS.DESIGN:\nThis single blind RCT, funded by the Canadian institutes of Health Research, used a parallel group design (1:1:1). This community-based study was approved by the University of Ottawa Research Ethics Board and the City of Ottawa Public Health Research Ethics Board. This study implemented one of the Ottawa Panel CPG recommendations related to a supervised community-based aerobic walking programs (SCAWPs) among individuals with mild to moderate OA of the knee \n[33-35]. In order to facilitate an understanding of the KT process, Graham et al. developed a conceptual framework entitled \"the Knowledge-To-Action Cycle\" (Figure \n1) which provides an approach which combines commonalities from various planned-action theories \n[8,9]. This framework was used to guide the development of the three KT strategies used in this RCT (Additional file \n1). The framework demonstrates the dynamic process of knowledge creation and application \n[9]. Knowledge creation consists of three phases: knowledge inquiry, knowledge synthesis, and knowledge tools/products. The knowledge creation cycle of the framework demonstrates how knowledge is refined through each phase to provide useful information for end users. The action cycle of the framework consists of seven phases which may occur sequentially or simultaneously: 1) Identify the Knowledge-To-Action Cycle gaps; 2) Adapt Knowledge to local context; 3) Assess barriers to Knowledge Use; 4) Select, Tailor, Implement Interventions; 5) Monitor Knowledge Use; 6) Evaluate outcomes; and 7) Sustained Knowledge Use. For part I, the emphasis was placed on the \"Evaluate outcomes (KT outcomes)\" phase as participants' knowledge uptake was measured as adherence to the effective walking program for OA and attitude/behaviour change (self-efficacy and confidence) after participating in the SCAWP. Figure 1Knowledge-To-Action Cycle. This figure illustrates the Knowledge-To-Action Cycle Framework \n[8]. This figure is used with permission: Lost in knowledge translation: Time for a map. Graham ID, et al. Journal of Continuing Education in the Health Professions, 26(1). Copyright © 2006. The Alliance for Continuing Medical Education, The Society for Academic Continuing Medical Education, and The Association for Hospital Medical Education. The hypothesis was that the additional behavioural approach of the multifaceted KT intervention would: 1) increase short and long term adherence to the SCAWP; 2) reduce the drop-out rate; 3) influence behaviour change by improving self-efficacy, confidence, QoL and other clinical outcomes.\n\nBODY.METHODS.SAMPLE AND RECRUITMENT:\nA total of 222 adults with knee OA were recruited. Participants were eligible to participate in the study if he/she 1) had a confirmed diagnosis with mild to moderate unilateral or bilateral OA according to the American College of Rheumatology clinical and radiographic/magnetic resonance imagery criteria; 2) reported pain for at least 3 months; 3) expected his/her medication to change during the study period; 4) demonstrated an ability to ambulate for a minimum of 20 minutes, at their own pace with minimal reports of pain (≤ 3 out of 10 on a visual analogue pain rating scale) \n[36]; 4) were able to be treated as an out-patient; and 5) were available three times a week over a period of 12 months. Potential study subjects were excluded if they had: 1) Participated in regular physical or aerobic sports ≥ 2 times per week for more than 20 minutes per session during the previous 6 months; 2) severe OA of the knee or other weight bearing joints of the lower extremity; 3) no written consent from their physician to participate in the study; 4) pain at rest or at night; 5) received rehabilitation treatment, corticosteroids injection, or any other pain-related treatment besides medication for arthritis within the last 12 months; 6) uncontrolled hypertension (Systolic blood pressure >160 mm Hg confirmed by the screening initial VO2 max test at the Ottawa Heart Institute) 7) other illnesses, such as rheumatoid arthritis (judged by the patient or study physician to make participation in this study inadvisable); 8) significant cognitive deficit resulting in an inability to understand or comply with instructions; 9) surgery planned in the next year; 10) Intention to move away from Ottawa region in the next year; 11) an inability to communicate in English or French; or 12) an unwillingness to sign informed consent. The study coordinator assessed the inclusion/exclusion criteria of all potential participants by telephone. At the first visit, written informed consent was obtained if the patient met all inclusion criteria.\n\nBODY.METHODS.INTERVENTION:\nParticipants were randomly assigned to one of the three KT intervention groups using central randomization \n[37] and computer generated numbers \n[38]: 1) Walking and Behavioural intervention (WB) (18 males, 57 females) which included the SCAWP with a behavioural intervention and an educational pamphlet on the benefits of walking for OA; 2) Walking intervention (W) (24 males, 57 females) wherein participants only received the SCAWP intervention and the educational pamphlet; 3) Self-directed control (C) (32 males, 52 females) wherein participants only received the educational pamphlet. All 3 groups were provided with pedometers and log books to be completed to measure physical performance (walking in minutes) and additional PA aside from the walking sessions (Table \n1). The KT strategies were implemented over a 12-month duration and participants were assessed for additional 6 months (15 and 18-month follow-up assessments). Table 1 Summary of the KT strategies used KT strategies in each group WB or WalkingClub+ (supervised walking program + behavioural approach at the community-based Walking Club) W or WalkingClub (supervised walking program only at the community-based Walking Club) C or Self-directed Home-based or community based different than W and WB (unsupervised/self-directed Walking program only) EBP walking program (Ottawa Panel, 2005/2012) refs: \n[ 33 - 35 ] EBP walking program (Ottawa Panel, 2005/2012) refs: \n[ 33 - 35 ] Walking program (general info from pamphlet on walking and OA) Walking Club + effect (supervised program, team, daily monitored vital measures: BP, HR, #steps,) Walking Club effect (supervised program, team, daily monitored vital measures: BP, HR, #steps,) N/A Pedometer as measurement tool, but becomes a KT strategy Pedometer as measurement tool, but becomes a KT strategy Pedometer as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy $ compensation each walking session and at evaluation session $ compensation each walking session and at evaluation session $ compensation each logbook fulfilled and at evaluation session Study affiliation/participation (feel committed) Study affiliation/participation (feel committed) Study affiliation/participation (feel committed) Behavioural intervention (Baycrest PACE-ex: patient education + goal settings; PA counselling, telephone support) N/A N/A Following the successful randomization process, wherein no statistical difference was found between the three groups (with the exception of the \"physical role\" category of the SF-36: part II) (Tables \n2, \n3, \n4, \n5), research staff and evaluators were blinded to the treatment allocation. An independent evaluator was blinded to assess outcome measures. Due to the nature of the physical intervention, it was not practical to blind the study participants and PA specialists supervising the aerobic walking program \n[39]. Table 2 Subject demographics and baseline characteristics Characteristic Walking (n=79) Walking and Behavioural (n=69) Self-directed Control (n=74) Total Mean age (SD), yrs 63.9 (10.3) 63.9 (8.2) 62.3(6.8) 63.4 (8.6) Missing Data 0 0 0 0 Men/women, (%) 24 (30.4)/55 (69.9) 18 (26.1)/51 (73.9) 27 (36.5)/47 (63.5) 69 (31.1)/153 (68.9) Missing Data 0 0 0 0 Affected knee, n (%) Right 33 (41.8) 31 (44.9) 25 (33.8) 89 (40.1) Left 31(39.2) 23 (33.3) 28 (37.8) 82 (36.9) Both side 15 (19.0) 15 (28.4) 21 (28.4) 51 (23.0) Missing Data 0 0 0 0 Mean duration of OA (SD), yrs 9.54 (8.09) 11.3 (9.7) 10.0 (9.9) 10.3 (9.26) Missing Data 0 0 0 0 Mean weight (SD), kg 80.7 (18.5) 83.1 (15.4) 83.0(15.8) 82.2 (16.6) Missing Data 0 1 0 0 Mean BMI (SD), kg/m² 29.4 (5.4) 30.3 (5.6) 29.9(5.3) 29.8 (5.4) Missing Data 0 2 4 6 Walking aid, n (%) Yes 10 (12.7) 10 (14.5) 9 (12.2) 29 (13.1) No 69 (87.3) 58 (84.1) 64 (86.5) 191 (86.0) Missing Data 0 1 1 2 Racial background, n (%) White 69 (87.3) 60 (87.0) 68 (91.9) 197 (88.7) Black 1 (1.3) 3 (4.3) 1 (1.4) 5 (2.3) Hispanic 2 (2.5) 2 (2.9) 4 (5.4) 8 (3.6) Asian or Pacific Islander 5 (6.3) 4 (5.8) 1 (1.4) 10 (4.5) American Indian or Alaskan native 1 (1.3) 0 (0) 0 (0) 1 (0.5) Other 1 (1.3) 0 (0) 0 (0) 1 (0.5) Missing Data 0 0 0 0 Marital status, n (%) Married 46 (58.2) 36 (52.2) 44 (59.5) 126 (56.8) Separated 2 (2.5) 1 (1.4) 1 (1.4) 4 (1.8) Divorced 9 (11.4) 17 (24.6) 8 (10.8) 34 (15.3) Widowed 17 (21.5) 11 (15.9) 9 (12.2) 37 (16.7) Never Married 5 (6.3) 4 (5.8) 12 (16.2) 21 (9.5) Missing Data 0 0 0 0 Level of education, n (%) Less than 7 yrs of school 2 (2.5) 1 (1.4) 1 (1.4) 4 (1.8) Grades 7 through 9 5 (6.3) 0 (0) 0 (0) 5 (2.3) Grades 10 through 11 7 (8.9) 4 (5.8) 5 (6.8) 16 (7.2) High school graduate 13 (16.5) 16 (23.2) 8 (10.8) 37 (16.7) 1 to 4 yrs of college 13 (16.5) 9 (13.0) 22 (29.7) 44 (19.8) College graduate 25 (31.6) 21 (30.4) 19 (25.7) 65 (29.3) Professional or Graduate school 14 (17.7) 18 (26.1) 19 (25.7) 51 (23.0) Missing Data 0 0 0 0 Yrs: years, OA: osteoarthritis, kg: kilograms, m: meters, %: validity percent. Table 3 Subject’s Medication at Baseline Medication Walking (W) only (n=79) Walking and Behavioural (WB) (n=69) Self-directed (C) (n=74) Oral hypoglycaemic agents Total 2 (3) 5 (7) 9 (12) Biguanide Class 2 (3) 4 (6) 9 (12) Sulfonylureas Class 0 (0) 0 (0) 2 (3) Thiazolidinedione 0 (0) 2 (3) 2 (3) Antihypertensive Agents Total 22 (28) 15 (22) 15 (22) Calcium channel blockers 6(8) 0(0) 7(9) Antiotensin-converting enzyme 3 (4) 7 (10) 7 (9) Angiotensin II receptor blockers 6 (8) 6 (9) 3 (4) Beta-blocker 4 (5) 3 (4) 4 (5) Alpha-blocker 3 (4) 0 (0) 0 (0) Diuretic 5 (6) 8 (12) 5 (7) Antiarrhythmic 1 (1) 0 (0) 0 (0) Anti-anginal 1 (1) 0 (0) 0 (0) Anti-platelet agent 1 (1) 1 (1) 1 (1) Anticoagulant 0 (0) 2 (3) 0 (0) Phosphodiesterase type 5 inhibitors 0 (0) 1 (1) 0 (0) Statins 8 (10) 12 (17) 10 (14) Hormone Total 11 (14) 10 (14) 11 (15) Thyroid 5 (6) 5 (7) 8 (11) Insulin 0 (0) 3 (4) 1 (1) Corticosteroid 4 (5) 2 (3) 3 (4) Progesterone 1 (1) 0 (0) 1 (1) Androgen 1 (1) 0 (0) 0 (0) Oestrogen 1 (1) 0 (0) 0 (0) Antithyroid 0 (0) 1 (1) 0(0) SERMs (Selective estrogen receptor modifiers) 1 (1) 0 (0) 0 (0) Beta 2-adrenergic receptor agonist (bronchodilator) 2(3) 1 (1) 3 (4) NSAIDs (Non-steroid anti-inflammatory drugs) 26 (33) 21 (30) 18 (24) COX-2 selective inhibitor 3 (4) 4 (6) 1 (1) NSAIDS Betahistine 0 (0) 1 (1) 0 (0) DMARDs (Disease modifying antirheumatic drugs) 0 (0) 1 (1) 0 (0) Histamine antagonist 0 (0) 2 (3) 0 (0) Bisphosphonate 6 (8) 4 (6) 4 (5) Antibiotics 2 (3) 1 (1) 4 (5) Analgesics 1 (1) 1 (1) 3 (4) Opiates 0 (0) 0 (0) 2 (3) Hypnotic 4 (5) 3 (4) 4 (5) Antidepressant 7 (9) 5 (7) 7 (9) Psychostimulant 0 (0) 1 (1) 0 (0) Antipsychotic 0 (0) 1 (1) 0 (0) Anti-manic 0 (0) 1 (1) 0 (0) Anti-convulsant 1 (1) 1 (1) 0 (0) Protein pump inhibitor (PPI) 9 (11) 5 (6) 6 (8) Enzyme inhibitor 0 (0) 1 (1) 2 (3) Muscle relaxant 0 (0) 1 (1) 1 (1) Antispasmodic 0 (0) 1 (1) 0 (0) Anti-cholinergic 1 (1) 1 (1) 0 (0) Antineoplastic 2 (3) 1 (1) 0 (0) Antimetabolite 1 (1) 1 (1) 1 (1) Antifolate 0 (0) 1 (1) 1 (1) Latanoprost 0 (0) 1 (1) 0 (0) Viscosupplementation 0 (0) 1 (1) 0 (0) Xanthine 1 (1) 0 (0) 0 (0) Antifungals 0 (0) 0 (0) 1 (1) Antimalarial 0 (0) 1 (1) 1 (1) Nitrate 0 (0) 0 (0) 2 (3) Laxative 0 (0) 0 (0) 2 (3) Supplements 22 (28) 22 (28) 18 (24) Homeopathic Medication 1 (1) 1 (1) 1 (1) None 11 (14) 10 (13) 9 (12) Not Specific 21 (27) 21 (27) 20 (27) Missing Data Total 4 (5) 8 (10) 17 (23) No Evaluation* 2 (3) 4 (5) 7 (9) No File** 2 (3) 4 (6) 10 (14) This table presents a list of medications which participants declared to be taking at baseline. Data is presented as n (%). Table 4 Summary of adherence based on attendance marked in trainers’ manuals and individual walkers’ logbooks Walking N Mean±SD Walking & Behavioural N Mean±SD Self-directed (C) N Mean±SD Walking vs. Self-directed t -test P value Walking & Behavioural Vs. Self-directed t -test P value Walking & Behavioural Vs. Walking t -test P value 0-3 months 79 69 73 (0.043) (0.012) (0.514) 0.770±0.299 0.802±0.290 0.652±0.403 3-6 months 79 69 73 (0.242) (0.159) (0.774) 0.617±0.410 0.636±0.390 0.535±0.459 6-9 months 79 69 73 (0.421) (0.937) (0.363) 0.471±0.418 0.534±0.425 0.528±0.463 9-12 months 79 69 73 (0.549) (0.551) (0.989) 0.446±0.441 0.445±0.433 0.490±0.462 Total Adherence 79 69 73 (0.690) (0.413) (0.619) 0.576±0.346 0.604±0.342 0.551±0.420 Table 5 Summary of self-efficacy, measured with Stanford questionnaire on chronic disease for three study arms (continued) Baseline 12 months 18 months W WB C W WB C W WB C N N N N N N N N N Variables Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD W.Vs. C(P) W.Vs. C(P) W.Vs. W(P) W.Vs. C(P) W.Vs. C(P) W.Vs. W(P) Coping 79 69 73 44 44 40 44 41 36 With 1.069±794 1.126±0.775 1.013±0.946 0.864±0.771 1.239±0.730 1.192±0.835 1.064±0.952 1.388±0.856 1.342±1.127 Symptoms (0.091) (0.858) (0.057) (0.190) (0.793) (0.286) Confidence 79 69 73 44 44 39 43 41 36 About 7.406±1.719 7.827±1.488 7.858±1.512 7.826±1.551 7.682±1.785 8.064±1.575 7.690±1.920 7.546±1.848 8.015±1.476 Doing Things (0.433) (0.297) (0.060) (0.235) (0.422) (0.041) (Higher is better) W: Walking only group; WB: Walking and Behavioural Group; C: Self-directed group (unsupervised/self-directed); N: number of subjects in each comparative group; SD: standard deviation; vs: versus; data is presented as mean (standard deviation); p: p-value (statistical significance); Statistically significant. \n\nBODY.METHODS.INTERVENTION.SUPERVISED WALKING PROGRAMS (WB & W GROUPS):\nThe SCAWPs took place at two walking club sites in Ottawa, Ontario, Canada and one in Gatineau, Québec, Canada. Participants took part in three weekly walking sessions over a 12-month period. Every walking session began with a 10-minute warm-up, consisting of light aerobic exercises, before engaging in the 45-minute aerobic walking phase. The walking sessions ended with a 10-minute cool-down consisting of light aerobic exercises and stretching. The target intensity of the walking phase was approximately 50% to 70% of the subjects' pre-determined maximum heart rate as recommended in The Ottawa Panel guidelines \n[33-35]. The SCAWP was divided into two stages: 1) A \"progressive aerobic phase\" wherein the duration and heart rate intensity progressively increased over time and 2) a \"maintenance aerobic phase\" wherein the duration and heart rate intensity remained constant for the remainder of the walking program (Additional file \n2). The selected dosage, frequency, intensity, and progression of the walking interventions were based on existing protocols proven effective for OA, described in several RCTs involving individuals with OA \n[33-35] (Additional file \n2). To avoid contamination between the two walking interventions, participants in the W group were instructed to walk in the mornings, while the WB group walked in the afternoons at the main walking site. In order to meet the prescribed target heart rate, heart rate monitors were provided to each participant prior to his/her walking session. As a safety precaution, participants who experienced prolonged pain lasting more than two hours within 24 hours after a walking session were asked to temporarily reduce their level of exercise until he/she felt comfortable enough to resume the appropriate duration, intensity and frequency of the walking program. Following randomization, the PA specialist met each subject in the walking groups to explain the SCAWP and its progression (Additional file \n2) and was present for a minimum of three weekly scheduled sessions over one year to supervise the subjects. The PA specialist was responsible for monitoring and recording attendance, blood pressure, heart rate (during and after the walking session), time duration, and number of steps (pedometer) at each walking session. Monetary compensation was given to each participant for attending each walking session.\n\nBODY.METHODS.INTERVENTION.BEHAVIOURAL INTERVENTION (WB GROUP):\nThe behavioural intervention was part of the multifaceted KT intervention (Table \n1) and was implemented using the adapted Program for Arthritis Control through Education and Exercise (PACEex) program \n[40]. The behavioural intervention was integrated into the PACEex program and consisted of the following components: (1) short- and long-term goal setting during PACEex classes; (2) an educational component, delivered by a trained instructor, involving consisting of instructional sessions about the benefits of PA, specifically walking; (3) monthly face-to-face counselling wherein participants received moral support/encouragement to adherence with PA. Potential barriers to program adherence were identified and self-management strategies were reviewed to overcome those barriers; (4) goal setting and telephone counselling were provided as an additional source of social support until the end of the supervised phase. As with the face-to-face counselling, barriers were identified and strategies were shared in an effort to promote the long-term maintenance of PA. In summary, the behavioural intervention consisted of twenty 2-hour group sessions discussing short-term goal setting and education of arthritis-related topics over a duration of 20 consecutive weeks. Individual long-term goal setting was discussed at the beginning of the PACEex program and was followed by monthly face-to-face meetings throughout the first 6 months of the program. The last six months of the 12-month supervised phase consisted of participants receiving counselling via telephone discussing long-term goals and barriers/facilitators to adhere to the walking program.\n\nBODY.METHODS.INTERVENTION.THE SELF-DIRECTED CONTROL (C GROUP):\nParticipants were invited to consult an educational pamphlet on walking and OA. One introductory session was provided to the participant wherein they were provided an educational pamphlet describing the benefits of walking for OA, a pedometer to monitor PA, and a logbook to record activity level and adherence while partaking in the self-directed walking program. Participants in this group received monetary compensation for the completion his/her log books. The self-directed (C) group did not have any contact with participants in the two other groups, avoiding potential contamination.\n\nBODY.METHODS.DATA COLLECTION:\nParticipants were assessed by an independent evaluator at baseline and at each 3 month interval (months 3, 6, 9, 12) during the intervention period. Participants were then assessed at 3 and 6 months post-intervention during the follow-up period (15 and 18-months). Participants were asked to complete a collection of validated questionnaires as well as perform physical tests at each assessment.\n\nBODY.RESULTS.KNOWLEDGE (CPG) UPTAKE OUTCOME MEASURES (KT OUTCOMES).ADHERENCE AND BEHAVIOUR CHANGE:\nSimilar to other studies \n[29,41,42], participant adherence was assessed as the number of attended walking sessions divided by the number of prescribed sessions (3 sessions per week). Among the W and WB groups, the number of attended walking sessions throughout the 12-month duration was recorded by the exercise therapist on site as well as through the use of participants' completed logbooks which provided information on the amount of performed PA during the 12-month intervention period. The C group's adherence was only assessed by the completed log books. Behaviour change was based on the concept of self-efficacy and was measured using the Stanford scale. In regards to the research question, behaviour change results were only reported at 12 and 18-months.\n\nBODY.RESULTS.KNOWLEDGE (CPG) UPTAKE OUTCOME MEASURES (KT OUTCOMES).ANALYSIS:\nThe analysis was conducted on an intention-to-treat basis. Descriptive statistics including mean, standard deviation and frequencies were used to summarize the study groups at baseline. A repeated measure mixed model was used to assess the change in adherence from baseline to end of treatment (12 months) among three study groups. Behavioural change outcomes were assessed from baseline to of end treatment (12 months) and at 6-month follow-up post-intervention (18 months). The model included variables such as intervention group, study month, and an interaction term between intervention group and study month. Missing data was assumed to be missing at random (MAR) in order to include incomplete data. Pairwise differences comparing each group to one another (W vs. C, W vs. WB, WB vs. C) were assessed. The repeated measure mixed model was used to compare the change of adherence from baseline to the 18- month follow-up. Statistical analyses were performed using SAS (version 9.2, SAS Institute Inc., Cary, North Carolina), and statistical significance was defined as p<0.05.\n\nBODY.RESULTS:\nBetween January 2007 and December 2008, 629 study participants were assessed for eligibility. Figure \n2 exhibits the flow of participants from recruitment to follow-up. The most common reasons for exclusion were: 1) time commitment (26.5%); 2) first diagnosed with OA by physician or X-Ray but later contradicted by MRI test result (18.1%); 3) loss of interest (14.2%); 4) severe OA of the weight bearing joint of LE (11.8%); 5) no medical clearance after VO2 max test (5.1%); 6) unable to contact (4.9%); 7) too active (2,9%); 8) knee replacement (2.7%); 9) age related (2.5%); 10) travelling too much (1.9%); 11) living too far (1.2%). Follow-up for the last recruited participant was completed in May 2010. Figure 2Study flow diagram. This figure provides a flow diagram of data collection from baseline to 18-months follow-up. The groups were similar in age, sex, ethnicity, OA duration and medication use (Table \n2 &3). Two hundred and twenty two subjects were included in the study. Women made up 153 of the 222 subjects. The mean age (±S.D.) was 63.4 (±8.6) years, the mean disease duration (±S.D.) was 10.3 (±9.3) years, the highest level of completed education was \"College graduate\" with 65 participants (±29.3) and \"Professional or graduate school\" with 51 participants (±23.0). There was no statistical difference between the three comparative groups at baseline for all the demographic variables.\n\nBODY.RESULTS.BLINDING:\nThe effectiveness of blinding the evaluator to treatment allocation was assessed through a questionnaire where she was asked to identify which group each participant belonged to. The blinding rate of the evaluator was high (98%).\n\nBODY.RESULTS.ADHERENCE AND ATTRITION:\nFrom baseline to 12 months, the adherence rates were expressed as percentages of adherence among walkers who did not drop out and were reported as means (+/−standard deviation) for each time period between groups (Table \n4). Statistically significant results for short-term adherence rates favoured participants in the WB group (80.2%) compared to the self-directed (C) group (65.2%) (p<0.012) after 3 months. For long term adherence (6 to 12 months), the WB group demonstrated superior adherence rates throughout each period compared to the other two groups, but results did not reach statistical significance. No statistical significance (p> 0.05) was observed for the total adherence rates between WB vs. W, W vs. C, and WB vs. C. During the 12-month intervention period, the dropout rates were 43.1% for the W group, 40.6% for the WB group and 49.3% for the self-directed (C) group. From baseline to 18 months, the dropout rates were 44.3% for the W group; 40.6% for the WB group and 52.1% for the self-directed (C) group (Figure \n2 and Additional files \n3 &4). The dropout rates were lower for the WB group at 12-months (36.2%) and 18-months (39.1%) compared to the W group (40.5% and 44.3%) and the self-directed (C) group (40.5% and 51.3%). The W and self-directed (C) groups had the highest dropout rates (40.5%) at 12 months while the self-directed (C) group had the highest at 18 months (52.1%).\n\nBODY.RESULTS.BEHAVIOUR CHANGE:\nAfter the 12 month intervention phase, no differences were found between the 3 comparative groups for any of the items on the Stanford scale (Table \n5). Moreover, variables related to coping with symptoms and confidence were higher among the WB group compared to the other two groups. At 18-months, statistically significant differences in scores between the WB and W groups revealed that the W group demonstrated an improved mean for the \"confidence about doing things\" variable (p=0.041). The self-directed group (C) demonstrated the highest mean \"confidence about doing things\" score 8.015± 1.476 (p=0.040) as it increased by 0.157 (p=0.048) when compared to baseline. The self-directed group (C) demonstrated the highest mean score 8.015± 1.476 (p=0.040).\n\nBODY.DISCUSSION.THE IMPACT OF THE MULTIFACETED KT INTERVENTIONS ON KNOWLEDGE (CPG) UPTAKE.ADHERENCE AND ATTRITION:\nThe additional behavioural approach of the multifaceted KT intervention (WB group) improved adherence to the SCAWP when compared to the other two groups over a short-term period. In addition, the WB group demonstrated reduced dropout rates compared to the W and self-directed (C) groups. Over a long-term period, the three groups were equivalent in improving behaviour change while adopting the Ottawa Panel recommendations on walking \n[33-35]. Adherence rates were higher among the WB group for each 3-month period compared to the other two groups. Improved adherence rates over the short-term period can be explained by the fact the PACEex program used in the behavioural intervention lasted for 20 consecutive weeks at the beginning of the study. The PACEex program \n[40] used in this study, allowed our participants to set general goals, which may have motivated participants to adhere to the walking program. Similar to a previous study \n[43], another reason may be that participants in the W and WB group lost motivation after the supervised phase, no longer having regular professional support from the PA specialist. The drop-out rate results are comparable to other long-term studies which have used an aerobic PA intervention with a behavioural intervention component \n[38,44-54]. Higher adherence rates were demonstrated at 2 to 4 months (85% - 90%) and at 10 to 18 months (50% - 90%). An initial 6-month center-based exercise program enhanced retention over short and the long-term periods while promoting short-term adherence and energy expenditure \n[55]. The moderate exercise intervention retained more subjects, but had little influence on adherence over a long-term period \n[56]. Home-based PA programs, such as self-directed walking, can achieve improved adherence rates compared to facility-based programs over a long period \n[55].\n\nBODY.DISCUSSION.BEHAVIOUR CHANGE:\nThere were no statistically significant results among the three groups at 12 months. These results concur with a similar study \n[53] and are normal in the context of a KT study which implemented an already proven effective walking program \n[33-35]. However, at 18-months, there were statistically significant results which favoured the self-directed group (C). One reason explaining why participants in the self-directed group (C) had higher confidence and self-efficacy scores may be due to the fact that since these individuals were not supervised, they may have been more independent, self-controlled, self-confident, and self-motivated. Participants in this group may have also had the opportunity, over the 12-month period, to develop confidence and self-efficacy skills compared to the two supervised groups during the unsupervised follow-up phase. The variable \"confidence about doing things\" decreased after 12 months for the WB group. Given the high amount of PA demonstrated by the WB group at 12 months, we were surprised with this result. On the other hand, at 18 months, statistically significant results favoured the W group compared to WB group for the variables \"confidence about doing things\". Again, these results about confidence were unexpected given that the WB group performed higher amounts of PA. Exercise therapists, pedometers, logbooks and social support from walking club members (Table \n1) assisted participants who had difficulties with activity adherence and maintenance \n[57]. Regular professional contact was recognised as the significant motivational factor for adherence to the supported walking program during the RCT \n[43]. Social support has been reported to be more successful in engaging participants in PA programs compared to programs which only provided written educational material \n[58,59]. The combination of using pedometers and goal-setting has been recognised as an effective KT tool for increasing PA \n[31,60-62]. However, despite the short-term effectiveness of pedometers and goal-setting, the success of these tools diminished over time. Other KT strategies are recommended to facilitate sustainability \n[62].\n\nBODY.DISCUSSION.LIMITATIONS:\nBarriers related to the implementation of SCAWP were identified and addressed to improve adherence for older individuals \n[57]. Acceptability (preferences, tolerance and accessibility) should be considered to promote PA adherence and to overcome associated barriers \n[63]. The most common barriers identified by participants with OA are perceptions about illness and recovery, transportation difficulties, family commitments and inconvenient timing \n[64]. Time commitment is also recognised as a significant barrier \n[55]. Additional barriers such as weather conditions including snow storms, freezing rain and humidity, a 3-month bus strike, and health problems of participants' partners may have contributed to study adherence. Adherence is influenced by participant's preference of intervention \n[65-70]. Unfortunately, with this study being a RCT, taking participants' preference into consideration was not possible due to the randomization procedure. This being said, randomisation may have contributed to higher dropout rates. The purpose of this KT study was to implement a scientifically proven effective walking program for OA \n[33-35]. Short term research suggests that self-management interventions \n[16,18], telephone counselling \n[22,46,71-73], peer support \n[13,74-76] and PA education \n[18,22,27,41,77] are effective behavioural strategies for improving self-efficacy. The long-term multifaceted behavioural strategy used in this study did not concur with the previous studies, as participants in the self-directed group (C group) were provided information and education on the benefits of PA. Methods of measurement for adherence for the W and WB groups were different than the self-directed (C) group. Observed attendance was recorded on site for each walking session for the W and WB groups by exercise therapists while adherence could only be measured in the self-directed group (C) using completed logbooks. The self-reporting of PA, which is commonly overstated, may have been subject to potential information bias. Selection bias may have occurred as our study population included individuals with mild to moderate OA, with a confirmed X-ray report. In addition, some participants were retired while some were still employed. Since participants were provided monetary compensation for their participation in the study, one may argue the generalizability of the results.\n\nBODY.DISCUSSION.IMPLICATIONS:\nThis KT RCT aimed to identify the best multifaceted strategy to implement a proven effective walking program for OA of the knee among older individuals. The epidemic public health problem of OA can be managed through the implementation of a proven effective walking program in existing community-based walking clubs as well as at home with minimal support. More studies are needed to improve the long-term walking adherence or knowledge uptake on SCAWP among participants with OA. Particular attention should focus on patients' characteristics and preferences.\n\nBODY.CONCLUSIONS:\nThis study partially supported our initial hypothesis regarding the impact of a multifaceted KT intervention as the combined walking and behavioural approach had greater benefits over the comparative groups resulting in improved long-term adherence to PA only over a short period (3-months). The WB group demonstrated to be the best KT strategy for reducing dropouts compared to the W group and self-directed (C) group. All three KT strategies were equivalent over the long-term period (up to 18 months) for improving behavioural change. However, the self-directed walking program (C group) was the least expensive to implement over a long-period (18 months). This RCT was a long-term adherence study as well as a KT study which addressed questions of clinical and scientific importance aimed at improving the understanding of effective KT strategies to promote the adoption and maintenance of a community-based walking program for OA.\n\nBODY.ABBREVIATIONS:\nOA: Osteoarthritis; QoL: Quality of Life; SCAWP: Supervised Community-based Aerobic Walking Program; CPG: Clinical Practice Guideline; KT: Knowledge Translation; KTAC: Knowledge-To-Action Cycle; EBCPG: Evidence-Based Clinical Practice Guidelines; CONSORT: Consolidated Standards of Reporting Trials; WB (group): Walking and Behavioural intervention; W (group): Walking intervention; C (group): Self-directed control intervention; RCT: Randomized Controlled Trial; PA: Physical Activity; PACE-ex: Program for Arthritis Control through Education and Exercise; AIMS2: Arthritis Impact Measurement Scale 2; SF-36: Short-Form 36 Health Survey; WOMAC: Western Ontario and McMaster Universities Osteoarthritis Index; MET: Multiples of basal metabolic rate; MAR: Missing At Random; CIHR: Canadian Institutes of Health Research.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS’ CONTRIBUTIONS:\nLB is a Full Professor of Rehabilitation, an epidemiologist and the principal investigator of this study and primary author of this manuscript. GAW the co-principal investigator of this study, is senior biostatistician and director, Cardiovascular Research Methods Centre at the University of Ottawa Heart Institute, and is a leading expert in the design and analysis of clinical trials. He provided assistance with the methodology and statistical analysis of the study. GPK is a Full Professor of Physiology at the University of Ottawa, and director of the university's Human Performance and Environmental Medicine Research Laboratory and Professional Fitness and Lifestyle Consultant Certification Training program. He assisted with the methodology of the study. RR is a senior researcher at the University of Ottawa Heart Institute and provided experience in applying innovative behavioural approaches aimed at increasing PA in healthy and chronic diseased populations. AM is a health economist and assisted with the economic evaluation concept in the original proposal. PT is a rheumatologist, an epidemiologist and chief of the Cochrane Musculoskeletal Group. He has experience in conducting RCTs and meta-analyses. He provided assistance with OA outcome measures in the study. MH & CM developed the PACEex program and was in charge of training the PA specialist. GDA was the research coordinator of this study and assisted with the writing of this manuscript. LC is a biostatistician and performed the analyses of this study. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2458/12/871/prepub\n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional file 1The knowledge –to-action framework and KT interventions. This table demonstrates how each step of the KTAC framework is applied to the RCT.Click here for file Additional file 2Post-Randomization Walking Interventions. The supervised phase of the walking intervention lasted 52 weeks following randomization. The unsupervised (follow-up) phase of the walking intervention lasted 26 additional weeks. For Intervention (one year): 52 weeks × 3 sessions =156 sessions attended; Follow-up (six month): 26 weeks x 3 sessions = 78 sessions attended. N.B. This structured and supervised walking program is based on Ottawa Panel Grade A recommendations \n[33-35] and was implemented to groups W and WB (Implementation groups). Individuals with OA in the self-directed group (C) received a pamphlet on OA and walking (which recommends regular walking in a unsupervised/self-directed way) (Dissemination group) \n[25].Click here for file Additional file 3Reasons of dropouts. This table demonstrates the reasons as to why participants decided to withdraw from the study.Click here for file Additional file 4Dropout rates and corresponding retention rates at 12-and 18-month time periods. This table demonstrates the drop-out rates and retention rates at end of intervention 12-months and follow-up at 18-months.Click here for file\n\nQuestion: Compared to Walking intervention (W) what was the result of Walking and Behavioural intervention (WB) on Long-term adherence to the program?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
973	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The implementation of a community-based aerobic walking program for mild to moderate knee osteoarthritis (OA): a knowledge translation (KT) randomized controlled trial (RCT): Part I: The Uptake of the Ottawa Panel clinical practice guidelines (CPGs)\n\n ABSTRACT.BACKGROUND:\nThe implementation of evidence based clinical practice guidelines on self-management interventions to patients with chronic diseases is a complex process. A multifaceted strategy may offer an effective knowledge translation (KT) intervention to promote knowledge uptake and improve adherence in an effective walking program based on the Ottawa Panel Evidence Based Clinical Practice Guidelines among individuals with moderate osteoarthritis (OA).\n\nABSTRACT.METHODS:\nA single-blind, randomized control trial was conducted. Patients with mild to moderate (OA) of the knee (n=222) were randomized to one of three KT groups: 1) Walking and Behavioural intervention (WB) (18 males, 57 females) which included the supervised community-based aerobic walking program combined with a behavioural intervention and an educational pamphlet on the benefits of walking for OA; 2) Walking intervention (W) (24 males, 57 females) wherein participants only received the supervised community-based aerobic walking program intervention and the educational pamphlet; 3) Self-directed control (C) (32 males, 52 females) wherein participants only received the educational pamphlet. One-way analyses of variance were used to test for differences in quality of life, adherence, confidence, and clinical outcomes among the study groups at each 3 month assessment during the 12-month intervention period and 6-month follow-up period.\n\nABSTRACT.RESULTS:\nShort-term program adherence was greater in WB compared to C (p<0.012) after 3 months. No statistical significance (p> 0.05) was observed for long-term adherence (6 to 12 months), and total adherence between the three groups. The three knowledge translation strategies demonstrated equivalent long-term results for the implementation of a walking program for older individuals with moderate OA. Lower dropout rates as well as higher retention rates were observed for WB at 12 and 18 months.\n\nABSTRACT.CONCLUSION:\nThe additional knowledge translation behavioural component facilitated the implementation of clinical practice guidelines on walking over a short-term period. More studies are needed to improve the long-term walking adherence or longer guidelines uptake on walking among participants with OA. Particular attention should be taken into account related to patient's characteristic and preference. OA can be managed through the implementation of a walking program based on clinical practice guidelines in existing community-based walking clubs as well as at home with the minimal support of an exercise therapist or a trained volunteer.\n\nABSTRACT.TRIAL REGISTRATION:\nCurrent Controlled Trials IRSCTNO9193542\n\nBODY.BACKGROUND:\nRising healthcare costs, limited resources, and the aging population have created new and growing challenges in the management of osteoarthritis (OA). The challenges associated with the management of OA are numerous as the prevalence of the population continues to increase while healthcare resources remain limited \n[1-7]. It is therefore necessary to determine the most effective methods of integrating research evidence in order to optimize health outcomes. The purpose of this randomized controlled trial (RCT) was to compare 1) improvements in quality of life (QoL) and clinical outcomes such as pain, mobility and endurance); 2) adherence rates; and 3) confidence and self-efficacy after the implementation of a 12-month supervised community-based aerobic walking program (SCAWP) based on the Ottawa Panel clinical practice guidelines (CPG) among three knowledge translation (KT) intervention arms. QoL, confidence, and self-efficacy were compared at 12- months (end of treatment) and at 18-months (6-months post-intervention). Adherence was compared during the intervention period at 3, 6, 9 and 12 months. The first part of this manuscript introduces each KT intervention and demonstrates the impact of knowledge (CPG) uptake of each by comparing outcomes influenced by the KT intervention such as adherene and behaviour change (confidence and self-efficacy). Knowledge application of each KT intervention is explained through the use a theoretical framework: Knowledge-To-Action Cycle (KTAC) \n[8,9]. The second part of this manuscript focuses on outcome evaluation, a specific phase in the KTAC framework used to guide this study. Part II demonstrates the effect of each intervention involving a walking program on outcomes which were influenced by the SCAWP including QoL (primary outcome) and other clinical outcomes such as pain, mobility, and endurance. These outcomes are exhibited in part II. Therefore, both parts of this manuscript were split according to the ''Evaluate outcomes\" phase of the KTAC framework. Part I focused on KT outcomes which measured the success of CPG uptake through participants' adherence and behavioural change while part II focused on clinical outcomes which measured the positive effect of SCAWP due to the indirect CPG uptake/implementation/adoption by individuals with OA of the knee.\n\nBODY.BACKGROUND.KNOWLEDGE TRANSLATION:\nA major issue in health research today is finding effective and efficient ways to exchange knowledge between researchers, clinicians and the general public. Potential benefits to health which could be accrued through the application of research findings are not realized due to challenges in research uptake and knowledge translation \n[10]. KT is defined by Estabrooks et al. \n[11] as \"the process by which specific research-based knowledge (science) is implemented in practice.\" The available evidence suggests that with an effective KT strategy, uptake of evidence-based clinical practice guidelines (EBCPGs) can be effective in improving patient health outcomes \n[12].\n\nBODY.BACKGROUND.PHYSICAL ACTIVITY AND OSTEOARTHRITIS:\nThe promotion of physical activity (PA) is a priority for health organizations serving the general population \n[13,14] and is highly recommended for subgroups affected by chronic diseases \n[15-19]. Community-based PA combined with a behavioural modification and self-management interventions can reduce the risk of disability and negative consequences of inactivity related to OA \n[20,21]. The challenge is to develop PA programs that will encourage OA patients to initiate and maintain improvements in exercise behaviour over a long-term period \n[22]. The available evidence suggests that with an effective KT strategy, uptake of evidence-based clinical practice guidelines (CPGs) can be effective in improving patient health outcomes \n[12].\n\nBODY.BACKGROUND.SELECTING AN EFFECTIVE KT STRATEGY:\nMultifaceted interventions combining more than one KT strategy have tended to be more effective than using a single KT strategy alone \n[23,24] and have shown to have the greatest impact on CPG adherence and PA performance \n[25]. Behavioural interventions have been used for other chronic conditions to improve long-term adherence and maintenance of PA regimens with varying success. The efficacy of different behavioural interventions including patient education, health counselling, goal setting, and social/peer support, delivered separately and or in combination, have been examined in the management of arthritis \n[26-31].\n\nBODY.METHODS:\nThe following methodology is in full agreement with the Consolidated Standards of Reporting Trials (CONSORT) 2010 Statement criteria for reporting RCTs \n[32].\n\nBODY.METHODS.DESIGN:\nThis single blind RCT, funded by the Canadian institutes of Health Research, used a parallel group design (1:1:1). This community-based study was approved by the University of Ottawa Research Ethics Board and the City of Ottawa Public Health Research Ethics Board. This study implemented one of the Ottawa Panel CPG recommendations related to a supervised community-based aerobic walking programs (SCAWPs) among individuals with mild to moderate OA of the knee \n[33-35]. In order to facilitate an understanding of the KT process, Graham et al. developed a conceptual framework entitled \"the Knowledge-To-Action Cycle\" (Figure \n1) which provides an approach which combines commonalities from various planned-action theories \n[8,9]. This framework was used to guide the development of the three KT strategies used in this RCT (Additional file \n1). The framework demonstrates the dynamic process of knowledge creation and application \n[9]. Knowledge creation consists of three phases: knowledge inquiry, knowledge synthesis, and knowledge tools/products. The knowledge creation cycle of the framework demonstrates how knowledge is refined through each phase to provide useful information for end users. The action cycle of the framework consists of seven phases which may occur sequentially or simultaneously: 1) Identify the Knowledge-To-Action Cycle gaps; 2) Adapt Knowledge to local context; 3) Assess barriers to Knowledge Use; 4) Select, Tailor, Implement Interventions; 5) Monitor Knowledge Use; 6) Evaluate outcomes; and 7) Sustained Knowledge Use. For part I, the emphasis was placed on the \"Evaluate outcomes (KT outcomes)\" phase as participants' knowledge uptake was measured as adherence to the effective walking program for OA and attitude/behaviour change (self-efficacy and confidence) after participating in the SCAWP. Figure 1Knowledge-To-Action Cycle. This figure illustrates the Knowledge-To-Action Cycle Framework \n[8]. This figure is used with permission: Lost in knowledge translation: Time for a map. Graham ID, et al. Journal of Continuing Education in the Health Professions, 26(1). Copyright © 2006. The Alliance for Continuing Medical Education, The Society for Academic Continuing Medical Education, and The Association for Hospital Medical Education. The hypothesis was that the additional behavioural approach of the multifaceted KT intervention would: 1) increase short and long term adherence to the SCAWP; 2) reduce the drop-out rate; 3) influence behaviour change by improving self-efficacy, confidence, QoL and other clinical outcomes.\n\nBODY.METHODS.SAMPLE AND RECRUITMENT:\nA total of 222 adults with knee OA were recruited. Participants were eligible to participate in the study if he/she 1) had a confirmed diagnosis with mild to moderate unilateral or bilateral OA according to the American College of Rheumatology clinical and radiographic/magnetic resonance imagery criteria; 2) reported pain for at least 3 months; 3) expected his/her medication to change during the study period; 4) demonstrated an ability to ambulate for a minimum of 20 minutes, at their own pace with minimal reports of pain (≤ 3 out of 10 on a visual analogue pain rating scale) \n[36]; 4) were able to be treated as an out-patient; and 5) were available three times a week over a period of 12 months. Potential study subjects were excluded if they had: 1) Participated in regular physical or aerobic sports ≥ 2 times per week for more than 20 minutes per session during the previous 6 months; 2) severe OA of the knee or other weight bearing joints of the lower extremity; 3) no written consent from their physician to participate in the study; 4) pain at rest or at night; 5) received rehabilitation treatment, corticosteroids injection, or any other pain-related treatment besides medication for arthritis within the last 12 months; 6) uncontrolled hypertension (Systolic blood pressure >160 mm Hg confirmed by the screening initial VO2 max test at the Ottawa Heart Institute) 7) other illnesses, such as rheumatoid arthritis (judged by the patient or study physician to make participation in this study inadvisable); 8) significant cognitive deficit resulting in an inability to understand or comply with instructions; 9) surgery planned in the next year; 10) Intention to move away from Ottawa region in the next year; 11) an inability to communicate in English or French; or 12) an unwillingness to sign informed consent. The study coordinator assessed the inclusion/exclusion criteria of all potential participants by telephone. At the first visit, written informed consent was obtained if the patient met all inclusion criteria.\n\nBODY.METHODS.INTERVENTION:\nParticipants were randomly assigned to one of the three KT intervention groups using central randomization \n[37] and computer generated numbers \n[38]: 1) Walking and Behavioural intervention (WB) (18 males, 57 females) which included the SCAWP with a behavioural intervention and an educational pamphlet on the benefits of walking for OA; 2) Walking intervention (W) (24 males, 57 females) wherein participants only received the SCAWP intervention and the educational pamphlet; 3) Self-directed control (C) (32 males, 52 females) wherein participants only received the educational pamphlet. All 3 groups were provided with pedometers and log books to be completed to measure physical performance (walking in minutes) and additional PA aside from the walking sessions (Table \n1). The KT strategies were implemented over a 12-month duration and participants were assessed for additional 6 months (15 and 18-month follow-up assessments). Table 1 Summary of the KT strategies used KT strategies in each group WB or WalkingClub+ (supervised walking program + behavioural approach at the community-based Walking Club) W or WalkingClub (supervised walking program only at the community-based Walking Club) C or Self-directed Home-based or community based different than W and WB (unsupervised/self-directed Walking program only) EBP walking program (Ottawa Panel, 2005/2012) refs: \n[ 33 - 35 ] EBP walking program (Ottawa Panel, 2005/2012) refs: \n[ 33 - 35 ] Walking program (general info from pamphlet on walking and OA) Walking Club + effect (supervised program, team, daily monitored vital measures: BP, HR, #steps,) Walking Club effect (supervised program, team, daily monitored vital measures: BP, HR, #steps,) N/A Pedometer as measurement tool, but becomes a KT strategy Pedometer as measurement tool, but becomes a KT strategy Pedometer as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy Log book including 7-day PAR as measurement tool, but becomes a KT strategy $ compensation each walking session and at evaluation session $ compensation each walking session and at evaluation session $ compensation each logbook fulfilled and at evaluation session Study affiliation/participation (feel committed) Study affiliation/participation (feel committed) Study affiliation/participation (feel committed) Behavioural intervention (Baycrest PACE-ex: patient education + goal settings; PA counselling, telephone support) N/A N/A Following the successful randomization process, wherein no statistical difference was found between the three groups (with the exception of the \"physical role\" category of the SF-36: part II) (Tables \n2, \n3, \n4, \n5), research staff and evaluators were blinded to the treatment allocation. An independent evaluator was blinded to assess outcome measures. Due to the nature of the physical intervention, it was not practical to blind the study participants and PA specialists supervising the aerobic walking program \n[39]. Table 2 Subject demographics and baseline characteristics Characteristic Walking (n=79) Walking and Behavioural (n=69) Self-directed Control (n=74) Total Mean age (SD), yrs 63.9 (10.3) 63.9 (8.2) 62.3(6.8) 63.4 (8.6) Missing Data 0 0 0 0 Men/women, (%) 24 (30.4)/55 (69.9) 18 (26.1)/51 (73.9) 27 (36.5)/47 (63.5) 69 (31.1)/153 (68.9) Missing Data 0 0 0 0 Affected knee, n (%) Right 33 (41.8) 31 (44.9) 25 (33.8) 89 (40.1) Left 31(39.2) 23 (33.3) 28 (37.8) 82 (36.9) Both side 15 (19.0) 15 (28.4) 21 (28.4) 51 (23.0) Missing Data 0 0 0 0 Mean duration of OA (SD), yrs 9.54 (8.09) 11.3 (9.7) 10.0 (9.9) 10.3 (9.26) Missing Data 0 0 0 0 Mean weight (SD), kg 80.7 (18.5) 83.1 (15.4) 83.0(15.8) 82.2 (16.6) Missing Data 0 1 0 0 Mean BMI (SD), kg/m² 29.4 (5.4) 30.3 (5.6) 29.9(5.3) 29.8 (5.4) Missing Data 0 2 4 6 Walking aid, n (%) Yes 10 (12.7) 10 (14.5) 9 (12.2) 29 (13.1) No 69 (87.3) 58 (84.1) 64 (86.5) 191 (86.0) Missing Data 0 1 1 2 Racial background, n (%) White 69 (87.3) 60 (87.0) 68 (91.9) 197 (88.7) Black 1 (1.3) 3 (4.3) 1 (1.4) 5 (2.3) Hispanic 2 (2.5) 2 (2.9) 4 (5.4) 8 (3.6) Asian or Pacific Islander 5 (6.3) 4 (5.8) 1 (1.4) 10 (4.5) American Indian or Alaskan native 1 (1.3) 0 (0) 0 (0) 1 (0.5) Other 1 (1.3) 0 (0) 0 (0) 1 (0.5) Missing Data 0 0 0 0 Marital status, n (%) Married 46 (58.2) 36 (52.2) 44 (59.5) 126 (56.8) Separated 2 (2.5) 1 (1.4) 1 (1.4) 4 (1.8) Divorced 9 (11.4) 17 (24.6) 8 (10.8) 34 (15.3) Widowed 17 (21.5) 11 (15.9) 9 (12.2) 37 (16.7) Never Married 5 (6.3) 4 (5.8) 12 (16.2) 21 (9.5) Missing Data 0 0 0 0 Level of education, n (%) Less than 7 yrs of school 2 (2.5) 1 (1.4) 1 (1.4) 4 (1.8) Grades 7 through 9 5 (6.3) 0 (0) 0 (0) 5 (2.3) Grades 10 through 11 7 (8.9) 4 (5.8) 5 (6.8) 16 (7.2) High school graduate 13 (16.5) 16 (23.2) 8 (10.8) 37 (16.7) 1 to 4 yrs of college 13 (16.5) 9 (13.0) 22 (29.7) 44 (19.8) College graduate 25 (31.6) 21 (30.4) 19 (25.7) 65 (29.3) Professional or Graduate school 14 (17.7) 18 (26.1) 19 (25.7) 51 (23.0) Missing Data 0 0 0 0 Yrs: years, OA: osteoarthritis, kg: kilograms, m: meters, %: validity percent. Table 3 Subject’s Medication at Baseline Medication Walking (W) only (n=79) Walking and Behavioural (WB) (n=69) Self-directed (C) (n=74) Oral hypoglycaemic agents Total 2 (3) 5 (7) 9 (12) Biguanide Class 2 (3) 4 (6) 9 (12) Sulfonylureas Class 0 (0) 0 (0) 2 (3) Thiazolidinedione 0 (0) 2 (3) 2 (3) Antihypertensive Agents Total 22 (28) 15 (22) 15 (22) Calcium channel blockers 6(8) 0(0) 7(9) Antiotensin-converting enzyme 3 (4) 7 (10) 7 (9) Angiotensin II receptor blockers 6 (8) 6 (9) 3 (4) Beta-blocker 4 (5) 3 (4) 4 (5) Alpha-blocker 3 (4) 0 (0) 0 (0) Diuretic 5 (6) 8 (12) 5 (7) Antiarrhythmic 1 (1) 0 (0) 0 (0) Anti-anginal 1 (1) 0 (0) 0 (0) Anti-platelet agent 1 (1) 1 (1) 1 (1) Anticoagulant 0 (0) 2 (3) 0 (0) Phosphodiesterase type 5 inhibitors 0 (0) 1 (1) 0 (0) Statins 8 (10) 12 (17) 10 (14) Hormone Total 11 (14) 10 (14) 11 (15) Thyroid 5 (6) 5 (7) 8 (11) Insulin 0 (0) 3 (4) 1 (1) Corticosteroid 4 (5) 2 (3) 3 (4) Progesterone 1 (1) 0 (0) 1 (1) Androgen 1 (1) 0 (0) 0 (0) Oestrogen 1 (1) 0 (0) 0 (0) Antithyroid 0 (0) 1 (1) 0(0) SERMs (Selective estrogen receptor modifiers) 1 (1) 0 (0) 0 (0) Beta 2-adrenergic receptor agonist (bronchodilator) 2(3) 1 (1) 3 (4) NSAIDs (Non-steroid anti-inflammatory drugs) 26 (33) 21 (30) 18 (24) COX-2 selective inhibitor 3 (4) 4 (6) 1 (1) NSAIDS Betahistine 0 (0) 1 (1) 0 (0) DMARDs (Disease modifying antirheumatic drugs) 0 (0) 1 (1) 0 (0) Histamine antagonist 0 (0) 2 (3) 0 (0) Bisphosphonate 6 (8) 4 (6) 4 (5) Antibiotics 2 (3) 1 (1) 4 (5) Analgesics 1 (1) 1 (1) 3 (4) Opiates 0 (0) 0 (0) 2 (3) Hypnotic 4 (5) 3 (4) 4 (5) Antidepressant 7 (9) 5 (7) 7 (9) Psychostimulant 0 (0) 1 (1) 0 (0) Antipsychotic 0 (0) 1 (1) 0 (0) Anti-manic 0 (0) 1 (1) 0 (0) Anti-convulsant 1 (1) 1 (1) 0 (0) Protein pump inhibitor (PPI) 9 (11) 5 (6) 6 (8) Enzyme inhibitor 0 (0) 1 (1) 2 (3) Muscle relaxant 0 (0) 1 (1) 1 (1) Antispasmodic 0 (0) 1 (1) 0 (0) Anti-cholinergic 1 (1) 1 (1) 0 (0) Antineoplastic 2 (3) 1 (1) 0 (0) Antimetabolite 1 (1) 1 (1) 1 (1) Antifolate 0 (0) 1 (1) 1 (1) Latanoprost 0 (0) 1 (1) 0 (0) Viscosupplementation 0 (0) 1 (1) 0 (0) Xanthine 1 (1) 0 (0) 0 (0) Antifungals 0 (0) 0 (0) 1 (1) Antimalarial 0 (0) 1 (1) 1 (1) Nitrate 0 (0) 0 (0) 2 (3) Laxative 0 (0) 0 (0) 2 (3) Supplements 22 (28) 22 (28) 18 (24) Homeopathic Medication 1 (1) 1 (1) 1 (1) None 11 (14) 10 (13) 9 (12) Not Specific 21 (27) 21 (27) 20 (27) Missing Data Total 4 (5) 8 (10) 17 (23) No Evaluation* 2 (3) 4 (5) 7 (9) No File** 2 (3) 4 (6) 10 (14) This table presents a list of medications which participants declared to be taking at baseline. Data is presented as n (%). Table 4 Summary of adherence based on attendance marked in trainers’ manuals and individual walkers’ logbooks Walking N Mean±SD Walking & Behavioural N Mean±SD Self-directed (C) N Mean±SD Walking vs. Self-directed t -test P value Walking & Behavioural Vs. Self-directed t -test P value Walking & Behavioural Vs. Walking t -test P value 0-3 months 79 69 73 (0.043) (0.012) (0.514) 0.770±0.299 0.802±0.290 0.652±0.403 3-6 months 79 69 73 (0.242) (0.159) (0.774) 0.617±0.410 0.636±0.390 0.535±0.459 6-9 months 79 69 73 (0.421) (0.937) (0.363) 0.471±0.418 0.534±0.425 0.528±0.463 9-12 months 79 69 73 (0.549) (0.551) (0.989) 0.446±0.441 0.445±0.433 0.490±0.462 Total Adherence 79 69 73 (0.690) (0.413) (0.619) 0.576±0.346 0.604±0.342 0.551±0.420 Table 5 Summary of self-efficacy, measured with Stanford questionnaire on chronic disease for three study arms (continued) Baseline 12 months 18 months W WB C W WB C W WB C N N N N N N N N N Variables Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD Mean±SD W.Vs. C(P) W.Vs. C(P) W.Vs. W(P) W.Vs. C(P) W.Vs. C(P) W.Vs. W(P) Coping 79 69 73 44 44 40 44 41 36 With 1.069±794 1.126±0.775 1.013±0.946 0.864±0.771 1.239±0.730 1.192±0.835 1.064±0.952 1.388±0.856 1.342±1.127 Symptoms (0.091) (0.858) (0.057) (0.190) (0.793) (0.286) Confidence 79 69 73 44 44 39 43 41 36 About 7.406±1.719 7.827±1.488 7.858±1.512 7.826±1.551 7.682±1.785 8.064±1.575 7.690±1.920 7.546±1.848 8.015±1.476 Doing Things (0.433) (0.297) (0.060) (0.235) (0.422) (0.041) (Higher is better) W: Walking only group; WB: Walking and Behavioural Group; C: Self-directed group (unsupervised/self-directed); N: number of subjects in each comparative group; SD: standard deviation; vs: versus; data is presented as mean (standard deviation); p: p-value (statistical significance); Statistically significant. \n\nBODY.METHODS.INTERVENTION.SUPERVISED WALKING PROGRAMS (WB & W GROUPS):\nThe SCAWPs took place at two walking club sites in Ottawa, Ontario, Canada and one in Gatineau, Québec, Canada. Participants took part in three weekly walking sessions over a 12-month period. Every walking session began with a 10-minute warm-up, consisting of light aerobic exercises, before engaging in the 45-minute aerobic walking phase. The walking sessions ended with a 10-minute cool-down consisting of light aerobic exercises and stretching. The target intensity of the walking phase was approximately 50% to 70% of the subjects' pre-determined maximum heart rate as recommended in The Ottawa Panel guidelines \n[33-35]. The SCAWP was divided into two stages: 1) A \"progressive aerobic phase\" wherein the duration and heart rate intensity progressively increased over time and 2) a \"maintenance aerobic phase\" wherein the duration and heart rate intensity remained constant for the remainder of the walking program (Additional file \n2). The selected dosage, frequency, intensity, and progression of the walking interventions were based on existing protocols proven effective for OA, described in several RCTs involving individuals with OA \n[33-35] (Additional file \n2). To avoid contamination between the two walking interventions, participants in the W group were instructed to walk in the mornings, while the WB group walked in the afternoons at the main walking site. In order to meet the prescribed target heart rate, heart rate monitors were provided to each participant prior to his/her walking session. As a safety precaution, participants who experienced prolonged pain lasting more than two hours within 24 hours after a walking session were asked to temporarily reduce their level of exercise until he/she felt comfortable enough to resume the appropriate duration, intensity and frequency of the walking program. Following randomization, the PA specialist met each subject in the walking groups to explain the SCAWP and its progression (Additional file \n2) and was present for a minimum of three weekly scheduled sessions over one year to supervise the subjects. The PA specialist was responsible for monitoring and recording attendance, blood pressure, heart rate (during and after the walking session), time duration, and number of steps (pedometer) at each walking session. Monetary compensation was given to each participant for attending each walking session.\n\nBODY.METHODS.INTERVENTION.BEHAVIOURAL INTERVENTION (WB GROUP):\nThe behavioural intervention was part of the multifaceted KT intervention (Table \n1) and was implemented using the adapted Program for Arthritis Control through Education and Exercise (PACEex) program \n[40]. The behavioural intervention was integrated into the PACEex program and consisted of the following components: (1) short- and long-term goal setting during PACEex classes; (2) an educational component, delivered by a trained instructor, involving consisting of instructional sessions about the benefits of PA, specifically walking; (3) monthly face-to-face counselling wherein participants received moral support/encouragement to adherence with PA. Potential barriers to program adherence were identified and self-management strategies were reviewed to overcome those barriers; (4) goal setting and telephone counselling were provided as an additional source of social support until the end of the supervised phase. As with the face-to-face counselling, barriers were identified and strategies were shared in an effort to promote the long-term maintenance of PA. In summary, the behavioural intervention consisted of twenty 2-hour group sessions discussing short-term goal setting and education of arthritis-related topics over a duration of 20 consecutive weeks. Individual long-term goal setting was discussed at the beginning of the PACEex program and was followed by monthly face-to-face meetings throughout the first 6 months of the program. The last six months of the 12-month supervised phase consisted of participants receiving counselling via telephone discussing long-term goals and barriers/facilitators to adhere to the walking program.\n\nBODY.METHODS.INTERVENTION.THE SELF-DIRECTED CONTROL (C GROUP):\nParticipants were invited to consult an educational pamphlet on walking and OA. One introductory session was provided to the participant wherein they were provided an educational pamphlet describing the benefits of walking for OA, a pedometer to monitor PA, and a logbook to record activity level and adherence while partaking in the self-directed walking program. Participants in this group received monetary compensation for the completion his/her log books. The self-directed (C) group did not have any contact with participants in the two other groups, avoiding potential contamination.\n\nBODY.METHODS.DATA COLLECTION:\nParticipants were assessed by an independent evaluator at baseline and at each 3 month interval (months 3, 6, 9, 12) during the intervention period. Participants were then assessed at 3 and 6 months post-intervention during the follow-up period (15 and 18-months). Participants were asked to complete a collection of validated questionnaires as well as perform physical tests at each assessment.\n\nBODY.RESULTS.KNOWLEDGE (CPG) UPTAKE OUTCOME MEASURES (KT OUTCOMES).ADHERENCE AND BEHAVIOUR CHANGE:\nSimilar to other studies \n[29,41,42], participant adherence was assessed as the number of attended walking sessions divided by the number of prescribed sessions (3 sessions per week). Among the W and WB groups, the number of attended walking sessions throughout the 12-month duration was recorded by the exercise therapist on site as well as through the use of participants' completed logbooks which provided information on the amount of performed PA during the 12-month intervention period. The C group's adherence was only assessed by the completed log books. Behaviour change was based on the concept of self-efficacy and was measured using the Stanford scale. In regards to the research question, behaviour change results were only reported at 12 and 18-months.\n\nBODY.RESULTS.KNOWLEDGE (CPG) UPTAKE OUTCOME MEASURES (KT OUTCOMES).ANALYSIS:\nThe analysis was conducted on an intention-to-treat basis. Descriptive statistics including mean, standard deviation and frequencies were used to summarize the study groups at baseline. A repeated measure mixed model was used to assess the change in adherence from baseline to end of treatment (12 months) among three study groups. Behavioural change outcomes were assessed from baseline to of end treatment (12 months) and at 6-month follow-up post-intervention (18 months). The model included variables such as intervention group, study month, and an interaction term between intervention group and study month. Missing data was assumed to be missing at random (MAR) in order to include incomplete data. Pairwise differences comparing each group to one another (W vs. C, W vs. WB, WB vs. C) were assessed. The repeated measure mixed model was used to compare the change of adherence from baseline to the 18- month follow-up. Statistical analyses were performed using SAS (version 9.2, SAS Institute Inc., Cary, North Carolina), and statistical significance was defined as p<0.05.\n\nBODY.RESULTS:\nBetween January 2007 and December 2008, 629 study participants were assessed for eligibility. Figure \n2 exhibits the flow of participants from recruitment to follow-up. The most common reasons for exclusion were: 1) time commitment (26.5%); 2) first diagnosed with OA by physician or X-Ray but later contradicted by MRI test result (18.1%); 3) loss of interest (14.2%); 4) severe OA of the weight bearing joint of LE (11.8%); 5) no medical clearance after VO2 max test (5.1%); 6) unable to contact (4.9%); 7) too active (2,9%); 8) knee replacement (2.7%); 9) age related (2.5%); 10) travelling too much (1.9%); 11) living too far (1.2%). Follow-up for the last recruited participant was completed in May 2010. Figure 2Study flow diagram. This figure provides a flow diagram of data collection from baseline to 18-months follow-up. The groups were similar in age, sex, ethnicity, OA duration and medication use (Table \n2 &3). Two hundred and twenty two subjects were included in the study. Women made up 153 of the 222 subjects. The mean age (±S.D.) was 63.4 (±8.6) years, the mean disease duration (±S.D.) was 10.3 (±9.3) years, the highest level of completed education was \"College graduate\" with 65 participants (±29.3) and \"Professional or graduate school\" with 51 participants (±23.0). There was no statistical difference between the three comparative groups at baseline for all the demographic variables.\n\nBODY.RESULTS.BLINDING:\nThe effectiveness of blinding the evaluator to treatment allocation was assessed through a questionnaire where she was asked to identify which group each participant belonged to. The blinding rate of the evaluator was high (98%).\n\nBODY.RESULTS.ADHERENCE AND ATTRITION:\nFrom baseline to 12 months, the adherence rates were expressed as percentages of adherence among walkers who did not drop out and were reported as means (+/−standard deviation) for each time period between groups (Table \n4). Statistically significant results for short-term adherence rates favoured participants in the WB group (80.2%) compared to the self-directed (C) group (65.2%) (p<0.012) after 3 months. For long term adherence (6 to 12 months), the WB group demonstrated superior adherence rates throughout each period compared to the other two groups, but results did not reach statistical significance. No statistical significance (p> 0.05) was observed for the total adherence rates between WB vs. W, W vs. C, and WB vs. C. During the 12-month intervention period, the dropout rates were 43.1% for the W group, 40.6% for the WB group and 49.3% for the self-directed (C) group. From baseline to 18 months, the dropout rates were 44.3% for the W group; 40.6% for the WB group and 52.1% for the self-directed (C) group (Figure \n2 and Additional files \n3 &4). The dropout rates were lower for the WB group at 12-months (36.2%) and 18-months (39.1%) compared to the W group (40.5% and 44.3%) and the self-directed (C) group (40.5% and 51.3%). The W and self-directed (C) groups had the highest dropout rates (40.5%) at 12 months while the self-directed (C) group had the highest at 18 months (52.1%).\n\nBODY.RESULTS.BEHAVIOUR CHANGE:\nAfter the 12 month intervention phase, no differences were found between the 3 comparative groups for any of the items on the Stanford scale (Table \n5). Moreover, variables related to coping with symptoms and confidence were higher among the WB group compared to the other two groups. At 18-months, statistically significant differences in scores between the WB and W groups revealed that the W group demonstrated an improved mean for the \"confidence about doing things\" variable (p=0.041). The self-directed group (C) demonstrated the highest mean \"confidence about doing things\" score 8.015± 1.476 (p=0.040) as it increased by 0.157 (p=0.048) when compared to baseline. The self-directed group (C) demonstrated the highest mean score 8.015± 1.476 (p=0.040).\n\nBODY.DISCUSSION.THE IMPACT OF THE MULTIFACETED KT INTERVENTIONS ON KNOWLEDGE (CPG) UPTAKE.ADHERENCE AND ATTRITION:\nThe additional behavioural approach of the multifaceted KT intervention (WB group) improved adherence to the SCAWP when compared to the other two groups over a short-term period. In addition, the WB group demonstrated reduced dropout rates compared to the W and self-directed (C) groups. Over a long-term period, the three groups were equivalent in improving behaviour change while adopting the Ottawa Panel recommendations on walking \n[33-35]. Adherence rates were higher among the WB group for each 3-month period compared to the other two groups. Improved adherence rates over the short-term period can be explained by the fact the PACEex program used in the behavioural intervention lasted for 20 consecutive weeks at the beginning of the study. The PACEex program \n[40] used in this study, allowed our participants to set general goals, which may have motivated participants to adhere to the walking program. Similar to a previous study \n[43], another reason may be that participants in the W and WB group lost motivation after the supervised phase, no longer having regular professional support from the PA specialist. The drop-out rate results are comparable to other long-term studies which have used an aerobic PA intervention with a behavioural intervention component \n[38,44-54]. Higher adherence rates were demonstrated at 2 to 4 months (85% - 90%) and at 10 to 18 months (50% - 90%). An initial 6-month center-based exercise program enhanced retention over short and the long-term periods while promoting short-term adherence and energy expenditure \n[55]. The moderate exercise intervention retained more subjects, but had little influence on adherence over a long-term period \n[56]. Home-based PA programs, such as self-directed walking, can achieve improved adherence rates compared to facility-based programs over a long period \n[55].\n\nBODY.DISCUSSION.BEHAVIOUR CHANGE:\nThere were no statistically significant results among the three groups at 12 months. These results concur with a similar study \n[53] and are normal in the context of a KT study which implemented an already proven effective walking program \n[33-35]. However, at 18-months, there were statistically significant results which favoured the self-directed group (C). One reason explaining why participants in the self-directed group (C) had higher confidence and self-efficacy scores may be due to the fact that since these individuals were not supervised, they may have been more independent, self-controlled, self-confident, and self-motivated. Participants in this group may have also had the opportunity, over the 12-month period, to develop confidence and self-efficacy skills compared to the two supervised groups during the unsupervised follow-up phase. The variable \"confidence about doing things\" decreased after 12 months for the WB group. Given the high amount of PA demonstrated by the WB group at 12 months, we were surprised with this result. On the other hand, at 18 months, statistically significant results favoured the W group compared to WB group for the variables \"confidence about doing things\". Again, these results about confidence were unexpected given that the WB group performed higher amounts of PA. Exercise therapists, pedometers, logbooks and social support from walking club members (Table \n1) assisted participants who had difficulties with activity adherence and maintenance \n[57]. Regular professional contact was recognised as the significant motivational factor for adherence to the supported walking program during the RCT \n[43]. Social support has been reported to be more successful in engaging participants in PA programs compared to programs which only provided written educational material \n[58,59]. The combination of using pedometers and goal-setting has been recognised as an effective KT tool for increasing PA \n[31,60-62]. However, despite the short-term effectiveness of pedometers and goal-setting, the success of these tools diminished over time. Other KT strategies are recommended to facilitate sustainability \n[62].\n\nBODY.DISCUSSION.LIMITATIONS:\nBarriers related to the implementation of SCAWP were identified and addressed to improve adherence for older individuals \n[57]. Acceptability (preferences, tolerance and accessibility) should be considered to promote PA adherence and to overcome associated barriers \n[63]. The most common barriers identified by participants with OA are perceptions about illness and recovery, transportation difficulties, family commitments and inconvenient timing \n[64]. Time commitment is also recognised as a significant barrier \n[55]. Additional barriers such as weather conditions including snow storms, freezing rain and humidity, a 3-month bus strike, and health problems of participants' partners may have contributed to study adherence. Adherence is influenced by participant's preference of intervention \n[65-70]. Unfortunately, with this study being a RCT, taking participants' preference into consideration was not possible due to the randomization procedure. This being said, randomisation may have contributed to higher dropout rates. The purpose of this KT study was to implement a scientifically proven effective walking program for OA \n[33-35]. Short term research suggests that self-management interventions \n[16,18], telephone counselling \n[22,46,71-73], peer support \n[13,74-76] and PA education \n[18,22,27,41,77] are effective behavioural strategies for improving self-efficacy. The long-term multifaceted behavioural strategy used in this study did not concur with the previous studies, as participants in the self-directed group (C group) were provided information and education on the benefits of PA. Methods of measurement for adherence for the W and WB groups were different than the self-directed (C) group. Observed attendance was recorded on site for each walking session for the W and WB groups by exercise therapists while adherence could only be measured in the self-directed group (C) using completed logbooks. The self-reporting of PA, which is commonly overstated, may have been subject to potential information bias. Selection bias may have occurred as our study population included individuals with mild to moderate OA, with a confirmed X-ray report. In addition, some participants were retired while some were still employed. Since participants were provided monetary compensation for their participation in the study, one may argue the generalizability of the results.\n\nBODY.DISCUSSION.IMPLICATIONS:\nThis KT RCT aimed to identify the best multifaceted strategy to implement a proven effective walking program for OA of the knee among older individuals. The epidemic public health problem of OA can be managed through the implementation of a proven effective walking program in existing community-based walking clubs as well as at home with minimal support. More studies are needed to improve the long-term walking adherence or knowledge uptake on SCAWP among participants with OA. Particular attention should focus on patients' characteristics and preferences.\n\nBODY.CONCLUSIONS:\nThis study partially supported our initial hypothesis regarding the impact of a multifaceted KT intervention as the combined walking and behavioural approach had greater benefits over the comparative groups resulting in improved long-term adherence to PA only over a short period (3-months). The WB group demonstrated to be the best KT strategy for reducing dropouts compared to the W group and self-directed (C) group. All three KT strategies were equivalent over the long-term period (up to 18 months) for improving behavioural change. However, the self-directed walking program (C group) was the least expensive to implement over a long-period (18 months). This RCT was a long-term adherence study as well as a KT study which addressed questions of clinical and scientific importance aimed at improving the understanding of effective KT strategies to promote the adoption and maintenance of a community-based walking program for OA.\n\nBODY.ABBREVIATIONS:\nOA: Osteoarthritis; QoL: Quality of Life; SCAWP: Supervised Community-based Aerobic Walking Program; CPG: Clinical Practice Guideline; KT: Knowledge Translation; KTAC: Knowledge-To-Action Cycle; EBCPG: Evidence-Based Clinical Practice Guidelines; CONSORT: Consolidated Standards of Reporting Trials; WB (group): Walking and Behavioural intervention; W (group): Walking intervention; C (group): Self-directed control intervention; RCT: Randomized Controlled Trial; PA: Physical Activity; PACE-ex: Program for Arthritis Control through Education and Exercise; AIMS2: Arthritis Impact Measurement Scale 2; SF-36: Short-Form 36 Health Survey; WOMAC: Western Ontario and McMaster Universities Osteoarthritis Index; MET: Multiples of basal metabolic rate; MAR: Missing At Random; CIHR: Canadian Institutes of Health Research.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS’ CONTRIBUTIONS:\nLB is a Full Professor of Rehabilitation, an epidemiologist and the principal investigator of this study and primary author of this manuscript. GAW the co-principal investigator of this study, is senior biostatistician and director, Cardiovascular Research Methods Centre at the University of Ottawa Heart Institute, and is a leading expert in the design and analysis of clinical trials. He provided assistance with the methodology and statistical analysis of the study. GPK is a Full Professor of Physiology at the University of Ottawa, and director of the university's Human Performance and Environmental Medicine Research Laboratory and Professional Fitness and Lifestyle Consultant Certification Training program. He assisted with the methodology of the study. RR is a senior researcher at the University of Ottawa Heart Institute and provided experience in applying innovative behavioural approaches aimed at increasing PA in healthy and chronic diseased populations. AM is a health economist and assisted with the economic evaluation concept in the original proposal. PT is a rheumatologist, an epidemiologist and chief of the Cochrane Musculoskeletal Group. He has experience in conducting RCTs and meta-analyses. He provided assistance with OA outcome measures in the study. MH & CM developed the PACEex program and was in charge of training the PA specialist. GDA was the research coordinator of this study and assisted with the writing of this manuscript. LC is a biostatistician and performed the analyses of this study. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2458/12/871/prepub\n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional file 1The knowledge –to-action framework and KT interventions. This table demonstrates how each step of the KTAC framework is applied to the RCT.Click here for file Additional file 2Post-Randomization Walking Interventions. The supervised phase of the walking intervention lasted 52 weeks following randomization. The unsupervised (follow-up) phase of the walking intervention lasted 26 additional weeks. For Intervention (one year): 52 weeks × 3 sessions =156 sessions attended; Follow-up (six month): 26 weeks x 3 sessions = 78 sessions attended. N.B. This structured and supervised walking program is based on Ottawa Panel Grade A recommendations \n[33-35] and was implemented to groups W and WB (Implementation groups). Individuals with OA in the self-directed group (C) received a pamphlet on OA and walking (which recommends regular walking in a unsupervised/self-directed way) (Dissemination group) \n[25].Click here for file Additional file 3Reasons of dropouts. This table demonstrates the reasons as to why participants decided to withdraw from the study.Click here for file Additional file 4Dropout rates and corresponding retention rates at 12-and 18-month time periods. This table demonstrates the drop-out rates and retention rates at end of intervention 12-months and follow-up at 18-months.Click here for file\n\nQuestion: Compared to Walking intervention (W) what was the result of Walking and Behavioural intervention (WB) on Total adherence to the program?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
975	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Treatment costs associated with interventional cancer clinical trials conducted at a single UK institution over 2 years (2009–2010)\n\n ABSTRACT.BACKGROUND:\nThe conduct of clinical trials should be an integral part of routine patient care. Treating patients in trials incurs additional costs over and above standard of care (SOC), but the extent of the cost burden is not known. We undertook a retrospective cost attribution analysis to quantitate the treatment costs associated with cancer clinical trial protocols conducted over a 2 year period.\n\nABSTRACT.METHODS:\nAll patients entered into oncology (non-haematology) clinical trials involving investigational medicinal products in 2009 and 2010 in a single UK institution were identified. The trial protocols on which they were treated were analysed to identify the treatment costs for the experimental arm(s) of the trial and the equivalent SOC had the patient not been entered in the trial. The treatment cost difference was calculated by subtracting the experimental treatment cost from SOC cost. For randomised trials, an average treatment cost was estimated by taking into account the number of arms and randomisation ratio. An estimate of the annual treatment costs was calculated.\n\nABSTRACT.RESULTS:\nA total of 357 adult oncology patients were treated on 53 different trial protocols: 40 phase III, 2 randomised II/III and 11 phase II design. A total of 27 trials were academic, non-commercial sponsored trials and 26 were commercial sponsored trials. When compared with SOC, the average treatment cost per patient was an excess of £431 for a non-commercial trial (range £6393 excess to £6005 saving) and a saving of £9294 for a commercial trial (range £0 to £71 480). There was an overall treatment cost saving of £388 719 in 2009 and £496 556 in 2010, largely attributable to pharmaceutical company provision of free drug supplies.\n\nABSTRACT.CONCLUSION:\nOn an average, non-commercial trial protocols were associated with a small per patient excess treatment cost, whereas commercial trials were associated with a substantially higher cost saving. Taking into account the total number of patients recruited annually, treatment of patients on clinical trial protocols was associated with considerable cost savings across both the non-commercial and commercial portfolio.\n\nBODY:\nThe drug development process is well established and randomised clinical trials remain the gold standard for testing new treatments against standard of care in order to advance clinical practice (Vogelzang et al, 2012). Even so, the proportion of patients entering clinical trials worldwide is remarkably low. Since 2001, when under 4% of cancer patients took part in a clinical trial, recruitment increased six-fold over the following 10 years in the UK due to significant investment in a unique national research infrastructure (Department of Health, 2006; NCRN, 2011), whereas recruitment in the USA has remained static (Califf et al, 2012). It is undisputed that conducting research incurs additional costs over and above standard of care (Emanuel et al, 2003), yet there is an international commitment to research being a core health service function (Zerhouni, 2003; Califf et al, 2012; The NHS Constitution, 2013). Attribution of research costs is complex and recovery of those costs, particularly for non-commercial clinical trials is very challenging (Snowdon et al, 2006; Seow et al, 2012). Costs incurred by conducting a clinical trial can broadly be attributed to one of the three elements (Attributing the costs of health and social care Research & Development (AcoRD), 2012): (1) research costs, that is, the costs of the trial itself, which end when the research ends and relate to activities being undertaken to answer the research question; (2) treatment costs, that is, the patient care costs, which would continue to be incurred if the patient care intervention continued to be provided after the trial had stopped; and (3) service support costs, that is, the additional patient care costs associated with the research, which would end once the trial had stopped, even if the patient care involved continued to be provided. For commercially sponsored trials, all three elements would normally be met by the sponsor. In the UK, pharmaceutical companies have, for many years, been able to access service support from the national health service by formal adoption into a national clinical trials portfolio. For non-commercial studies, research costs are generally met by grant funders. Service support costs are met from local R&D budgets (via comprehensive local research networks), whereas treatment costs are met through the normal commissioning process. The latter has been the cause of significant disharmony between commissioners and providers of health care. In the USA, private insurance companies are not obliged to cover non-routine patient care costs (Anonymous, 2007). Cancer drugs are generally expensive and it is widely perceived that cancer clinical trials generate an excess treatment cost, despite a lack of evidence to support this view. A single retrospective review of 932 cancer patients recruited to 35 trials in the USA between 1998–1999 suggested that the incremental costs of direct care in clinical trials was 6.5% higher than what they would be outside of a trial (Goldman et al, 2003). The investigators concluded that the additional treatment costs of an open reimbursement policy for government-sponsored cancer clinical trials seem minimal. Even so, risk of excess treatment costs remains a barrier to academic clinical trials being performed in many countries today. We undertook a review of cancer clinical trials conducted in a single, research-active institution in the UK over a 2-year period (2009–2010), to identify the extent of treatment costs involved.\n\nBODY.MATERIALS AND METHODS:\nCambridge University Hospitals NHS Foundation Trust (Addenbrooke's Hospital, Cambridge) is a major university teaching hospital and cancer centre in the UK. It also hosts the West Anglia Cancer Research Network (WACRN), one of the highest recruiting regional research networks in the UK, where 45.1% of patients newly diagnosed with cancer entered a research study in 2011/12. Although WACRN supports research across seven hospitals in the region, 64% of all patients were recruited at Addenbrooke's hospital. For this retrospective cost attribution analysis, all patients recruited to interventional, research ethics committee approved, oncology drug trials between 1 January 2009 and 31 December 2010 at Addenbrooke's Hospital were identified from the Cambridge Cancer Trials Centre patient database. Haematology trials were excluded. The clinical trial protocols for each identified patient were reviewed to determine the treatment costs associated with each arm of the trial. The following activities were attributed to being treatment costs (as described in the AcoRD guidance): (1) supplying an investigation medicinal product and pharmacy costs associated with administering oral agents under investigation; (2) supplying and administering any active comparators, but not placebo; (3) nursing time to administer the drug, time taken to deliver the treatment either as an outpatient ('day unit chair time') or as an inpatient ('bed days'); (4) investigations, including imaging and laboratory tests, which would continue to be incurred if the patient care service in question continued to be provided after the trial stopped; (5) additional clinic visits. Costs were calculated for the active treatment phase of the trial only and did not include follow-up once treatment had finished. For all protocols, a standard of care (SOC) was identified as the standard treatment that would have been offered locally to the patient had the trial not been available. For randomised trials, if the control arm differed to the local standard treatment, the local standard treatment was used to cost SOC. The treatment costs of the SOC were determined as for the experimental arm. Costs were determined for the duration of treatment defined in each trial protocol and did not include costs of follow-up once treatment stopped. For adjuvant, neo-adjuvant and some palliative protocols which specified the treatment programme duration, costs were determined for the entire prespecified treatment programme. For palliative protocols where treatment duration was until disease progression, the actual number of cycles and/or months of treatment delivered to the patients recruited to each protocol was obtained from the patient records and an average treatment duration was determined for each protocol. The same treatment duration was used for estimating SOC costs, unless the SOC treatment maximum duration was specified, in which case the shorter duration was used. Cancer drug costs were obtained from the British National Formulary (2010) and excluded additional taxes or local negotiated discounts. Supportive drugs such as antiemetics, antidiarrhoeals, steroids, intravenous hydration fluids were excluded. For dose calculations, an average body surface area of 1.75 m2 was used. Staff and facility direct costs without overheads were obtained from local reference costs. Imaging and laboratory tests were costed locally or using the NIHR costing template. Where costs differed, local costs were used. The data was cross-checked with the lead clinical trials nurse responsible for each protocol. For each protocol, the treatment cost (TC) difference for the experimental arm(s) was the difference between the experimental arm treatment cost and the SOC cost. For randomised trials, an average treatment cost was attributed to the protocol, by taking into account the number of arms of the trial and randomisation ratio (see Table 1 as an example of how the TC difference was calculated). Finally, using the total number of patients recruited to each trial protocol, the annual overall TC excess or saving in 2009 and 2010 was estimated.\n\nBODY.RESULTS:\nDuring the 2-year review period, 357 cancer patients were recruited to 53 different interventional clinical trials involving IMPs (Tables 2 and 3): 159 patients in 2009 and 198 patients in 2010. A total of 27 trials were academic, non-commercial sponsored trials with variable levels of industry support. A total of 26 trials were commercial sponsored trials, of which 26 of the non-commercial trials and 9 of the commercial trials were adopted in the NIHR portfolio. Thirty-nine of the 53 trials were randomised phase III design. The remainder were 1 non-randomised phase III, 2 randomised phase II/III, 9 randomised phase II and 2 non-randomised phase II trials. Patients received IMPs that were either unlicensed (22), licensed for the indicated disease (10) or licensed drugs being used in an unlicensed condition (21). Compared with 2009, in 2010, 24 new trials had opened to recruitment and 12 had closed. The average TC per protocol across the portfolio of 53 trials ranged from an excess of £6393 to a saving of £71 480 (Figure 1). For 27 non-commercial trials (Table 2), the average TC per protocol ranged from an excess of £6393 to a saving of £6005 (mean excess TC was £431, median £126 per protocol). The main source of excess TC was due to extra hospital day unit delivery time associated with 9 protocols evaluating IMPs given in addition to, or in place of, SOC (7 protocols) or where the SOC was observation (2 protocols). For example, in the AVAST-M clinical trial comparing 12 months of 3 weekly adjuvant bevacizumab as treatment for patients with resected melanoma versus standard observation, the additional cost of treatment delivery accounted for £4250 (83%) of the £5144 excess TC. In this case, the investigation medicinal product cost did not contribute to the excess TC, as all bevacizumab was supplied free of charge by the manufacturer. A total of 7 non-commercial trials were associated with a TC saving. Two of these trials, SCOT (comparing 3 months versus 6 months standard adjuvant chemotherapy in colorectal cancer) and PERSEPHONE (comparing 6 months versus 12 months standard adjuvant chemotherapy in breast cancer), were evaluating whether shorter durations of adjuvant treatment were as effective as SOC, in which the TCs were, in effect, halved. In 2 trials, the source of saving was free drug supplies in the experimental arms from manufacturers (SoFEA and BR13). As each trial randomised one or more treatment against a standard treatment, taking into account the number of arms and randomisation ratio, the average cost of a patient recruited to the protocol was less than SOC. In one trial (REAL-3), an industry grant provided a per payment fee of £1000 and in another trial (Telovac), one of the experimental arms was associated with fewer cycles of SOC chemotherapy given in association with the investigation medicinal product. In one trial (QUASAR2) comparing adjuvant capecitabine with capecitabine plus bevacizumab, the manufacturer supplied both the investigation medicinal product (bevacizumab) and the SOC (capecitabine) free of charge for patients recruited to either arm of the trial. With the exception of REAL-3, treatment of patients on the other six non-commercial trial protocols associated with an overall TC saving offered financial benefits that would have been passed on to commissioners, primarily by the provision of free drug that would have had to be paid for if the patient was not on trial. Considering the actual numbers of patients recruited to all of the non-commercial trials annually, the net TC saving was estimated at £67 962 in 2009 and £29 002 in 2010. For the 26 commercial trials (Table 3), the average TC per protocol ranged from £0 to a saving of £71 480 (mean saving was £9294, median £4370 per protocol). Commercial trials were not associated with excess TCs, as income from the trial conduct was gained to cover all costs associated with treatment. The main source of cost saving was through provision of free drug supplies from the sponsor. In two renal cancer trials (Bevlin and Rad001), the sponsors provided the experimental drug free and in a third renal trial (Torisel404) both experimental and SOC drug were provided. With the exception of four randomised trials where SOC was observation or best supportive care, treating patients on the remaining 22 protocols would have passed on significant drug cost savings to commissioners, by avoiding the SOC costs the commissioners would have incurred if the patients were not on trial. Using the actual numbers of patients recruited to all of the commercial trials, there was an estimated net treatment cost saving of £320 758 in 2009 and £467 554 in 2010. Figure 2 summarises the distribution of average TCs for all 26 non-commercial and 27 commercial trial protocols. In general, it can be seen that both commercial and non-commercial trials saved drug costs, whereas the extent of drug and dispensing cost savings was markedly higher for commercial compared with non-commercial trials. The main source of excess TC was the cost of delivering treatment, most often generated by trials evaluating IMPs given in addition to SOC. The contribution of extra clinic visits and investigations, in particular CT scans used for response assessment, was significantly higher for commercial compared with non-commercial trials. By taking into account the number of patients entered on each protocol, the overall annual TCs incurred were estimated. On an average, treating a patient on a clinical trial protocol was associated with a TC saving of £4340. The overall TCs incurred annually was a saving of £388 719 in 2009 and £496 556 in 2010 (Figure 3), around 90% of the savings coming from commercial sponsored trials.\n\nBODY.DISCUSSION:\nResearch is considered an integral part of healthcare by many nations, as the benefits of new treatments tested in clinical trials are recognised to improve patient outcomes. It is important that the cost of that research is identified and properly funded. In the UK, the AcoRD guidance (2012) provides a framework to identify, attribute and recover the various costs associated with research, in a transparent, robust and consistent manner. It clarifies the distinction between research costs, service support costs and TCs. We have focused on quantitating the TCs associated with treating patients in cancer clinical trials, as uncertainty surrounding the size of cost difference between treatment in or outside of trials, particularly non-commercial trials, is a barrier to their efficient conduct. We have previously sought to estimate the cost of the treatment administered to patients recruited to cancer trials using individual patient data from clinical research forms and pharmacy prescriptions (Corrie et al, 2011). However, TCs extend beyond the drug costs alone. So, to better inform service delivery, we developed a methodology designed to include all elements of TCs as described in the AcoRD guidelines. The method provides a unit TC difference associated with an individual trial protocol, taking into account the number of arms in a trial and, where appropriate, the randomisation ratio. The unit TC difference can only be an estimate, as the duration of treatment may vary for an individual patient, whereas for randomised trials, one might expect the estimate to be more accurate the more patients recruited to any protocol. In addition, we tailored SOC to local treatment guidelines, which may differ between regions. There are several limitations associated with this methodology. First, we did not take into account changes to the treatment plan associated with adverse drug reactions and did not include any associated non-elective hospital admissions, as individual patient data was not analysed in depth other than to estimate duration of palliative treatment in some instances. In addition, we did not include follow-up of patients after completion of anticancer therapy, assuming that this would account for a proportionally small element of treatment costs: commercial trials would be expected to fully reimburse all costs above SOC, whereas in general, frequency of follow-up in non-commercial trials tends to reflect routine follow-up arrangements. Finally, costing of commercial trials was based on direct costs only and did not include overheads charged to industry. Despite these limitations, we believe this methodology has the potential to be applied on a wider scale to inform providers and commissioners regarding the impact of conducting cancer clinical trials on health service resources. Review of patients recruited to interventional cancer trials in a single research active institution over a 2-year period identified significant variation in associated TCs between protocols. The average TC for 27 non-commercial trials was an excess of £431 (range £6393 excess to £6005 saving) and for 26 commercial trials was an average saving of £9294 (range £0 to £71 480). Breaking down the TCs by the main categories, by far the largest contribution to cost savings was provision or reimbursement of IMPs by pharmaceutical companies, primarily as part of the conduct of commercial sponsored studies, but also, and to a lesser extent, in partnership with academic groups conducting non-commercial NIHR portfolio studies. The distribution of TCs was rather different for commercial and non-commercial trials. For non-commercial trials, the main excess TC was due to administering IMPs. For commercial trials, considerable extra costs were incurred by additional clinic visits and imaging investigations. This might suggest that pharmaceutical companies drive a more intensive patient management plan, and/or that, as many of the commercial protocols were for international multi-centre trials, they were designed to reflect practice in countries outside of the UK. Even so, because commercial trials were fully funded, the potential excess TCs associated with these protocols should not be passed on to commissioners. Our findings confirmed that the pathway for patients entered into academic trials did, in general, reflect routine clinical practice. By assigning the 357 patients to the protocols in which they were enroled, the overall treatment cost saving to the NHS was estimated to be approaching £0.5 million per annum. In our view, this data provides overwhelming evidence to refute any concern that clinical research generates a cost pressure for the health service. On the contrary, we have demonstrated significant financial gains. The largest gains were from commercial sponsored trials. There is currently a growing emphasis on expanding the commercial trial portfolio across all disease areas. Although this may bring financial benefits, the main reason for our undertaking this review was to address concerns that academic clinical trials were a financial liability. Taken individually, this may be the case in some instances, but viewed across a whole portfolio, there are clear gains even for non-commercial clinical trials. Academic trials represent an important part of the NIHR portfolio, affording the opportunity to address questions that would not be a priority for industry sponsors. For example, two non-commercial trials testing whether shorter durations of adjuvant therapy might be as effective as longer durations were associated with significant TC savings during their conduct, whereas positive outcomes would have much wider implications for health service savings. In summary, this unique analysis of TCs associated with patients recruited to cancer clinical trials indicates a wide range of per patient TC differences associated with individual trials compared with SOC, whereas the risk of there being an excess TC (as opposed to a saving) primarily lies with non-commercial studies. However, over the course of a year, clinical trials—both commercial and non-commercial—offer an opportunity to realise considerable TC savings. These findings support the Department of Health's directive for commissioning of clinical trials as an integral part of service delivery. A balanced portfolio of both commercial and non-commercial research should offer the greatest benefits to patients and the overall health economy.\n\nQuestion: Compared to Commercial sponsored trials what was the result of Academic, non-commercial sponsored trials on Savings in drugs and dispensing costs?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
978	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The effect of aerobic exercise in the maintenance treatment of depression\n\n ABSTRACT:\nWe investigated the efficacy of aerobic exercise alongside antidepressant medication as an adjuvant maintenance treatment for depression. Fifty patients in remission were randomly assigned to either medication only or medication plus exercise. Assessment of psychopathology was made at 6-weekly intervals (for 24 weeks) using the Hamilton Rating Scale for Depression. The medication-plus-exercise group showed significantly more improvement at 12 and 24 weeks than the medication-only group. This study adds to a growing evidence base that suggests aerobic exercise is worthy of further development in the treatment of depressive disorders.\n\nBODY:\nThe role of exercise in treating depression has been studied extensively in recent years. For example, Rethorst et al (2009) carried out a meta-analysis of 58 randomised controlled trials, and found that groups whose treatment incorporated exercise had significantly lower depression scores than controls. De Zeeuw et al (2010) showed that exercise could have preventive potential, as it was found to reduce the likelihood of depression in high-risk employees with sedentary jobs and an inactive lifestyle. Exercise has also been reported to reduce relapse rates. For example, Babyak et al (2000) found that participants with major depressive disorder who used exercise therapy alone had significantly lower relapse rates than those who received medication. Despite these promising findings and its low cost, the effectiveness of exercise is yet to be fully addressed in the psychosocial treatment literature or incorporated into mainstream treatment practice. For example, the National Institute for Health and Clinical Excellence (NICE, 2009) recommended 'structured group physical activity' only as a low-intensity psychosocial intervention for subthreshold depressive symptoms, or depression with chronic physical health problems. This may be because many studies have been criticised for their methodological limitations and incomplete literature searches (Rethorst et al, 2009); indeed, the classification and duration of exercise are not specified in the majority of reports. Of further note is that the efficacy of exercise in a maintenance capacity remains largely unexplored. Thus, our rationale was to investigate the role of exercise alongside antidepressant medication as a post-remission maintenance therapy, in terms of reducing both the severity of psychopathology and relapse rates.\n\nBODY.METHOD:\nThe 50 patients recruited were attending the psychiatric out-patient department of Sir Sunderland Hospital, Banaras Hindu University, India. Selection was made (via referrals from two senior psychiatrists at the hospital) by the researcher who carried out the post-treatment evaluations. The following selection criteria were used:\nage 15–45 years, in order to cope with the physical exercise regimea diagnosis of major depressive or dysthymic disorder, according to DSM-IV-TR criteria (American Psychiatric Association, 2000)absence of any comorbid psychiatric illnessno major cardiac or orthopaedic illness that would contraindicate exercise. Ethical approval was granted by the University's research ethics committee. After inclusion in the study, patients were prescribed sertraline (200 mg/day – the maximum permitted daily dose) and alprazolam (1 mg/day) for 3–4 weeks in order to achieve remission of clinical depression. Once significant remission – defined as scoring less than 16 on the 21-item Hamilton Rating Scale for Depression (HRSD; Hamilton, 1960) – was obtained, patients were randomly allocated to groups; blinding was not possible, however, as participants were necessarily aware of the treatment group they were in and the researcher who administered exercise therapy also did the follow-up assessment of psychopathology.\n\nBODY.METHOD.PRE-TREATMENT EVALUATION:\nThe researcher assessed the following using a semi-structured pro forma:\nsociodemographic and clinical dataseverity of depressive psychopathology (using the HRSD, plus a structured interview guide)stressful life events (lifetime and past 3 months), using the 51-item Presumptive Stressful Life Events Scale (PSLES; Singh et al, 1984) (a culturally appropriate instrument)melancholic and atypical features of depression (as per DSM-IV-TR)baseline heart rate (mean taken from three 1-minute time slots)fitness levels using the Harvard Step Test, to monitor compliance with the exercise programme (Brouha, 1943).\n\nBODY.METHOD.TREATMENT:\nBoth groups continued to receive sertraline (200 mg/day) and alprazolam (1 mg/day) and did not take part in any form of counselling or psychotherapy. For the medication-plus-exercise group, participants also received training in daily exercise therapy. That therapy consisted of a 5-minute warm-up, 15 minutes of stationary running, and a 10-minute cool-down, this being convenient and economical for all participants regardless of gender or location and within guidelines on exer cise (Whaley et al, 2006). Participants were also advised not to perform any other exercise beyond usual daily activities. Heart rate recordings were made in order to adjust the intensity of exercise to keep within the target heart rate zone, this being 60–84% of the maximum achievable heart rate (Whaley et al, 2006); exercise sessions at home were logged and monitored by carers, and the logs were reviewed by the researcher at every follow-up. None of the participants or their carers reported missing any exercise sessions or cutting sessions short. Follow-up was at 6-weekly intervals for 24 weeks for all participants, and HRSD and PSLES scores were assessed on each occasion. The medication-plus-exercise group also received refresher exercise training and the Harvard Step Test was performed at every follow-up.\n\nBODY.METHOD.ANALYSIS:\nStatistical tests used were the chi-square and Student t-test. Epi Info 6 software, version 6.04a, was used to analyse the data.\n\nBODY.RESULTS:\nAlthough all 50 patients initially agreed to participate, seven did not complete the study (three from the medication-plus-exercise group and four from the medication-only group). Table 1 shows the sample characteristics and features of depression, which were evenly distributed between the groups. Table 2 shows the inter-group comparisons at all 6-weekly follow-ups. The medication-plus-exercise group showed a greater improvement in HRSD scores (change in score from baseline) than the medication-only group from the first follow-up, at 6 weeks, and this difference became statistically significant at weeks 12 (P = 0.04, t = 2.10) and 24 (P = 0.02, t = 2.42); there was no significant difference between the groups' PSLES scores at any follow-up point. Table 1 Baseline characteristics of the sample Variable Medication-only group ( n = 25) Medication-and-exercise group ( n = 25) Number (%) female 9 (60) 6 (40) Number (%) male 16 (46) 19 (54) Usual degree of physical activity: number (%) sedentary light moderate 15 (65) 9 (41) 1 (20) 8 (35) 13 (59) 4 (80) Mean (s.d.) age (years) 29.6 (8.2) 30.5 (8.9) Mean (s.d.) PSLES score for lifetime 216.2 (124.9) 188.0 (86.3) Mean (s.d.) PSLES score for last 3 months 105.0 (72.6) 107.2 (65.3) Mean (s.d.) HRSD score * 23.2 (4.2) 22.8 (3.7) Mean (s.d.) number of melancholic features * 1.2 (1.6) 0.7 (1.1) Mean (s.d.) number of atypical features * 0.1 (0.33) 0.0 (0.3) HRSD, Hamilton Rating Scale for Depression; PSLES, Presumptive Stressful Life Events Scale. * Between group comparisons were non-significant. Table 2 Mean (s.d.) improvement (difference from baseline) in score on the Hamilton Rating Scale for Depression Follow-up Medication-only group Medication-and-exercise group t d.f. P 6 weeks 2.6 (5.3) 4.1 (3.4) 1.17 46 >0.05 12 weeks 2.3 (5.2) 5.0 (3.4) 2.10 45 0.04 18 weeks 3.0 (6.5) 5.6 (5.1) 1.45 42 >0.05 24 weeks 1.0 (7.0) 5.6 (5.4) 2.42 41 0.02 Relapse rates were also recorded via subjective reports and as a measured increase of >50% from baseline HRSD scores (Neumeister et al, 1997). In total, nine patients relapsed, two from the medication-plus-exercise group (both in week 18) and seven from the medication-only group (one relapse in week 6, two in week 12 and four in week 24). This difference in relapse rates did not reach significance (Fisher's exact test: one-tailed, P = 0.07; two-tailed, P = 0.14).\n\nBODY.DISCUSSION:\nWe found that the maintenance treatment of medication-plus-exercise resulted in significantly lower HRSD scores than medication alone at 12-week and 24-week assessments, as well as a promising reduction of relapse rates. These differences were not considered to be due to extraneous life events, as there was no significant difference between the two groups' PSLES scores. These findings are in line with Rethorst et al's (2009) meta-analysis in terms of the potential for exercise to lower depression scores, and with the finding from Babyak et al (2000) that exercise is effective in reducing relapse. We found no studies, however, on the combined role of exercise and antidepressant medication as a maintenance therapy for depressive disorder. The present findings suggest a potential role for exercise as a protective agent during remission, and one which might reduce long-term cost. The study was limited in several ways. There is potential for bias via use of a clinician-rated tool such as the HRSD, particularly in an unblinded study. However, to reduce this, the same experienced assessor was used for the pre-intervention and follow-up assessments and a second assessor made random cross-checks at least once for every participant. Assessors completed the rating scales with the participants through discussion. The sample size was limited to 50, which precluded analysis of potential confounds. For example, the medication-only group was randomly allocated a greater proportion of sedentary members from the outset. There was also an unequal proportion of male/female participants; however, this reflected the population of patients within the hospital. A further limitation was the lack of comparison with an exercise-only group. It is possible that the exercise group may have derived social gain from the increased contact with carers and researchers; interestingly, Babyak et al (2000) raise the point that psychological factors such as proactive agency may be engaged via choosing to exercise. A further issue for the current study was the drop in the rate of improvement for the medication-only group at week 24. The reasons for this are unclear; however, such a change dictates that studies with longer periods of assessment are needed to make stronger interpretations. Thus, future studies could benefit from: larger and more representative samples; extended follow-up periods; additional outcome measures (including patient-rated scales); and the inclusion of further control groups, such as exercise only, social contact only, and group versus solitary exercise. In conclusion, this study adds to the growing evi dence base that suggests exercise is valuable in the treatment of depressive disorders. In particular, we highlight its potential role as a supplementary maintenance treatment during remission. It is worth highlighting that, despite the relatively short time for which the participants exercised, there were measurable benefits. We believe this area of research warrants further attention, particularly as exercise provides a low-cost, flexible and easily implemented treatment with minimal adverse effects, and especially where costly delays in receiving mainstream psychological interventions are commonplace.\n\nQuestion: Compared to Medication only what was the result of Medication plus exercise on Improvement in the Hamilton Rating Scale for Depression at 24 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
988	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Singing teaching as a therapy for chronic respiratory disease - a randomised controlled trial and qualitative evaluation\n\n ABSTRACT.BACKGROUND:\nDespite optimal pharmacological therapy and pulmonary rehabilitation, patients with COPD continue to be breathless. There is a need to develop additional strategies to alleviate symptoms. Learning to sing requires control of breathing and posture and might have benefits that translate into daily life.\n\nABSTRACT.METHODS:\nTo test this hypothesis we performed a randomised controlled trial, comparing a six week course of twice weekly singing classes to usual care, in 28 COPD patients. The experience of singing was assessed in a qualitative fashion, through interviews with a psychologist. In addition, we surveyed patients with chronic respiratory conditions who participated in a series of open singing workshops.\n\nABSTRACT.RESULTS:\nIn the RCT, the physical component score of the SF36 improved in the singers (n = 15) compared to the controls (n = 13); +7.5(14.6) vs. -3.8(8.4) p = 0.02. Singers also had a significant fall in HAD anxiety score; -1.1(2.7) vs. +0.8(1.7) p = 0.03. Singing did not improve single breath counting, breath hold time or shuttle walk distance. In the qualitative element, 8 patients from the singing group were interviewed. Positive effects on physical sensation, general well-being, community/social support and achievement/efficacy emerged as common themes. 150 participants in open workshops completed a questionnaire. 96% rated the workshops as \"very enjoyable\" and 98% thought the workshop had taught them something about breathing in a different way. 81% of attendees felt a \"marked physical difference\" after the workshop.\n\nABSTRACT.CONCLUSION:\nSinging classes can improve quality of life measures and anxiety and are viewed as a very positive experience by patients with respiratory disease; no adverse consequences of participation were observed.\n\nABSTRACT.TRIAL REGISTRATION:\nCurrent Controlled Trials - ISRCTN17544114.\n\nBODY.BACKGROUND:\nChronic obstructive pulmonary disease (COPD) causes breathlessness, which can occur on exertion or, in some individuals, at rest. Although therapy including bronchodilators, pulmonary rehabilitation and oxygen can improve symptoms, the underlying pathology is largely irreversible, meaning that many patients remain limited despite optimal therapy [1,2]. The pattern of breathing typically adopted in COPD is caused by the presence of expiratory flow limitation which leads patients to adopt higher operating lung volumes - dynamic hyperinflation [3]. Although this pattern allows increased expiratory flow rates, this comes at the expense of a greater inspiratory load and mechanical disadvantage for the respiratory muscles. A rapid breathing pattern reduces expiratory time and will exacerbate this. The disparity between respiratory work and ventilatory output that develops is an important determinant of symptoms [4]. A range of non-pharmacological measures for breathlessness have been trialled in respiratory patients [5], including pursed lip breathing [6,7], yoga [8,9], singing [10] and laughter [11], all based on the premise that changing patients' pattern of breathing will improve symptoms A limitation of some physiotherapy approaches is that by focusing attention on breathing pattern they may accentuate awareness of respiratory limitation [12]. Singing requires the development of skills in controlling posture and breath that might be transferrable to everyday life. Breathlessness is a complex sensation [13]; singing lessons might offer techniques that address both the sensory component - largely control of respiratory pattern to reduce hyperinflation, and the affective component - a conscious experience of using the breath for 'something positive'. In addition, there is some evidence that singing may have beneficial effects on wellbeing in healthy [14] and chronic disease populations [15,16]. To evaluate this further we used three approaches; firstly a randomized controlled trial of a six week course of singing training in COPD, secondly an evaluation of a program of open 'drop-in' singing lessons for patients with respiratory disease and thirdly a qualitative evaluation of patients' experience of participating in singing.\n\nBODY.METHODS.RANDOMIZED CONTROLLED TRIAL:\nPatients with COPD, diagnosed according to the GOLD guidelines, who were attending respiratory clinics at the Royal Brompton Hospital, were invited to participate. The study was approved by the Royal Brompton, Harefield and National Heart and Lung Institute Research Ethics Committee and all subjects gave written informed consent. The trial was registered at Current Controlled Trials - ISRCTN17544114. Demographics, height, weight, clinical history and spirometry (Microlab, CareFusion, Kent, UK,) were recorded. Participants completed the Hospital Anxiety and Depression (HAD) Questionnaire [17], St George's Respiratory Questionnaire [18], and the Short Form 36 Questionnaire [19]. Functional exercise capacity was assessed using the incremental shuttle walk test (ISWT). Time to recovery of oxygen saturation, Borg dyspnoea score and heart rate following the walk was documented [20]. Control of breathing was assessed using two measures. 1) Breath hold test - subjects held their breath from maximum inspiration [21,22]. 2) Single breath counting - subjects were instructed to breathe in and then count out loud in time with a metronome running at 60 beats/min[23]. Three attempts at each manoeuvre were made and the mean values recorded. Both techniques were in routine use in the physiotherapy department for the assessment of hyperventilation. All subjects received a thirty minute standard session on breathing control and techniques to manage breathlessness, delivered by one of two senior respiratory physiotherapists involved in the study. Pursed lip breathing and nose breathing were also discussed in relation to managing episodes of shortness of breath. Each subject received a standard Royal Brompton Hospital \"Help Yourself - physiotherapy for people with respiratory symptoms\" booklet (Additional file 1) and was advised to practice the techniques at home. At the end of the baseline session, patients were randomised to either the singing or control groups, using block randomization through consecutive sealed envelopes. The subjects in the singing group attended a hospital-based workshop, led by a singing teacher (PC), twice weekly for six weeks. Each session lasted approximately one hour and included teaching of posture, relaxation and vocal exercises. Tasks of increasing difficulty were given as the sessions progressed - described in more detail in additional file 2. Each subject was given homework and an accompanying CD of songs to practice at home. The teacher was unaware of the tests being used to assess breathing control, so that she would not 'teach to the test'. The control group had no further intervention. At seven weeks follow-up, study participants were again assessed by the same respiratory physiotherapists, who were blinded to treatment allocation. All subjects were instructed not to tell the physiotherapist which group they had been allocated to. Control of breathing, quality of life and functional exercise capacity were measured as at baseline. Statistical analysis was performed using StatView 4.0, using t-tests to compare change in outcome measures between patients and controls. A p value of < 0.5 was taken as significant.\n\nBODY.METHODS.EVALUATION OF OPEN SINGING WORKSHOPS FOR RESPIRATORY PATIENTS:\nAlongside the randomized control study, we ran open, twice-weekly, 'Singing for BreathingTM' workshops for patients with any respiratory condition who were at Royal Brompton Hospital either as inpatients, day cases or outpatients. Conditions included interstitial lung disease, cystic fibrosis, asthma, bronchiectasis and COPD. The sessions were advertised through posters in the hospital and by word of mouth to patients from the arts team, respiratory nurses, physiotherapists and other healthcare professionals. Patients involved in the randomized control study were excluded from these sessions as were those where infection control issues existed. The open sessions were led by the same singing teacher as the randomised study and encompassed relaxation and posture education, as well as phonation exercises. Patients attending these workshops for the first time were asked to complete an anonymous satisfaction questionnaire at the end (Additional file 3).\n\nBODY.METHODS.QUALITATIVE SURVEY OF PATIENT EXPERIENCE OF SINGING:\nFollowing completion of the randomized control study, a chartered counselling psychologist (AE), who had not otherwise participated in the study, interviewed a random sample of eight individuals who had been in the singing arm of the trial. The thirty minute interviews were structured and each subject was asked about 1) physical changes they had noticed. 2) Emotional changes they had noticed. 3) Behavioural changes they had noticed. 4) Any detrimental effects or negative experiences. Participants were assured that they could make negative comments if they wished and that their responses would be anonymous. The interview sheet is shown in additional file 4.\n\nBODY.RESULTS.RANDOMIZED CONTROLLED TRIAL:\nParticipation in the study is described in the CONSORT diagram (Figure 1). Ninety two patients were approached to participate in the study. Fifty four did not wish to take part, one person who was already enrolled in another trial was excluded and one lived too far away to participate. Of the remaining thirty six patients, twenty were allocated to the singing group and sixteen to the control group. Of the singing group, two subjects withdrew from the study once the workshops had begun and three did not attend the final assessment once completing the workshops. In the control group, one withdrew and two did not attend the final assessment. Data are therefore presented for the 15 singers and 13 controls who completed the study. Of these, 6 attended 12 sessions, 4 attended 11, 2 came to 10 and 3 to 9. Figure 1CONSORT Flow Diagram. The baseline characteristics of the singing and control groups were well matched (Table 1). Four of each group were on long term oxygen therapy. In singers, there was a significant improvement in HAD anxiety score -1.1(2.7) vs. +0.8(1.7) p = 0.03 and SF-36 physical component score +7.5(14.6) vs. -3.8(8.4) p = 0.02. Breath hold time actually increased in the control group relative to the singing group -0.3(6.9) sec vs. +5.3(5.7) sec (p = 0.03). There was no significant difference in single breath counting, functional exercise capacity or recovery times following ISWT (Table 2). On direct questioning by the physiotherapist at the end of the study all participants in the singing group reported that they had found the workshops helpful, had practiced their singing at home and that they had found the singing helped them to control their breathing. Table 1 Baseline characteristics Total n = 28 Singing n = 15 Control n = 13 P value Age (yrs) 67.3 (8.1) 66.6 (9.3) 68.1 (6.8) 0.6 FEV 1 % predicted 37.2 (18.6) 36.8 (15.4) 37.7 (22.4) 0.9 Breath hold time (s) 26.3 (11.1) 27.4 (11.7) 24.9 (10.5) 0.9 Single breath counting (n) 23.4 (6.9) 24.8 (7.7) 21.8 (5.7) 0.3 HAD - anxiety score 5.8 (2.9) 6.3 (3.1) 5.3 (2.6) 0.4 HAD -depression score 5.8 (3.1) 5.7 (2.8) 5.8 (3.6) 1.0 SGRQ Total 48.4 (14.5) 51.1 (14.8) 45.3 (14.0) 0.3 SF36 PCS 36.8 (18.4) 32.0 (14.0) 42.2 (21.8) 0.1 SF36 MCS 52.0 (17.9) 47.4 (14.8) 57.2 (20.1) 0.2 ISWT (m) 198.6 (131.3) 174.0 (137.2) 226.9 (123.3) 0.3 Subjective recovery (s) 124.2 (77.6) 115.9 (50.4) 133.8 (102.0) 0.6 O 2 sat n recovery (s) 77.7 (71.6) 73.5 (44.6) 82.6 (95.7) 0.7 HR recovery (s) 131.0 (89.5) 97.6 (40.8) 169.6 (114.3) 0.03* FEV 1 - forced expiratory volume in one second, HAD - hospital anxiety and depression score, SGRQ - St George's Respiratory Questionnaire, SF36 short form 36, PCS - physical component score, MCS - mental component score, ISWT - incremental shuttle walk test distance, HR heart rate. p < 0.05 unpaired t test singing group vs control group. Table 2 Changes from baseline Singing group n = 15 Control group n = 13 Δ breath hold time (s) - 0.3 (6.9) + 5.3 (5.7) 0.029 Δ single breath counting + 0.3 (7.7) + 2.0 (2.7) 0.46 Δ HAD anxiety - 1.1 (2.7) + 0.8 (1.7) 0.033* Δ HAD depression - 1.1 (2.5) - 0.1 (1.7) 0.21 Δ SGRQ Total - 1.1 (10.6) - 0.4 (5.6) 0.81 Δ ISWT (m) + 26 (52.6) + 11.3 (83.0) 0.58 Δ ISWT subjective recovery (s) + 9.9 (60.7) - 7.4 (81.7) 0.53 Δ O 2 Sat n recovery (s) + 47.3 (67.6) + 32.2 (124.7) 0.69 Δ HR recovery time (s) + 29 (63.8) + 19.4 (110.0) 0.78 Δ SF36 PCS + 7.5 (14.6) - 3.8 (8.4) 0.02* Δ SF36 MCS + 2.5 (20.9) - 3.2 (10.5) 0.38 HAD - hospital anxiety and depression score, SGRQ - St George's Respiratory Questionnaire, ISWT - incremental shuttle walk test distance, HR heart rate, SF36 short form 36, PCS - physical component score, MCS - mental component score. p < 0.05 unpaired t test singing group vs control group. \n\nBODY.RESULTS.EVALUATION OF OPEN SINGING WORKSHOPS FOR RESPIRATORY PATIENTS:\n150 patients attended the open workshops. 61% had never attended singing lessons or workshops previously. 96% rated the workshops as \"very enjoyable\" and 98% thought the workshop had taught them something about breathing in a different way. 81% of attendees felt a marked physical difference after the workshop. 92% of the participants said that they would like to attend a further singing workshop at the hospital. The remaining patients stated that the distance to the hospital would be the main reason for not attending.\n\nBODY.RESULTS.QUALITATIVE SURVEY OF PATIENT EXPERIENCE OF THE SINGING CLASSES:\nEight patients who had participated in the singing groups were interviewed. The effect of the group was described by all in mainly positive terms and no participants reported any negative effects. Positive effects occurred in two main areas: physical and general well-being. Positive physical effects reported by the participants often related to the breathing training which was an integral part of the program, particularly \"diaphragmatic breathing\". This training brought a feeling of awareness and control which many of the participants found helped their breathing and eased symptoms of breathlessness. Singing training itself brought breathing control too; \"It has made my life easier; I would have liked this when I was first diagnosed\", \"I increased my out breath from 4 to 14 counts\", \"I started breathing much better, from the stomach\", \"The exercises, thinking about breathing and relaxing when I have (breathing) problems....this has been very useful\", \"I always felt better afterwards physically\". Other positive physical effects described were an impact on lifestyle and functional ability; \"I have better posture now\"; \"Walking better, I go out more when it's not cold\", \"Now things are less of a chore, housework is no longer a struggle\". Beneficial effects relating to general wellbeing also emerged. Relating to mood/pleasure participants reported that; \"It was very enjoyable\", \"It opened up a new lease of life\", \"Emotionally......during singing it lifts you. I feel on top on the world. I also feel like that the day after. It makes COPD a lot easier to live with\", \"Its uplifting to sing...this diagnosis is gloomy so the psychological effect of the group is good\". A feeling of community/social support was also reported; \"Nice to have human contact, we achieved something together in the group\", \"I enjoyed the social contact it was great fun\", \"In six weeks we gelled as a group\", \"It felt good to be part of a team\". Achievement/efficacy - many participants had carried aspects of the courses into daily life. Many of them continued to sing songs and perform the exercises from the group using printed sheets or a CD. It seems that learning to sing in a group brought a sense of achievement. \"I do the exercises from the CD 2-3 times a week. I am looking for a local choir\"; \"I will keep it up; it's more enjoyable than other kinds of exercise\"; \"I learnt a lot, you are never too old to learn\"; \"The group taught me how and when to breathe; I got to relive my past (of singing) and get praise\". Others reported that participating in the group had motivated them to reengage with pulmonary rehabilitation classes, or to take up exercises such as swimming and walking. One was having private singing lessons and several expressed a desire for such groups to be ongoing and made more available to patients with respiratory problems.\n\nBODY.DISCUSSION:\nThe main findings of this study are that (1) the program of singing classes improved quality of life and anxiety but did not improve the control of breathing measures, or functional exercise capacity. (2) In interviews, patients who had participated in the trial reported benefits in their physical performance and general well-being as well as a sense of achievement and self-efficacy. (3) Individuals who chose to participate in the open singing sessions were overwhelmingly positive about the experience.\n\nBODY.DISCUSSION.SIGNIFICANCE OF FINDINGS:\nThe idea that singing was beneficial for health goes back at least to the 19th century [24]. Two previous studies have looked specifically at singing in COPD patients. Bonilha et al randomised patients to either singing lessons, or a handicraft class once a week for 6 months [10]. Although singing practice produced an acute increase in inspiratory capacity, implying a reduction in gas trapping, it did not alter basal dyspnoea index (BDI). SGRQ improved equally in both groups and the singing group had an improvement in maximum expiratory pressure. Exercise capacity was not assessed. Engen studied 7 patients with emphysema who attended twice weekly vocal instruction classes for 6 weeks [23]. There was no change in spirometry, inspiratory muscle strength or exercise capacity, but patients had an improvement in single breath counting, which was associated with a change from a 'clavicular' to a 'diaphragmatic' pattern of breathing. In that study there was no control group and the teacher was not blind to the outcome measures. In the present study, anxiety score and physical component score of the SF36 improved and participants who were interviewed reported that they felt that the singing had been helpful in their everyday lives. HAD scores were not particularly high at baseline and patients were selected on the basis that they had symptomatic COPD and were able to attend, rather than because they were felt specifically to have a dysfunctional breathing pattern or psychological difficulties. It is possible that greater improvements might be found in particularly anxious sub-populations. The benefit in the physical rather than the mental component is consistent with the open workshop participants' reports that they felt physically different after the sessions. The immediate benefits reported by patients participating in the open workshops and from the interviews with singing patients are consistent with the previous observation that singing has an acute effect of reducing gas trapping [10]. Most reported sustained physical benefits, specifically identifying the value of learning breathing control. Several participants also mentioned that they felt that it was important to keep up the vocal exercises and singing in order to maintain any gains which may suggest that a longer period is necessary. The present study is also consistent with previous work that has found that singing training does not change, at least over the time courses explored to date, parameters such as exercise capacity [10,23]. We had expected that even if the singing class did not improve exercise tolerance it might hasten recovery, with patients adopting a more efficient breathing strategy. However, recovery time for heart rate, oxygen saturation or symptoms did not improve. Given the subjective benefits in physical sensation described by patients, the lack of change in exercise capacity is interesting. One possibility is that the improvements are entirely mediated in a psychological fashion. Since anxiety and depression are common and important co-morbidities in COPD [25,26] a novel approach to dealing with them could in any case be useful, particularly a non-drug treatment. An analogy would be the use of exercise prescriptions to treat depression [27]. Given the clear effects on wellbeing mentioned by the participants, one could also speculate that there might be benefits to efficacy and control in the absence of great physiological improvement. A patient's experience of their illness will be affected by a range of psychosocial factors in addition to their physical condition. All patients interviewed reported doing more singing and other pleasurable activities in their lives, suggesting that there may be long term benefits to participation in such a group. Consistent with this, singing has been used with some success in small studies to treat chronic pain where it seemed to improve coping [15] and after knee surgery [28]. A second possibility is that the 'dose' of singing was insufficient to alter conventional measures of breathing control or exercise capacity and that a longer or more intense period would be required to produce changes apparent in daily life. The singing teacher reported that she felt that after 6 weeks she was \"only just starting to make progress\" with many of the participants. It is interesting that in the current study, patients reported that what was identified to them as a 'diaphragmatic' breathing pattern was helpful. This involves facilitating outward movement of the abdomen while reducing upper ribcage movement during inspiration. It has been thought to be helpful in some patients, but although a reduction in oxygen cost of breathing has been noted [29], the approach has been associated with both an increased sensation of breathlessness and reduced mechanical efficiency in severe COPD [30,31] and is not recommended for routine use in the recent British Thoracic Society/Association for Chartered Physiotherapist in Respiratory Care(BTS/ACPRC) guidelines on \"Physiotherapy management of the adult, medical, spontaneously breathing patient\" [12]. The improvement in breath hold time observed in the control group was unexpected. A strength of the study was that the singing teacher was blind to the outcome measures used so could not \"teach to the test\". The teacher speculated that the singing group may have learnt to take a more controlled or comfortable breath and therefore smaller breath in, leading paradoxically to a reduction in breath hold time. Hyperventilation has been shown to increase breath hold time in patients with respiratory disease which might also be relevant [22]. If the benefits of participating in a singing group are largely psychological, it would suggest that attention would need to be focused on the aspects of the singing that addressed this, or even on the choice of material, rather than focussing on particular nuances of technique. Singing is, of course, likely to be a therapy that suits some people and not others, and the benefits that accrue are likely to be greatest in those who enjoy the experience. This is to some extent different from pulmonary rehabilitation where the health benefits of exercise are generally accepted. As with pulmonary rehabilitation the physiological and psychological effects could be complementary. A limitation of our study was the absence of an active control group. The previous paper of Bonilha et al. showed similar improvements of quality of life in patients submitted to singing training or handcraft artwork [10], so the observed improvements in anxiety and quality of life in the trial may have been due to regular contact with a social group rather than the singing specifically. However, in our study patients reported immediate positive effects on well being (probably because of a reduction in dynamic hyperinflation [10]) and this may therefore have reinforced participation in singing groups (as opposed to other 'social activities' which, although social have no physical effect), making the provision of singing classes a good strategy for reducing social isolation, a significant problem in chronic respiratory disease [32].\n\nBODY.CONCLUSIONS:\nSinging lessons improved anxiety and the physical component score of the SF36 but did not improve measures of breathing control, functional exercise capacity or recovery time. Participants reported that they found the singing beneficial and reported positive changes in their physical ability and wellbeing. It is likely that the effects of singing training will vary between individuals, but that it will be a positive experience for those who choose to take part. Further work is needed to quantify the magnitude and duration of improvement benefits, to set them in context against the resource implications of making singing groups for patients more widely available as a palliative therapy.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nNSH, VML, VJH, PC and MIP conceived the study; VML, PC, EJF, AE and JLK performed the study measurements. VML, VJH, AE and NSH performed the data analysis. VML wrote the first draft of the paper to which all authors subsequently made contributions. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2466/10/41/prepub\n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional file 1Help Yourself - physiotherapy for people with respiratory symptoms\". Standard booklet given to all patients participating in the trial.Click here for file Additional file 2Singing for breathing - description of program. Detailed description of singing program, selection of materials and conduct of classes.Click here for file Additional file 3Open sessions satisfaction survey. Survey used for participants to assess the open singing sessions.Click here for file Additional file 4Structured interview template. Template used to guide assessments by psychologists following the singing trial.Click here for file\n\nQuestion:* Compared to Usual care what was the result of Singing classes on Improvement in SF-36 physical component score?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
989	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Singing teaching as a therapy for chronic respiratory disease - a randomised controlled trial and qualitative evaluation\n\n ABSTRACT.BACKGROUND:\nDespite optimal pharmacological therapy and pulmonary rehabilitation, patients with COPD continue to be breathless. There is a need to develop additional strategies to alleviate symptoms. Learning to sing requires control of breathing and posture and might have benefits that translate into daily life.\n\nABSTRACT.METHODS:\nTo test this hypothesis we performed a randomised controlled trial, comparing a six week course of twice weekly singing classes to usual care, in 28 COPD patients. The experience of singing was assessed in a qualitative fashion, through interviews with a psychologist. In addition, we surveyed patients with chronic respiratory conditions who participated in a series of open singing workshops.\n\nABSTRACT.RESULTS:\nIn the RCT, the physical component score of the SF36 improved in the singers (n = 15) compared to the controls (n = 13); +7.5(14.6) vs. -3.8(8.4) p = 0.02. Singers also had a significant fall in HAD anxiety score; -1.1(2.7) vs. +0.8(1.7) p = 0.03. Singing did not improve single breath counting, breath hold time or shuttle walk distance. In the qualitative element, 8 patients from the singing group were interviewed. Positive effects on physical sensation, general well-being, community/social support and achievement/efficacy emerged as common themes. 150 participants in open workshops completed a questionnaire. 96% rated the workshops as \"very enjoyable\" and 98% thought the workshop had taught them something about breathing in a different way. 81% of attendees felt a \"marked physical difference\" after the workshop.\n\nABSTRACT.CONCLUSION:\nSinging classes can improve quality of life measures and anxiety and are viewed as a very positive experience by patients with respiratory disease; no adverse consequences of participation were observed.\n\nABSTRACT.TRIAL REGISTRATION:\nCurrent Controlled Trials - ISRCTN17544114.\n\nBODY.BACKGROUND:\nChronic obstructive pulmonary disease (COPD) causes breathlessness, which can occur on exertion or, in some individuals, at rest. Although therapy including bronchodilators, pulmonary rehabilitation and oxygen can improve symptoms, the underlying pathology is largely irreversible, meaning that many patients remain limited despite optimal therapy [1,2]. The pattern of breathing typically adopted in COPD is caused by the presence of expiratory flow limitation which leads patients to adopt higher operating lung volumes - dynamic hyperinflation [3]. Although this pattern allows increased expiratory flow rates, this comes at the expense of a greater inspiratory load and mechanical disadvantage for the respiratory muscles. A rapid breathing pattern reduces expiratory time and will exacerbate this. The disparity between respiratory work and ventilatory output that develops is an important determinant of symptoms [4]. A range of non-pharmacological measures for breathlessness have been trialled in respiratory patients [5], including pursed lip breathing [6,7], yoga [8,9], singing [10] and laughter [11], all based on the premise that changing patients' pattern of breathing will improve symptoms A limitation of some physiotherapy approaches is that by focusing attention on breathing pattern they may accentuate awareness of respiratory limitation [12]. Singing requires the development of skills in controlling posture and breath that might be transferrable to everyday life. Breathlessness is a complex sensation [13]; singing lessons might offer techniques that address both the sensory component - largely control of respiratory pattern to reduce hyperinflation, and the affective component - a conscious experience of using the breath for 'something positive'. In addition, there is some evidence that singing may have beneficial effects on wellbeing in healthy [14] and chronic disease populations [15,16]. To evaluate this further we used three approaches; firstly a randomized controlled trial of a six week course of singing training in COPD, secondly an evaluation of a program of open 'drop-in' singing lessons for patients with respiratory disease and thirdly a qualitative evaluation of patients' experience of participating in singing.\n\nBODY.METHODS.RANDOMIZED CONTROLLED TRIAL:\nPatients with COPD, diagnosed according to the GOLD guidelines, who were attending respiratory clinics at the Royal Brompton Hospital, were invited to participate. The study was approved by the Royal Brompton, Harefield and National Heart and Lung Institute Research Ethics Committee and all subjects gave written informed consent. The trial was registered at Current Controlled Trials - ISRCTN17544114. Demographics, height, weight, clinical history and spirometry (Microlab, CareFusion, Kent, UK,) were recorded. Participants completed the Hospital Anxiety and Depression (HAD) Questionnaire [17], St George's Respiratory Questionnaire [18], and the Short Form 36 Questionnaire [19]. Functional exercise capacity was assessed using the incremental shuttle walk test (ISWT). Time to recovery of oxygen saturation, Borg dyspnoea score and heart rate following the walk was documented [20]. Control of breathing was assessed using two measures. 1) Breath hold test - subjects held their breath from maximum inspiration [21,22]. 2) Single breath counting - subjects were instructed to breathe in and then count out loud in time with a metronome running at 60 beats/min[23]. Three attempts at each manoeuvre were made and the mean values recorded. Both techniques were in routine use in the physiotherapy department for the assessment of hyperventilation. All subjects received a thirty minute standard session on breathing control and techniques to manage breathlessness, delivered by one of two senior respiratory physiotherapists involved in the study. Pursed lip breathing and nose breathing were also discussed in relation to managing episodes of shortness of breath. Each subject received a standard Royal Brompton Hospital \"Help Yourself - physiotherapy for people with respiratory symptoms\" booklet (Additional file 1) and was advised to practice the techniques at home. At the end of the baseline session, patients were randomised to either the singing or control groups, using block randomization through consecutive sealed envelopes. The subjects in the singing group attended a hospital-based workshop, led by a singing teacher (PC), twice weekly for six weeks. Each session lasted approximately one hour and included teaching of posture, relaxation and vocal exercises. Tasks of increasing difficulty were given as the sessions progressed - described in more detail in additional file 2. Each subject was given homework and an accompanying CD of songs to practice at home. The teacher was unaware of the tests being used to assess breathing control, so that she would not 'teach to the test'. The control group had no further intervention. At seven weeks follow-up, study participants were again assessed by the same respiratory physiotherapists, who were blinded to treatment allocation. All subjects were instructed not to tell the physiotherapist which group they had been allocated to. Control of breathing, quality of life and functional exercise capacity were measured as at baseline. Statistical analysis was performed using StatView 4.0, using t-tests to compare change in outcome measures between patients and controls. A p value of < 0.5 was taken as significant.\n\nBODY.METHODS.EVALUATION OF OPEN SINGING WORKSHOPS FOR RESPIRATORY PATIENTS:\nAlongside the randomized control study, we ran open, twice-weekly, 'Singing for BreathingTM' workshops for patients with any respiratory condition who were at Royal Brompton Hospital either as inpatients, day cases or outpatients. Conditions included interstitial lung disease, cystic fibrosis, asthma, bronchiectasis and COPD. The sessions were advertised through posters in the hospital and by word of mouth to patients from the arts team, respiratory nurses, physiotherapists and other healthcare professionals. Patients involved in the randomized control study were excluded from these sessions as were those where infection control issues existed. The open sessions were led by the same singing teacher as the randomised study and encompassed relaxation and posture education, as well as phonation exercises. Patients attending these workshops for the first time were asked to complete an anonymous satisfaction questionnaire at the end (Additional file 3).\n\nBODY.METHODS.QUALITATIVE SURVEY OF PATIENT EXPERIENCE OF SINGING:\nFollowing completion of the randomized control study, a chartered counselling psychologist (AE), who had not otherwise participated in the study, interviewed a random sample of eight individuals who had been in the singing arm of the trial. The thirty minute interviews were structured and each subject was asked about 1) physical changes they had noticed. 2) Emotional changes they had noticed. 3) Behavioural changes they had noticed. 4) Any detrimental effects or negative experiences. Participants were assured that they could make negative comments if they wished and that their responses would be anonymous. The interview sheet is shown in additional file 4.\n\nBODY.RESULTS.RANDOMIZED CONTROLLED TRIAL:\nParticipation in the study is described in the CONSORT diagram (Figure 1). Ninety two patients were approached to participate in the study. Fifty four did not wish to take part, one person who was already enrolled in another trial was excluded and one lived too far away to participate. Of the remaining thirty six patients, twenty were allocated to the singing group and sixteen to the control group. Of the singing group, two subjects withdrew from the study once the workshops had begun and three did not attend the final assessment once completing the workshops. In the control group, one withdrew and two did not attend the final assessment. Data are therefore presented for the 15 singers and 13 controls who completed the study. Of these, 6 attended 12 sessions, 4 attended 11, 2 came to 10 and 3 to 9. Figure 1CONSORT Flow Diagram. The baseline characteristics of the singing and control groups were well matched (Table 1). Four of each group were on long term oxygen therapy. In singers, there was a significant improvement in HAD anxiety score -1.1(2.7) vs. +0.8(1.7) p = 0.03 and SF-36 physical component score +7.5(14.6) vs. -3.8(8.4) p = 0.02. Breath hold time actually increased in the control group relative to the singing group -0.3(6.9) sec vs. +5.3(5.7) sec (p = 0.03). There was no significant difference in single breath counting, functional exercise capacity or recovery times following ISWT (Table 2). On direct questioning by the physiotherapist at the end of the study all participants in the singing group reported that they had found the workshops helpful, had practiced their singing at home and that they had found the singing helped them to control their breathing. Table 1 Baseline characteristics Total n = 28 Singing n = 15 Control n = 13 P value Age (yrs) 67.3 (8.1) 66.6 (9.3) 68.1 (6.8) 0.6 FEV 1 % predicted 37.2 (18.6) 36.8 (15.4) 37.7 (22.4) 0.9 Breath hold time (s) 26.3 (11.1) 27.4 (11.7) 24.9 (10.5) 0.9 Single breath counting (n) 23.4 (6.9) 24.8 (7.7) 21.8 (5.7) 0.3 HAD - anxiety score 5.8 (2.9) 6.3 (3.1) 5.3 (2.6) 0.4 HAD -depression score 5.8 (3.1) 5.7 (2.8) 5.8 (3.6) 1.0 SGRQ Total 48.4 (14.5) 51.1 (14.8) 45.3 (14.0) 0.3 SF36 PCS 36.8 (18.4) 32.0 (14.0) 42.2 (21.8) 0.1 SF36 MCS 52.0 (17.9) 47.4 (14.8) 57.2 (20.1) 0.2 ISWT (m) 198.6 (131.3) 174.0 (137.2) 226.9 (123.3) 0.3 Subjective recovery (s) 124.2 (77.6) 115.9 (50.4) 133.8 (102.0) 0.6 O 2 sat n recovery (s) 77.7 (71.6) 73.5 (44.6) 82.6 (95.7) 0.7 HR recovery (s) 131.0 (89.5) 97.6 (40.8) 169.6 (114.3) 0.03* FEV 1 - forced expiratory volume in one second, HAD - hospital anxiety and depression score, SGRQ - St George's Respiratory Questionnaire, SF36 short form 36, PCS - physical component score, MCS - mental component score, ISWT - incremental shuttle walk test distance, HR heart rate. p < 0.05 unpaired t test singing group vs control group. Table 2 Changes from baseline Singing group n = 15 Control group n = 13 Δ breath hold time (s) - 0.3 (6.9) + 5.3 (5.7) 0.029 Δ single breath counting + 0.3 (7.7) + 2.0 (2.7) 0.46 Δ HAD anxiety - 1.1 (2.7) + 0.8 (1.7) 0.033* Δ HAD depression - 1.1 (2.5) - 0.1 (1.7) 0.21 Δ SGRQ Total - 1.1 (10.6) - 0.4 (5.6) 0.81 Δ ISWT (m) + 26 (52.6) + 11.3 (83.0) 0.58 Δ ISWT subjective recovery (s) + 9.9 (60.7) - 7.4 (81.7) 0.53 Δ O 2 Sat n recovery (s) + 47.3 (67.6) + 32.2 (124.7) 0.69 Δ HR recovery time (s) + 29 (63.8) + 19.4 (110.0) 0.78 Δ SF36 PCS + 7.5 (14.6) - 3.8 (8.4) 0.02* Δ SF36 MCS + 2.5 (20.9) - 3.2 (10.5) 0.38 HAD - hospital anxiety and depression score, SGRQ - St George's Respiratory Questionnaire, ISWT - incremental shuttle walk test distance, HR heart rate, SF36 short form 36, PCS - physical component score, MCS - mental component score. p < 0.05 unpaired t test singing group vs control group. \n\nBODY.RESULTS.EVALUATION OF OPEN SINGING WORKSHOPS FOR RESPIRATORY PATIENTS:\n150 patients attended the open workshops. 61% had never attended singing lessons or workshops previously. 96% rated the workshops as \"very enjoyable\" and 98% thought the workshop had taught them something about breathing in a different way. 81% of attendees felt a marked physical difference after the workshop. 92% of the participants said that they would like to attend a further singing workshop at the hospital. The remaining patients stated that the distance to the hospital would be the main reason for not attending.\n\nBODY.RESULTS.QUALITATIVE SURVEY OF PATIENT EXPERIENCE OF THE SINGING CLASSES:\nEight patients who had participated in the singing groups were interviewed. The effect of the group was described by all in mainly positive terms and no participants reported any negative effects. Positive effects occurred in two main areas: physical and general well-being. Positive physical effects reported by the participants often related to the breathing training which was an integral part of the program, particularly \"diaphragmatic breathing\". This training brought a feeling of awareness and control which many of the participants found helped their breathing and eased symptoms of breathlessness. Singing training itself brought breathing control too; \"It has made my life easier; I would have liked this when I was first diagnosed\", \"I increased my out breath from 4 to 14 counts\", \"I started breathing much better, from the stomach\", \"The exercises, thinking about breathing and relaxing when I have (breathing) problems....this has been very useful\", \"I always felt better afterwards physically\". Other positive physical effects described were an impact on lifestyle and functional ability; \"I have better posture now\"; \"Walking better, I go out more when it's not cold\", \"Now things are less of a chore, housework is no longer a struggle\". Beneficial effects relating to general wellbeing also emerged. Relating to mood/pleasure participants reported that; \"It was very enjoyable\", \"It opened up a new lease of life\", \"Emotionally......during singing it lifts you. I feel on top on the world. I also feel like that the day after. It makes COPD a lot easier to live with\", \"Its uplifting to sing...this diagnosis is gloomy so the psychological effect of the group is good\". A feeling of community/social support was also reported; \"Nice to have human contact, we achieved something together in the group\", \"I enjoyed the social contact it was great fun\", \"In six weeks we gelled as a group\", \"It felt good to be part of a team\". Achievement/efficacy - many participants had carried aspects of the courses into daily life. Many of them continued to sing songs and perform the exercises from the group using printed sheets or a CD. It seems that learning to sing in a group brought a sense of achievement. \"I do the exercises from the CD 2-3 times a week. I am looking for a local choir\"; \"I will keep it up; it's more enjoyable than other kinds of exercise\"; \"I learnt a lot, you are never too old to learn\"; \"The group taught me how and when to breathe; I got to relive my past (of singing) and get praise\". Others reported that participating in the group had motivated them to reengage with pulmonary rehabilitation classes, or to take up exercises such as swimming and walking. One was having private singing lessons and several expressed a desire for such groups to be ongoing and made more available to patients with respiratory problems.\n\nBODY.DISCUSSION:\nThe main findings of this study are that (1) the program of singing classes improved quality of life and anxiety but did not improve the control of breathing measures, or functional exercise capacity. (2) In interviews, patients who had participated in the trial reported benefits in their physical performance and general well-being as well as a sense of achievement and self-efficacy. (3) Individuals who chose to participate in the open singing sessions were overwhelmingly positive about the experience.\n\nBODY.DISCUSSION.SIGNIFICANCE OF FINDINGS:\nThe idea that singing was beneficial for health goes back at least to the 19th century [24]. Two previous studies have looked specifically at singing in COPD patients. Bonilha et al randomised patients to either singing lessons, or a handicraft class once a week for 6 months [10]. Although singing practice produced an acute increase in inspiratory capacity, implying a reduction in gas trapping, it did not alter basal dyspnoea index (BDI). SGRQ improved equally in both groups and the singing group had an improvement in maximum expiratory pressure. Exercise capacity was not assessed. Engen studied 7 patients with emphysema who attended twice weekly vocal instruction classes for 6 weeks [23]. There was no change in spirometry, inspiratory muscle strength or exercise capacity, but patients had an improvement in single breath counting, which was associated with a change from a 'clavicular' to a 'diaphragmatic' pattern of breathing. In that study there was no control group and the teacher was not blind to the outcome measures. In the present study, anxiety score and physical component score of the SF36 improved and participants who were interviewed reported that they felt that the singing had been helpful in their everyday lives. HAD scores were not particularly high at baseline and patients were selected on the basis that they had symptomatic COPD and were able to attend, rather than because they were felt specifically to have a dysfunctional breathing pattern or psychological difficulties. It is possible that greater improvements might be found in particularly anxious sub-populations. The benefit in the physical rather than the mental component is consistent with the open workshop participants' reports that they felt physically different after the sessions. The immediate benefits reported by patients participating in the open workshops and from the interviews with singing patients are consistent with the previous observation that singing has an acute effect of reducing gas trapping [10]. Most reported sustained physical benefits, specifically identifying the value of learning breathing control. Several participants also mentioned that they felt that it was important to keep up the vocal exercises and singing in order to maintain any gains which may suggest that a longer period is necessary. The present study is also consistent with previous work that has found that singing training does not change, at least over the time courses explored to date, parameters such as exercise capacity [10,23]. We had expected that even if the singing class did not improve exercise tolerance it might hasten recovery, with patients adopting a more efficient breathing strategy. However, recovery time for heart rate, oxygen saturation or symptoms did not improve. Given the subjective benefits in physical sensation described by patients, the lack of change in exercise capacity is interesting. One possibility is that the improvements are entirely mediated in a psychological fashion. Since anxiety and depression are common and important co-morbidities in COPD [25,26] a novel approach to dealing with them could in any case be useful, particularly a non-drug treatment. An analogy would be the use of exercise prescriptions to treat depression [27]. Given the clear effects on wellbeing mentioned by the participants, one could also speculate that there might be benefits to efficacy and control in the absence of great physiological improvement. A patient's experience of their illness will be affected by a range of psychosocial factors in addition to their physical condition. All patients interviewed reported doing more singing and other pleasurable activities in their lives, suggesting that there may be long term benefits to participation in such a group. Consistent with this, singing has been used with some success in small studies to treat chronic pain where it seemed to improve coping [15] and after knee surgery [28]. A second possibility is that the 'dose' of singing was insufficient to alter conventional measures of breathing control or exercise capacity and that a longer or more intense period would be required to produce changes apparent in daily life. The singing teacher reported that she felt that after 6 weeks she was \"only just starting to make progress\" with many of the participants. It is interesting that in the current study, patients reported that what was identified to them as a 'diaphragmatic' breathing pattern was helpful. This involves facilitating outward movement of the abdomen while reducing upper ribcage movement during inspiration. It has been thought to be helpful in some patients, but although a reduction in oxygen cost of breathing has been noted [29], the approach has been associated with both an increased sensation of breathlessness and reduced mechanical efficiency in severe COPD [30,31] and is not recommended for routine use in the recent British Thoracic Society/Association for Chartered Physiotherapist in Respiratory Care(BTS/ACPRC) guidelines on \"Physiotherapy management of the adult, medical, spontaneously breathing patient\" [12]. The improvement in breath hold time observed in the control group was unexpected. A strength of the study was that the singing teacher was blind to the outcome measures used so could not \"teach to the test\". The teacher speculated that the singing group may have learnt to take a more controlled or comfortable breath and therefore smaller breath in, leading paradoxically to a reduction in breath hold time. Hyperventilation has been shown to increase breath hold time in patients with respiratory disease which might also be relevant [22]. If the benefits of participating in a singing group are largely psychological, it would suggest that attention would need to be focused on the aspects of the singing that addressed this, or even on the choice of material, rather than focussing on particular nuances of technique. Singing is, of course, likely to be a therapy that suits some people and not others, and the benefits that accrue are likely to be greatest in those who enjoy the experience. This is to some extent different from pulmonary rehabilitation where the health benefits of exercise are generally accepted. As with pulmonary rehabilitation the physiological and psychological effects could be complementary. A limitation of our study was the absence of an active control group. The previous paper of Bonilha et al. showed similar improvements of quality of life in patients submitted to singing training or handcraft artwork [10], so the observed improvements in anxiety and quality of life in the trial may have been due to regular contact with a social group rather than the singing specifically. However, in our study patients reported immediate positive effects on well being (probably because of a reduction in dynamic hyperinflation [10]) and this may therefore have reinforced participation in singing groups (as opposed to other 'social activities' which, although social have no physical effect), making the provision of singing classes a good strategy for reducing social isolation, a significant problem in chronic respiratory disease [32].\n\nBODY.CONCLUSIONS:\nSinging lessons improved anxiety and the physical component score of the SF36 but did not improve measures of breathing control, functional exercise capacity or recovery time. Participants reported that they found the singing beneficial and reported positive changes in their physical ability and wellbeing. It is likely that the effects of singing training will vary between individuals, but that it will be a positive experience for those who choose to take part. Further work is needed to quantify the magnitude and duration of improvement benefits, to set them in context against the resource implications of making singing groups for patients more widely available as a palliative therapy.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nNSH, VML, VJH, PC and MIP conceived the study; VML, PC, EJF, AE and JLK performed the study measurements. VML, VJH, AE and NSH performed the data analysis. VML wrote the first draft of the paper to which all authors subsequently made contributions. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2466/10/41/prepub\n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional file 1Help Yourself - physiotherapy for people with respiratory symptoms\". Standard booklet given to all patients participating in the trial.Click here for file Additional file 2Singing for breathing - description of program. Detailed description of singing program, selection of materials and conduct of classes.Click here for file Additional file 3Open sessions satisfaction survey. Survey used for participants to assess the open singing sessions.Click here for file Additional file 4Structured interview template. Template used to guide assessments by psychologists following the singing trial.Click here for file\n\nQuestion:* Compared to Usual care what was the result of Singing classes on Breath hold time?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1117	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effect of a randomised exclusive breastfeeding counselling intervention nested into the MINIMat prenatal nutrition trial in Bangladesh\n\n ABSTRACT.ABSTRACT.AIM:\nIt is unknown whether maternal malnutrition reduces the effect of counselling on exclusive breastfeeding. This study evaluated the effect of breastfeeding counselling on the duration of exclusive breastfeeding, and whether the timing of prenatal food and different micronutrient supplements further prolonged this duration.\n\nABSTRACT.ABSTRACT.METHODS:\nPregnant women in Matlab, Bangladesh, were randomised to receive daily food supplements of 600 kcal at nine weeks of gestation or at the standard 20 weeks. They also were allocated to either 30 mg of iron and 400 μg folic acid, or the standard programme 60 mg of iron and folic acid or multiple micronutrients. At 30 weeks of gestation, 3188 women were randomised to receive either eight breastfeeding counselling sessions or the usual health messages.\n\nABSTRACT.ABSTRACT.RESULTS:\nThe median duration of exclusive breastfeeding was 135 days in the counselling group and 75 days in the usual health message group (p < 0.001). Prenatal supplements did not modify the effects of counselling. Women in the usual health message group who were randomised to multiple micronutrients exclusively breastfed for 12 days longer than mothers receiving the standard iron–folate combination (p = 0.003).\n\nABSTRACT.ABSTRACT.CONCLUSION:\nBreastfeeding counselling increased the duration of exclusive breastfeeding by 60 days. This duration was not influenced by the supplements.\n\nBODY:\n\nKey notes\nEarlier studies of breastfeeding counselling have shown positive effects on duration of exclusive breastfeeding, but it is not known whether prenatal nutrition interventions increase this effectEight counselling sessions increased exclusive breastfeeding by 60 days, but timing of prenatal food supplementation and different micronutrient alternatives did not increase the durationAmong women who did not receive the breastfeeding counselling, prenatal multiple micronutrient supplementation was associated with 12 days longer exclusive breastfeeding that may be of small public health importance\n\n\n\nBODY.INTRODUCTION:\nExclusive breastfeeding for the first six months of life, and continued breastfeeding together with adequate and safe complementary feeding for two years, is critical for physical well‐being, cognitive development and child survival. Exclusive breastfeeding until six months of age could reportedly prevent more than 800 000 child deaths worldwide every year 1. In Bangladesh, around 90% of mothers are still breastfeeding their babies at one year of age and 88% are still breastfeeding at around two years 2. Despite breastfeeding promotional activities over the last two decades, the prevalence of exclusive breastfeeding at four to five months of age has remained relatively small, at 32% 2. Rapid urbanisation and female employment could partly explain the introduction of other foods before the age of six months. Many women in rural areas, and those who are not employed, introduce milk or semisolid foods to children at less than three months of age. Earlier studies reported that a high proportion of the mothers felt that they did not have enough breastmilk 3. Peers and other family members, such as mothers‐in‐law or elderly family members, could also influence perceptions of insufficient breastmilk. Studies in Bangladesh have documented a significant increase in exclusive breastfeeding as a result of community‐based peer counselling 4 or breastfeeding counselling in hospitals 5. A systematic review and meta‐analysis confirmed that peer counselling enhanced the duration of exclusive breastfeeding, although the contextual influence of a formula‐feeding tradition might have decreased the effect 6. A wide range of counselling and breastfeeding promotion activities have been shown to increase the duration of exclusive breastfeeding 7. Continuous, repeated interactive sessions with counsellors in the health system were reported to be effective by a systematic review 8. Despite this, our knowledge is limited regarding the optimal timing, dose and mode of counselling that could be scaled‐up as an integrated part of the continuum of care provided by the health system to mothers and their children 8. Furthermore, it has been questioned whether underweight mothers are less able to breastfeed their infants successfully 9. A review of multiple micronutrient supplements provided to breastfeeding women was inconclusive regarding the effects on breastfeeding performance due to the lack of good‐quality studies 10. To the best of our knowledge, there have been no previous studies that have evaluated the effect of prenatal food and multiple micronutrient supplementations on later breastfeeding performance. The Maternal and Infant Nutrition Interventions (MINIMat) was a randomised trial in Matlab in rural Bangladesh (International Standard Randomised Control Trial Number: ISRCTN16581394). It was designed to examine the effect of combined food and micronutrient interventions on haemoglobin, birthweight and infant survival 11. An exclusive breastfeeding counselling intervention was nested into the trial and was provided to consenting mothers at around week 30 of pregnancy. We postulated that in a population where being underweight was common, the early timing of prenatal food supplements combined with multiple micronutrients would enhance the effect of exclusive breastfeeding counselling. The aim was to assess the effect of eight breastfeeding counselling sessions from late pregnancy to early infancy on the prevalence and duration of exclusive breastfeeding and to evaluate whether this effect was further increased by an early invitation to prenatal food supplements versus the usual timing and supplements with multiple micronutrients instead of the standard iron and folate combination.\n\nBODY.METHODS:\nThe MINIMat trial was conducted in Matlab, a rural subdistrict 57 km south‐east of Dhaka, the capital of Bangladesh. The International Centre for Diarrhoeal Diseases Research, Bangladesh (icddr,b), maintains the Health and Demographic Surveillance System in Matlab that monitors demographic and selected health information in the area. A total of 4436 pregnant women were enrolled from November 2001 to October 2003 and were randomised to the different nutritional interventions. The infants born to these women have been followed since birth. Written, informed consent was obtained from all of the participating mothers, and the study was approved by the Research and Ethical Review Committees of icddr,b.\n\nBODY.METHODS.STUDY DESIGN:\nThe MINIMat trial had a factorial design with two food supplement alternatives and three micronutrient supplements. At around week 30 of pregnancy, consenting women were allocated to breastfeeding counselling or received the usual antenatal healthcare messages. This study focuses on the effect of these interventions on the prevalence and duration of exclusive breastfeeding.\n\nBODY.METHODS.RANDOMISATION:\nIn the MINIMat trial, all pregnant women were individually randomised to one of the food supplement groups and to one of the three micronutrient interventions, as previously described 11. The following eligibility criteria had to be met for enrolment: viable foetus, gestational age of less than 14 weeks by ultrasound examination, no severe illness and written consent for participation. At around nine weeks of pregnancy, women were randomly invited to receive food supplements at around nine weeks of gestation or to the standard programme where they could start the supplements when they chose, usually at around 20 weeks of gestation. Food supplements of 600 kcal per day was made available through community nutrition centres six days per week and continued up to the end of pregnancy. At 13 weeks of gestation, women started to receive the randomly allocated micronutrient supplementations that continued for their entire pregnancy: (i) 30 mg Fe fumarate and 400 μg folate, (ii) the standard 60 mg Fe fumarate and 400 μg folate or (iii) multiple micronutrients with 15 micronutrients including 30 mg Fe fumarate and 400 μg folate. At around 30 weeks of gestation, simple random sampling was used to allocate consenting pregnant women to receive either counselling on exclusive breastfeeding or to receive the usual health message delivered by the regular icddr,b health staff during the antenatal clinic visits. The micronutrient supplementation was double‐blinded, while the food supplementation and the later breastfeeding counselling were randomly allocated but not blinded. An independent statistician performed all the randomisation procedures using a computer program. Randomisation lists were generated that included participant identity codes of the Health and Demographic Surveillance System and codes for the allocated interventions. Field staff, supervised by study supervisors, carried out the practical allocation to the different interventions. There were no deviations from the randomly decided allocations. Randomisation codes were safely kept at the administrative office of icddr,b and were not accessed until after performing the intent‐to‐treat analyses of the primary outcomes.\n\nBODY.METHODS.EXCLUSIVE BREASTFEEDING INTERVENTION:\nNine women were recruited and trained as breastfeeding counsellors. Five were recruited at the start of the study, and another four joined after six months. They all lived in the local community, the Matlab study area, were married with at least one child, had breastfeeding experience and had a bachelor's degree equivalent to 14 years of schooling. One of the authors (IK) and one senior breastfeeding counsellor trained the other counsellors using a 40‐hour World Health Organization (WHO) and United Nations Children's Fund Breastfeeding Counselling Training module, which had been translated into the local Bangla language and adjusted to the local context. This training module had been successfully used in previous studies 4. The training was provided in daily four‐hour sessions over ten days. Counselling skills were taught using demonstrations and role‐play and included listening to mothers, learning about their difficulties, assessing the position and attachment of babies during breastfeeding, building mothers' confidence, giving support and providing relevant information and practical help when required. The training also included practical sessions with pregnant women and mothers with infants. Two senior breastfeeding counsellors with at least six years of experience in counselling and one of the authors (IK) supervised the fieldwork and provided practical help at fortnightly sessions or via cell phones when required. All women received basic healthcare messages, as is the usual practice in this region of Bangladesh. The women allocated to breastfeeding counselling received eight sessions: two sessions during the last trimester of pregnancy, one session in the seven days after delivery and five sessions at monthly intervals up to six months after childbirth. Counsellors were free to make additional contact if required. Counselling was given individually at home, but key family members were also included. The duration of each counselling visit was typically 20–40 minutes, depending upon the mother's lactation stage and her individual needs. Usually, the first two to three visits were longer, to build the mothers' confidence, and the later counselling visits were shorter as they aimed to just give support to mothers and reinforce the health messages. The women in the usual health message group received the messages on breastfeeding practices that were provided by the health staff of icddr,b when pregnant mothers visited the subcentres for their regular antenatal visits. These messages included the benefits of colostrum, advice on exclusive breastfeeding for four to six months and the recommended starting of complementary feeding from four to six months along with continuing breastfeeding for two years.\n\nBODY.METHODS.OUTCOME DATA:\nTrained female interviewers collected data on infant feeding status every month up to 12 months of age. Data collection interviews were carried out one to three days before the counselling visits. A precoded semistructured feeding chart was developed, and feeding during the last 24 hours was recorded. Furthermore, the mother was asked whether the baby had received anything else besides breastmilk during the last month. If the mother had given the infant any other food or liquid than breastmilk for two consecutive days or more during the last month, this information was considered when classifying the feeding status and coded as partially breastfed.\n\nBODY.METHODS.FEEDING CLASSIFICATION:\nThe WHO definitions were used. To be classified as exclusive breastfeeding during the last month, only breastmilk could be given, not even water. Oral rehydration solution, liquid medicines and vitamins were allowed within the definition of exclusive breastfeeding.\n\nBODY.METHODS.OTHER DATA:\nMaternal nutritional status and information regarding place and mode of delivery were extracted from the MINIMat databases 11. The socio‐economic characteristics of the households were determined using a continuous household asset score previously generated for this population, including data on land ownership, the construction materials used for house walls and the ownership of household assets. Data on the presence of such characteristics were analysed by principal component analysis, and a score was generated for each household, according to the principles that have been used by the World Bank and several other organisations 12.\n\nBODY.METHODS.DATA QUALITY AND MANAGEMENT:\nAn additional team cross‐checked one‐tenth of the interviewers' scheduled visits to ensure the quality of the collected data. The questionnaires were checked daily, and, if the information was incomplete or not clear, a supervisor returned to the home the next day to complete and clarify the information. Data were stored in relational databases and further checked for any inconsistencies that were corrected in comprehensive data cleaning procedures.\n\nBODY.METHODS.STATISTICAL METHODS:\nThe chi‐square test was used to compare the proportions receiving colostrum and the effect of the randomised breastfeeding intervention, namely the breastfeeding counselling versus the usual health message, on exclusive breastfeeding prevalence at four and six months. The total duration of exclusive breastfeeding was assessed in an intent‐to‐treat analysis, by including every participant in the analysis according to their initial randomisation. The analyses of the duration of exclusive breastfeeding were performed by analysis of variance (ANOVA). Interactions between prenatal food and micronutrient groups and the breastfeeding counselling intervention were analysed using product terms in ANOVA. First, a three‐way interaction was examined as follows: exclusive breastfeeding counselling × food supplementation × micronutrient supplements. If this was not statistically significant, two‐way interactions were examined as follows: exclusive breastfeeding counselling × food supplementation and exclusive breastfeeding counselling × micronutrient supplements. The significance level for interactions was set at p = 0.10.\n\nBODY.METHODS.SAMPLE SIZE:\nThe sample size for the MINIMat trial had been calculated for one of the primary outcomes, that is the effect of food and micronutrient supplements on birthweight. The sample size available for this study provided a power of 0.90 (type II error) and a probability of 0.05 (type I error) for a 6% difference in the prevalence of exclusive breastfeeding for the counselling group compared to the usual health message group. Such a difference was much smaller than those observed in previous studies. The sample size available for this study also provided a power of 0.88 (type II error) and a probability of 0.05 (type I error) for a 10% difference in the prevalence of exclusive breastfeeding for simple effect comparisons between any two of the six groups defined by the combination of the two counselling groups and the three micronutrient groups.\n\nBODY.RESULTS:\nA total of 3188 mothers were randomised either to receive exclusive breastfeeding counselling from the counsellors or to receive the usual health messages from the Matlab regular health staff. The latter group served as the control. After omissions, 1387 mother–infant pairs in the counselling group and 1402 mother–infant pairs in the usual health message group completed six months of follow‐up. The distribution of pregnant women and their children in the exclusive breastfeeding counselling groups and the numbers lost to follow‐up are shown in Figure 1. The main reason for the women's lack of availability at the time of randomisation, at week 30, was the custom for pregnant women to visit their parents' home at this time. Figure 1Study flow chart. The distribution of pregnant women and their children in the exclusive breastfeeding (EBF) counselling groups and the numbers lost to follow‐up during the Maternal and Infant Nutrition Interventions in Matlab (MINIMat) trial. Mothers in the randomisation groups were similar at baseline (Table 1). The average age of the mothers was 26 years, their mean body weight was 45 kg, and their average height was 150 cm. Socio‐economic variables were similar across groups. The mean birthweights were 2690 and 2697 g and the birth lengths were 47.7 and 47.6 cm in the breastfeeding counselling and usual health message groups, respectively. About 57% and 56% had been delivered at home. The mean and standard deviation (SD) gestational age at birth was 38.7 ± 1.8 weeks and 38.7 ± 1.7 weeks in the breastfeeding counselling and usual health message groups, respectively. Table 1 Baseline characteristics of mothers and infants at birth in the two intervention groups Characteristic Breastfeeding counselling group (n = 1387) Usual health message group (n = 1402) \n Maternal \n Age (years) 25.8 ± 6.0 25.7 ± 5.8 Education (mean number of years completed in formal education) 7.1 ± 2.9 7.2 ± 2.9 Asset score −0.10 ± 2.30 0.06 ± 2.33 \nAsset score \n(n/n % in lowest quintile)\n 291/1417 (20.5) 278/1428 (19.5) \nAsset score \n(n/n % in highest quintile)\n 260/1417 (18.3) 303/1428 (21.2) Height (cm) 149.7 ± 5.3 149.8 ± 5.4 Weight at 8 weeks of gestation (kg) 45.1 ± 6.8 45.4 ± 6.9 BMI (at 8 weeks of gestation) 20.1 ± 2.7 20.2 ± 2.7 Place of delivery (n/n % at home) 808/1417 (57.0) 795/1428 (55.7) Type of delivery (n/n % Caesarean section) 63/1417 (4.4) 59/1428 (4.1) \n Infant \n Sex (n/n % female) 684/1417 (48.3) 699/1428 (48.9) Birthweight (g) 2690 ± 415 2697 ± 409 Birth length (cm) 47.7 ± 2.2 47.7 ± 2.1 Data are mean (SD) unless indicated to be n/n (%). John Wiley & Sons, Ltd In the breastfeeding counselling group, 95.5% of the babies had received colostrum as the first food, compared with 85.8% in the usual health message group (p < 0.001). By 72 hours, almost all babies in both groups had been breastfed. The median duration of exclusive breastfeeding was longer in the breastfeeding counselling group (135 days, 95% CI: 131–139) than in usual health message group (75 days, 95% CI: 68–82) – a difference of 60 days (p < 0.001). At four months, 69.0% (95% CI: 66.1–71.9) of the breastfeeding counselling group were being exclusive breastfed, as were 46.6% (95% CI: 42.8–50.4) in the usual health message group, while the corresponding figures at six months were 15.3% (95% CI: 10.4–20.1) and 6.4% (95% CI: 1.3–11.5), respectively. There was no statistically significant three‐way interaction between breastfeeding counselling, food supplements and micronutrient supplements. The timing of the food supplements did not influence the effect by counselling on the duration of exclusive breastfeeding, with a p for interaction of 0.115 (Table 2). Table 2 Analysis of breastfeeding counselling intervention with food and micronutrient supplementations on duration of exclusive breastfeeding Interventions n Mean duration 95% CI p value for interaction Analysis of breastfeeding counselling × food supplementation 0.115 BFC + Early food 699 108.8 104.3–113.3 BFC+ Usual food 688 113.7 109.2–118.1 UHM+ Early food 708 77.3 72.8–81.8 UHM+ Usual food 694 75.0 70.5–79.5 Analysis of breastfeeding counselling × micronutrient supplementation 0.064 BFC+ Fe30 451 111.4 105.8–116.9 BFC+ MMS 447 111.2 105.6–116.8 BFC+ Fe60 489 111.1 105.8–116.4 UHM+ Fe30 466 73.3 68.0–78.6 UHM+ MMS 467 83.7 78.1–89.2 UHM+ Fe60 469 71.6 66.0–77.1 Interventions: BFC = breastfeeding counselling; UHM = usual health message; Early food = early invitation to food supplementation (around week 9), Usual food = usual timing of start of food supplementation (around week 20), Fe30 = 30 mg Fe and folic acid, Fe60 = 60 mg Fe and folic acid, MMS = multiple micronutrients. John Wiley & Sons, Ltd Multiple micronutrient supplements did not further increase the effect of counselling on the duration of exclusive breastfeeding (Table 2). In the group of mothers who did not receive counselling, multiple micronutrient supplements were associated with longer exclusive breastfeeding of 12 days (p = 0.003).\n\nBODY.DISCUSSION:\nWe have shown that one‐to‐one breastfeeding counselling with eight sessions from pregnancy to six months after delivery with trained local counsellors resulted in higher prevalence and longer duration of two months of exclusive breastfeeding. The comparison group received the usual health messages that also included some breastfeeding promotion. Data were longitudinally collected by interview at home every month, reducing the risk of recall bias. We also conducted a validation study using the deuterium dilution technique of mothers' reported feeding behaviour and found a strong association between the questionnaire‐based information and the validation data, with positive predicted value of 0.84 13. As shown in reviews of breastfeeding counselling interventions, continued counselling, support over time and contextual factors influence the magnitude of effects 6, 7, 8. In a previous peer‐counselling trial in urban Dhaka, the dose of the intervention, namely the number of counselling sessions, was almost double the number in the present study, and the size of the effect was larger 4. The present study showed that a lower number of contacts, close to the number of contacts a pregnant and delivering woman usually has with the regular maternal and infant health services, also resulted in a substantial increase in the duration of exclusive breastfeeding. The optimal number of counselling sessions across late pregnancy and early infancy is not known 6. Importantly, the training provided in this study emphasised the interactive character of the sessions 8 and the continuity of contact between the counsellor and the mother. The total duration of exclusive breastfeeding in this trial may also have been influenced by the previous WHO guideline of exclusive breastfeeding four to six months that was still Bangladesh government policy at the time of the study. Previous studies have asked whether marginally nourished women have the needed lactational capacity to breastfeed. A study in Bangladesh found evidence that the volume and quality of breastmilk in marginally nourished women may still be sufficient to ensure the healthy growth of their infants 9. A Cochrane review departed from the fact that many lactating women in low‐income settings suffer from multiple micronutrient deficiencies that might impair lactation performance. The authors found no trials, and only a few other studies, that addressed the possible impact of multiple micronutrients on breastfeeding outcomes and the result was nonconclusive 10. In this study, we hypothesised that prenatal multiple micronutrient supplementation versus iron–folate along with breastfeeding counselling would further increase the duration and rates of exclusive breastfeeding and providing prenatal food supplements earlier would further influence the effect in a positive way. In the group randomised to receive breastfeeding counselling, neither the multiple micronutrients nor the timing of the prenatal food supplementation affected exclusive breastfeeding duration. In the control group that was randomised to receive the usual health message, the allocation of multiple micronutrients was associated with longer duration of 12 days of exclusive breastfeeding. Even if this is valid, the public health importance of such a small difference might be limited.\n\nBODY.CONCLUSION:\nTo conclude, the relatively limited number of eight counselling sessions with trained counsellors from pregnancy to the first part of infancy increased exclusive breastfeeding by two months. This is a 'dose' of the intervention that could be part of regular antenatal and child health services in order to achieve better adherence to the recommended duration of exclusive breastfeeding 1. However, the timing of a prenatal food supplementation and different micronutrient alternatives did not increase the effect of counselling. Among women who did not receive breastfeeding counselling, multiple micronutrients were associated with slightly longer exclusive breastfeeding that most likely may be of a small public health importance.\n\nBODY.CONFLICTS OF INTEREST:\nThe authors declare that they have no competing interests.\n\nBODY.FUNDING:\nThe MINIMat research study was funded by icddr,b, the United Nations Children's Fund, the Swedish International Development Cooperation Agency, the UK Medical Research Council, the Swedish Research Council, the Department for International Development, the Japan Society for the Promotion of Science, the Child Health and Nutrition Research Initiative, the Uppsala University and United States Agency for International Development. The funders had no role in any aspect of the study design or resulting manuscript.\n\nQuestion: Compared to receive the usual health messages from the Matlab regular health staff what was the result of receive exclusive breastfeeding counselling from the counsellors on The median duration of exclusive breastfeeding?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1118	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Social Presence and Use of Internet-Delivered Interventions: A Multi-Method Approach\n\n ABSTRACT.OBJECTIVE:\nInternet-delivered interventions can effectively change health risk behaviors and their determinants, but adherence to intervention websites once they are accessed is very low. This study tests whether and how social presence elements can increase website use.\n\nABSTRACT.METHODS:\nA website about Hepatitis A, B, and C virus infections was used in a preparatory lab-based eye-tracking study assessing whether social presence elements attract participants' attention, because this is a prerequisite for affecting website use. In the following field study, 482 participants representative of the Dutch population were randomized to either a website with or a website without social presence elements. Participants completed a questionnaire of validated measures regarding user perceptions immediately after exposure to the website. Server registrations were used to assess website use.\n\nABSTRACT.RESULTS:\nParticipants in the experimental condition focused on the social presence elements, both in terms of frequency (F(1, 98) = 40.34, p<.001) and duration (F(1, 88) = 39.99, p<.001), but did not differ in website use in comparison with the control condition; neither in terms of the number of pages visited (t(456) = 1.44, p = .15), nor in terms of time on the website (t(456) = 0.01, p = .99).\n\nABSTRACT.CONCLUSIONS:\nAdding social presence elements did not affect actual use of an intervention website within a public health context. Possible reasons are limited attention for these elements in comparison with the main text and the utilitarian value of intervention websites.\n\nBODY.INTRODUCTION:\nInternet-delivered interventions can effectively change health risk behaviors and their determinants [1], but the actual use of these interventions by the target group once they access the website is very low [2]. Eysenbach [3] even defined the \"law of attrition\", which considers high attrition rates as a natural and typical feature of Internet-delivered interventions. For example, server statistics of an intervention promoting heart-healthy behaviors showed that 285,146 visitors from unique IP addresses accessed the home page in a 36-month period, but 56.3% of them left the intervention website within 30 seconds [4]. This finding touches upon a critical issue in Internet-delivered interventions: how can they ever have a public health impact if people only briefly use the actual intervention? It is therefore relevant and necessary to focus on factors related to the use of an Internet-delivered intervention once people arrive at the intervention website (i.e., website use) [5]. These factors relate to the visitor (e.g., people's motivation to be healthy [6], [7]) as well as the intervention website (e.g., offering tailored information [8], [9]). Not only is the content of the website important [10], but also the specific characteristics of the website itself. The current study aims to systematically manipulate a website characteristic – i.e., social presence – and link this to (1) website use and (2) user perceptions as the working mechanisms behind this possible effect of social presence. The rationale behind this aim is explained in the follow paragraphs, resulting in hypotheses to be tested in the current study. The focus of the current study is on social presence, which can be seen as the extent to which a medium is perceived to convey a feeling of human contact, sociability, and sensitivity [11]. This is realized by adding social presence elements: presenting human images [12] and testimonials [13] in which people share their experiences and ideas regarding the information presented on the website with others. Previous studies revealed that adding these social presence elements increases perceived social presence and positively affects attitude towards shopping websites [14] as well as intention to use them [13]. Two issues remain unclear, however. First, whether social presence also has added value in a public health context. Second, whether the positive effect regarding attitude and intention to use also hold when looking at the actual behavior (i.e., website use) instead of its precursors. Given that intention is the most important predictor of actual behavior [15], this is hypothesized to be the case. Thus, social presence is expected to increase website use in a public health context (Hypothesis 1). What are the working mechanisms behind this possible effect of social presence on website use? The main idea is that social presence results in a positive user experience, which increases website use. User experience refers to what a person thinks and feels during and after being exposed to a website [16] and is deemed even more important than usability, which only concerns ease of use [17]. User experience consists of both cognitive perceptions (e.g., efficiency, effectiveness) and affective perceptions (e.g., enjoyment) [18]. Efficiency refers to easy search and access of information provided and effectiveness refers to the quality of that information (e.g., in terms of relevance) [19]. These cognitive perceptions have parallels with perceived ease of use and perceived usefulness in the technology acceptance model, but are applicable in a broader context [20]. The affective perceptions of user experience are often referred to as enjoyment\n[21], [22]. Active trust refers to the confidence in acting on the provided information on a website, which can result in increased website use [23]. Efficiency, effectiveness and enjoyment can be expected to be positively associated with website use and these associations are hypothesized to be partly mediated by active trust, which is in line with the limited evidence that is currently available [24], [25] (Hypothesis 2). Previous studies investigating social presence and user perceptions consistently demonstrated that social presence positively affects perceptions of both effectiveness and enjoyment regarding shopping websites [13], [14], [26]. The current study extends previous studies by including a measure of interest besides enjoyment, because this is a motivational factor that \"guarantees the person's engagement\" [27]. Although interest is sometimes defined as feelings of enjoyment [28], interest and enjoyment differ in critical ways [29]. Experiments using several kinds of stimuli (e.g., random polygons, poetry, and experimental paintings) indicate that enjoyment is not a necessary condition for interest [30]. The two antecedents of interest are, according to Silvia [29], appraisal of coping potential (e.g., that people can deal with the presented information due to the use of everyday language) and appraisal of novelty-complexity (e.g., due to the use of imagery). The previously discussed social presence elements are in line with Silvia's [29] suggestion to use imagery (e.g., human images) and everyday language (e.g., testimonials) to positively affect appraisal of novelty-complexity and coping potential respectively, resulting in increased interest. Moreover, increased interest results in spending more time reading information on a topic [31]. An initial hypothesis would therefore be that interest due to adding social presence elements increases website use (Hypothesis 3a). However, the increased complexity due to adding social presence elements can also have a negative impact. Previous studies demonstrated that complexity has a negative effect on attitude towards a website and therewith on intention to use [32], [33], pleading for simplicity of websites [34]. An alternative hypothesis would therefore be that adding social presence elements decreases website use because of increased complexity (Hypothesis 3b).\n\nBODY.INTRODUCTION.WEBSITE:\nA website about Hepatitis A, B, and C virus (HAV, HBV, HCV) infections was used to test the effect of adding social presence elements on website use and the working mechanisms behind this possible effect. These infections all affect the liver, but there are differences in terms of mode of transmission, consequences, and prevention. Besides the home page, the website consisted of four pages per Hepatitis virus. The first page introduced the virus briefly and the other three pages outlined transmission, consequences, and prevention respectively. This resulted in a total of twelve pages of website content (for all virus types) besides the home page. The content for these pages was based on information from the Dutch National Hepatitis Centre. The content was text-based, purely informative, non-tailored, and very brief (i.e., 5–10 lines of text per page). Use of this website has been proven to result in increasing practical knowledge regarding Hepatitis [25], which is currently very low in the Netherlands [35]. The experimental website for this study was created by adding social presence elements to the website previously used, which served as the control website in this study.\n\nBODY.INTRODUCTION.SOCIAL PRESENCE ELEMENTS:\nSocial presence elements were based on previous studies and consisted of adding human images (of people varying in age and gender) [12] and testimonials [13] in which people shared their experiences and ideas regarding the information presented on the website with the visitor. The above social presence elements were added to the home page and three pages per virus type that outlined transmission, consequences, and prevention respectively. Therefore, a total number of ten pages contained social presence elements. The number of pages of both website versions were identical. Previous research proved that JPEG file sizes are a good proxy for complexity of web pages [36]. File sizes are not only related to complexity, but also to page size (i.e., resolution). Therefore, screenshots of pages to which social presence elements were added in the experimental website, were captured for both websites at the same resolution (1024×768 pixels). The screenshots of the experimental website were – according to the JPEG file sizes – more complex in comparison with the control website (218 vs 137 kB, t(18) = 22.42, p<.001), which is a presumption in Hypothesis 3b (i.e., adding social presence elements increases complexity).\n\nBODY.INTRODUCTION.PREPARATORY STUDY:\nThe aim of the preparatory study was to assess whether social presence elements attract participants' attention, because this is a prerequisite for them to affect user perceptions and (intention to) use. A previous study – based on self-reports – found a positive relationship between attention and user perceptions [37]. Eye-tracking, however, is a more suitable method to assess the course of attention over time [38]. This preparatory study built upon previous studies that successfully applied eye-tracking with regard to perceptions of health-related information [39] and websites [12]. There is general agreement on the strong association between eye movements and attention [40]. The idea behind eye-tracking is that saccadic eye movements are associated with shifts in attention. Fixations refer to the periods between saccadic eye movements in which gaze is held almost stationary.\n\nBODY.METHODS.PARTICIPANTS:\nParticipants were a convenience sample of undergraduate students that received course credits for their participation in this preparatory study. Participants were screened to ensure normal or corrected vision, and those wearing hard contact lenses or eyeglasses were excluded from participation, because this can result in difficulties in capturing eye movements. A total of 24 participants were randomized (16 women, 8 men). Mean age of the sample was 20.1 years (SD = 1.8). Participants were recruited through a research panel of a Dutch Internet research agency; therefore, they could be considered computer literate. From this panel, a stratified sample of 982 potential participants was invited to participate in a study about Hepatitis through email. Informed consent was obtained online, which is the regular procedure for this research panel. This sample was representative of the Dutch Internet population above 18 years, taking into account gender, age, and level of education.\n\nBODY.METHODS.DESIGN AND PROCEDURE:\nAfter explaining the study procedure and signing informed consent, participants were seated approximately 25 inches from a computer screen. The laboratory room was artificially lit and there was no influx of sunlight. First, the eye-tracker system (more detailed information in the Apparatus section) was calibrated. Subsequently, participants were told that we were interested in their opinion to improve a website and that they could freely explore this website. Participants were randomly assigned to two conditions. The control condition consisted of the existing website as used in a previous study [25]. The experimental condition added social presence elements to this website (as described above). A brief questionnaire had to be completed immediately following exposure to the website and consisted of measures regarding interest and perceived social presence as a manipulation check. It was stressed that there were no right or wrong answers. Participants were randomly assigned to either the control condition or the experimental condition (Figure 4). Both conditions were similar to those in the preparatory study. The pre-test (i.e., before being exposed to the website) consisted of a Hepatitis knowledge questionnaire. After the pre-test, participants were directed to their assigned version of the website. Participants were asked to base their opinion about the website on their first impression and were told they could freely explore the website until they started completing the post-test (immediately after visiting the website). The objective was not to force participants to thoroughly study the website, but to mimic a real-life situation in which time and opportunity to invest in the website is limited [4]. The post-test consisted of measures regarding user perceptions and perceived social presence as a manipulation check. For these measures, it was stressed that there are no right or wrong answers. One week later, participants were invited to complete the follow-up measure, which was the same as the pre-test (i.e., the Hepatitis knowledge questionnaire). The follow-up measure was added to test whether participants did not only click through the website but actually processed and memorized its content (i.e., by looking at both within- and between-group differences regarding Hepatitis knowledge over time). 10.1371/journal.pone.0057067.g004Figure 4Flowchart of study design and attrition. Participants received an incentive (i.e., credit points for panel members) to participate in the study, which represented a value of € 2.50. Panel members can save credit points over time, which can be exchanged for online vouchers valid in several stores in the Netherlands. Relevant ethical safeguards were met with regard to the participant confidentiality and consent.\n\nBODY.METHODS.ETHICS STATEMENT:\nThe Simon Fraser University Research Ethics Board granted ethical approval (file number: 2012s0168).\n\nBODY.METHODS.APPARATUS:\nThe eye-tracker system used was Applied Science Laboratories Model 504 with head tracking integration. Eye movements were processed using an autofocus eye camera mounted on a optics mechanism (max. 100° pan, 25° tilt), which was positioned under the computer screen. The camera has eye illumination that consists of a ring of near-infrared light-emitting diodes. The sampling rate was 60 Hz and the measurement error was <1.0°. Participants wore a headband with a mounted sensor, which allowed tracking of head movements without loss of eye image. This permitted participants to move their heads in a relatively natural manner. Gaze Tracker software was used to capture and process eye-tracking data (measures are explained in the following section).\n\nBODY.METHODS.MEASUREMENTS:\nThe following measurements were used within the preparatory study. The following measurements were used within the main study.\n\nBODY.METHODS.MEASUREMENTS.ATTENTION:\nAttention is assessed by the number of fixations and total fixation duration in milliseconds (ms) within each area of interest on the website as defined by rectangular regions called lookzones. There were two lookzones on each page; the main text and the social presence elements (Figure 1). The main text lookzone was similar for both conditions. The threshold for minimal duration for a fixation was set at 50 ms [40]. 10.1371/journal.pone.0057067.g001Figure 1Example of lookzones on a page (image has been blurred to ensure anonymity).\n\nBODY.METHODS.MEASUREMENTS.INTEREST:\nIn line with Turner and Silvia [30], two items measured interest (uninteresting-interesting and boring-engaging; alpha = .72) on a 7-point Likert scale.\n\nBODY.METHODS.MEASUREMENTS.PERCEIVED SOCIAL PRESENCE:\nFive items (e.g., \"There is a sense of human warmth in the website\"; alpha = .87) were used to measure perceived social presence as a manipulation check [12], [41]. Items were answered on a 7-point Likert scale ranging from (1) 'strongly disagree' to (7) 'strongly agree'. Similar to the preparatory study, five items (alpha = .95) were used to measure perceived social presence as a manipulation check.\n\nBODY.METHODS.ANALYSES:\nData from participants who encountered technical problems (e.g., difficulties in capturing eye movements) or artifacts (e.g., too many blinks) resulting in >25% missing eye-tracking data were excluded from the analyses regarding attention (n = 5). Mixed models were used to test for differences in the measures of attention, using page as a within-subject factor and condition as a between-subject factor. Two-tailed effect sizes (i.e., Cohen's d), given the means, standard deviations, and sample sizes per condition, were used to test differences between conditions regarding interest and perceived social presence. Effect sizes were divided into the following five levels: trivial (Cohen's d≤.2), small (>.2), moderate (>.5), large (>.8), and very large (>1.3) [42].\n\nBODY.RESULTS:\nParticipants in the experimental condition focused on the social presence elements, both in terms of frequency (F(1, 98) = 40.34, p<.001) and duration (F(1, 88) = 39.99, p<.001), while participants in the control condition paid hardly any attention to these lookzones. There were, however, no differences between conditions in terms of frequency (F(1, 101) = 1.59, p = .21) and duration (F(1, 90) = 0.13, p = .72) of fixations on the main text. Figures 2 and 3 indicate that participants in the experimental condition were attracted by the social presence elements, but this did not affect their attention to the main text. Participants in the experimental condition scored higher on interest (M = 4.7 vs. 4.2, Cohen's d = 0.32) and perceived social presence (M = 4.6 vs. 3.1, Cohen's d = 1.22) in comparison with the control condition. These effects can be classified as small and very large respectively. 10.1371/journal.pone.0057067.g002Figure 2Number of fixations per page. 10.1371/journal.pone.0057067.g003Figure 3Total fixation duration (ms) per page.\n\nBODY.RESULTS.MAIN STUDY:\nThe preparatory study demonstrated that the social presence elements attract participants' attention and increase perceived social presence, without decreasing attention for the main text. The aim of the main study was to test the proposed conceptual model and associated hypotheses.\n\nBODY.METHODS.MEASUREMENTS.HEPATITIS KNOWLEDGE QUESTIONNAIRE:\nFifteen true/false items (including a 'don't know' option) about transmission, consequences, and prevention of HAV, HBV and HCV infections were used to assess Hepatitis knowledge. The sum score of all correctly answered items was used in the analyses. The correct answer to these items was available on the website. The items concerned practical knowledge and were used in a previous study [35].\n\nBODY.METHODS.MEASUREMENTS.WEBSITE USE:\nServer registrations were used to assess website use [43], [44] which was operationalized by the number of pages visited (ranging from 0 to 12). Furthermore, time on the website was tracked to detect whether participants were simply clicking from one page to the other and therefore artificially boosting the number of pages visited.\n\nBODY.METHODS.MEASUREMENTS.USER PERCEPTIONS:\nSets of three items each were used to measure efficiency (e.g., \"I was able to access the information quickly on this website\"; alpha = .97), effectiveness (e.g., \"The website provided me with relevant information about ...\"; alpha = .92), enjoyment (e.g., \"I found my visit to this website enjoyable\"; alpha = .97), and active trust (e.g., \"I would act upon the information presented on this website if needed\"; alpha = .89). Items were answered on a 7-point Likert scale ranging from (1) 'strongly disagree' to (7) 'strongly agree'. These measures were previously used and validated in the Dutch language [24]. Similar to the preparatory study, two items were used to measure interest (alpha = .82).\n\nBODY.ANALYSES:\nFirst, independent samples t-tests and chi-square tests were conducted to test whether there was selective dropout or differences in dropout between conditions. Subsequently, independent-samples t-test were conducted to test for differences between conditions in terms of perceived social presence and both measures of website use. For this analysis, time on website was log-transformed to meet the assumption of normality. A repeated measures analysis of variance (ANOVA) was conducted to test for differences in Hepatitis knowledge between conditions over time. Multivariate ANOVAs were conducted to test for differences in user perceptions between conditions. All these analyses were conducted using Predictive Analytics SoftWare Statistics 18.0 (International Business Machines Corporation, Armonk, NY). Second, using Mplus 5 (Muthén & Muthén, Los Angeles, CA), structural equation models (SEMs) using all available data were constructed to test the hypothesized conceptual model. Website use—a latent construct made up from number of pages visited and time on the website—was regressed on efficiency, effectiveness, enjoyment, interest, and active trust, which were all latent constructs using the items described above. Active trust was regressed on efficiency, effectiveness, and enjoyment. Effectiveness, enjoyment, and interest were regressed on social presence. Subsequently, (1) non-significant paths were left out of the conceptual model for the sake of parsimony, and (2) additional paths were added to the conceptual model based on significant modification indices. The latter was done to explore whether unanticipated relationships might explain variance in website use (which was not the case). A level of significance of p<.05 was used for the relationships within the model. Model fit indices used were the comparative fit index (CFI), the Tucker-Lewis index (TLI), the root mean square error of approximation (RMSEA), and the standardized root mean square residual (SRMR). Both CFI and TLI are goodness-of-fit indices where larger values signal better fit. Values over .95 indicate close fit. The RMSEA and SRMR are goodness-of-fit indices where larger values signal worse fit. Indicators of close fit are, respectively, RMSEA ≤.05 and SRMR ≤.09 [45], [46].\n\nBODY.RESULTS.PARTICIPANTS:\nOf those 982 potential participants that were invited, 458 participated in the study (47%). Half of the participants were female and the mean age of participants was 49 years (SD = 16). Of the participants, 30% had a low level of highest completed education (equivalent to primary school/junior high school), 38% an intermediate level (equivalent to senior high school/junior college), and 32% a high level (equivalent to college/university). Those 458 that participated were invited to complete the follow-up measure and 402 of them did so (88%). There was no selective dropout regarding gender (χ2 (1, N = 458) = 0.3, p = .57), level of education (χ2 = 5.0, p = .08), or Hepatitis knowledge at baseline (t(456) = 1.83, p = .07). Furthermore, dropout did not differ between the two conditions (χ2 (1, N = 458) = 3.2, p = .08). Those who dropped out, however, were younger (M = 43 vs 50 years, (t(456) = 3.19, p = .002).\n\nBODY.RESULTS.MANIPULATION CHECK:\nParticipants in the experimental condition scored higher on perceived social presence than the control condition (M = 4.9 vs. 4.4, t(456) = 4.11, p<.001, Cohen's d = 0.38), which indicates that the manipulation did succeed. This effect can be classified as small.\n\nBODY.RESULTS.WEBSITE USE AND HEPATITIS KNOWLEDGE:\nParticipants in the experimental condition did not differ in website use in comparison with the control condition; neither in terms of the number of pages visited, nor in terms of time on the website (Table 1). Effect sizes were trivial. Thus, there is no support for Hypothesis 1. The increase in Hepatitis knowledge between pre-test and post-test did not differ between both conditions (F(1, 400) = 0.72, p = .40), but there was a significant increase regarding Hepatitis knowledge between pre-test and post-test across conditions (M = 6.4 vs. 8.3, F(1,400) = 172.98, p<.001, Cohen's d = 0.65), which can be defined as a moderate effect size. 10.1371/journal.pone.0057067.t001 Table 1 Differences in website use between conditions. Variable Experimental condition Control condition \n t \n \n p \n Cohen's d M SD M SD Number of pages (0–12) 7.5 4.0 8.0 3.8 1.44 .15 0.14 Time on website (sec) 151.0 117.4 150.8 107.8 0.01 .99 0.00 \n\nBODY.RESULTS.USER PERCEPTIONS:\nThere were no differences between conditions in terms of efficiency (F(1, 456) = 0.84, p = .36), effectiveness (F(1, 456) = 0.03, p = .87), enjoyment (F(1, 456) = 0.08, p = .78), active trust (F(1, 456) = 0.03, p = .87) and interest (F(1, 456) = 0.07, p = .80). Figure 5 illustrates the final structural equation model testing the associations between user perceptions and website use across conditions, because there were no differences on both measures of website use. The final model is mostly in line with Hypothesis 2: Efficiency (M = 6.5, SD = 0.84), effectiveness (M = 6.4, SD = 0.87), and enjoyment (M = 5.6, SD = 1.21) were positively associated with website use and these associations were partly mediated by active trust (M = 5.8, SD = 1.23). The association between efficiency and website use, however, was fully mediated by active trust. Since there were no differences between conditions in terms of website use, there is neither support for Hypothesis 3a nor for Hypothesis 3b. Interest (M = 5.9, SD = 1.06), however, was positively associated with and contributed to explaining variance in website use besides efficiency, effectiveness, enjoyment, and active trust. The explained variance (R2) of the number of pages visited and time on the website is .63 and .51 respectively. The CFI and TLI are .98 and .97, respectively; RMSEA and SRMR are .06 and .04, respectively. All of these fit indices indicate a close fit for the final model. 10.1371/journal.pone.0057067.g005Figure 5Final model including standardized betas of significant paths within the model.\n\nBODY.DISCUSSION:\nThe key finding of the current study is that adding social presence elements did not affect actual use of an intervention website within a public health context. A possible explanation for this lack of effect can be derived from the results of the preparatory study: Even though the social presence elements attract attention, the frequency and duration of fixations on these elements was limited in comparison with the fixations on the main text. If the findings of the preparatory study are extrapolated to the main study, then this might explain the limited impact of social presence elements on actual website use. It could be that people on a health-related website are mainly interested in the actual information it provides (i.e., the main text instead of social presence elements), which is mostly related to the utilitarian value of a website [47]. To date, however, the use of social presence elements has only been tested on more hedonically oriented websites (such as shopping for clothing) [14], [48]. It might be that social presence is more important on hedonically oriented websites in comparison with health-related websites, which are more utilitarian in nature. Even within the e-commerce context, there are differences between products: A previous study compared clothing (a more hedonic product for which consumers seek fun and entertaining shopping experiences) and headphones (a more utilitarian product for which consumers primarily seek detailed product information). Unlike clothing, higher levels of social presence on websites selling headphones did not have a positive effect on attitudinal antecedents [49]. In line with this, Nusair, Yoon, and Parsa [50] found that motivation variables, utilitarian and hedonic, moderate the effect of the web quality dimensions on satisfaction. There are two other points that need to be raised while interpreting the findings of this study. First, there was a difference in effect size regarding perceived social presence, which was very large in the preparatory study, but only small in the main study. A speculative explanation could be that the sample of the preparatory study was much younger and might therefore be more open to social presence elements on websites. It is in our opinion more likely, however, that this is indicative of the difference between the lab setting in which participants had to look at the website in a more controlled environment versus the main study in which a real-life situation was mimicked. In the latter case, participants might pay only limited attention to a website [51], especially when added elements increase its complexity [33]. Second, this is the first study to investigate the effect of adding social presence elements on actual use instead of only intention to use or attitude towards a website. Although intention and attitude are important predictors of behavior [15], the intention-behavior gap is a well-known phenomenon in behavioral research: intentions account for 28% of the variance in behavior in prospective studies [52]. The explained variance of both behavioral measures in the current study (i.e., the number of pages visited and time on the website) was high and there was a close fit for the final model. In other words, user perceptions are appropriate predictors for explaining use of an intervention website in a public health context. Moreover, the relationships between these user perceptions and website use are comparable to the few other studies that are available within the field of attrition science regarding Internet-delivered interventions [24], [25]. The current study extends previous studies by including a measure of interest and demonstrates its added value besides the other perceptions. This is in line with the theoretical assumption of Silvia [29] that interest and enjoyment differ in critical ways and contributes to highly needed theory development within the field of attrition science [3]. A possible limitation of the study at hand is that participants in the main study were highly interested in the subject (i.e., Hepatitis), since they agree to participate in a study about this topic. Although participants perceived the website to be interesting (after being exposed to it), the low scores regarding Hepatitis knowledge at pre-test do not provide support for a possible selection bias regarding participants that were highly interested in the subject before the study. The increase regarding Hepatitis knowledge one week later is very positive, especially since participants were not necessarily looking for information on Hepatitis. The latter is essential in primary prevention websites aimed at the general public. Future research needs to focus on characteristics of social presence elements that might affect their impact. The human images of people in the current study, for example, varied in age and gender. A previous study on Product Recommendation Agents (PRA; a decision support system that helps consumers to gather, screen, and evaluate available product information on the Internet), however, found that ethnicity-matched PRAs scored higher on perceived social presence, enjoyment, and effectiveness [53]. Another study revealed that PRAs with higher personalization also elicited more trust [54]. Personalization is one of the strategies, besides feedback and content matching, that is part of tailoring: creating communications individualized for their receivers, with the expectation that this individualization will lead to larger intended effects of these communications [55]. It might be that social presence elements on intervention websites in a public health context need to be tailored – a commonly used and effective method for the actual information on intervention websites [56]. Furthermore, the website used in this study was limited to providing knowledge about Hepatitis. It is worthwhile to investigate whether social presence elements may be more effective in increasing website use regarding intervention websites that are aimed at demonstrating and practicing skills (e.g., using role models) or reducing stigma that may be related to health behavior. Another possible avenue for future research is whether or not cultural differences might be in play. Based on Hofstede's cultural value dimensions [57], a previous study revealed that the impact of pleasure on online behavior was higher for Canadian website visitors, while the impact of dominance was higher for Chinese website visitors [58]. To our knowledge, only one study has made a cross-cultural comparison of the impact of social presence elements, but this was limited to the impact user perceptions and actual use was not taken into account [59]. Hence, this is a nascent area worthy of additional investigation.\n\nQuestion: Compared to website without social presence elements. what was the result of website with social presence elements. on website use and terms of the number of pages visited and terms of time on the website?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1119	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Social Presence and Use of Internet-Delivered Interventions: A Multi-Method Approach\n\n ABSTRACT.OBJECTIVE:\nInternet-delivered interventions can effectively change health risk behaviors and their determinants, but adherence to intervention websites once they are accessed is very low. This study tests whether and how social presence elements can increase website use.\n\nABSTRACT.METHODS:\nA website about Hepatitis A, B, and C virus infections was used in a preparatory lab-based eye-tracking study assessing whether social presence elements attract participants' attention, because this is a prerequisite for affecting website use. In the following field study, 482 participants representative of the Dutch population were randomized to either a website with or a website without social presence elements. Participants completed a questionnaire of validated measures regarding user perceptions immediately after exposure to the website. Server registrations were used to assess website use.\n\nABSTRACT.RESULTS:\nParticipants in the experimental condition focused on the social presence elements, both in terms of frequency (F(1, 98) = 40.34, p<.001) and duration (F(1, 88) = 39.99, p<.001), but did not differ in website use in comparison with the control condition; neither in terms of the number of pages visited (t(456) = 1.44, p = .15), nor in terms of time on the website (t(456) = 0.01, p = .99).\n\nABSTRACT.CONCLUSIONS:\nAdding social presence elements did not affect actual use of an intervention website within a public health context. Possible reasons are limited attention for these elements in comparison with the main text and the utilitarian value of intervention websites.\n\nBODY.INTRODUCTION:\nInternet-delivered interventions can effectively change health risk behaviors and their determinants [1], but the actual use of these interventions by the target group once they access the website is very low [2]. Eysenbach [3] even defined the \"law of attrition\", which considers high attrition rates as a natural and typical feature of Internet-delivered interventions. For example, server statistics of an intervention promoting heart-healthy behaviors showed that 285,146 visitors from unique IP addresses accessed the home page in a 36-month period, but 56.3% of them left the intervention website within 30 seconds [4]. This finding touches upon a critical issue in Internet-delivered interventions: how can they ever have a public health impact if people only briefly use the actual intervention? It is therefore relevant and necessary to focus on factors related to the use of an Internet-delivered intervention once people arrive at the intervention website (i.e., website use) [5]. These factors relate to the visitor (e.g., people's motivation to be healthy [6], [7]) as well as the intervention website (e.g., offering tailored information [8], [9]). Not only is the content of the website important [10], but also the specific characteristics of the website itself. The current study aims to systematically manipulate a website characteristic – i.e., social presence – and link this to (1) website use and (2) user perceptions as the working mechanisms behind this possible effect of social presence. The rationale behind this aim is explained in the follow paragraphs, resulting in hypotheses to be tested in the current study. The focus of the current study is on social presence, which can be seen as the extent to which a medium is perceived to convey a feeling of human contact, sociability, and sensitivity [11]. This is realized by adding social presence elements: presenting human images [12] and testimonials [13] in which people share their experiences and ideas regarding the information presented on the website with others. Previous studies revealed that adding these social presence elements increases perceived social presence and positively affects attitude towards shopping websites [14] as well as intention to use them [13]. Two issues remain unclear, however. First, whether social presence also has added value in a public health context. Second, whether the positive effect regarding attitude and intention to use also hold when looking at the actual behavior (i.e., website use) instead of its precursors. Given that intention is the most important predictor of actual behavior [15], this is hypothesized to be the case. Thus, social presence is expected to increase website use in a public health context (Hypothesis 1). What are the working mechanisms behind this possible effect of social presence on website use? The main idea is that social presence results in a positive user experience, which increases website use. User experience refers to what a person thinks and feels during and after being exposed to a website [16] and is deemed even more important than usability, which only concerns ease of use [17]. User experience consists of both cognitive perceptions (e.g., efficiency, effectiveness) and affective perceptions (e.g., enjoyment) [18]. Efficiency refers to easy search and access of information provided and effectiveness refers to the quality of that information (e.g., in terms of relevance) [19]. These cognitive perceptions have parallels with perceived ease of use and perceived usefulness in the technology acceptance model, but are applicable in a broader context [20]. The affective perceptions of user experience are often referred to as enjoyment\n[21], [22]. Active trust refers to the confidence in acting on the provided information on a website, which can result in increased website use [23]. Efficiency, effectiveness and enjoyment can be expected to be positively associated with website use and these associations are hypothesized to be partly mediated by active trust, which is in line with the limited evidence that is currently available [24], [25] (Hypothesis 2). Previous studies investigating social presence and user perceptions consistently demonstrated that social presence positively affects perceptions of both effectiveness and enjoyment regarding shopping websites [13], [14], [26]. The current study extends previous studies by including a measure of interest besides enjoyment, because this is a motivational factor that \"guarantees the person's engagement\" [27]. Although interest is sometimes defined as feelings of enjoyment [28], interest and enjoyment differ in critical ways [29]. Experiments using several kinds of stimuli (e.g., random polygons, poetry, and experimental paintings) indicate that enjoyment is not a necessary condition for interest [30]. The two antecedents of interest are, according to Silvia [29], appraisal of coping potential (e.g., that people can deal with the presented information due to the use of everyday language) and appraisal of novelty-complexity (e.g., due to the use of imagery). The previously discussed social presence elements are in line with Silvia's [29] suggestion to use imagery (e.g., human images) and everyday language (e.g., testimonials) to positively affect appraisal of novelty-complexity and coping potential respectively, resulting in increased interest. Moreover, increased interest results in spending more time reading information on a topic [31]. An initial hypothesis would therefore be that interest due to adding social presence elements increases website use (Hypothesis 3a). However, the increased complexity due to adding social presence elements can also have a negative impact. Previous studies demonstrated that complexity has a negative effect on attitude towards a website and therewith on intention to use [32], [33], pleading for simplicity of websites [34]. An alternative hypothesis would therefore be that adding social presence elements decreases website use because of increased complexity (Hypothesis 3b).\n\nBODY.INTRODUCTION.WEBSITE:\nA website about Hepatitis A, B, and C virus (HAV, HBV, HCV) infections was used to test the effect of adding social presence elements on website use and the working mechanisms behind this possible effect. These infections all affect the liver, but there are differences in terms of mode of transmission, consequences, and prevention. Besides the home page, the website consisted of four pages per Hepatitis virus. The first page introduced the virus briefly and the other three pages outlined transmission, consequences, and prevention respectively. This resulted in a total of twelve pages of website content (for all virus types) besides the home page. The content for these pages was based on information from the Dutch National Hepatitis Centre. The content was text-based, purely informative, non-tailored, and very brief (i.e., 5–10 lines of text per page). Use of this website has been proven to result in increasing practical knowledge regarding Hepatitis [25], which is currently very low in the Netherlands [35]. The experimental website for this study was created by adding social presence elements to the website previously used, which served as the control website in this study.\n\nBODY.INTRODUCTION.SOCIAL PRESENCE ELEMENTS:\nSocial presence elements were based on previous studies and consisted of adding human images (of people varying in age and gender) [12] and testimonials [13] in which people shared their experiences and ideas regarding the information presented on the website with the visitor. The above social presence elements were added to the home page and three pages per virus type that outlined transmission, consequences, and prevention respectively. Therefore, a total number of ten pages contained social presence elements. The number of pages of both website versions were identical. Previous research proved that JPEG file sizes are a good proxy for complexity of web pages [36]. File sizes are not only related to complexity, but also to page size (i.e., resolution). Therefore, screenshots of pages to which social presence elements were added in the experimental website, were captured for both websites at the same resolution (1024×768 pixels). The screenshots of the experimental website were – according to the JPEG file sizes – more complex in comparison with the control website (218 vs 137 kB, t(18) = 22.42, p<.001), which is a presumption in Hypothesis 3b (i.e., adding social presence elements increases complexity).\n\nBODY.INTRODUCTION.PREPARATORY STUDY:\nThe aim of the preparatory study was to assess whether social presence elements attract participants' attention, because this is a prerequisite for them to affect user perceptions and (intention to) use. A previous study – based on self-reports – found a positive relationship between attention and user perceptions [37]. Eye-tracking, however, is a more suitable method to assess the course of attention over time [38]. This preparatory study built upon previous studies that successfully applied eye-tracking with regard to perceptions of health-related information [39] and websites [12]. There is general agreement on the strong association between eye movements and attention [40]. The idea behind eye-tracking is that saccadic eye movements are associated with shifts in attention. Fixations refer to the periods between saccadic eye movements in which gaze is held almost stationary.\n\nBODY.METHODS.PARTICIPANTS:\nParticipants were a convenience sample of undergraduate students that received course credits for their participation in this preparatory study. Participants were screened to ensure normal or corrected vision, and those wearing hard contact lenses or eyeglasses were excluded from participation, because this can result in difficulties in capturing eye movements. A total of 24 participants were randomized (16 women, 8 men). Mean age of the sample was 20.1 years (SD = 1.8). Participants were recruited through a research panel of a Dutch Internet research agency; therefore, they could be considered computer literate. From this panel, a stratified sample of 982 potential participants was invited to participate in a study about Hepatitis through email. Informed consent was obtained online, which is the regular procedure for this research panel. This sample was representative of the Dutch Internet population above 18 years, taking into account gender, age, and level of education.\n\nBODY.METHODS.DESIGN AND PROCEDURE:\nAfter explaining the study procedure and signing informed consent, participants were seated approximately 25 inches from a computer screen. The laboratory room was artificially lit and there was no influx of sunlight. First, the eye-tracker system (more detailed information in the Apparatus section) was calibrated. Subsequently, participants were told that we were interested in their opinion to improve a website and that they could freely explore this website. Participants were randomly assigned to two conditions. The control condition consisted of the existing website as used in a previous study [25]. The experimental condition added social presence elements to this website (as described above). A brief questionnaire had to be completed immediately following exposure to the website and consisted of measures regarding interest and perceived social presence as a manipulation check. It was stressed that there were no right or wrong answers. Participants were randomly assigned to either the control condition or the experimental condition (Figure 4). Both conditions were similar to those in the preparatory study. The pre-test (i.e., before being exposed to the website) consisted of a Hepatitis knowledge questionnaire. After the pre-test, participants were directed to their assigned version of the website. Participants were asked to base their opinion about the website on their first impression and were told they could freely explore the website until they started completing the post-test (immediately after visiting the website). The objective was not to force participants to thoroughly study the website, but to mimic a real-life situation in which time and opportunity to invest in the website is limited [4]. The post-test consisted of measures regarding user perceptions and perceived social presence as a manipulation check. For these measures, it was stressed that there are no right or wrong answers. One week later, participants were invited to complete the follow-up measure, which was the same as the pre-test (i.e., the Hepatitis knowledge questionnaire). The follow-up measure was added to test whether participants did not only click through the website but actually processed and memorized its content (i.e., by looking at both within- and between-group differences regarding Hepatitis knowledge over time). 10.1371/journal.pone.0057067.g004Figure 4Flowchart of study design and attrition. Participants received an incentive (i.e., credit points for panel members) to participate in the study, which represented a value of € 2.50. Panel members can save credit points over time, which can be exchanged for online vouchers valid in several stores in the Netherlands. Relevant ethical safeguards were met with regard to the participant confidentiality and consent.\n\nBODY.METHODS.ETHICS STATEMENT:\nThe Simon Fraser University Research Ethics Board granted ethical approval (file number: 2012s0168).\n\nBODY.METHODS.APPARATUS:\nThe eye-tracker system used was Applied Science Laboratories Model 504 with head tracking integration. Eye movements were processed using an autofocus eye camera mounted on a optics mechanism (max. 100° pan, 25° tilt), which was positioned under the computer screen. The camera has eye illumination that consists of a ring of near-infrared light-emitting diodes. The sampling rate was 60 Hz and the measurement error was <1.0°. Participants wore a headband with a mounted sensor, which allowed tracking of head movements without loss of eye image. This permitted participants to move their heads in a relatively natural manner. Gaze Tracker software was used to capture and process eye-tracking data (measures are explained in the following section).\n\nBODY.METHODS.MEASUREMENTS:\nThe following measurements were used within the preparatory study. The following measurements were used within the main study.\n\nBODY.METHODS.MEASUREMENTS.ATTENTION:\nAttention is assessed by the number of fixations and total fixation duration in milliseconds (ms) within each area of interest on the website as defined by rectangular regions called lookzones. There were two lookzones on each page; the main text and the social presence elements (Figure 1). The main text lookzone was similar for both conditions. The threshold for minimal duration for a fixation was set at 50 ms [40]. 10.1371/journal.pone.0057067.g001Figure 1Example of lookzones on a page (image has been blurred to ensure anonymity).\n\nBODY.METHODS.MEASUREMENTS.INTEREST:\nIn line with Turner and Silvia [30], two items measured interest (uninteresting-interesting and boring-engaging; alpha = .72) on a 7-point Likert scale.\n\nBODY.METHODS.MEASUREMENTS.PERCEIVED SOCIAL PRESENCE:\nFive items (e.g., \"There is a sense of human warmth in the website\"; alpha = .87) were used to measure perceived social presence as a manipulation check [12], [41]. Items were answered on a 7-point Likert scale ranging from (1) 'strongly disagree' to (7) 'strongly agree'. Similar to the preparatory study, five items (alpha = .95) were used to measure perceived social presence as a manipulation check.\n\nBODY.METHODS.ANALYSES:\nData from participants who encountered technical problems (e.g., difficulties in capturing eye movements) or artifacts (e.g., too many blinks) resulting in >25% missing eye-tracking data were excluded from the analyses regarding attention (n = 5). Mixed models were used to test for differences in the measures of attention, using page as a within-subject factor and condition as a between-subject factor. Two-tailed effect sizes (i.e., Cohen's d), given the means, standard deviations, and sample sizes per condition, were used to test differences between conditions regarding interest and perceived social presence. Effect sizes were divided into the following five levels: trivial (Cohen's d≤.2), small (>.2), moderate (>.5), large (>.8), and very large (>1.3) [42].\n\nBODY.RESULTS:\nParticipants in the experimental condition focused on the social presence elements, both in terms of frequency (F(1, 98) = 40.34, p<.001) and duration (F(1, 88) = 39.99, p<.001), while participants in the control condition paid hardly any attention to these lookzones. There were, however, no differences between conditions in terms of frequency (F(1, 101) = 1.59, p = .21) and duration (F(1, 90) = 0.13, p = .72) of fixations on the main text. Figures 2 and 3 indicate that participants in the experimental condition were attracted by the social presence elements, but this did not affect their attention to the main text. Participants in the experimental condition scored higher on interest (M = 4.7 vs. 4.2, Cohen's d = 0.32) and perceived social presence (M = 4.6 vs. 3.1, Cohen's d = 1.22) in comparison with the control condition. These effects can be classified as small and very large respectively. 10.1371/journal.pone.0057067.g002Figure 2Number of fixations per page. 10.1371/journal.pone.0057067.g003Figure 3Total fixation duration (ms) per page.\n\nBODY.RESULTS.MAIN STUDY:\nThe preparatory study demonstrated that the social presence elements attract participants' attention and increase perceived social presence, without decreasing attention for the main text. The aim of the main study was to test the proposed conceptual model and associated hypotheses.\n\nBODY.METHODS.MEASUREMENTS.HEPATITIS KNOWLEDGE QUESTIONNAIRE:\nFifteen true/false items (including a 'don't know' option) about transmission, consequences, and prevention of HAV, HBV and HCV infections were used to assess Hepatitis knowledge. The sum score of all correctly answered items was used in the analyses. The correct answer to these items was available on the website. The items concerned practical knowledge and were used in a previous study [35].\n\nBODY.METHODS.MEASUREMENTS.WEBSITE USE:\nServer registrations were used to assess website use [43], [44] which was operationalized by the number of pages visited (ranging from 0 to 12). Furthermore, time on the website was tracked to detect whether participants were simply clicking from one page to the other and therefore artificially boosting the number of pages visited.\n\nBODY.METHODS.MEASUREMENTS.USER PERCEPTIONS:\nSets of three items each were used to measure efficiency (e.g., \"I was able to access the information quickly on this website\"; alpha = .97), effectiveness (e.g., \"The website provided me with relevant information about ...\"; alpha = .92), enjoyment (e.g., \"I found my visit to this website enjoyable\"; alpha = .97), and active trust (e.g., \"I would act upon the information presented on this website if needed\"; alpha = .89). Items were answered on a 7-point Likert scale ranging from (1) 'strongly disagree' to (7) 'strongly agree'. These measures were previously used and validated in the Dutch language [24]. Similar to the preparatory study, two items were used to measure interest (alpha = .82).\n\nBODY.ANALYSES:\nFirst, independent samples t-tests and chi-square tests were conducted to test whether there was selective dropout or differences in dropout between conditions. Subsequently, independent-samples t-test were conducted to test for differences between conditions in terms of perceived social presence and both measures of website use. For this analysis, time on website was log-transformed to meet the assumption of normality. A repeated measures analysis of variance (ANOVA) was conducted to test for differences in Hepatitis knowledge between conditions over time. Multivariate ANOVAs were conducted to test for differences in user perceptions between conditions. All these analyses were conducted using Predictive Analytics SoftWare Statistics 18.0 (International Business Machines Corporation, Armonk, NY). Second, using Mplus 5 (Muthén & Muthén, Los Angeles, CA), structural equation models (SEMs) using all available data were constructed to test the hypothesized conceptual model. Website use—a latent construct made up from number of pages visited and time on the website—was regressed on efficiency, effectiveness, enjoyment, interest, and active trust, which were all latent constructs using the items described above. Active trust was regressed on efficiency, effectiveness, and enjoyment. Effectiveness, enjoyment, and interest were regressed on social presence. Subsequently, (1) non-significant paths were left out of the conceptual model for the sake of parsimony, and (2) additional paths were added to the conceptual model based on significant modification indices. The latter was done to explore whether unanticipated relationships might explain variance in website use (which was not the case). A level of significance of p<.05 was used for the relationships within the model. Model fit indices used were the comparative fit index (CFI), the Tucker-Lewis index (TLI), the root mean square error of approximation (RMSEA), and the standardized root mean square residual (SRMR). Both CFI and TLI are goodness-of-fit indices where larger values signal better fit. Values over .95 indicate close fit. The RMSEA and SRMR are goodness-of-fit indices where larger values signal worse fit. Indicators of close fit are, respectively, RMSEA ≤.05 and SRMR ≤.09 [45], [46].\n\nBODY.RESULTS.PARTICIPANTS:\nOf those 982 potential participants that were invited, 458 participated in the study (47%). Half of the participants were female and the mean age of participants was 49 years (SD = 16). Of the participants, 30% had a low level of highest completed education (equivalent to primary school/junior high school), 38% an intermediate level (equivalent to senior high school/junior college), and 32% a high level (equivalent to college/university). Those 458 that participated were invited to complete the follow-up measure and 402 of them did so (88%). There was no selective dropout regarding gender (χ2 (1, N = 458) = 0.3, p = .57), level of education (χ2 = 5.0, p = .08), or Hepatitis knowledge at baseline (t(456) = 1.83, p = .07). Furthermore, dropout did not differ between the two conditions (χ2 (1, N = 458) = 3.2, p = .08). Those who dropped out, however, were younger (M = 43 vs 50 years, (t(456) = 3.19, p = .002).\n\nBODY.RESULTS.MANIPULATION CHECK:\nParticipants in the experimental condition scored higher on perceived social presence than the control condition (M = 4.9 vs. 4.4, t(456) = 4.11, p<.001, Cohen's d = 0.38), which indicates that the manipulation did succeed. This effect can be classified as small.\n\nBODY.RESULTS.WEBSITE USE AND HEPATITIS KNOWLEDGE:\nParticipants in the experimental condition did not differ in website use in comparison with the control condition; neither in terms of the number of pages visited, nor in terms of time on the website (Table 1). Effect sizes were trivial. Thus, there is no support for Hypothesis 1. The increase in Hepatitis knowledge between pre-test and post-test did not differ between both conditions (F(1, 400) = 0.72, p = .40), but there was a significant increase regarding Hepatitis knowledge between pre-test and post-test across conditions (M = 6.4 vs. 8.3, F(1,400) = 172.98, p<.001, Cohen's d = 0.65), which can be defined as a moderate effect size. 10.1371/journal.pone.0057067.t001 Table 1 Differences in website use between conditions. Variable Experimental condition Control condition \n t \n \n p \n Cohen's d M SD M SD Number of pages (0–12) 7.5 4.0 8.0 3.8 1.44 .15 0.14 Time on website (sec) 151.0 117.4 150.8 107.8 0.01 .99 0.00 \n\nBODY.RESULTS.USER PERCEPTIONS:\nThere were no differences between conditions in terms of efficiency (F(1, 456) = 0.84, p = .36), effectiveness (F(1, 456) = 0.03, p = .87), enjoyment (F(1, 456) = 0.08, p = .78), active trust (F(1, 456) = 0.03, p = .87) and interest (F(1, 456) = 0.07, p = .80). Figure 5 illustrates the final structural equation model testing the associations between user perceptions and website use across conditions, because there were no differences on both measures of website use. The final model is mostly in line with Hypothesis 2: Efficiency (M = 6.5, SD = 0.84), effectiveness (M = 6.4, SD = 0.87), and enjoyment (M = 5.6, SD = 1.21) were positively associated with website use and these associations were partly mediated by active trust (M = 5.8, SD = 1.23). The association between efficiency and website use, however, was fully mediated by active trust. Since there were no differences between conditions in terms of website use, there is neither support for Hypothesis 3a nor for Hypothesis 3b. Interest (M = 5.9, SD = 1.06), however, was positively associated with and contributed to explaining variance in website use besides efficiency, effectiveness, enjoyment, and active trust. The explained variance (R2) of the number of pages visited and time on the website is .63 and .51 respectively. The CFI and TLI are .98 and .97, respectively; RMSEA and SRMR are .06 and .04, respectively. All of these fit indices indicate a close fit for the final model. 10.1371/journal.pone.0057067.g005Figure 5Final model including standardized betas of significant paths within the model.\n\nBODY.DISCUSSION:\nThe key finding of the current study is that adding social presence elements did not affect actual use of an intervention website within a public health context. A possible explanation for this lack of effect can be derived from the results of the preparatory study: Even though the social presence elements attract attention, the frequency and duration of fixations on these elements was limited in comparison with the fixations on the main text. If the findings of the preparatory study are extrapolated to the main study, then this might explain the limited impact of social presence elements on actual website use. It could be that people on a health-related website are mainly interested in the actual information it provides (i.e., the main text instead of social presence elements), which is mostly related to the utilitarian value of a website [47]. To date, however, the use of social presence elements has only been tested on more hedonically oriented websites (such as shopping for clothing) [14], [48]. It might be that social presence is more important on hedonically oriented websites in comparison with health-related websites, which are more utilitarian in nature. Even within the e-commerce context, there are differences between products: A previous study compared clothing (a more hedonic product for which consumers seek fun and entertaining shopping experiences) and headphones (a more utilitarian product for which consumers primarily seek detailed product information). Unlike clothing, higher levels of social presence on websites selling headphones did not have a positive effect on attitudinal antecedents [49]. In line with this, Nusair, Yoon, and Parsa [50] found that motivation variables, utilitarian and hedonic, moderate the effect of the web quality dimensions on satisfaction. There are two other points that need to be raised while interpreting the findings of this study. First, there was a difference in effect size regarding perceived social presence, which was very large in the preparatory study, but only small in the main study. A speculative explanation could be that the sample of the preparatory study was much younger and might therefore be more open to social presence elements on websites. It is in our opinion more likely, however, that this is indicative of the difference between the lab setting in which participants had to look at the website in a more controlled environment versus the main study in which a real-life situation was mimicked. In the latter case, participants might pay only limited attention to a website [51], especially when added elements increase its complexity [33]. Second, this is the first study to investigate the effect of adding social presence elements on actual use instead of only intention to use or attitude towards a website. Although intention and attitude are important predictors of behavior [15], the intention-behavior gap is a well-known phenomenon in behavioral research: intentions account for 28% of the variance in behavior in prospective studies [52]. The explained variance of both behavioral measures in the current study (i.e., the number of pages visited and time on the website) was high and there was a close fit for the final model. In other words, user perceptions are appropriate predictors for explaining use of an intervention website in a public health context. Moreover, the relationships between these user perceptions and website use are comparable to the few other studies that are available within the field of attrition science regarding Internet-delivered interventions [24], [25]. The current study extends previous studies by including a measure of interest and demonstrates its added value besides the other perceptions. This is in line with the theoretical assumption of Silvia [29] that interest and enjoyment differ in critical ways and contributes to highly needed theory development within the field of attrition science [3]. A possible limitation of the study at hand is that participants in the main study were highly interested in the subject (i.e., Hepatitis), since they agree to participate in a study about this topic. Although participants perceived the website to be interesting (after being exposed to it), the low scores regarding Hepatitis knowledge at pre-test do not provide support for a possible selection bias regarding participants that were highly interested in the subject before the study. The increase regarding Hepatitis knowledge one week later is very positive, especially since participants were not necessarily looking for information on Hepatitis. The latter is essential in primary prevention websites aimed at the general public. Future research needs to focus on characteristics of social presence elements that might affect their impact. The human images of people in the current study, for example, varied in age and gender. A previous study on Product Recommendation Agents (PRA; a decision support system that helps consumers to gather, screen, and evaluate available product information on the Internet), however, found that ethnicity-matched PRAs scored higher on perceived social presence, enjoyment, and effectiveness [53]. Another study revealed that PRAs with higher personalization also elicited more trust [54]. Personalization is one of the strategies, besides feedback and content matching, that is part of tailoring: creating communications individualized for their receivers, with the expectation that this individualization will lead to larger intended effects of these communications [55]. It might be that social presence elements on intervention websites in a public health context need to be tailored – a commonly used and effective method for the actual information on intervention websites [56]. Furthermore, the website used in this study was limited to providing knowledge about Hepatitis. It is worthwhile to investigate whether social presence elements may be more effective in increasing website use regarding intervention websites that are aimed at demonstrating and practicing skills (e.g., using role models) or reducing stigma that may be related to health behavior. Another possible avenue for future research is whether or not cultural differences might be in play. Based on Hofstede's cultural value dimensions [57], a previous study revealed that the impact of pleasure on online behavior was higher for Canadian website visitors, while the impact of dominance was higher for Chinese website visitors [58]. To our knowledge, only one study has made a cross-cultural comparison of the impact of social presence elements, but this was limited to the impact user perceptions and actual use was not taken into account [59]. Hence, this is a nascent area worthy of additional investigation.\n\nQuestion: Compared to website without social presence elements. what was the result of website with social presence elements. on focused on the social presence elements in terms of frequency and duration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1123	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Comparative utility of disability progression measures in PPMS\n\n ABSTRACT.OBJECTIVE:\nTo assess the comparative utility of disability progression measures in primary progressive MS (PPMS) using the PROMiSe trial data set.\n\nABSTRACT.METHODS:\nData for patients randomized to placebo (n = 316) in the PROMiSe trial were included in this analysis. Disability was assessed using change in single (Expanded Disability Status Scale [EDSS], timed 25-foot walk [T25FW], and 9-hole peg test [9HPT]) and composite disability measures (EDSS/T25FW, EDSS/9HPT, and EDSS/T25FW/9HPT). Cumulative and cross-sectional unconfirmed disability progression (UDP) and confirmed disability progression (CDP; sustained for 3 months) rates were assessed at 12 and 24 months.\n\nABSTRACT.RESULTS:\nCDP rates defined by a ≥20% increase in T25FW were higher than those defined by EDSS score at 12 and 24 months. CDP rates defined by T25FW or EDSS score were higher than those defined by 9HPT score. The 3-part composite measure was associated with more CDP events (41.4% and 63.9% of patients at 12 and 24 months, respectively) than the 2-part measure (EDSS/T25FW [38.5% and 59.5%, respectively]) and any single measure. Cumulative UDP and CDP rates were higher than cross-sectional rates.\n\nABSTRACT.CONCLUSIONS:\nThe T25FW or composite measures of disability may be more sensitive to disability progression in patients with PPMS and should be considered as the primary endpoint for future studies of new therapies. CDP may be the preferred measure in classic randomized controlled trials in which cumulative disability progression rates are evaluated; UDP may be feasible for cross-sectional studies.\n\nBODY:\nPatients with primary progressive MS (PPMS) represent 10%–15% of patients with MS and suffer the highest neurodegeneration-related disability.1–4 There are currently no approved treatments to ameliorate disease progression in PPMS, and there are several barriers to developing therapeutics in progressive MS.2,5 Specifically, individual disability measures may lack the sensitivity required to reveal all cases of disease progression within the defined time frame of a clinical trial.6 The Expanded Disability Status Scale (EDSS) remains the typical outcome measure in PPMS trials. However, it has been widely recognized as inadequate7 and is associated with several important weaknesses.3 Other widely used measures of disability in MS include the timed 25-foot walk (T25FW) and the 9-hole peg test (9HPT).8,9 Recent studies have suggested that a combined disability measure that incorporates scoring from multiple instruments—for example, using T25FW, 9HPT, and EDSS—may be associated with more progression events among patients with PPMS, and thus higher reported event rates than achieved with any single instrument alone.9,10 The PROMiSe study represents one of the best and largest (N = 943) data sources on patients with PPMS and offers a unique opportunity to assess the value of different functional measures of disability progression in a clinical trial setting.11 We report here the results of an analysis of the PROMiSe data set undertaken to better understand the utility of the different measures of disability progression—EDSS, T25FW, and 9HPT alone and in combinations—and to inform the design of future trials in PPMS.\n\nBODY.METHODS.STANDARD PROTOCOL APPROVALS, REGISTRATIONS, AND PATIENT CONSENTS.:\nParticipating study sites in each individual country locally ensured all necessary regulatory approvals (e.g., institutional review boards/institutional ethics committees) in accordance with local regulations, including local data protection regulations used in the original collection of the data for this secondary data analysis.\n\nBODY.METHODS.STUDY DESIGN.:\nThe data set for this analysis was derived from the PROMiSe study, a randomized, double-blind, placebo-controlled clinical trial with a planned duration of 3 years.11 The design of the PROMiSe study has been reported previously.11 In summary, patients who took part in the PROMiSe study (N = 943) were randomized in a 2:1 ratio to receive glatiramer acetate (GA) 20 mg once daily (n = 627) or identical-appearing placebo (n = 316) by daily subcutaneous injection.11 The primary endpoint was time to confirmed disability progression (CDP), with CDP being defined as a change of ≥1 point on the EDSS sustained for 3 months in patients with a baseline EDSS score of 3.0–5.0, or a change of ≥0.5 points for 3 months in those with a baseline score of 5.5–6.5.11 Patients also completed the MS Functional Composite (MSFC) evaluation, a 3-part test including the T25FW and 9HPT and the Paced Auditory Serial Addition Test (PASAT).11\n\nBODY.METHODS.PATIENTS.:\nPatients eligible to participate in the PROMiSe study were aged between 30 and 65 years, with an EDSS score of 3.0–6.5, investigator-confirmed PPMS, and progressive symptoms including myelopathy for ≥6 months before screening. Additional eligibility criteria included evidence of pyramidal damage on neurologic examination, including a pyramidal functional system score ≥2, and evidence of multilevel CNS disease.11 Patients with any history of MS relapse, those with lymphopenia <3,000 cells/mL, and those who had used an interferon-β drug, immunosuppressant, immunomodulating agent, corticosteroid, or investigational drug within 3 months of study initiation were not eligible to take part.11 Only data for patients randomized to placebo in the PROMiSe trial were included in this analysis in order to compare clinical measures in patients with PPMS for whom the natural course of the disease was not potentially affected by exposure to GA treatment.\n\nBODY.METHODS.OUTCOME EVALUATIONS.:\nDisability was assessed using change in single (EDSS, T25FW, and 9HPT) and composite disability measures. Combination endpoints were defined as progression by EDSS or T25FW, 9HPT or T25FW, or by EDSS or T25FW or 9HPT. The PASAT was not included in this analysis of the PROMiSe database because of the potential for practice effects occurring from repeated administration. Moreover, the test may have limited measurement reliability, is sometimes difficult to administer, has been used less frequently in recent MS trials, and is not anticipated to be featured in future trials. As per the PROMiSe study protocol, worsening of the EDSS was defined as a change from baseline of ≥1 point (for baseline EDSS 3.0–5.0) or ≥0.5 points (for baseline EDSS 5.5–6.5).11 Worsening of the T25FW was defined as an increase of ≥20% compared with baseline or as the inability to complete the T25FW after baseline due to worsening disability (increase of EDSS to 7.0 or higher).12 Worsening of the 9HPT was defined as an increase of ≥20% compared with baseline (calculated as the average across 4 trials: 2 in the dominant hand and 2 in the nondominant hand) or as the inability to complete the 9HPT after baseline due to worsening disability.12 For each measure, rates of unconfirmed disability progression (UDP) and of 3-month CDP were determined. Two trial methodologies were evaluated: cumulative and cross-sectional. The cumulative approach describes the design of the PROMiSe trial and similar large-scale randomized clinical trials, with outcome measurement every 3 months and disability progression at any time point during follow-up contributing to an overall CDP proportion. The cross-sectional approach describes the design for simple, straightforward investigator-initiated trials such as futility trials13 and observational studies on PPMS disability progression.10 In this case, the measurement at one follow-up time point (e.g., 12 months) is compared with the baseline measurement. This analysis is restricted to patients in the PROMiSe trial receiving placebo in order to compare clinical measures in patients with PPMS for whom the natural course of the disease was not affected by exposure to GA treatment.\n\nBODY.METHODS.STATISTICAL ANALYSES.:\nCumulative progression rates were estimated using the Kaplan-Meier methodology. For summaries by month, 1 month was defined as 28 days. For confirmed disability events, patients who experienced a worsening event in the measure of interest that could not be confirmed due to the patient's discontinuation from the trial prior to the confirmation visit were censored at the time of the worsening. Other patients who did not experience the progression event were censored at their last day in the study. Cross-sectional progression rates were determined by comparing baseline and follow-up disability measures. Patients missing any of the 3 disability measures at baseline, the time point of interest, or the corresponding confirmation assessment were excluded from the analysis. The relative percentage contribution of each disability measure to disease progression rates observed for the combined EDSS or T25FW or 9HPT measure was derived by determining the number of individual patients progressing on 1, 2, or all 3 outcomes measures.\n\nBODY.RESULTS:\nA total of 316 patients were assigned to receive placebo in the PROMiSe study; 314 of these patients had a postbaseline EDSS assessment, and these patients constituted the population for the cumulative analyses presented here. Of these, 272 patients were included in the 12-month cross-sectional analysis, and 214 patients constitute the population for the 24-month cross-sectional analysis. Baseline demographic and clinical characteristics for the 314 patients who received placebo are shown in table 1.11 The baseline characteristics of the subgroup of patients assigned to receive placebo were consistent with those of the entire PROMiSe patient population.11 Table 1 Baseline demographic and clinical characteristics of patients who took part in the PROMiSe trial and were randomized to receive placebo Table 2 shows cumulative and cross-sectional UDP and CDP rates at 12 and 24 months. Among single measures, a ≥20% worsening in T25FW (T25FW 20%) was associated with the highest cumulative progression rates, followed by EDSS and then a ≥20% worsening in 9HPT (9HPT 20%) at both the 12- and 24-month time points. Among combined measures, the composite of all 3 individual measures (i.e., EDSS or T25FW 20% or 9HPT 20%) had the highest cumulative 3-month CDP rate at both 12 and 24 months (41.4% and 63.9%, respectively). Cross-sectional 3-month CDP rates were also highest for the composite of all 3 scores than for any single or dual combination of scores at both 12 and 24 months (37.5% and 57.5%, respectively). UDP proportions were consistently higher than CDP proportions for all measures, with a considerably greater difference between UDP and CDP in the cumulative incidence of the composite of all 3 individual measures (1 year: 63.8% and 41.4%, respectively; 2 years: 82.1% and 63.9%, respectively) compared with the cross-sectional proportions (1 year: 47.8% and 37.5%, respectively; 2 years: 57.5% and 52.8%, respectively). Table 2 Cumulative and cross-sectional PROMiSe disease progression rates at 12 and 24 months The proportion of patients with UDP and 3-month CDP for each of the disability metrics over the course of the study is shown in figure 1 for each study paradigm (cumulative and cross sectional). The T25FW 20%-alone values were closely aligned with those from the combined EDSS-or-T25FW 20% values at all time points over the course of the study (table 3). Figure 1Comparison of cumulative and cross-sectional UDP and CDP rates for EDSS, T25FW 20%, and 9HPT 20%(A) EDSS rates. (B) T25FW 20% rates. (C) 9HPT 20% rates. 3M CDP = 3-month confirmed disability progression; 9HPT = 9-hole peg test; EDSS = Expanded Disability Status Scale; T25FW = timed 25-foot walk; UDP = unconfirmed disability progression. Table 3 Disease progression rates over the course of the PROMiSe study The relative contribution of each of the individual component measures—together and in different combinations—of a 3-part composite measure (EDSS or T25FW 20% or 9HPT 20%) is shown in figure 2 and figure e-1 at Neurology.org/nn. T25FW 20% had the greatest contribution to the overall measure, followed by EDSS, and then 9HPT 20%. These figures support the notion that CDP as defined by T25FW identifies individuals as progressors that the other measures would not have been identified. In other words, a greater proportion of patients identified as progressors by T25FW were not identified as progressors by EDSS or 9HPT, as compared with the proportion of patients identified as progressors by EDSS who were not identified as progressors by T25FW or 9HPT (figure e-2). Figure 2Contribution of individual clinical measures evaluating patient worsening at 24 months (cross-sectional 3-month CDP) within a 3-part combined measure (EDSS or T25FW 20% or 9HPT 20%)(A) Cumulative UDP. (B) Cumulative 3-month CDP. (C) Cross-sectional UDP. (D) Cross-sectional 3-month CDP. 3M CDP = 3-month confirmed disability progression; 9HPT = 9-hole peg test; EDSS = Expanded Disability Status Scale; T25FW = timed 25-foot walk; UDP = unconfirmed disability progression.\n\nBODY.DISCUSSION:\nThe data presented here show that among patients with PPMS randomized to receive placebo in the PROMiSe study, T25FW 20% at 12 and 24 months was associated with higher rates of disability progression than EDSS, and both T25FW 20% and EDSS were associated with higher disability rates than 9HPT 20%. The 3-part combination measure (EDSS or T25FW 20% or 9HPT 20%) was associated with more 3-month CDP events (41.4% and 63.9% of patients as 12 and 24 months, respectively) than the 2-part measure (EDSS or T25FW 20% [38.5% and 59.5%, respectively]), and more progression events than any single measure (EDSS, 14.9% and 32.4%, respectively; T25FW, 33.5% and 52.0%, respectively; 9HPT, 8.4% and 18.0%, respectively). Minimal changes in the 9HPT 20% outcome were noted over the course of the PROMiSe trial. As such, this measure may be less suitable than EDSS and T25FW 20% when used alone; however, 9HPT may still have utility as part of a composite measure. Moreover, future studies should explore thresholds other than 20% worsening on performance measures such as 9HPT. A marked difference was noted between cumulative and cross-sectional progression rates, which may inform the design of PPMS trials. Cumulative progression rates were generally higher than cross-sectional rates, but more strikingly, there was a greater difference between unconfirmed and CDP using the cumulative approach. Based on our results, the normative approach to use CDP in classic randomized controlled trials is supported. Failure to confirm disability progression may have a neurobiological basis or may be due to measurement unreliability; it would be preferable to exclude these from pivotal trial analyses in both cases. For trials using the cross-sectional approach, measures of UDP may still be feasible. Such studies would be resource-sparing and less burdensome for participants, but would have acknowledged data sparsity and methodological limitations. The observations presented here add to a growing body of evidence that suggests that combining specific disability measurements may be more useful in the clinical trial setting for assessing progression in patients with PPMS than single measures.9,10,14–16 In a retrospective database study of 181 patients with progressive MS (primary 47% of patients and secondary 53% of patients), combining change in T25FW with EDSS was significantly more predictive of patient prognosis than EDSS alone.15 An earlier retrospective database study of 161 patients with PPMS found that when comparing single measures or 2-instrument combinations involving EDSS, T25FW, and 9HPT, T25FW/9HPT predicted the greatest number of progression events after 1 year (46% of patients progressed compared with 17%, 34%, and 20% for the individual measures, respectively), and the combination of T25FW/EDSS predicted the greatest number of progression events after the second year (57% of patients progressed compared with 32%, 46%, and 24% for the individual measures, respectively).11 An evaluation of data from the 96-week Olympus (rituximab) trial17 in the 147 patients with PPMS randomized to placebo found that a combined measure consisting of EDSS/T25FW/9HPT was associated with more CDP events than did any single or dual combination measure.11 Progression rates at 96 weeks were 61.9% and 54.8% for those patients with an initial confirmed progression event at 12 and 24 weeks, respectively.9 Confirmed progression rates for EDSS alone were 38.5% and 30.4%; for T25FW alone the rates were 51.0% and 44.5%; and for the 9HPT alone the rates were 21.1% and 17.4%, respectively.9 Most recently, the large, prospective INFORMS (fingolimod) study, comprising patients with PPMS treated for at least 3 years, reported that a composite of EDSS, T25FW, or 9HPT predicted more progression events (80.3% cumulative probability of CDP) than any of the individual components alone (EDSS 58.7%, T25FW 70.0%, and 9HPT 41.3% of patients) among those randomized to placebo.14 Although those previous published studies offer similar conclusions to this study regarding the relative utility of outcome measures, they differ in several important ways that distinguish them from our analysis of the PROMiSe data set. The retrospective database study included both primary and secondary progressive patients with MS, was primarily focused on outcomes of early vs late changes on clinical scales, included patients who were exposed to disease-modifying therapies (DMTs) during the course of the study, did not set a minimum disability criterion as per EDSS for study entry, and included less-frequent patient assessment.15 Similarly, the earlier study likely included patients exposed to DMTs, while its entry criteria included an EDSS threshold score of 2.0–6.5, representing a less-disabled patient population than that of the PROMiSe study.10 The same EDSS criteria applied to the Olympus study, whereas none of these 3 studies, nor the INFORMS study, compared confirmed with unconfirmed progression or offered a cross-sectional analysis of disease progression data.9,14 Two other recently published studies address similar themes and arrive at compatible conclusions to those of this study.18,19 In one of these studies, however, the patient population consisted entirely of those with secondary progressive MS,18 whereas the other had a lower EDSS inclusion threshold (1–7), allowed inclusion of patients who had been treated with DMTs as recently as 3 months prior to study entry, and was intended as a validation study of a novel disability score (CombiWISE); that scoring measure, in addition to EDSS, T25FW, and 9HPT, also includes the Scripps Neurological Rating Scale.19 And, as with the previously noted studies, neither unconfirmed disease nor a cross-sectional analysis was included in the design of these studies.18,19 Thus, this study offers several unique features that make it a potentially valuable contribution to the literature, such as reflecting the untreated natural history of PPMS by including only patients receiving placebo, including patients with more severe disability, comparing confirmed and unconfirmed disease progression, and including a cross-sectional analysis. There is an unmet need for controlling disease progression in patients with PPMS. For these patients, individual measures of disease progression may limit the potential to assess the benefit of new agents to the extent that the composite measures have higher event rates. Based on the observations presented here and those from previous studies, future studies of agents for the treatment of PPMS may benefit from either using T25FW 20% as a single outcome measure or using T25FW 20% in combination with the EDSS as a primary efficacy endpoint rather than EDSS alone, particularly if higher event rates over shorter exposure periods are sought. It is largely unknown whether specific disability outcomes would differentially detect treatment effects or whether this would differ according to the mechanism of the treatment under study.\n\nBODY.SUPPLEMENTARY MATERIAL:\n\n\nData Supplement\n\nQuestion: Compared to EDSS/T25FW or EDSS/9HPT what was the result of EDSS/T25FW/9HPT on confirmed disability progression?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1124	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Clinical efficacy of \n\n ABSTRACT:\nAging has become one of the distinctive demographic phenomena in the 21st century and its social, economic and health implications are the most challenging issues. Senile Memory Impairment is a common condition characterized by mild symptoms of cognitive decline and occurs as a part of the normal aging process. It can be correlated to \"Jarajanya Smrtibhramsha\" according to Ayurveda. The present study deals with the efficacy of Guduchyadi Medhya Rasayana on Senile Memory Impairment. A total of 138 patients aged in between 55–75 years were registered and randomly divided into two groups as the trial and control groups. The drugs were administered for 3. The trial drug showed memory enhancement, anti-stress, anti-depressant and anxiolytic properties. The trial group showed better results in the management compared to the control group.\n\nBODY.INTRODUCTION:\nAging has become a great issue for many countries due to a worldwide life prolongation. Number of people over 60 years has grown rapidly to 10% of the world population.[1] In India too, in the last decade, increasing population aged has been projected significantly.[2] So, it is associated with physiological, functional, and pathological changes affecting physical, psychological, emotional and social well-being.[3] The major consequences of the increasing number of individuals in advanced age group is the increase in number of patients suffering from age-related disorders. Conservative estimation revealed that 25% of the elderly persons have significant psychiatric symptoms[4] and the number of psychologicaly ill elderly persons was estimated to be 9 million in the year 2005.[5] Though psychological disorders are common among the aged, it frequently remains undetected and untreated. It induces functional disability, disturbs rehabilitation, burdens the health system and impairs the quality of life of elderly individuals.[6] Research based on the psychological health revealed that age-associated cognitive like memory disorders are found in high prevalence among the aged.[7] Subjective complaints from individuals with age-associated memory impairment often include difficulties in remembering names and words, etc. So, this condition is the result of physiological changes in the aging brain and not a specific neurological disorder.[8] In Ayurveda literature, impairment of memory is mentioned as Smritibhramsha which occurs due to vitiation of Rajas and Tamas Doshas in the mind.[9] The appearance of Jara (aging) at the appropriate age is termed as \"Kalaja Jara\",[10] and memory impairment appears as a clinical Rupa (feature) of Jara,[11] hence Senile Memory Impairment can be correlated as Jarajanya Smritibhramsha according to Ayurveda. In Sarangadhara Samhita, it is clearly emphasized that Medha (intellect) and Buddhi (wisdom) deteriorate in the fourth and ninth decades of life accordingly.[12] Both are closely associated with the mind and help for the normal function of the mind. If these components decrease in the mind, then it will affect the normal function of mind. Moreover, Caraka has noted that cognitive functions are thoroughly affected in old age as Grahana (power of understanding), Dharana (power of retention), Smarana (power of memorizing), Vachana (speech) and functions of sense organs qualitatively.[13]\n\nBODY.INTRODUCTION.IMPORTANCE OF :\nThe aging process occurs over all the body. It does not occur in the same way in every human being. People's lifestyles also have additional influence on aging.[14] The decline in brain weight and volume, degeneration of intracellular organelles, changes in cellular DNA and RNA, neuronal degeneration as well as significant loss of synapses are the salient features of aging in the brain.[15] Therefore, psychological and neurological manifestations often form the hallmark of senility. Hence, Ayurveda clearly emphasizes that in the fourth and ninth decades of lifespan, individuals are subjected to the loss of Medha (intellect) and Buddhi (wisdom). Hence, it seems therapeutic measures of Medhya Rasayanas are exclusively needed for elders because they are brain tonics and improve the psychological faculties. It is responsible for Dhi (intelligence), Dhrti (retention power), Smriti (memory) and also possesses anti-stress and adaptogenic effect.[16] Having considered all literary views and ideas as above mentioned, Guduchyadi Medhya Rasayana (GMR)[17] has been attempted to evaluate its efficacy on Senile Memory Impairment.\n\nBODY.MATERIALS AND METHODS.SELECTION OF THE PATIENTS:\nTotal 138 patients having symptoms of memory impairment attending O.P.D. and I.P.D. of Department of Kaya Chikitsa of I.P.G.T. and R.A., Gujarat Ayurved University, Jamnagar were selected for the present study. A purposive sampling technique was adopted irrespective of their sex, religion, occupation, educational status, etc.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF INCLUSION:\nPatients aged 55 and above up to75 years of age.Complaints of memory impairment on the basis of short term and long term.\nShort term, e.g. misplacing objects, difficulty in remembering multiple items to be purchased, difficulty in recalling information quickly, problems in remembering names and telephone numbers.Long term, e.g. difficulty in recall of special events of personal life, difficulty in recall of previous histories of life and recognition.Patients suffering from dementia.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF EXCLUSION:\nPatients below 55 years and above 75 years of age.Patients with evidence of delirium, confusion or other disturbances of consciousness, Parkinson's disease, stroke, intracranial hemorrhage, brain tumors, history of alcoholism or drug dependence, use of any psychotropic drug, Alzheimer's disease, diabetes mellitus, etc.\n\nBODY.MATERIALS AND METHODS.INVESTIGATIONS:\nRoutine hematological and biochemical tests were carried out before and after the treatment. Among the biochemical tests, serum Acetylcholine Esterase (AChE) estimation, as a biomarker of Senile Memory Impairment, was carried out.\n\nBODY.MATERIALS AND METHODS.PLAN OF THE STUDY:\nPatients fulfilling the inclusion criterion were grouped in to two after obtaining written consent.\n\nBODY.MATERIALS AND METHODS.GROUP A (TRIAL GROUP):\nPatients of this group were administered with the Granules of Guduchyadi Medhya Rasayana (GMR), which contains Guduchi (Tinospora cordifolia Wild.), Apamarga (Achyranthes aspera Linn.), Vidanga (Embelia ribes Burm. f.), Shankhapushpi (Convolvulus pluricaulis Chois.), Vaca (Acorus calamus Linn.), Haritaki (Terminalia chebula Zetz.), Kushtha (Saussurea lappa C.B. Clarke), Shatavari (Asparagus racemosus Wild.), Cow's ghee and sugar. Dosage: 5 g, 3 times per day, after meal Anupana: Water in sufficient quantity Duration: 3 months Total, 73 patients were registered.\n\nBODY.MATERIALS AND METHODS.GROUP B (CONTROL GROUP):\nPatients of this group were administered Sarkaradi Granules (SG). Dosage: 3 g, 3 times per day, after meal Anupana: Water in sufficient quantity Duration: 3 months Total 65 patients were registered.. Both the drugs were prepared at Pharmacy, Gujarat Ayurved University, Jamnagar.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT:\nEffects of Medhya Rasayana on memory impairment were assessed in two ways, i.e. as subjective and objective, before and after the treatment. After completion of the treatment, the patients were graded into five groups based on their improvement in order to ascertain the overall therapeutic efficacy. The data so obtained were analyzed using SPSS and Sigma Stat statistical packages. Observations and results pertaining to clinical parameters were presented in tabular form along with the findings of statistical analysis. Paired \"t\" test was adopted to find out the effect of therapy for each group individually, while unpaired \"t\" test used for comparative effect.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT.SUBJECTIVE CRITERIA:\nAssessments on improvements in signs and symptoms were carried out using appropriately designed scoring method, with the scores ranging from 0 to 4. Cognitive state was assessed by Mini Mental State Examination.[18] and psychological health of the patients was evaluated with Hamilton Rating Scales for Depression and Anxiety.[19]\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT.OBJECTIVE CRITERIA:\nSerum AChE estimation was carried out as a biomarker of Senile Memory Impairment.\n\nBODY.OBSERVATIONS AND RESULTS:\nTotal 138 patients of Senile Memory Impairment were registered in the study. Forty-three patients in the Group A (trial group) and 56 patients in the Group B (control group) completed the treatment, while 30 patients in Group A and 9 patients in Group B discontinued. In this study, various etiological factors were identified. Maximum number of patients reported Chinta (thoughts; 92%), followed by Krodha (anger; 83.3%), Shoka (worries; 70.2%), Chittodvega (anxiety; 64.4%), Bhaya (fear; 51.4%), Ruksha Ahara (dried food; 55.7%), Rattri Jagarana (awaking at night; 87%), etc.\n\nBODY.OBSERVATIONS AND RESULTS.EFFECT OF THERAPY:\nBoth the groups showed highly significant (P`0.001) relief from all the chief complaints [Table 1 and Table 2]. Table 1 Effect of GMR in Group A on the symptoms of Senile Memory Impairment Table 2 Effect of SG in Group B on the symptoms of Senile Memory Impairment In comparison to Group B, Group A showed highly significant relief in symptoms such as names forgotten (63.56%), numbers forgotten (61.62%), and memory impairment in recalling special events in life (59.71%) at a level of P`0.001, and forgetfulness (68.60%), losing of valuables (73.64%), difficulty in remembering multiple items to be purchased (68.21%), inability to concentrate (68.14%), impaired recognition (79.7%), memory impairment of recall of previous histories (60.66%) at a level of P`0.01, and a significant relief (P`0.05) from difficulty in recalling information quickly (71.57%), depression (89.66%), and inability to relax (82.93%) [Table 3]. Table 3 Comparison of the effects of GMR and SG on the symptoms of Senile Memory Impairment With respect to Dosha Dushti, the Group A showed significant relief from Vata Dushti (85.48%), Pitta Dushti (94.15%) and in Kapha Dushti (84.3%), while the Group B showed significant relief from Vata Dushti (68.3%), Pitta Dushti (61.78%) and in Kapha Dushti (62.75%). On Hamilton Anxiety Rating Scale, both the groups showed highly significant relief (P`0.001) from all the symptoms individually. In comparison to the results obtained from Group B, the Group A showed highly significant relief with respect to intellectual cognitive functions (79.03%), somatic (muscular) disorders (83.71%), depression (74.12%), and a significant relief from fear (81.11%). On Hamilton Depression Rating Scale, both the groups showed highly significant relief (P`0.001) from all the symptoms individually. However, the comparative results were insignificant. The results of symptoms of Mini Mental State Examination showed that both the groups provided highly significant (P`0.001) improvement individually. In comparison with SG, GMR showed highly significant improvement in registration (9.30%), attention and calculation (24.49%), and a significant improvement in language (13.51%) and in total score (14.89%) [Table 4]. The results obtained with hematological parameters reveal that Group A showed [Table 5] highly significant increase in total RBC (1.20%) count, a significant increase in Hb% (1.34%), packed cell volume (PCV) (1.30%) and a significant decrease in erythrocyte sedimentation rate (ESR) value (7.40%), while Group B showed highly significant decrease in RBC count (4.30%), PCV (3.34%), and a significant decrease in Hb% (1.55%). Table 4 Comparison of the effects of GMR and SG on the symptoms of mini mental state examination Table 5 Effect of GMR on hematological parameters in Group A (n=43) With regard to the biochemical parameters, Group A showed highly significant decrease (P`0.01) in serum cholesterol, serum triglyceride, low density lipoprotein (LDL), and very low density lipoprotein (VLDL) levels, while high density lipoprotein (HDL) increased highly significantly (P`0.01) and a significant decrease (P`0.05) was found in blood urea (13.80%) as well as serum AChE (3.67%) within normal limits [Table 6]. The Group B showed highly significant increase in blood urea (10.04%), but it was within normal limit. Other parameters were found to be statistically insignificant. Table 6 Effect of GMR on biochemical parameters in Group A (n=43) Regarding the overall effect, Group A showed marked improvement in 18.6% patients, moderate improvement in 74.4% patients and mild improvement in 7.0% patients, while Group B showed moderate improvement in 32.2% patients and mild improvement in 67.8% patients.\n\nBODY.DISCUSSION:\nIt has been mentioned in texts that GMR contributes to enhance the memory power within a short period. On the basis of Rasapanchaka, the pharmacotherapeutic properties reveal that it contains Katu, Tikta and Madhura in Rasa, and the effect of Katu and Madhura in Vipaka. Moreover, due to various properties of Tikshna, Laghu, Ruksha, Sara, Guru and Snigdha, it possesses markedly Ushna Virya and mildly Sheeta Virya. Accordingly, GMR was considered to be an effective treatment for Tridoshahara. In Ayurveda, it is clearly emphasized that Smritibhramsha (memory impairment) results due to Rajas and Tamasdoshas in the mind. These doshas are responsible for producing avarana over the mind. The relief from the symptoms has been found to be statistically highly significant. These observations reveal that the drug might have counteracted or pacified Raja and Tamo Doshas, so Avarana of mind was removed and the disease was subsided or controlled. Further pharmacological studies have proven that Vaca (Acorus calemus Linn.) and Shankhapushpi (Convolvulus pluricaulis Chois) have anxiolytic, memory enhancing, anti-stress, antidepressant, tranquilizing and sedative activities.[20, 21] Further, it was found that there was a significant improvement by 14.84% on the total score of the Mini Mental State Examination [Table 4]. So, these evidences indicate the positive role of Medhya property of GMR on Senile Memory Impairment among elderly individuals. Considering the symptoms of memory impairment along with the cognitive decline, a highly significant result was obtained both from GMR and SG [Table 1 and Table 2]. However, in comparison, GMR has given better relief for the majority of symptoms [Table 3]. The Medhya Rasayanas are special Ayurvedic neuro nutraceuticals which are specific to brain and nervous system. They are claimed to promote cognitive function of the brain.[22] Further, it was mentioned in the Caraka Samhita that Shankhapushpi, a Rasayana drug, has the property of promoting intellect.[23] Moreover, Group B also showed improvement of memory due to the Medhya effect of ghee.[24] The serum AChE value has shown an upper range in both the groups before the treatment and a significant decrease was observed after the treatment in Group A [Table 6]. The recent advances in clinical research reveal that AChE activity is increased in human cerebrospinal fluid during aging[25] and scientists believe that dementia-related memory issues stem from the increased breakdown of acetylcholine due to a preponderance of AChE which degrades acetylcholine.[26] Furthermore, a decrease in AChE activity has noted in the treated animals, leading to an increase in the cholinergic activity in the brain.[27] The significant reduction of AChE in Group A shows that GMR exerts its effect on memory enhancement by increasing the cholinergic function by preventing the breakdown of acetylcholine in the aging human brain.\n\nBODY.CONCLUSIONS:\nSenile Memory Impairment can be correlated to Jarajanya Smritibhramsha according to Ayurveda, and imbalance of Trigunas through aggravation of Rajas and Tamas Doshas in the mind leads to development of Senile Memory Impairment among elders. Modern literature reveals that Senile Memory Impairment is closely associated with cognitive decline during aging. All the patients of Senile Memory Impairment were having features of impairment of short memory and long memory in this study. Manasika Nidana (psychic factors), Aharaja (dietary) and Viharaja (behavioral) factors, which were reported by the patients, play a major role in the pathogenesis of Senile Memory Impairment by vitiating Rajas and Tamas Doshas in the mind. Those factors were Chinta (thoughts), Krodha (anger), Shoka (worries), Chittodvega (anxiety), Bhaya (fear), Moha (illusions), Ruksha Ahara (dried food), Ratri Jagarana (awaking at night), etc. GMR has shown statistically highly significant improvement on short memory impairment as well as long memory impairment in Senile Memory Impairment, at the level of P`0.001. Reduction of AChE showed enhancement of memory functions due to improvement of cholinergic actions in the human brain in the trial group (Group A). GMR has shown memory enhancing, antidepressant, anti-stress, and anxiolytic potential. Hence, Guduchyadi Medhya Rasayana therapy has proved so as to provide better improvement in comparison to the control group.\n\nQuestion: Compared to administered Sarkaradi Granules (SG). what was the result of administered with the Granules of Guduchyadi Medhya Rasayana (GMR), which contains Guduchi (Tinospora cordifolia Wild.), Apamarga (Achyranthes aspera Linn.), Vidanga (Embelia ribes Burm. f.), Shankhapushpi (Convolvulus pluricaulis Chois.), Vaca (Acorus calamus Linn.), Haritaki (Terminalia chebula Zetz.), Kushtha (Saussurea lappa C.B. Clarke), Shatavari (Asparagus racemosus Wild.), Cow's ghee and sugar. on names forgotten, numbers forgotten, memory impairment in recalling special events in life, forgetfulness, losing of valuables, difficulty in remembering multiple items to be purchased, inability to concentrate, impaired recognition, memory impairment of recall of previous histories, difficulty in recalling information quickly, depression, and inability to relax ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1006	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effect of \n\n ABSTRACT.BACKGROUND:\nTo evaluate the value of KRAS codon 13 mutations in patients with advanced colorectal cancer (advanced CRC) treated with oxaliplatin and fluoropyrimidines.\n\nABSTRACT.METHODS:\nTumor specimens from 201 patients with advanced CRC from a randomized, phase III trial comparing oxaliplatin/5-FU vs. oxaliplatin/capecitabine were retrospectively analyzed for KRAS mutations. Mutation data were correlated to response data (Overall response rate, ORR), progression-free survival (PFS) and overall survival (OS).\n\nABSTRACT.RESULTS:\n201 patients were analysed for KRAS mutation (61.2% males; mean age 64.2 ± 8.6 years). KRAS mutations were identified in 36.3% of tumors (28.8% in codon 12, 7.4% in codon 13). The ORR in codon 13 patients compared to codon 12 and wild type patients was significantly lower (p = 0.008). There was a tendency for a better overall survival in KRAS wild type patients compared to mutants (p = 0.085). PFS in all patients was not different in the three KRAS genetic groups (p = 0.72). However, we found a marked difference in PFS between patients with codon 12 and 13 mutant tumors treated with infusional 5-FU versus capecitabine based regimens.\n\nABSTRACT.CONCLUSIONS:\nOur data suggest that the type of KRAS mutation may be of clinical relevance under oxaliplatin combination chemotherapies without the addition of monoclonal antibodies in particular when overall response rates are important.\n\nABSTRACT.TRIAL REGISTRATION NUMBER:\n2002-04-017\n\nBODY.BACKGROUND:\nThe oncogene KRAS belongs to the protein family of small G-proteins and is mutated in 35-40% of colorectal cancers (CRC) [1]. RAS mutations are considered early events in colon carcinogenesis and are well conserved between primary tumor and corresponding metastases [2]. KRAS mutations tested routinely include six mutations in codon 12 and one mutation in codon 13. KRAS has been studied extensively as a prognostic marker in CRC, but results are still conflicting. Overall, there seems a tendency towards inferior outcome for patients with KRAS mutant tumors even in large randomized trials [3-7]. Importantly, KRAS has recently been identified as a strong predictive marker for patients with advanced CRC under anti-EGFR-treatment. Various studies demonstrated that while patients with tumors expressing wild type KRAS may benefit from anti-EGFR (epidermal growth factor receptor)-antibody treatment, patients carrying a mutated KRAS gene do not [5,8-10]. In contrast, two large trials using oxaliplatin-based chemotherapy-backbones did not confirm KRAS wild type to be a powerful predictor of treatment efficacy in metastatic CRC [4,11]. However, the studies published until recently did not differentiate between the different KRAS mutations and other histopathological or molecular features of their patients. The clinical observation, that some patients with KRAS mutation may respond to anti-EGFR-antibody therapy, as well as experimental data, that the biological effects of KRAS mutations may differ, was addressed recently by de Roock and Tejpar [12,13]. They reported that patients with codon 13 mutations in KRAS exhibit a worse overall prognosis with short overall survival times under standard chemotherapy, but may benefit from anti-EGFR-antibody therapy similar to wild type patients. These observations prompted us to look for the effect of the KRAS mutational status in correlation with response and survival data in patients with advanced colorectal cancer receiving oxaliplatin containing chemotherapy from a prospective randomized multicenter phase III trial of the German AIO study group.\n\nBODY.METHODS.PATIENTS:\nAll patients participated in a prospective randomized phase III first-line palliative chemotherapy trial of advanced CRC of the AIO colorectal study group (Arbeitsgemeinschaft Internistische Onkologie of the German Cancer Society). The study was performed according to the Helsinki declaration and it was approved by the ethics review board of the Central Hospital Bremen and of the Medical Faculty of the Ruhr-University Bochum. The study design, patient characteristics, treatment plans and results of the clinical trial have been reported previously [14]. Briefly, a total of 474 patients were randomized to be treated with either 5-FU/folinic acid (FA) and oxaliplatin (FUFOX: oxaliplatin, 50 mg/m2; FA, 500 mg/m2; continuous 5-FU, 2,000 mg/m2/22 h; on day 1, 8, 15, 22; q day 36) or capecitabine and oxaliplatin (CAPOX: oxaliplatin, 70 mg/m2 on day 1 and 8; capecitabine, 2 × 1,000 mg/m2/day consecutively for 2 weeks, q day 22). No clinical factor was found to be predictive for definition of a subgroup of patients benefiting more or less from each fluoropyrimidine backbone. We here present data on a subcohort of 201 patients (42.4%) with available formalin-fixed paraffin-embedded tissue. Samples were retrieved from pathologists responsible for first diagnosis, pseudononymized and forwarded to the Institute of Pathology of the Ruhr-University Bochum, which was blinded to treatment allocation and prognostic outcomes.\n\nBODY.METHODS.DNA EXTRACTION AND MUTATION ANALYSIS:\nDNA was extracted from anonymized formalin-fixed paraffin embedded tissue samples. For each patient, five 10-μm sections were prepared. An additional representative 1-μm section was deparaffinized, stained with H&E, and analyzed for detailed morphology. Regions displaying tumor cellularity of >70% were marked and macrodissected. Tissue was extracted using QIAmp DNA Mini kit (Qiagen, Hilden, Germany). Real-Time PCR amplification for the most frequent seven KRAS mutations was performed using commercially available kits from DxS Ltd. (Manchester, UK) according to the manufacturer's instructions. This kit detects >95% of known KRAS mutations. Laboratory staff was blinded to the patient data and clinical outcome. BRAF mutation analysis to detect the V600E substitution was performed by RT-PCR (see supplemental file for further details).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nChi-square test was used to evaluate the associations between KRAS status and other dichotomous variables. The analysis of progression-free survival (PFS) and overall survival (OS) was done using the Kaplan-Meier method and differences between subgroups were calculated by log-rank test. Data have been analyzed using SPSS 18.0 (Munich, Germany). All tests were two sided. For all tests, p values <0.05 were considered significant.\n\nBODY.RESULTS.PATIENT CHARACTERISTICS:\nThe subcohort of patients successfully analyzed for KRAS mutations consisted of 201 patients (61.2% males with a mean age of 64.2 ± 8.6 years, range 35 – 82). Colon cancer was diagnosed in 131 (65.2%) patients while rectal cancer was diagnosed as primary tumor in 61 (30.3%) patients. Localization was not known for 9 cases (4.5%). 105 (52.2%) patients were treated with FUFOX, whereas 96 (47.7%) patients received CAPOX. 115 (57.2%) patients had synchronous metastases, whereas 59 (29.4%) had metachronous metastases. Whether metastases were synchronous or metachronous was not known for 27 ( 13.4%) patients (Table1). The subcohort reported here was representative of the complete study cohort with respect to age, gender, treatment plans (i.e. percentage of patients with FUFOX and CAPOX respectively). Median PFS and OS of the total ITT (intention-to-treat) population [14] and the biomarker subpopulation were fully comparable (PFS under FUFOX was 8.0 in the ITT cohort vs. 7.8 in the KRAS cohort; PFS under CAPOX was 7.1 vs. 7.0; OS under FUFOX was 18.8 in the ITT cohort vs. 17.5 in the KRAS subcohort and OS under CAPOX was 16.8 vs. 18.4). Table 1 Baseline characteristics of the investigated subcohort Biomarker population N % Age Mean 64.15 years Range 35–82 years ≤60 y 58 28.9 >60 y 143 71.1 Sex Female 78 38.8 Male 123 61.2 Treatment arm FUFOX 105 52.2 CAPOX 96 47.8 Localization of primary tumor Colon 131 65.2 Rectum 61 30.3 n.k. 9 4,5 T stage at initial diagnosis T1 1 0.4 T2 15 7.5 T3 132 65.7 T4 49 24.4 n.k. 4 2.0 N stage at initial diagnosis N0 46 22.9 N1 57 28.3 N2 89 44.3 n.k. 9 4.5 M stage at initial diagnosis M0* 59 29.4 M1 115 57.2 n.k. 27 13.4 M0 indicates metachronous metastatic disease at initial diagnosis of CRC, M1 indicates synchronous metastatic disease at initial diagnosis of CRC. n.k. = not known – there were no data available. \n\nBODY.RESULTS.MUTATION FREQUENCY:\nKRAS mutations could be successfully analyzed in 201 samples. We identified KRAS mutations in 73/201 (36.3%) tumors. 58 (28.9%) of KRAS mutations were located in codon 12, whereas 15 (7.46%) were found in codon 13(see Table2). The three most frequent KRAS alterations in our samples were c.35 G > A (G12D, n = 25; 12.4%), c.38 G > A (G13D, n = 15; 7.46%), and c.35 G > T (G12V, n = 13, 6.46%). In 128 patients no KRAS mutation was found (63.6%). In these patients we detected 13 mutations in the BRAF gene (V600E) (10% of wild type patients). Table 2 KRAS mutation frequency in the investigated subcohort ( KRAS Wild type: 128 (63.7%), KRAS Mutation 73 (36.3%)) relative frequency of occurrence (%) absolute frequency of occurrence CODON 12 mutation: Aspartate (G12D) c.35G>A 12,4 25 Valine (G12V) c.35G>T 6,5 13 Alanine (G12A) c.35G>C 3,4 7 Cysteine (G12C) c.34G>T 3 6 Serine (G12S) c.34G>A 3 6 Arginine (G12R) c.34G>C 0,5 1 CODON 13 mutation: Aspartate (G13D) c.38G>A 7,5 15 \n\nBODY.RESULTS.CORRELATION BETWEEN MUTATIONS AND RESPONSE RATE:\nTumor response evaluation was available for 201 patients. Grouping all KRAS mutations together, mutated tumors were associated with a significantly lower response rate (RR; defined as partial or complete remission by RECIST) as compared to tumors without KRAS mutations (44.4% vs. 63.0%, p = 0.012). When patients with codon 13 mutated tumors were analysed separately the overall response rate in this cohort was 23% as compared to 49% in codon 12 mutated tumors and 63% in wild type tumors (Table3, p = 0.008). Disease control rates (DCR) were 77%, 81% and 88%, respectively, which was not statistically significant (Table3, p = 0.29). Table 3 Tumor response assessment and correlation to KRAS mutational status All patients All WT Codon 12 mutation Codon 13 mutation p-value No. of patients% 201 128 58 15 100 63.6 28.9 7.5 ORR% 55 63 49 23 0.008 95% CI (49–61) (54–71) (37–62) (8–51) (Chi-Square) DCR% 85 88 81 77 0.29 95% CI (80–90) (80–92) (68–89) (49–93) (Chi-Square) All patients. Percentages based on non-missing data, p-values for WT vs Codon 12 mutations vs codon 13 mutations; WT wild type; ORR overall response rate, DCR disease control rate. \n\nBODY.RESULTS.CORRELATION BETWEEN MUTATIONS AND PROGRESSION-FREE SURVIVAL:\nDuring follow-up, 170 of 201 evaluable patients had progressed. The median PFS in all patients of the KRAS subcohort was not statistically different in relation to the KRAS mutational status (wild type: 7.5 months, mutation codon 12: 8.2 months, mutation codon 13: 10.0 months; p = 0.71) (Figure1). However, when analysing the two treatment arms separately, we found a substantial, non-significant, difference in PFS in codon 13 mutated tumors versus codon 12 mutated tumors. While median PFS was as low as 6.1 months for codon 13 patients receiving infusional 5-FU, median PFS was 13.3 months in patients treated with capecitabine (HR: 2.52, p = 0.22). Patients with codon 12 mutations showed a trend towards the opposite effect: median PFS was 7.0 months under CAPOX therapy while median PFS was 9.9 months under FUFOX (HR: 0.62, p = 0.12) (Table4). Figure 1 Progression-free survival according to KRAS status. Table 4 PFS (progression free survival) according to KRAS mutation for the two different treatment arms PFS FUFOX CAPOX p-value (log rank) n = 105 n = 96 HR (95% CI) All patients 8.2 months 6.4 months 0.18 0.81 (0.61-1.09) WT 8.1 months 6.4 months 0.29 0.82 (0.56-1.19) Codon 12 mutation 9.9 months 7.0 months 0.12 0.62 (0.33-1.14) Codon 13 mutation 6.1 months 13.3 months 0.22 2.52 (0.54-11.70) PFS, HR hazard ratio by cox regression, CI confidence interval, WT wild type. \n\nBODY.RESULTS.CORRELATION BETWEEN MUTATIONS AND OVERALL SURVIVAL:\nDuring follow-up 135 of 201 evaluated patients had died. We observed a trend towards a better survival time in patients with wild type tumors compared to those with a mutation of KRAS. The overall survival of wild type KRAS patients was 19.2 months, for patients with codon 12 mutations 15.6 months and for patients with codon 13 mutations 16.5 months. These differences were of marginal significance (p = 0.085) (Figure2). Figure 2 Overall survival according to KRAS status. Evaluating the different treatment arms separately, we found comparable survival times without significant differences (Table5). Since the survival curves seemed to separate for wild type KRAS and mutant KRAS patients at 14 months we hypothesised that this difference was most likely caused by the influence of post-study treatment. 71 out of 128 (55.4%) wild type patients received further lines of therapy while 32 out of 128 wild type patients (25%) received cetuximab. Out of 73 patients with KRAS mutations 42 were treated in further lines (57.5%) with 10 patients receiving cetuximab (13.7%). When analysing post progression survival (PPS) in these patients receiving second and further line therapies, patients receiving cetuximab had a significant better overall survival when compared to those patients under irinotecan therapy only, irrespective of the KRAS status. PPS in KRAS wild type patients: 32.2 months when cetuximab was given and 18.8 months when cetuximab was not included (p < 0.001). PPS for KRAS mutant patients: 27.9 months under cetuximab and 16.9 months without cetuximab (p = 0.032). Table 5 OS (overall survival) according to KRAS mutation for the two different treatment arms OS FUFOX CAPOX p-value (log rank) n = 105 n = 96 HR (95% CI) WT 24.2 months 18.9 months 0.31 0.79 (0.51-1.24) Codon 12 15.6 months 15.5 months 0.54 mutation 0.83 (0.45-1.53) Codon 13 16.1 months 16.5 months 0.62 mutation 1.39 (0.37-5.37) OS, HR hazard ratio by cox regression, CI confidence interval. \n\nBODY.DISCUSSION AND CONCLUSIONS:\nWe assessed the prognostic value of KRAS codon 12 and codon 13 mutations in tumor tissue from patients with advanced CRC recruited into a phase III clinical trial using CAPOX or FUFOX treatment regimens. This is the first randomized phase III trial retrospectively investigating the role of codon 13 mutations in advanced CRC patients treated with oxaliplatin combination chemotherapy only, without the addition of a monoclonal antibody. While the overall response rate in codon 13 patients was significantly lower, PFS was not different in the three KRAS mutational groups. Interestingly, we found a substantial difference in PFS between patients with codon 12 and 13 mutant tumors when looking at infusional 5-FU versus capecitabine based regimens. Patients with codon 13 mutations seem to benefit more in terms of PFS from the oral capecitabine based protocols. Moreover, there was a strong trend towards better overall survival in patients with wild type KRAS compared to all mutant KRAS patients. Lastly, when analysing OS in patients who received second and further line therapy we found that KRAS wild type and KRAS mutant patients alike showed a significantly higher OS post progression when treated with cetuximab. A number of studies have looked at the potential prognostic or predictive value of KRAS mutations on response rates and survival in patients with CRC and several studies found a negative impact of KRAS mutations on prognosis [3,7,15-17]. Recently, a number of randomized trials have included translational research programs to evaluate certain target genes and their role as prognostic or predictive markers in patients with metastatic disease. Thereby, the mutational status of KRAS has now been established as a strong predictive marker of resistance to anti-EGFR-antibody treatment [5,8,10], although some trials could not fully confirm these results [4,11]. We still do not exactly know whether KRAS mutations influence the response to other treatment regimens such as standard chemotherapy or bevacizumab combinations. While bevacizumab efficacy seems independent from the KRAS status [18], the activity of certain chemotherapeutic agents may be influenced by KRAS mutations. There, patients seem to do worse under oxaliplatin combinations when carrying a mutant KRAS gene within their primary cancer [4,5,7,16,19,20]. For example, in the recently reported COIN study patients under oxaliplatin/5-FU combinations showed a median PFS of 8.6 months in the wild type KRAS cohort while median PFS was only 6.9 months in the KRAS mutant cohort [4]. Similarily, ORR was lower in KRAS mutant patients receiving chemotherapy with oxaliplatin only (41% vs. 50%). Furthermore, another recent small study evaluated the KRAS status in 66 patients receiving a second line chemotherapy with oxaliplatin and infusional 5-FU refractory to 5-FU/irinotecan based chemotherapy [16]. This study found a significantly lower response rate (7% vs. 27%, p = 0.026) and significantly shorter median PFS (3.1 vs. 5.2 months, p = 0.007) for patients with mutant KRAS tumors compared to patients with wild type KRAS tumors under oxaliplatin containing therapy. Very recently, experimental and some clinical reports suggested that not all KRAS mutations behave alike [12,13,21]. In fact, there is evidence that patients carrying mutations in codon 13 of the KRAS oncogene which is found in about 8% of patients with advanced CRC have a substantially worse overall prognosis but may, on the other hand, benefit from anti-EGFR-treatment. In our study we found a similar rate of codon 13 mutations as described before. The overall response rate in patients with codon 13 mutations in our analysis was as low as 23%, significantly lower than in patients with wild type or codon 12 mutations. The CRYSTAL- and the OPUS-studies alike found low response rates in patients with codon 13 mutations treated with combination chemotherapy only (17% for irinotecan combinations and 33% for oxaliplatin combinations) [13]. In contrast to previous reports, ORR was substantially higher in this codon 13 mutant patient cohort when cetuximab was added. Our study was conducted using combination chemotherapy with oxaliplatin in first line treatment without the addition of monoclonal antibodies. Interestingly, the PFS and OS in our codon 13 cohort compared to the other mutated groups and other previously published works was rather long with a PFS of 10 months and an OS of 16.5 months [13]. We do not know why PFS and OS of the codon 13 cohort in our study was prolonged when response rates were as low as 23%. Either low patient numbers or a yet unknown functional mechanism of codon 13 mutated KRAS proteins within colon cancers may be responsible for the observation. The present analysis also suggests that there may be an interaction between the type of KRAS mutation and the mode of application of 5-FU, i.e. whether administered intravenously or orally as capecitabine. In particular, patients with codon 13 mutations showed longer median PFS intervals when receiving capecitabine compared to infusional 5-FU. Although the overall efficacy of infusional 5-FU and capecitabine in advanced CRC has been found to be comparable [22] there may be some patient subpopulations or treatment regimen where the mode of application of the fluoropyrimidine is more crucial. For example, anti-EGFR antibodies in wild type KRAS patients may only be active when infusional 5-FU regimens are used, but not when capecitabine based protocols are applied [4]. The potential resistance of KRAS mutated tumors to oxaliplatin containing regimens seems interesting and may reveal more general mechanisms of drug resistance in cancers. Oxaliplatin belongs to the platinum containing compounds like cisplatinum and carboplatinum. Metabolites of platinum compounds interact with DNA and form crosslinks. In addition, platinum-DNA-adducts strongly inhibit DNA polymerases and therefore act antineoplastic. Some authors have studied in cell culture systems and preclinical models the influence of oncogenic RAS mutations on the activity of platinum compounds and found that the nucleotide excision repair protein ERCC-1 may be upregulated through activated RAS. ERCC-1 may subsequently activate DNA repair capacity and thus mediate platinum resistance. A recent study evaluated the role of ERCC-1 mRNA levels in 191 patients treated with FOLFOX within the CONFIRM1 and CONFIRM2 studies. Low ERCC-1 gene expression was correlated with higher response rates to FOLFOX chemotherapy and better overall survival. In contrast patients with high ERCC-1 did not have benefit from FOLFOX chemotherapy [23]. Of note, we have examined the expression of ERCC-1 by immunohistochemistry in our cohort and found no obvious correlation with KRAS status, response rates or survival and ERCC-1 expression (data not shown). The analysis of the ERCC-1 expression levels by RT-PCR as reported by other studies has not been performed so far [24]. Median overall survival after first progression correlated with cetuximab-treatment in patients bearing KRAS wild type and mutant tumors alike. The role of codon 13 mutation in this setting appears minor since there were only two patients with a codon 13 mutated tumor in the cohort with KRAS mutations of whom we know about cetuximab application. However, there are at least two limitations to our analysis. First, numbers are low in particular in the cetuximab group and secondly addition of cetuximab was not randomized for. There seems to be a selection of patients with good performance status and good prognosis who received third line therapy compared to those who did not. Therefore, we can not draw definite conclusions from our analysis whether anti-EGFR antibodies are effective in patients with KRAS G13D mutations or not. We presently can not draw final conclusions regarding patient management from this study. It remains unclear whether chemotherapy backbones with irinotecan are less prone to interactions with mutated KRAS because data regarding this issue are conflicting. Independent validation of the findings is essential. Therefore, the standardized, thorough and comprehensive collection of tissue and blood samples of all trial patients within independent cancer tissue banks should be a major goal of modern clinical cancer trials.\n\nBODY.MISC:\nAnke Reinacher-Schick and Karsten Schulmann are contributed equally\n\nBODY.COMPETING INTERESTS:\nD. Arnold: Honoraria from Roche, Sanofi-Aventis. U. Graeven: Honoraria from Roche, Amgen, Sanofi-Aventis, Merck-Serono; Advisory Board Roche, Amgen. A. Reinacher-Schick: Honoraria from Amgen, Roche, Pfizer, Sanofi-Aventis; Advisory board member: Amgen, Roche, Pfizer; Studies sponsored by: Roche, Sanofi-Aventis. W. Schmiegel: Honoraria from Merck-Serono, Roche, Abott, Amgen, Astra-Zeneca, Pfizer, Falk; Advisory board member: Astra-Zeneca, Roche, Amgen; Studies sponsored by: Novartis, Amgen, Roche. K. Schulmann: Honoraria from Astra-Zeneca, Amgen, Falk; Travel support: Pfizer, Merck-Serono, Novartis. A. Tannapfel: Honoraria from Amgen, Roche, Pfizer, Sanofi-Aventis. Studies sponsored by: Roche, Sanofi-Aventis. The other authors declare that they have no competing interests.\n\nBODY.AUTHORS’ CONTRIBUTIONS:\nARS and KS: analysis and interpretation of data, drafting of the manuscript, revising the manuscript critically, final approval of manuscript. DPM: interpretation of data, biostatistic analysis, revising the manuscript critically, final approval of manuscript. NB: acquisition of data, analysis and interpretation of data, final approval of manuscript. UG: conception and design, recruitment of patients, revising the manuscript critically, final approval of manuscript. MJ: acquisition of data, analysis and interpretation of data, final approval of manuscript. RG: recruitment of patients, revising the manuscript critically, final approval of manuscript. RP and WS: recruitment of patients, conception and design, revising the manuscript critically, final approval of manuscript. DA: conception and design, revising the manuscript critically, final approval of manuscript. AT: conception and design, data acquisition, analysis and interpretation of data, revising the manuscript critically, final approval of manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2407/12/349/prepub\n\nQuestion:* Compared to CAPOX what was the result of FUFOX on Overall survival?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1133	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: First-in-Human Evaluation of the Safety and Immunogenicity of an Intranasally Administered Replication-Competent Sendai Virus–Vectored HIV Type 1 Gag Vaccine: Induction of Potent T-Cell or Antibody Responses in Prime-Boost Regimens\n\n ABSTRACT:\nBackground. We report the first-in-human safety and immunogenicity assessment of a prototype intranasally administered, replication-competent Sendai virus (SeV)–vectored, human immunodeficiency virus type 1 (HIV-1) vaccine. Methods. Sixty-five HIV-1–uninfected adults in Kenya, Rwanda, and the United Kingdom were assigned to receive 1 of 4 prime-boost regimens (administered at 0 and 4 months, respectively; ratio of vaccine to placebo recipients, 12:4): priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Results. All vaccine regimens were well tolerated. Gag-specific IFN-γ enzyme-linked immunospot–determined response rates and geometric mean responses were higher (96% and 248 spot-forming units, respectively) in groups primed with SeV-Gag and boosted with Ad35-GRIN (SLA and SHA) than those after a single dose of Ad35-GRIN (56% and 54 spot-forming units, respectively) or SeV-Gag (55% and 59 spot-forming units, respectively); responses persisted for ≥8 months after completion of the prime-boost regimen. Functional CD8+ T-cell responses with greater breadth, magnitude, and frequency in a viral inhibition assay were also seen in the SLA and SHA groups after Ad35-GRIN boost, compared with those who received either vaccine alone. SeV-Gag did not boost T-cell counts in the ASH group. In contrast, the highest Gag-specific antibody titers were seen in the ASH group. Mucosal antibody responses were sporadic. Conclusions. SeV-Gag primed functional, durable HIV-specific T-cell responses and boosted antibody responses. The prime-boost sequence appears to determine which arm of the immune response is stimulated. Clinical Trials Registration. NCT01705990.\n\nBODY:\nDespite significant progress in prevention and treatment of human immunodeficiency virus type 1 (HIV-1) infection, development of a safe and effective preventive HIV-1 vaccine remains a global priority [1, 2]. Several vaccine regimens have been tested for efficacy, but only one conferred modest, transient protection against HIV-1 acquisition [3]. Various methods have been evaluated to enhance responses to HIV vaccines, including booster injections, cytokine administration, adjuvants, electroporation, vector delivery systems, and prime-boost approaches [4–8]. Development of a vaccine that stimulates sustained humoral and/or cellular immunity at mucosal entry points may be critical for an HIV preventive vaccine. Although mucosally administered vaccines have been tested and licensed for other diseases [9–12], mucosal administration of an HIV preventive vaccine has seldom been evaluated [13]. Sendai virus (SeV) is a nonsegmented negative-sense RNA virus in the Paramyxoviridae family that can infect the upper respiratory tract [14–17]. As a live viral vector that is not pathogenic in humans, SeV offers several properties important for a successful vaccine: it does not integrate into the host genome, it replicates only in the cytoplasm without DNA intermediates or a nuclear phase, and it does not undergo genetic recombination. SeV is genetically and antigenically related to hPIV-1 [18–21]. A live nonrecombinant SeV vaccine against human parainfluenza virus type 1 (hPIV-1) administered intranasally in adults and young children was safe and immunogenic [22, 23]. SeV antibodies cross-reactive with hPIV-1 antibodies are present in most people [24]. Intranasal delivery of a vaccine could induce a first line of defense at mucosal points of entry and induce effective systemic immune responses [12, 25, 26]. Nonhuman primate studies with SeV bearing simian immunodeficiency virus (SIV) genes demonstrated protection against SIV challenge and evidence that SeV vectors may boost responses primed by other HIV-1 vaccines [27–29]. Intranasal administration and heterologous prime-boost administration were shown to reduce effects of preexisting immunity [29, 30]. In this study, we report the first-in-human safety and immunogenicity evaluation of a replication-competent SeV-vectored HIV-1 vaccine administered intranasally; the vaccine was administered intranasally at a lower dose (SL) or higher dose (SH) of SeV vector encoding clade A HIV-1 Gag (SeV-Gag), given alone or as a heterologous prime-boost with a nonreplicating adenovirus (Ad) serotype 35 HIV-1 vaccine containing genes HIV-1 encoding Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) administered intramuscularly. The Ad35-GRIN was selected for these prime-boost regimens because it has well-known safety profile and robust immunogenicity in both US and African populations [4, 7, 8, 31].\n\nBODY.METHODS.VOLUNTEERS AND STUDY DESIGN:\nThis study was a multicenter, randomized, placebo-controlled, dose-escalation trial that was double blinded with respect to vaccine or placebo but not regimen. The doses were based on preclinical data [28, 29] and a nonrecombinant live SeV vaccine study in humans [23]; the initial group was administered a lower dose for safety. The study was conducted at Projet San Francisco (Kigali, Rwanda), the Kenya AIDS Vaccine Initiative Institute of Clinical Research (Nairobi, Kenya), and the St Stephen's AIDS Trust (London, United Kingdom). The objectives were to evaluate the safety and immunogenicity of 4 different 2-dose regimens (administered at 0 and 4 months) that comprised SeV-Gag administered at 2 × 107 (SL) or 2 × 108 (SH) cell infectious units and Ad35-GRIN vaccine administered at 1 × 1010 viral particles. Volunteers and clinical/laboratory personnel were blind to allocation between active vaccine and placebo. The participants were healthy HIV-negative adults 18–50 years of age engaging in behavior at low risk for HIV-1 infection; all women were nonpregnant and used an effective method of contraception until 4 months after the last vaccination (detailed inclusion/exclusion criteria are in Supplementary Materials). The respective local governmental ethics and regulatory bodies for each clinical research center approved the study. Written informed consent was obtained from each volunteer prior to undertaking any study procedure. The study was conducted in accordance with International Conference on Harmonization's good clinical practice and good clinical laboratory practice guidelines [32]. The study design is presented in Table 1 and in the Consolidated Standards of Reporting Trials diagram (Supplementary Figure 1). Volunteers in part I received low-dose SeV-Gag vaccine followed by Ad35-GRIN vaccine (SLA) or placebo. Following review of safety data from part I by an independent safety review board, a different set of volunteers was randomly assigned to participate in part II. Volunteers in part II received either the higher dose of SeV-Gag as a prime followed by Ad35-GRIN vaccine (SHA); an Ad35-GRIN prime given intramuscularly, followed by the higher-dose SeV-Gag boost given intranasally (ASH); prime-boost with the higher-dose SeV-Gag given intranasally (SHSH); or placebo.\nTable 1.Study Immunization Regimens and ScheduleGroupRegimenSubjects, No.Month 0Month 4Vaccine GroupPlacebo GroupVaccineRouteDoseaVaccineRouteDoseaASLA124SeV-GagIntranasal2 × 107Ad35-GRINIntramuscular1 × 1010BSHA124SeV-GagIntranasal2 × 108Ad35-GRINIntramuscular1 × 1010CASH125bAd35-GRINIntramuscular1 × 1010SeV-GagIntranasal2 × 108DSHSH124SeV-GagIntranasal2 × 108SeV-GagIntranasal2 × 108Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are 1 × 107 or 1 × 108 cell infectious units/100 μL per nostril (for SeV-Gag) or 1 × 1010 viral particles (for Ad35-GRIN).b Overenrollment was allowed per protocol; one additional volunteer, identified post unblinding as a placebo recipient, was enrolled. Each group had 16 volunteers: 12 vaccine recipients and 4 placebo recipients. Enrollment of an additional volunteer was allowed yielding a sample size of 65. Local and systemic reactogenicity were reported for days 0 through 14 following each vaccination, adverse events (AEs) were reported through month 1 following the second study vaccination, and serious adverse events (SAEs) were reported through the final study visit. Hematologic and biochemical parameters were assessed at 4 time points after vaccination (Supplementary Materials). Reactogenicity and AEs were assessed using an adapted version of the Division of AIDS Table for Grading the Severity of Adult and Pediatric Adverse Events, version 1.0.\n\nBODY.METHODS.STUDY VACCINES:\nThe SeV-Gag vaccine is based on a replication-competent vector derived from the SeV Z strain [33] with HIV-1 subtype A gag inserted in the 3′ terminal region of the virus genome [34], upstream of the nucleoprotein gene. SeV-Gag vaccine and placebo were administered by syringe; the head was tilted back, and 100 μL was instilled into each nostril of the volunteer over approximately 3 minutes to allow absorption. The Ad35-GRIN vaccine is a recombinant, replication-defective Ad35 vaccine; it has been previously tested in 4 clinical trials [4, 7, 8, 31] and a recently completed trial in Kenya [35]. The Ad35-GRIN vaccine and placebo were both administered intramuscularly in 0.5 mL. The gag in SeV-Gag and Ad35-GRIN were fully homologous with regard to amino acid sequence.\n\nBODY.METHODS.LABORATORY ASSESSMENTS FOR SAFETY AND IMMUNOGENICITY:\nHematologic and biochemical assays were conducted at the clinical sites in Africa and at a third-party accredited laboratory in the United Kingdom. Vaccine-induced seropositivity/seroreactivity was assessed in each country (Supplementary Materials). For detailed collection and immunogenicity testing methods, see the Supplementary Materials. Briefly, peripheral blood mononuclear cells (PBMCs) were processed and cryopreserved at each clinical site. Mucosal fluids from nasal swabs, parotid and transudated saliva, rectal secretions, and cervicovaginal secretions in females were processed as previously described [36, 37]. Colorectal biopsy specimens were pooled and disaggregated by collagenase digestion to isolate mucosal mononuclear cells within 6 hours of collection, and intracellular cytokine staining (ICS) assays were performed after an overnight rest as described elsewhere [38, 39]. T-cell responses were assessed by qualified interferon-γ (IFN-γ) enzyme-linked immunospot (ELISPOT) and ICS assays, using peptides matched to Gag, and by a functional viral inhibition assay, using a panel of 8 HIV-1 strains from subtypes A, B, C, and D [7, 8, 31, 40, 41]. An enzyme-linked immunosorbent assay (ELISA) was used with HIV-1 subtype B Gag p24 protein (BH10) to assess Gag p24 binding antibodies in serum and mucosal samples [7, 31, 36]. Serum neutralizing antibodies (NAbs) against SeV were assessed as described previously [24]. Samples for analysis of viral shedding were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 (±1 day) after the first vaccination with SeV-Gag or placebo in the SLA, SHA, and SHSH groups as described in the Supplementary Materials.\n\nBODY.METHODS.STATISTICAL METHODS:\nThe statistical methods are described in the Supplementary Materials.\n\nBODY.RESULTS.DEMOGRAPHIC CHARACTERISTICS AND PARTICIPANT FLOW AND RECRUITMENT:\nThe study was conducted between March 2013 and March 2015. Of 65 volunteers, 36 (55.4%) were enrolled in Rwanda, 21 (32.3%) were enrolled in Kenya, and 8 (12.3%) were enrolled in the United Kingdom. Volunteers were first enrolled in group SLA only in Rwanda, followed by competitive enrollment at all sites for groups SHA, ASH, and SHSH. Twenty participants (30.8%) were female, and the mean age was 31.3 years (range, 19–48 years; Supplementary Table 1). All volunteers completed study vaccinations and visits per protocol (Supplementary Figure 1).\n\nBODY.RESULTS.VACCINE SAFETY AND TOLERABILITY:\nAll vaccination regimens were generally well tolerated (Supplementary Figures 2A and 2B). There was no statistically significant difference in the frequency of grade 2 or higher upper or lower respiratory tract reactogenicity following any SeV-Gag vaccination, compared with placebo (Supplementary Table 2). All local reactogenicity events after Ad35-GRIN intramuscular injection were graded as mild or moderate. The frequency of grade 2 local pain, tenderness, erythema, and swelling following Ad35-GRIN vaccination was similar in the vaccine and placebo groups (Supplementary Table 3). Most systemic reactogenicity (chills, malaise, myalgia, headache, nausea, vomiting, and fever) was grade 1 or 2. The overall frequency of any grade 2 or higher systemic reactogenicity following any vaccination was similar in vaccine and placebo groups (Supplementary Tables 2 and 3). One volunteer (in the ASH group) reported grade 3 malaise on day 2 after Ad35 vaccination and grade 3 chills, malaise, and myalgia on day 0 after SeV-Gag vaccination (Supplementary Figure 2). There was no difference between groups in the proportion of volunteers with grade 2 or higher unsolicited AEs (P = .525; data not shown). The proportions of volunteers with any unsolicited respiratory AEs (cough, influenza-like illness, nasal congestion, pneumonia, and/or rhinitis) within 4 weeks of vaccination or at any time during the trial were not statistically significant between volunteers receiving SeV-Gag vaccination and placebo recipients (Supplementary Table 4). No vaccine-related SAE was reported, and no apparent pattern in clinical AEs or AEs determined by laboratory analysis was observed. No volunteers tested positive for vaccine-induced seropositivity/seroreactivity at the end of the study. Mucosal samples, including nasopharyngeal fluid, parotid gland saliva, oral fluid (transudate), and cervicovaginal and rectal secretions, were collected at 8 time points. Compliance was excellent for nasal and oral sampling, good for cervicovaginal sampling, but poor for rectal sampling (Supplementary Materials).\n\nBODY.RESULTS.SEV-GAG SHEDDING:\nViral shedding samples were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 after first vaccination with SeV-Gag or placebo. Overall, 20% of all samples (vaccine vs placebo, P = not significant) across all groups and visits (141 of 702) were positive by the cell infectious unit assay, which used immunostaining to detect cells infected with SeV. The polyclonal SeV antiserum used in this assay cross-reacts with hPIV-1, and a positive readout in this assay is either SeV or hPIV-1. Further analysis by PCR specific for SeV indicated that 12% of the cell infectious unit–positive samples (17 of 141) were positive for SeV and that all bore the intact HIV-1 gag insert. These 17 samples were from nasal swabs from 15 of 36 volunteers (42%) receiving only SeV-Gag. No SeV-Gag virus was detected in nasal samples after day 4 or at any time in saliva or urine (Supplementary Table 5).\n\nBODY.RESULTS.IFN-Γ ELISPOT FINDINGS:\nFew ELISPOT responses were detected after 1 or 2 vaccinations with SeV-Gag alone; in contrast, responses were detected in the heterologous regimens after the second vaccination (groups SLA, SHA, and ASH; Figure 1 and Table 2). Two weeks after the Ad35-GRIN boost, 12 of 12 volunteers in group SLA and 10 of 11 in group SHA demonstrated Gag-specific responses. Five group ASH volunteers had positive Gag responses at both time points, 1 group ASH volunteer had a positive Gag response after the first vaccination only, and 1 group ASH volunteer had a positive Gag response after the second vaccination only. The proportions were similar in groups SLA (100%) and SHA (90.9%; P = not significant). In the ASH group, 6 of 11 individuals (54.5%) had positive responses to the Gag peptide pool 2 weeks after the Ad35-GRIN prime (Table 2), and their responses remained steady after the SeV-Gag boost (Supplementary Table 6). In the SLA and SHA groups combined, the Gag response rate was significantly higher 2 weeks after the second vaccination (95.7%), compared with the rate in the ASH group 2 weeks after either the Ad35-GRIN prime or the SeV-Gag boost (54.5% for both; P = .008).\nTable 2.Human Immunodeficiency Virus Type 1 (HIV-1) Gag–Specific Interferon γ (IFN-γ) Enzyme-Linked Immunospot–Determined T-Cell Responses 2 Weeks After the First and Second VaccinationsGroup2 Weeks After First Vaccination2 Weeks After Second VaccinationSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSLA100 (0)3 (2–5)...1212 (100)275 (138–546)53–1740SHA110 (0)2 (1–5)...1110 (91)222 (101–488)60–1061SA210 (0)3 (2–4)...2322 (96)248 (154–400)53–1740ASH116 (55)54 (25–120)48–381116 (55)59 (30–113)43–485SHSH120 (0)3 (2–7)...120 (0)4 (2–8)...Placebo170 (0)2 (1–3)...160 (0)2 (1–4)...Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; CI, confidence interval; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Excludes samples in which the prevaccination values for the Gag peptide pool were positive (ie, cross-reactive).b Data are IFN-γ spot-forming units per million peripheral blood mononuclear cells.\nFigure 1.Administration of a Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) primes Gag-specific T-cell responses detected by interferon γ enzyme-linked immunospot analysis. The y-axis shows spot-forming units (SFU)/106 peripheral blood mononuclear cells (PBMCs) on a log scale. All responses reflect subtraction of background spots. Black circles denote response below the cutoff, defined in the Materials and Methods, to the Gag peptide pool; red circles denote response above the cutoff to the Gag peptide pool. The overlaid box plots summarize the responses (ie, median value, the 1st and 3rd quartiles, and the 5th and 95th percentiles). Red bars represent median values. The placebo responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Arrows show the timing of vaccinations in each group. In the x-axis, weeks represent the time after the most recent vaccination, to facilitate cross-regimen comparisons. With respect to the magnitude of the response, the IFN-γ ELISPOT responses to Gag 2 weeks after Ad35-GRIN receipt were greater after SeV-Gag priming (in groups SLA and SHA combined) than after the Ad35-GRIN prime (in the ASH group), with geometric mean responses of 248 and 54 IFN-γ spot-forming units (SFU)/106 PBMCs (P = .002; Table 2). The geometric mean responses in the SLA and SHA groups 2 weeks after Ad35-GRIN receipt were similar (275 and 222 IFN-γ SFU/106 PBMCs, respectively; P = .73). The response rate and magnitude in group SLA waned over time but remained constant in group SHA; the ASH group had lower but more-stable response rates (Figure 1 and Supplementary Table 6).\n\nBODY.RESULTS.ICS FINDINGS:\nFlow cytometry was used to characterize the phenotype and polyfunctionality of the response. Low responses were detected in group ASH 2 weeks after the Ad35-GRIN prime and 2 weeks after the SeV-Gag boost (Figure 2 and Supplementary Table 7). However, in groups SLA and SHA, 2 weeks after receipt of the Ad35-GRIN boost, the median magnitude of the Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α was significantly higher than after receipt of each dose of the ASH regimen (P = .006 and P = .013, respectively). After prime and boost (in the SLA group), the median number of Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α increased approximately 45-fold, from 0.005% to 0.225% (Figure 2A and Supplementary Table 7). In contrast, 2 weeks after receipt of the Ad35-GRIN boost in the SLA and SHA groups and 2 weeks after receipt of each dose of the ASH regimen, no significant difference was observed in the magnitude of the Gag-specific CD8+ T-cells (Figure 2B and Supplementary Table 7).\nFigure 2.Characterization of human immunodeficiency virus (HIV-1) Gag–specific CD4+ and CD8+ T-cell responses. Gag-specific CD4+ and CD8+ T-cell responses as assessed by intracellular cytokine staining (ICS; A and B). Time points displayed are 2 weeks after the indicated vaccination. T-cell responses were evaluated by 7-color ICS to assess the expression of interleukin 2 (IL-2), interferon γ (IFN-γ), and tumor necrosis factor α (TNF-α) with peptides matched to the Gag peptide pool. The percentage of T cells expressing at least 1 cytokine (IL-2, IFN-γ, or TNF-α) is shown. Boxes represent interquartile ranges (IQRs), and whiskers extend to the 5th and 95th percentiles. Red bars represent median values. The placebo responses are combined for all groups. For the polyfunctional responses (bottom panels C and D), each dot represents a single volunteer. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA; red dots); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA; green dots); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH; orange dots); and priming and boosting with a higher-dose SeV-Gag given intranasally. Ad35-GRIN prime alone is represented by blue dots, and placebo is represented by purple dots. Gag-specific CD4+ polyfunctional T-cell responses predominated over CD8+ T-cell responses in groups SLA and SHA, with the majority of volunteers positive for all 3 cytokines tested (Figure 2C). Gag CD8+ T-cell responses were highest in group SHA, with the majority being either triple positive or double positive for IFN-γ and TNF-α (Figure 2D). Fresh colorectal biopsy mucosal mononuclear cells and PBMCs were tested in parallel by ICS in 16 volunteers, including placebo recipients who consented to the procedures. The mucosal mononuclear cells and PBMC samples had responses to SEB and/or CMV as expected, but only 1 vaccinee, in group SHA, had Gag-specific responses in both PBMCs and mucosal mononuclear cells 2 weeks after prime-boost (data not shown).\n\nBODY.RESULTS.VIRAL INHIBITION ASSAY:\nViral inhibition was detected in 2 of 9 and 3 of 9 individuals after SeV-Gag prime and in 11 of 12 and 9 of 9 individuals after the Ad35-GRIN boost in groups SLA and SHA, respectively (P = not significant). When the vaccination order was reversed, in the ASH group, viral inhibition was detected after the Ad35-GRIN prime in 9 of 10 volunteers but in only 4 of 10 after the SeV-Gag boost (Table 3 and Supplementary Figure 3A and 3B). The viral inhibition response rate after the boost in groups SLA and SHA combined was greater than in the ASH group (20 of 21 [95%] vs 4 of 10 [40%]; P = .0017, by the Fisher exact 2-tailed test).\nTable 3.Viral Inhibition Responses 2 Weeks After the First and Second VaccinationsVariableSLASHASAASHPlacebobPrimeBoostPrimeBoostPrimeBoostPrimeBoostAnyPositive results, proportiona2/911/123/99/95/1820/219/104/101/4Log10 p24 inhibition Median0.881.720.952.070.891.851.290.850.79 Maximum2.124.862.134.832.134.863.142.771.76Breadthc Median0.06.00.04.00.06.03.00.00.0 Mean0.224.750.674.780.475.003.001.200.50 Range0–10–70–41–80–40–80–60–60–2Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are no. positive/no. tested. Positive results correspond to any positive value per individual over all 8 virus isolates. Any virus isolate that was positive at baseline (which occurred in 3 individuals) was counted as negative. All other values are calculated using all results over all virus isolates per volunteer.b At least 1 positive result after prime or boost. Other statistics include both prime and boost values.c Breadth corresponds to the no. of positive virus isolates per individual. In the SLA and SHA groups, the median log inhibition after the SeV-Gag prime was 0.88 and 0.95, respectively, and it increased significantly to 1.72 and 2.07 after the Ad35-GRIN boost (P < .0001). In group ASH, the median log inhibition after receipt of Ad35-GRIN alone was 1.29, decreasing to 0.85 after SeV-Gag receipt (Table 3). The magnitude of viral inhibition after boost in the SLA and SHA groups combined (1.85) was greater than after the Ad35-GRIN prime (1.29) and the SeV-Gag boost (0.85) in group ASH (P < .0001 for each comparison). A response to 2 viruses was detected after the second dose of placebo in 1 volunteer. The breadth of viral inhibition was assessed by the number of viruses inhibited out of a panel of 8 viruses from multiple HIV-1 clades. The greatest median breadth was observed in groups SLA and SHA after the Ad35-GRIN boost (6 and 4, respectively), compared with a median breadth of 3 after the Ad35-GRIN prime alone in the ASH group (Figure 3 and Table 3). Viral inhibition was not assessed in group SHSH.\nFigure 3.Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) enhances the breadth of inhibition of a panel of diverse HIV-1 isolates. The breadth of inhibition among 8 viruses was assessed at baseline (bl) and specified time points 2 weeks after the indicated vaccination (vac). Lines represent median values, whiskers represent the 1st and 3rd quartiles, and gray dots represent individual responses. The placebo (Pbo) responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH).\n\nBODY.RESULTS.GAG P24 ANTIBODIES:\nGag p24–specific IgG and IgA were measured in serum samples at baseline, 2 and 16 weeks after the first vaccination, and 2, 16, 32, and 48 weeks after the second vaccination. In SLA, SHA, and SHSH recipients, GMTs were negative at all time points (ie, they were ≤100) after prime and boost. The GMTs were significantly higher (P < .0001, by the Kruskal-Wallis test) in the ASH group after the SeV boost than in the other groups (53, 53, 245, 50, and 59 in the SLA, SHA, ASH, SHSH, and placebo groups, respectively; Figure 4). Two volunteers in group ASH were excluded from this analysis owing to positive titers at baseline. ASH titers decreased to a GMT of 72 at 48 weeks after SeV-Gag receipt. Gag p24–specific IgA responses were detected sporadically and at low titers (data not shown).\nFigure 4.Human immunodeficiency virus type 1 (HIV-1) Gag p24 immunoglobulin G (IgG) geometric mean titers (GMTs) after the following prime-boost combinations: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Titers below the level of detection (ie, <100) were given a value of 50. Arrows indicate vaccination time points for each group. Placebo responses are combined for all groups. Abbreviation: CI, confidence interval.\n\nBODY.RESULTS.SEV NABS:\nMost volunteers from all groups had a preexisting positive titer of serum SeV NAbs, with similar magnitudes and rates in vaccine and placebo recipients before and after vaccination (Supplementary Figure 4). There was no correlation between SeV NAb titers at baseline and the magnitude of Gag ELISPOT responses 4 weeks after Ad35-GRIN receipt in groups SLA and SHA and Gag-specific ELISA responses 2 weeks after the SeV boost in group ASH (Supplementary Figure 5). Mucosal secretions were not tested for SeV NAbs.\n\nBODY.DISCUSSION:\nThis was the first-in-human trial assessing safety and immunogenicity of a replication-competent SeV-vectored HIV-1 vaccine; it was administered in prime-boost regimens with Ad35-GRIN in healthy volunteers. SeV has been safely tested as a nonrecombinant Jennerian vaccine against hPIV-1 in adult and pediatric populations [22, 23]. Both SeV-vectored and Ad35-vectored vaccines were well tolerated, and adverse events were not significantly different from those in placebo recipients. Mucosal sampling was well accepted in this study when it was limited to saliva, nasal, or cervicovaginal fluids, but rectal fluid collection and biopsy had more-limited acceptance, as in previous studies [36, 37]. We postulated that delivery of SeV-Gag by the intranasal route might induce mucosal immune responses and circumvent preexisting immunity to SeV, allowing immune responses to the vaccine insert, as shown previously in animal models [30, 42]. Despite preexisting SeV NAbs in all groups and a lack of persistent SeV shedding indicative of replication, there was a clear take of SeV-Gag, as indicated by much greater Gag-specific T-cell and antibody responses in the heterologous regimens, compared with either vaccine given once. Mucosal antibody responses were weak and sporadic, and neither mucosal application nor parenteral priming or boosting amplified mucosal responses. Remarkably, the vaccines induced very different immune responses when given in a different order. As a homologous regimen, 2 doses of SeV-Gag induced minimal humoral and cellular immune responses. In contrast, SeV-Gag primed T-cell responses for a subsequent boost by Ad35-GRIN, while SeV-Gag boosted humoral responses after priming with Ad35-GRIN. The strongest Gag-specific T-cell responses were detected by ELISPOT and ICS assays after the SeV-Gag prime and Ad35-GRIN boost, with no clear effect of the SeV-Gag dose. Functional viral inhibition responses mediated by T cells [41] with greater breadth, magnitude, and frequency were also seen in groups SLA and SHA after the Ad35-GRIN boost. The frequency and magnitude of Gag ELISPOT responses in the SLA and SHA groups combined were equivalent to those of Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a prime as an Ad vector given intramuscularly [31]. A so-called hidden prime has been postulated previously in studies of DNA vaccines followed by Ad vector boosts [43, 44], in which plasmid DNA vaccines with or without electroporation and/or molecular adjuvants such as interleukin 12 or interleukin 15 elicit very modest T-cell and antibody responses in humans, but prime for anamnestic responses when Ad vectors are given as a boost [8, 45–49]. One dose of SeV-Gag appears to be equivalent to 3 doses of DNA vaccine (up to 8 mg) in terms of priming responses and is perhaps more effective at priming than a highly attenuated VSV-Gag delivered intramuscularly [6, 50, 51]. The ICS studies demonstrated that SeV-Gag stimulated CD4+ T cells, which may have provided help for the development of CD8+ T cells [44]. It was not possible in this study to determine how SeV-Gag provides this potent T-cell priming; its ability to infect mucosal cells after intranasal delivery may be important. A direct comparison of 2 routes of delivery could help to resolve this issue. In contrast, Gag-specific antibody responses were detected only when Ad35-GRIN was given first and boosted by SeV-Gag in group ASH. Previous studies have shown low-to-negligible Gag-specific antibody responses after administration of a single dose of Ad35-GRIN [31]. After priming with Ad35-GRIN and boosting with SeV-Gag, the Gag ELISA responses were equivalent to those seen with Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a boost as an Ad vector given intramuscularly [31]. In summary, intranasal delivery of SeV is feasible, safe, and immunogenic in the presence of preexisting systemic antivector antibodies; neither antibody nor T-cell responses were equivalent at the 2 SeV-Gag doses tested. The type of response elicited was determined by the order of vaccines in the heterologous regimen, as SeV-Gag priming mainly induced cellular immunity whereas SeV-Gag boosting mainly induced serum humoral immune responses against Gag. Mucosal antibody responses were weak and sporadic, and only 1 participant had a mucosal T-cell response. Whether mucosal antibodies are necessary or sufficient for protection against sexual transmission of HIV is unknown; if they are important, a more powerful immunogen or different regimen will be needed. Further studies to elucidate the mechanism of this antibody–T cell shift may be warranted. These data suggest that intranasal delivery of a viral vector capable of limited replication as part of a heterologous prime-boost regimen may be a valuable way to stimulate immune responses, even in the presence of preexisting antivector antibodies. SeV-Gag was shown to prime for T-cell responses and to boost antibody responses, but in this configuration the SeV-Gag by itself is not sufficiently immunogenic for further development.\n\nBODY.STUDY GROUP MEMBERS:\nThe S001 Study Team includes the following individuals: Rosine Ingabire, Gina Ouattara, Alan Steele, Anne Gumbe, Kundai Chinyenze, Sabrina Welsh, Carl Verlinde, Deborah King, Cynthia Bishop, Paramesh Chetty, Lorna Clark, Mumtaz Booley, Devika Zachariah, Kristen Syvertsen, Kamaal Anas, Marloes Naarding, Emmanuel Cormier, Jim Ackland, and Mamoru Hasegawa.\n\nBODY.SUPPLEMENTARY DATA:\nSupplementary materials are available at http://jid.oxfordjournals.org. Consisting of data provided by the author to benefit the reader, the posted materials are not copyedited and are the sole responsibility of the author, so questions or comments should be addressed to the author.\n \n\nSupplementary Data\n\nQuestion: Compared to ASH group what was the result of SLA and SHA groups on the Gag response rate?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1008	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The Effect of Stretching Exercises on Severity of Restless Legs Syndrome in Patients on Hemodialysis\n\n ABSTRACT.BACKGROUND:\nThe restless legs syndrome is a sensorimotor disorder that is very common in patients on hemodialysis. Due to pharmacological treatments which have their own side effects, nowadays, studies have turned to non-pharmacological treatments.\n\nABSTRACT.OBJECTIVES:\nThe present study aims to assess the effect of stretching exercises on the severity of restless legs syndrome in patients on hemodialysis.\n\nABSTRACT.PATIENTS AND METHODS:\nThis clinical trial study was conducted on 33 patients who had been identified using diagnostic criteria from the hemodialysis ward of Hasheminejad Hospital in Tehran. Participants were randomly divided into the intervention group (n = 17) and control group (n = 16). Stretching exercises were performed on legs during the dialysis for half an hour, three times a week for 8 weeks in intervention group. Data were collected by using the international restless legs syndrome study group scale.\n\nABSTRACT.RESULTS:\nThe results showed that the majority of participants were suffering from moderate restless legs syndrome. The symptom severity of this syndrome meaningfully changed eight weeks after intervention in the intervention group compared to the control group (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nThe results highlighted the significance of training and performing the stretching exercises during dialysis for the purpose of improving restless legs syndrome symptoms and the quality of care of hemodialysis patients.\n\nBODY.1. BACKGROUND:\nRestless legs syndrome (RLS) is a neurological movement disorder that affects a large number of people (1). RLS prevalence studies show that 10% of the adult population is affected by this disorder (2). The outbreak of the disease is more common in end stage renal disease (ESRD) patients than general population (3). 20% to 70% of the dialysis patients report symptoms of RLS (4). Some studies also indicate that 33% of ESRD patients suffer from RLS (3). Restless legs syndrome has been shown to have a significant impact on the quality of life of the patients on hemodialysis mainly because of the poor quality of sleep and inadequate rest (2). RLS is a disorder that gives the patient unpleasant sensations in his limbs, especially legs. These sensations make an urge to move the legs to stop the sensations (5). The syndrome is a sensorimotor disorder that is characterized by restlessness symptoms that lead to an irresistible urge to move some body parts (2). This comes in the evening after sitting for a long time and the sensations are expressed in tickling, pain, itching, and stretching feelings. The symptoms of RLS may appear at any age; 12% of RLS symptoms appear before ten (6). But overall, RLS often appears in middle age (5). Many factors of RLS are unknown or hereditary (7), but it is usually most common in people suffering from chronic renal diseases, diabetes, iron deficiency anemia, Parkinson's, neuropathy, pregnancy, use of caffeine, calcium channel blocker drugs, lithium, and sedative drugs withdrawal (5). The special criteria for diagnosis of RLS have been introduced by the international restless legs syndrome study group (IRLSSG) and including; 1) a uncontrolled urge to frequently move the limbs due to RLS symptoms, 2) temporary relief of the unpleasant symptoms by moving; 3) worsening of the symptoms after resting or lack of movement, 4) worsening of the symptoms in the evening or at night (8). Worsening of the symptoms in night in patients with moderate to severe RLS leads to sleep disorder. As a result, RLS patients may experience anxiety and sleep deprivation or drowsiness during the day that can disrupt the daily functioning of the patient (9). Also RLS causes sleep disorder, daily fatigue, depression, disruption of the ability to work and social isolation (10). These problems lead to poor quality of life and have adverse effects on social activities and family life (9). Regarding this information, studies have shown that the reduced quality of life in hemodialysis patients with RLS is possible because of inadequate sleep quality and quantity (2). Common medications for RLS has been dopamine agonists or benzodiazepines, but the drugs have some side-effects (1). Initially, to treat RLS, non-pharm logical treatments like sleep hygiene, warm bath, massages, reduction of stimulating factors such as caffeine and alcohol should be tried (11). Recently, some researcher has been conducted on the effect of changing lifestyle like performing exercises (1). Since the symptoms of the syndrome appear or worsen in resting and immobility times, these symptoms may improve by moving. Therefore, moderate exercise can be helpful (2). Exercises like walking, massaging, stretching, swimming, and stationary cycle can help relieve symptoms (12). The effects of exercise on RLS symptoms are unknown. A research by Ohayon et al. (13) in 2002 showed that severe physical activities like high intensity sports just before bedtime exacerbate the symptoms of RLS. Also Aukerman and Sakkas concluded that a daily mild exercise program can alleviate the RLS symptoms (1, 2).\n\nBODY.2. OBJECTIVES:\nReview of recent studies showed that we need more research about the effects of exercise on RLS symptoms. Therefore, the present study aims to assess the effects of stretching exercises on severity of RLS symptoms in patients on hemodialysis because stretching exercises are easily applicable by the patients and are applied on legs and don't cause disruption in dialysis. \n\nBODY.3. PATIENTS AND METHODS.3.1. DESIGN AND SAMPLE:\nThis study was a randomized controlled trial conducted on hemodialysis patients from the hemodialysis ward of Hasheminejad Hospital affiliated to Tehran University of Medical Sciences in Tehran. Given the study by Aukerman et al. (1) with a confidence interval of 95% and testing power of 90%, the sample size was calculated 13 for each group, but totally 18 people were considered for each group considering the possible dropout, so 36 people were enrolled.\n\nBODY.3. PATIENTS AND METHODS.3.2. INCLUSION AND EXCLUSION CRITERIA:\nThe inclusion criteria were having diagnostic criteria for RLS according to IRLSSG, age over 18, at least 6 months since the start of dialysis treatment, being on the weekly list of dialysis for 3 times a week and each time for 3 to 4 hours, having no mental or physical disability, being completely alert, having acceptable hearing and speaking ability for answering the questions, absence of any infection, injuries, and peripheral neuropathy or vascular problems in legs, absence of orthopedic problems, and confirmation of RLS by physician in research centers. The exclusion criterion was refusal to do the stretching exercises for 3 consecutive sessions and overall 6 sessions. \n\nBODY.3. PATIENTS AND METHODS.3.3. PROCEDURE AND INSTRUMENTS:\nTo identify the patients with RLS, initially, four diagnostic criteria were given to all the patients at the hemodialysis ward. Patients, who answered \"yes\" to all 4 questions, were examined by the physician for confirmation of RLS. The patients with RLS were included in the study consensually and randomly divided into intervention and control groups. Initially, the stretching exercises were taught to the intervention group during two sessions. After the training, the intervention group participated in 8 weeks of a stretching exercise program three times a week during the last two hours of hemodialysis session and each time for 30 minutes. The researcher closely monitored the exercises. Each session involved 5 minutes of initial warm-up. Then, the participants did stretching exercises on legs for 20 minutes and then cooled down for 5 minutes. The stretching exercises that were confirmed by a sports medicine specialist were applied to the legs and included hip rotation to the sides, quadriceps stretch, knee to chest stretch, hamstring stretch, gluteal stretch, straight leg raise, side lying leg lift and so on. Each muscle was stretched to three sets of ten. Duration of each stretching was 5 seconds. After training sessions these exercises was performed by the participants under the supervision of the researcher. For assessment of the effect of stretching exercises on severity of RLS we used the international RLS study group (IRLSSG) Scale. This scale was completed at baseline, at the end of the 4th week, and at the end of the 8th week by the subjects. The demographic information was collected by a questionnaire. The scale for assessing the severity of RLS involved 10 items each having 5 options. Every question had 0 to 4 points. The maximum score was 40 and a high score indicated the severity of disease. The participants with less than 10 points were mild, 11 to 20 points were moderate; 21 to 30 points were severe and above 31 was very severe. All interviewers and personnel who handled the questionnaires were blinded to study allocation of the participants. In order to determine content validity and reliability of the IRLSSG questionnaire, Cornbrash's alpha coefficient was used in this study. The validity of IRLSSG questionnaire was 0.87. The Data were collected in two months in 2012 and were analyzed using SPSS16 software program and Fisher's statistical test, two-sample Kolmogorov-Smirnov test, t-test and ANOVA. A P value < 0.05 was considered statistically significant. The study was introduced and approved by the Ethics Committee of the Tehran University of Medical Sciences in 09 September 2012. All participants signed written consent after full explanation of the procedure. \n\nBODY.4. RESULTS:\nAfter screening all the patients who were in the list of hemodialysis ward and identifying patients with RLS, 36 people were included in the study. They were divided randomly into two 18-member control and intervention groups. One patient was excluded from the intervention group because of not completing stretching exercises sessions, and two patients were excluded from the control group (one of them had died and the other one was not cooperative). In total, the study continued with 33 people (17 patients in the intervention group and 16 patients in the control group). According to the results, 51.5% of the participants were men and 30.3% were above 66-years-old. Most participants were married (63.6%) and jobless or retired (78.1%). The most common diseases among the participants were hypertension (48.5%) and diabetes (42.4%) and the most used drug was amlodipine (45.5%). The results also showed that 100% of the participants were unaware that they were suffering from RLS and they did not take any medications to relieve symptoms of RLS. An overwhelming majority of the participants (87.9%) did not do exercises and any sports regularly. Most of the participants were suffering from medium to severe of RLS and there was no meaningful difference between the intervention and control groups in the beginning of the study. Repeated ANOVA test showed that the severity of RLS scores (according to IRLSSG scale) decreased meaningfully in the intervention group by 8 weeks, but these scores didn't change significantly in the same period in the control group (P < 0.001) (Table 1). Table 1. Comparison of Severity of RLS Scores in Control and Intervention Group at Baseline, End of 4 th Week and End of 8 th Week by ANOVA Test a , b , c Variable Baseline (A) End of 4 th Week (B) End of 8 th Week (C) ANOVA Test \n Control group \n d \n 19 ± 4.78 18.43 ± 4.47 19.06 ± 4.71 0.55 \n Intervention group \n e \n 18.94 ± 5.44 17.47 ± 5.1 12.41 ± 3.79 < 0.001 a Total severity of RLS scores range from zero to 40 with higher values being indicative of severe RLS symptoms. b P < 0.05 are considered significant. c Values are expressed as Mean ± SD. d A and B, NS (P = 0.262); A and C, NS (P = 0.937); B and C, NS (P = 0.307). e A and B, SN (P = 0.001); A and C, SN (P < 0.001); B and C, SN (P < 0.001). Also the results of t-test show that the changes in the severity of RLS symptoms before intervention and after 4 weeks were not statistically meaningful between intervention and control groups. However, the changes were meaningful at the end of the 8th week (P < 0.001) (Table 2). Table 2 . Comparison of Severity of RLS Scores in Control and Intervention Group at Baseline, End of 4 th Week and End of 8 th Week by t-test a , b , c Variable Intervention Group d Control Group e t-test Value P Value \n Baseline (A) \n 18.94 ± 5.44 19 ± 4.78 -0.33 0.97 \n End of 4 \n th \n week (B) \n 17.47 ± 5.1 18.43 ± 4.47 -0.57 0.56 \n End of 8 \n th \n week (C) \n 12.4 1± 3.79 19.06 ± 4.71 -4.48 < 0.001 a Total severity of RLS scores range from zero to 40 with higher values being indicative of severe RLS symptoms. b P < 0.05 are considered significant. c Values are expressed as Mean ± SD. d A and B, SN (P = 0.001); A and C, SN (P < 0.001); B and C, SN (P < 0.001). e A and B, NS (P = 0.262); A and C, NS (P = 0.937); B and C, NS (P = 0.307). \n\nBODY.5. DISCUSSION:\nIn this study, the severity scores in the intervention group were 18.94 in the beginning and it decreased to 12.41 at the end of the 8th week. The changes are totally significant, but not in the control group. The present research indicated that stretching exercises for 8 weeks (24 sessions) on legs during hemodialysis improves the RLS symptoms (Figure 1). Figure 1.Comparison of RLS Severity Scores Changes in Intervention and Control Groups During the Eight Week's InterventionNo changes in the RLS severity scores were found in the Control Group while statistically significant differences were found only between week 0 and week 8 for the intervention group (P < 0.05). Since the hemodialysis patients are often disabled and they spend most of their time on dialysis beds, they are usually inactive. Therefore, the proposed stretching exercises can be very helpful because they focus only on lower body limbs and have no side effects such as disruption in the hemodialysis treatment due. The results of this research are compatible with the other studies. Sakkas et al. (2) showed that aerobic exercises (as a mild sport) during hemodialysis reduce the severity of RLS symptoms in 16 weeks. Aukerman et al. (1) showed that meaningful changes in the severity of RLS symptoms are observed from onset of first week to the end of 6th week. However, in this study no meaningful change was detected after the 6th week to the end of 12th week. Therefore, 8 weeks exercise can suffice to prove the effectiveness of stretching exercises on the severity of RLS symptoms. In contrast, some researchers like Ohayon et al. (13) showed that relatively severe physical activity like high intensity sports before bedtime is meaningfully linked to the severity of RLS symptoms. Therefore, hemodialysis patients are recommended to avoid severe and hard sport programs especially before bedtime. According to this fact, the present study examined the effects of intradialytic mild or moderate stretching exercises. The present research also showed that most participants (78.51%) were jobless or retired that leads to inactivity. Since the RLS symptoms appear or worsen in immobility, physical activity improves the symptoms (13). Therefore, having a mild, regular exercise program can help to alleviate the RLS symptoms and will enhance the health of the people suffering from the syndrome. Scientists believe despite the fact that the real cause of RLS is still unknown; the syndrome is more common among diabetic patients (5). On the other hand, diabetes is one of causes of renal failure; it is more common among hemodialysis patients. This study proved this finding too. Because in our findings, the most common diseases in patients suffering from RLS were diabetes. Regarding the positive effect of stretching exercises on hemodialysis patients, nurses in charge of diabetic patients are also recommended to train them in the exercises to improve their life quality. This study has found that the most common drug used by the participants is amlodipine. This drug blocks calcium channels and is used for heart diseases. According to different studies, people who use calcium channel blockers are more vulnerable to RLS (5). It seems that there is a meaningful relation between this drug and RLS. It is recommended that further studies are needed to assess this relationship. An absolute majority of the participants in this study did not perform any exercises regularly. Although hard exercises, particularly before sleep can worsen the RLS symptoms and may lead to sleep disorder and chronic insomnia, moderate or light exercises program can be helpful during the day to improve RLS symptoms. This study showed that regular stretching exercises on legs during hemodialysis can help alleviate the severity of RLS symptoms. The exercises have no side effects and no cost and can be done without help. Nurses can help alleviate the RLS symptoms by training the patients and thus take a positive step towards healthcare objectives.\n\nQuestion: Compared to No exercises what was the result of Stretching exercises on Symptom severity after 8 weeks ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1134	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of High-Intensity Interval Training versus Continuous Training on Physical Fitness, Cardiovascular Function and Quality of Life in Heart Failure Patients\n\n ABSTRACT.INTRODUCTION:\nPhysical fitness is an important prognostic factor in heart failure (HF). To improve fitness, different types of exercise have been explored, with recent focus on high-intensity interval training (HIT). We comprehensively compared effects of HIT versus continuous training (CT) in HF patients NYHA II-III on physical fitness, cardiovascular function and structure, and quality of life, and hypothesize that HIT leads to superior improvements compared to CT.\n\nABSTRACT.METHODS:\nTwenty HF patients (male:female 19:1, 64±8 yrs, ejection fraction 38±6%) were allocated to 12-weeks of HIT (101-minute at 90% maximal workload—alternated by 2.5 minutes at 30% maximal workload) or CT (30 minutes at 60–75% of maximal workload). Before and after intervention, we examined physical fitness (incremental cycling test), cardiac function and structure (echocardiography), vascular function and structure (ultrasound) and quality of life (SF-36, Minnesota living with HF questionnaire (MLHFQ)).\n\nABSTRACT.RESULTS:\nTraining improved maximal workload, peak oxygen uptake (VO2peak) related to the predicted VO2peak, oxygen uptake at the anaerobic threshold, and maximal oxygen pulse (all P<0.05), whilst no differences were present between HIT and CT (N.S.). We found no major changes in resting cardiovascular function and structure. SF-36 physical function score improved after training (P<0.05), whilst SF-36 total score and MLHFQ did not change after training (N.S.).\n\nABSTRACT.CONCLUSION:\nTraining induced significant improvements in parameters of physical fitness, although no evidence for superiority of HIT over CT was demonstrated. No major effect of training was found on cardiovascular structure and function or quality of life in HF patients NYHA II-III.\n\nABSTRACT.TRIAL REGISTRATION:\nNederlands Trial Register NTR3671\n\n\nBODY.INTRODUCTION:\nHeart failure (HF) is a common disease with an increasing prevalence worldwide [1], and is characterized by a low 5-year survival of 35–55% [2–4]. Several studies have indicated that physical fitness is an important prognostic factor for HF patients, in which a low physical fitness is associated with higher mortality rates [5,6]. Previous studies demonstrate that exercise training can improve physical fitness [7], cardiac function [8], vascular function [9,10], and quality of life [7] in HF patients [11]. Therefore, exercise training is recommended for HF patients and encompasses a central component of cardiac rehabilitation [12]. Most previous studies examining the impact of exercise training in HF patients have adopted exercise at moderate-intensity. Recent studies explored the impact of high-intensity interval training (HIT), which can be described as short periods of exercise performed at high-intensity (>80–85% peak oxygen uptake [13–15]), alternated by periods of active or passive rest. Wisløff et al. suggested a superior effect of HIT compared to continuous training (CT) on physical fitness, cardiovascular function and quality of life in HF patients [16]. This study applied an intensive HIT training regimen in HF patients and found large improvements in fitness levels. After this promising study, Fu et al. found similar results [17], but not all subsequent studies [18–22], reinforced the superior effect of HIT compared to CT in HF patients. Previous studies that revealed a superior effect of HIT adopted relatively long bouts of high-intensity exercise (3–4 min) [16,17], followed by active 'rest' periods of 3 minutes at an intensity up to 70% of maximal heart rate. Performance of such long bouts of exercise at high-intensity and/or 'rest' periods at such vigorous intensity levels may not be feasible for all HF patients. Furthermore, most previous training studies have applied a training frequency of three times per week, which is time consuming. Whilst training frequencies of twice per week can be sufficient to induce a positive effect on fitness levels [23], no previous study examined the efficacy of HIT with lower training frequency or whether there is a difference between such HIT and CT training protocols. Therefore, we explored the benefits of a feasible HIT-protocol with high-intensity bouts of moderate duration (i.e. 1 min), the active rest at relatively low intensity (i.e. 30% maximal workload), and a training frequency of twice a week. In this study, we examined whether 12-weeks of CT or HIT is effective and feasible for HF patients, and whether this HIT-protocol leads to superior effects on fitness, cardiovascular function and quality of life compared to CT. We hypothesize that the HIT-protocol is feasible, whilst the effects on physical fitness, cardiovascular function and quality of life in HF patients New York Heart Association (NYHA) class II-III are superior compared to CT.\n\nBODY.METHODS.SUBJECTS:\nWe included 29 patients (65±8 yrs) diagnosed with HF classified as NYHA class II-III, with a history of left ventricular ejection fraction (LVEF) ≤45% (assessed by 2D/4D echocardiography). Patients were recruited from the department of Cardiology of the Radboud university medical center and the Canisius-Wilhelmina Hospital (Nijmegen, the Netherlands) and through advertisements. Patients with HF due to congenital heart disease or HF caused by valve pathology were excluded. Other exclusion criteria were: diabetes mellitus (type 1 or 2), hypercholesterolemia (total cholesterol >6.5mmol/L), severe renal failure (glomerular filtration rate<30 mL/min/1.73m2), exercise-induced ischemia (i.e. ECG abnormalities suggestive for ischemia on maximal exercise testing), severe co-morbidities (e.g. COPD GOLD ≥3), pathology that restricts patients from participation to exercise (e.g. orthopedic/neurological disorders interfering with movement), pre-menopausal women or women on hormone replacement therapy, and subjects with contra-indications for maximal exercise testing [24]. Subjects had to be in a clinically and pharmacologically stable situation (>3 months) prior to participation. The Medical Ethical Committee of the Radboud university medical center approved this study (CMO region Arnhem-Nijmegen) on October 26th 2010. This trial is registered in the Dutch Trial Register (NTR3671) 3 months after the start due to practical reasons. The authors confirm that all ongoing and related trials for this intervention are registered. Written informed consent was obtained from each subject before participation in this study. Subject recruitment was done between July 2011 and September 2014. Follow-up lasted until February 2015. This study was monitored by a data safety monitoring board, which also approved the submission of this study.\n\nBODY.METHODS.EXPERIMENTAL PROTOCOL:\nSubjects reported to our laboratory for a medical screening, after which they were allocated to 12-weeks moderate-intensity CT or HIT. In addition, to assess changes over time in HF patients, we included a control group consisting of HF patients who were unable to participate in the training program due to geographical reasons or time-constraints, which was tested before and after a 12-week control period. Before and after the 12-week intervention/control period, subjects underwent a maximal incremental cycling test to determine physical fitness, echocardiography to examine cardiac function and structure, and vascular ultrasound measurements to examine peripheral artery vascular function and structure. Finally, questionnaires were used before and after the intervention to assess health-related quality of life and HF symptoms. All measurements were performed in the Radboud university medical center (Nijmegen, the Netherlands). Due to the nature of the study design and practical reasons, blinding participants and researchers was not possible.\n\nBODY.METHODS.MEASUREMENTS.SUBJECT CHARACTERISTICS:\nWe determined height, weight (Seca 888 Scale, Seca, Hamburg, Germany), body mass index, body fat percentage [25], and waist and hip circumference. Furthermore, we obtained heart rate and blood pressure (manually, WelchAllyn, Maxi-Stabil 3, NY, USA), an electrocardiogram to determine heart rhythm, and a venous blood sample to determine fasted glucose and (total) cholesterol concentrations.\n\nBODY.METHODS.MEASUREMENTS.PRIMARY OUTCOME—PHYSICAL FITNESS:\nAn incremental maximal cycling test was performed on a cycle ergometer (Ergoline, Ergoselect 200k, Bitz, Germany). Subjects were instructed to pedal (>60rpm) whilst workload was increased 10–15 Watt/min, depending on the expected physical fitness of the participant (based on sex, age, height, and previous results on exercise testing). During exercise, breath-by-breath gas analysis was recorded continuously (LabManager V5.32.0). For the termination of maximal exercise testing we adhered to recent guidelines [24]. Peak oxygen uptake (VO2peak) was defined as the highest oxygen uptake (30-second average).\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—PHYSICAL FITNESS:\nOxygen uptake at the anaerobic threshold (AT) was determined using the V-slope method [26]. Peak oxygen uptake and oxygen uptake at the AT was also expressed as a percentage of the predicted maximal oxygen consumption [27]. Ventilatory efficiency was defined as the slope of the ventilation to the carbon dioxide production (VE/VCO2 slope) calculated over the linear phase of the response up to the AT. The maximal oxygen pulse (oxygen consumption per heart rate, O2/HR) was determined (10-second average). The presence of chronotropic incompetence, defined as a heart rate reserve <80% of predicted [28], was noted. Prior to testing, all medication was continued.\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—VASCULAR FUNCTION AND STRUCTURE:\nSubjects were prepared according to guidelines for the assessment of flow-mediated dilation (FMD) [29]. Subjects were instructed to continue medication, but to refrain from diuretics the day of testing for practical reasons. The measurements were performed in a temperature-controlled room (22.5±0.7°C). Prior to testing, subjects rested in the supine position for 10 minutes. Vascular function measurements were performed using a 10-MHz multifrequency linear array probe attached to a high-resolution ultrasound machine (Terason T3000, Burlington, MA, USA). We examined brachial and superficial femoral artery endothelial function using the FMD according to the guidelines [29]. Subsequently, we measured the brachial artery maximal diameter and blood flow responses to ischemic handgrip exercise, as described in previous studies [30,31]. The peak blood flow provides a valid and accepted index of resistance artery size and remodelling and the brachial artery diameter response for maximal dilating capacity [30]. We examined carotid artery intima-media thickness (IMT), which represents a surrogate measure for atherosclerosis [32]. Finally, we examined the endothelium-independent dilation of the brachial artery by examining the diameter response to an exogenous nitric oxide donor (sublingual administration of 400μg glyceryl trinitrate (GTN)).\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—CARDIAC FUNCTION:\nTransthoracic (4D) echocardiography was performed with an ultrasound scanner (Vivid E9, General Electric Healthcare, Horten, Norway) with M5-S and V4 probe according to the guidelines of the American Society of Echocardiography [33]. Echocardiographic images were analyzed post-hoc with EchoPAC software (version 112, General Electric Healthcare, Horten, Norway). From 4D-images we assessed: left ventricular end-diastolic volume, left ventricular end-systolic volume, stroke volume, LVEF, cardiac output, and cardiac index. Left ventricular longitudinal, circumferential, radial, and area strain were analyzed by 4D speckle tracking. Moreover, we measured the isovolumetric contraction and relaxation time from tissue Doppler tracings of the lateral and septal mitral annulus. To describe diastolic function we obtained the following parameters by (tissue) pulsed-wave Doppler tracings: peak mitral flow velocity during early (E) and late (A) diastole, the systolic (S) and diastolic (D) inflow velocity over the pulmonary valve, and the peak mitral annulus velocity during early filling (E') of the lateral and septal mitral annulus. The E/A-ratio, S/D-ratio, and E/E'-ratio were calculated.\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME–QUESTIONNAIRES:\nTo measure health-related quality of life, the SF-36 Health Survey was used [34,35]. Additionally, we used the Minnesota living with Heart Failure Questionnaire (MLHFQ), to measure patient perceptions of the effects of HF on their physical, psychological and socioeconomic lives [36].\n\nBODY.METHODS.12-WEEK INTERVENTION:\nTraining was performed twice a week for 12 weeks in a rehabilitation setting or hospital and was supervised by physiotherapists. When a participant missed a training session, this session was rescheduled to ensure a total of 24 training sessions (i.e. 100% compliance). Training was performed on a cycle ergometer (Lode Corival, Procare, Groningen, The Netherlands). Both the CT- and HIT-session started with a warm-up of 10-minutes at 40% of maximal workload (Watt) as obtained from the cardiopulmonary maximal exercise test at baseline, and concluded with a cooling-down of 5-minutes at 30% of maximal workload. Workload was increased during the 12-week training period based on the Borg scores of perceived exertion, to maintain a sufficient training stimulus when physical fitness was expected to improve.\n\nBODY.METHODS.12-WEEK INTERVENTION.CT-GROUP:\nCT consisted of 30-minutes at 60–75% of maximal workload. Training intensity was controlled using the Borg score (scale 6–20) [37], aiming at a Borg score of 12–14 during the training session, as recommended in the current exercise guidelines for HF patients [12]. Borg score and heart rate were determined after the warm-up, at 20, 30 and 40 minutes of exercise, and after the cooling-down.\n\nBODY.METHODS.12-WEEK INTERVENTION.HIT-GROUP:\nHIT consisted of 10 periods of 3.5-minutes of exercise, consisting of intervals of 1-minute at 90% of maximal workload, and 2.5-minutes at 30% of maximal workload, aiming at a Borg score of 15–17 during the high-intensity intervals. Borg score and heart rate were determined at the end of the warm-up, after repetition 1, 3, 7 and 10, and after the cooling-down.\n\nBODY.METHODS.12-WEEK INTERVENTION.CONTROL GROUP:\nControl subjects were instructed not to alter their daily physical activities.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nWe have made a pre-study sample size calculation based on previous studies examining the difference in effect between CT and HIT. Some studies suggest n = 2–3 per group is sufficient [16,17], whilst data from others suggest several thousand subjects must be recruited to detect differences between CT and HIT [19]. We rationalized that n = 10–20 will provide (clinically) meaningful insight into the effect of CT versus HIT. Therefore, using a conservative approach (accounting for drop-outs), we aimed for n = 20 for both exercise training groups (and n = 10 in the control group). Data was analyzed using IBM SPSS Statistics 20.0 (IBM Corp., Armonk, NY, USA). Parameters were checked for normality using a Kolmogorov-Smirnov test. When data was not normally distributed, a non-parametric alternative was used or natural logarithmic data transformation was applied. Categorical and nominal parameters were compared with a Chi-Square test. Baseline characteristics of the groups were compared with a 1-way ANOVA or Kruskal-Wallis test when data was not normally distributed. A 2-way repeated measures ANOVA was used to examine the impact of exercise training (time-effect), and whether the change differs between HIT and CT (timegroup-effect). When a significant main effect (time) or interaction-effect (timegroup) was observed, post-hoc tests with least-significant difference were used to identify differences between and within groups. When data for this 2-way comparison was not normally distributed, we used individual tests to examine the effect of time, group and timegroup. Changes in the control group were tested with a paired Student's t-test, or Wilcoxon test when data was not normally distributed. To control for the potential impact of baseline diameter on FMD [38], we used logarithmically transformed diameter data and adopted a univariate General Linear Model with baseline arterial diameter as a covariate, to compare differences between groups. Potential drop-outs were left out of the analysis and were not replaced. A Pearson correlation coefficient was determined for the relation between baseline quality of life and exercise-induced changes in quality of life. Data are presented as mean±standard deviation (SD), unless stated otherwise. Significance level was set at P<0.05.\n\nBODY.RESULTS:\nFor this study, 59 HF patients were screened. Fifteen patients did not meet inclusion criteria (screen failures) and 11 patients declined to participate after screening due to lack of time (n = 10) or change in health (n = 1) (Fig 1). We allocated 24 patients to HIT or CT. Nine HF patients were included in the control group (non-randomized). In both the HIT- and CT-group, 2 drop-outs were reported after allocation (71±2yrs; male:female 3:1; NYHA class II:III 3:1), which makes the total drop-out 17%. A patient in both training groups dropped out due to musculoskeletal complaints and a patient in both training groups dropped out due to progression of HF. Twenty patients in the training-groups and nine controls completed the study and were available for final analysis. The groups were not significantly different in age, body mass index, NYHA class, etiology of HF, blood pressure, heart rate, LVEF and physical fitness (Table 1). The control group consisted of significantly more females than the CT-group (P = 0.028, Table 1). Cardiovascular medication use is documented in Table 1. 10.1371/journal.pone.0141256.g001Fig 1Flow-chart of the inclusion of subjects. 10.1371/journal.pone.0141256.t001 Table 1 Subject characteristics and cardiovascular medication. CT (n = 10) HIT (n = 10) Control (n = 9) Age (yrs) 64±8 63±8 67±7 0.57 Sex (male:female) 10:0 * \n 9:1 5:4 0.028 Body weight (kg) 89.7±11.9 87.6±23.6 77.0±10.5 0.16 Height (cm) 177±5 177±3 174±9 0.66 Body mass index (kg/m 2 ) 28.9±4.7 28.1±7.5 25.4±2.7 0.24 NYHA class (II:III) 8:2 8:2 8:1 0.84 Etiology (Isch:Non-isch) 8:2 7:3 5:4 0.51 Systolic blood pressure (mmHg) 132±23 132±18 130±25 0.98 Diastolic blood pressure (mmHg) 83±11 79±10 78±14 0.48 Resting heart rate (/min) 59±11 57±7 60±10 0.80 Maximal heart rate (/min) \n † \n \n 129±19 126±16 120±15 0.53 Chronotropic incompetence (yes:no) \n † \n \n 5:4 8:2 6:1 0.33 VO 2peak \n \n † \n (mL/min/kg) 21.0±3.4 19.1±4.1 17.4±5.8 0.26 VO 2peak \n \n † \n (% of predicted VO 2peak ) 86±8 79±17 81±22 0.63 LVEF (%) 38±6 37±6 40±11 0.84 Medication Angiotensin converting enzyme-inhibitors 5 (50%) 6 (60%) 8 (89%) 0.19 Angiotensin II receptor antagonists 4 (40%) 4 (40%) 1 (11%) 0.30 Aldosterone antagonist 6 (60%) 7 (70%) 8 (89%) 0.36 Diuretics (loopdiuretics) 7 (70%) 6 (60%) 4 (44%) 0.50 β-blockers 10 (100%) 9 (90%) 9 (100%) 0.37 Antiplatelet drugs 6 (60%) 4 (40%) 3 (33%) 0.47 Coumarin derivates 4 (40%) 7 (70%) 4 (44%) 0.35 Statins 10 (100%) 9 (90%) 4 (44%) \n § \n \n 0.007 Data is presented as mean±SD. P-values refer to a 1-way ANOVA. \n † Data was unavailable for 1 subject in the CT-group and 3 subjects in the control-group. * Significantly less females compared to the control-group. \n § Lower compared to CT-group and HIT-group. \n\nBODY.RESULTS.EXERCISE TRAINING:\nWhen averaging all training sessions, CT was performed at 66±5% of maximal workload, whilst the high-intensity intervals during HIT were performed at 102±7% of maximal workload (P<0.001). CT was performed at 81±7% of maximal heart rate, and the high-intensity intervals during HIT were performed at 83±9% of maximal heart rate (P = 0.70). Borg-scores during CT and HIT were 13±1 and 14±1 respectively (P = 0.27).\n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.PHYSICAL FITNESS:\nVO2peak tended to increase after training (P = 0.06), whilst VO2peak/kg did not change after exercise (P = 0.10). A significant increase after training was found in the VO2peak related to predicted VO2peak (%), maximal workload, oxygen uptake at the AT and maximal oxygen pulse (Table 2). No significant differences were observed between both interventions (Table 2). 10.1371/journal.pone.0141256.t002 Table 2 Maximal incremental cycling test. CT (n = 10) HIT (n = 10) P-value \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n VO 2peak (mL/min) 1881±214 1887±27 1662±562 1792±559 0.06 0.44 0.08 VO 2peak (mL/min/kg) 21.2±3.6 21.3±3.7 19.1±4.1 20.4±4.3 0.10 0.14 0.09 \n # \n \n VO 2peak (% pred. VO 2peak ) 86±8 87±10 79±17 85±16 0.044 0.48 0.08 Max. workload (Watt) 145±22 152±26 126±38 142±45 <0.001 0.24 0.07 Max. heart rate (/min) 129±19 132±24 126±16 125±15 0.78 0.30 0.51 VE/VCO 2 slope 32.2±3.3 32.7±5.8 28.7±5.8 29.4±7.7 0.52 0.18 0.91 VO 2 at AT (mL) 1030±287 1248±388 1033±319 1090±225 0.041 0.54 0.22 Max. O 2 /HR (mL) 16.2±2.2 16.7±2.8 14.0±4.0 15.4±3.8 0.006 0.25 0.13 Data is presented as mean±SD. P-values refer to a 2-way repeated measures ANOVA between the two training groups. One subject in the CT-group did not reach VO 2peak , and therefore only VE/VCO 2 slope and VO 2 at AT could be determined. \n # For statistical reasons, data was analyzed with three separate tests to determine time , group and timegroup P-values. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.VASCULAR FUNCTION/STRUCTURE:\nWe found no significant changes in brachial and superficial femoral artery diameter, peak blood flow, and FMD (Table 3). No change in endothelium-independent dilation of the brachial artery was observed after training for both groups (Table 3). Furthermore, we found no significant impact of HIT or CT on carotid artery IMT or IMT-to-lumen ratio (Table 3). 10.1371/journal.pone.0141256.t003 Table 3 Brachial (BA) and superficial femoral artery (SFA) endothelium-dependent vasodilation through flow-mediated dilation (FMD), peak diameter and endothelium-independent dilation (GTN), and common carotid artery (CCA) intima-media thickness (IMT). CT (n = 10) HIT (n = 10) P-value \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n BA diameter (mm) 4.5±0.5 4.5±0.5 4.4±0.9 4.4±0.8 0.83 0.68 0.86 BA FMD (%) 5.2±2.5 4.8±3.0 5.3±2.6 4.7±2.5 0.33 0.92 0.98 BA FMD (%, scaled) 5.3±2.5 4.8±2.5 5.2±2.5 4.6±2.5 0.47 >0.999 0.91 \n # \n \n BA SR AUC (s, 10 3 ) 19.9±9.6 18.6±7.4 17.8±9.2 22.3±7.7 0.42 0.80 0.14 BA GTN (%) 17.6±7.0 16.3±6.5 16.8±8.7 15.2±4.9 0.33 0.74 0.92 BA GTN (%, scaled) 17.9±4.5 16.6±4.5 16.1±4.5 14.6±4.5 0.42 0.27 0.94 BA FMD-GTN ratio 0.34±0.21 0.33±0.24 0.42±0.30 0.34±0.15 0.46 0.63 0.82 BA CADC (%) 10.6±6.4 11.3±4.8 16.1±7.4 13.4±5.5 0.52 0.12 0.26 BA CADC (%, scaled) 11.0±4.2 12.0±4.2 15.0±4.2 12.8±4.2 0.72 0.11 0.27 BA peak blood flow (mL/min) 794±139 862±261 711±264 556±165 0.38 0.56 0.46 SFA diameter (mm) 7.1±1.2 6.9±1.2 6.7±1.1 6.5±1.0 0.38 0.48 0.88 SFA FMD (%) 3.3±1.9 5.1±4.8 4.2±1.8 3.4±2.8 0.58 0.74 0.19 SFA FMD (%, scaled) 3.5±2.9 5.1±2.9 4.1±2.9 3.1±2.9 0.74 0.50 0.19 SFA SR AUC (s, 10 3 ) 9.2±5.6 10.4±10.8 13.5±7.2 6.9±3.9 0.11 0.80 0.07 CA IMT (mm) 0.80±0.13 0.76±0.20 0.72±0.12 0.67±0.16 0.20 0.24 0.96 CA IMT-to-lumen ratio 0.12±0.02 0.11±0.02 0.11±0.02 0.11±0.02 0.40 0.59 0.45 Data is presented as mean±SD. P-values refer to 2-way repeated measures ANOVA between the 2 training groups. \n # For statistical reasons, data was analyzed with three separate tests to determine time , group and timegroup P-values. Due to technical problems, BA GTN/FMD-GTN ratio/peak blood flow was available for 9 subjects in the HIT-group and SFA FMD was available for 8 subjects in the HIT-group. CCA IMT and IMT-to-lumen ratio were available for 8 subjects in each group. SR AUC ; shear rate area-under-the-curve. CADC; conduit artery dilating capacity. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.CARDIAC FUNCTION/STRUCTURE:\nMost of the parameters of cardiac systolic function, left ventricle strain, or diastolic function demonstrated no change after HIT or CT (Table 4). Negligible but significant changes were found in area strain and isovolumetric contraction time (Table 4). 10.1371/journal.pone.0141256.t004 Table 4 Echocardiographic left ventricular volumes, systolic function, strain and diastolic function. CT (n = 10) HIT (n = 10) P-value Systolic function \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n LVEDV (ml) 154±24 159±28 194±39 204±44 0.26 0.002 0.64 \n # \n \n LVESV (ml) 98±14 102±19 134±32 132±40 0.87 0.037 0.63 Stroke volume (ml) 56±13 57±13 61±14 72±16 0.06 0.16 0.12 LVEF (%) 36±4 36±5 32±7 36±9 0.09 0.57 0.07 Cardiac output (L/min) 3.5±0.6 3.4±0.7 3.5±0.8 4.3±1.0 0.20 0.21 0.07 Cardiac index (L/min/m 2 ) 1.7±0.3 1.6±0.3 1.7±0.4 2.1±0.5 0.22 0.14 0.08 Longitudinal strain (%) -9±3 -9±3 -9±3 -8±3 0.60 0.47 0.38 \n # \n \n Circumferential strain (%) -10±2 -10±3 -9±3 -8±3 0.22 0.43 0.19 Radial strain (%) 23±7 22±6 23±8 20±8 0.13 0.71 0.48 Area strain (%) -17±4 -15±6 -17±5 -14±5 0.044 0.73 0.97 IVCT-L (ms) 52±7 50±10 49±12 58±7 0.18 0.56 0.029 IVCT-S (ms) 57±14 59±11 53±9 56±11 0.35 0.46 0.87 \n Diastolic function \n IVRT-L (ms) 145±32 149±27 142±27 159±27 0.13 0.75 0.38 IVRT-S (ms) 160±36 148±22 164±41 170±37 0.60 0.45 0.22 \n # \n \n E/A 1.15±0.71 1.17±0.89 1.53±1.42 1.60±1.53 0.49 0.36 0.59 \n # \n \n S/D 1.38±0.74 1.17±0.34 1.00±0.40 1.26±0.59 0.85 0.48 0.14 E/E’-L 6.8±1.9 6.7±1.9 10.3±4.4 9.8±6.3 0.71 0.07 0.74 E/E’-S 10.1±4.1 11.1±5.2 12.6±9.8 11.8±11.2 0.93 0.67 0.42 Data is presented as mean±SD. P-values refers to 2-way repeated measures ANOVA between the 2 training groups. \n # For statistical reasons, data was analyzed with three separate tests were performed to determine time , group and timegroup P-values. 4D data was available for 7 patients in the CT-group and 8 patients in the HIT-group. IVCT-l, IVRT-C, IVRT-S and E/E’-L was available for 9 patients in the HIT-group. IVCT-S and E/E’-S was available for 8 patients in the HIT-group. IVCT-L and S/D ratio was available for 9 subjects in the CT-group. IVRT-L and E/A ratio was available for 8 subjects in the CT-group. LVEDV; left ventricular end-diastolic volume. LVESV; left-ventricular end-systolic volume. IVCT-L/S: isovolumetric contraction time, lateral/septal. IVRT-L/S; isovolumetric relaxation time, lateral/septal. E/A ratio; peak mitral flow velocity during early filling/peak mitral flow velocity during atrial contraction. S/D; systolic flow velocity pulmonary vein/diastolic flow velocity pulmonary vein. E/E’-L/S; peak mitral flow velocity during early filling/peak mitral annulus velocity during early filling, lateral/septal. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.QUALITY OF LIFE:\nThere was no significant change in the SF-36 total score (Table 5). There was a significant increase in the SF-36 subscale 'physical function' after training (P = 0.004, Table 5), which did not differ between groups (timegroup P = 0.11). A trend for an inverse correlation was found between baseline SF-36 scores and training-induced change in SF-36 scores (r = -0.51, P = 0.052). We found no change in the MLHFQ for both groups (Table 5). No significant correlations were found between baseline MLHFQ scores and training-induced change in MLHFQ. 10.1371/journal.pone.0141256.t005 Table 5 Results of the SF-36 and Minnesota living with HF questionnaire (MLHFQ). CT (n = 9) HIT (n = 8) P-value \n SF-36 \n \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n Physical functioning 74±22 78±17 57±21 69±17 0.004 0.16 0.11 Physical health subscore \n † \n \n 73±20 76±16 60±22 67±19 0.15 0.26 0.52 Mental health subscore \n † \n \n , \n \n ‡ \n \n 81±9 83±10 83±5 82±10 0.75 0.87 0.54 Total score \n † \n \n , \n \n ‡ \n \n 75±16 78±13 68±14 73±14 0.18 0.42 0.76 \n CT (n = 9) \n \n HIT (n = 10) \n \n P-value \n \n MLHFQ \n \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n Total score 18±14 16±16 21±15 20±14 0.81 0.56 0.89 Data is presented as mean±SD. P-values refers to 2-way repeated measures ANOVA between the 2 training groups. Results of the SF-36 were scored on a 0–100 scale, in which a high score represents a better quality of life. Results of the MLHFQ were scored on a 0–105 scale, in which a low score indicates few HF-related complaints. \n † Data was available for 7 subjects in the HIT-group. \n ‡ Data was available for 8 subjects in the CT-group. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.CONTROL GROUP:\nWe found no changes over the 12-week period in maximal oxygen uptake (17.4±5.9 versus 17.5±5.8 ml/min/kg, P = 0.79) or in any of the other parameters of physical fitness (all P>0.05, S1 Table). Except for a decrease across time in the superficial femoral artery FMD and an increase in lateral E-E'-ratio, we found no changes in cardiac and vascular structure or function or in the SF-36 score and MLHFQ in controls (all P>0.05, S1 Table).\n\nBODY.DISCUSSION:\nThis study comprehensively compared physical fitness, vascular function, cardiac function and quality of life between a feasible and practical HIT-protocol versus traditional CT in HF patients. We have demonstrated that CT and HIT are both feasible in HF patients and induced a significant improvement in measures of (sub)maximal exercise performance and fitness, with no significant differences between both types of exercise training. Despite these changes in fitness, we did not find improvement in measures of resting cardiac and vascular structure and function. Furthermore, except an improvement in the subscale 'physical function' that may be related to the change in fitness, no effect of training was found on quality of life. Therefore, our data suggest that both types of exercise training successfully improve measures of physical fitness within 12-weeks, but not cardiovascular function at rest or quality of life. Moreover, we found no evidence for superiority of this more feasible HIT-protocol over traditional CT on the parameters presented in our study.\n\nBODY.DISCUSSION.PHYSICAL FITNESS:\nPrevious work found improvements in physical fitness in HF after HIT ranging from 8–46% [16,20,21], whilst studies adopting CT found changes ranging between 0–22% [17,19]. Most of these training studies have included low numbers of participants, which may explain the large variation in results. The largest HF exercise training study so far (>1,000 participants), the HF-ACTION trial, reported a median increase in fitness of 4% [39]. Although in the lower ends of the spectrum, the change in physical fitness in our study (~4%) is within the range of improvements as reported in previous work. As demonstrated in various previous studies, training characteristics (e.g. frequency, intensity and duration) are important factors determining training responses [40]. Nonetheless, our relatively low-frequency protocols were sufficient to induce significant improvements in fitness levels. Similar observations were made by Belardinelli et al [23], who adopted a long-term (10-year), low-frequency exercise training program in HF patients. They reported improvement in physical fitness levels in trained subjects after 1 year of training, whilst fitness levels remained higher than in controls across the 10-year intervention. In addition to the low frequency of training, the relatively modest changes in fitness in our study may relate to characteristics of the included participants, such as genetic factors [41] or to a priori higher levels of physical fitness as lower physical fitness levels are associated with larger training-induced improvements in HF patients [42,43]. Indeed, some previous HIT-studies demonstrated large improvement after exercise training in HF patients with low baseline levels of physical fitness [16–18]. Moreover, patients with chronotropic incompetence (i.e. 68% in our study) have attenuated exercise-induced improvement in parameters of fitness, which could have affected the effect size in our study [44]. Despite the relatively modest effect sizes, our exercise training protocols were successful in improving parameters of physical fitness. We did not demonstrate significant differences between CT and HIT on the change in physical fitness, a finding which is in agreement with some [18,19,22], but not all previous studies [16,17]. Interestingly, recent meta-analyses suggest that (high-intensity) interval training results in superior effects on physical fitness compared to CT in HF [45,46]. Despite these promising results of HIT in HF, larger trials that focus on clinical end-points are needed [47]. Also, limitations of a meta-analysis should be taken into consideration, as both HIT and CT interventions included in these meta-analyses comprise of many different protocols and exercise intensities. Especially for HIT, it is suggested that the time spent at a high percentage of peak oxygen uptake, determined by intensity and duration of the work and rest intervals, importantly contributes to the effect size [48]. Whilst the intensity of our high-intensity-bouts is high, the time spent at these high-intensity bouts was lower than in previous studies demonstrating superior effects of HIT compared to CT [16,17]. Furthermore, to validly compare exercise training regimes, it is important that total workload is not significantly different. A study that compared training-effects of HIT and CT and applied individually designed training programs with specific emphasis on comparable workloads for HIT and CT, found no differences between training modalities [19]. Therefore, more rigorous exercise programs (both in frequency, duration, and training load) rather than the type of training per se may contribute to larger improvements in physical fitness.\n\nBODY.DISCUSSION.CARDIAC AND VASCULAR ADAPTATION:\nExercise in HF patients is associated with beneficial cardiac remodelling [8]. After 12-weeks of training, we found no improvements in cardiac structure and function at rest, although the increase in maximal oxygen pulse suggests an increase in stroke volume during exercise. Previous studies that reported significant changes in cardiac function or structure generally applied training periods ≥6 months [8]. Therefore, the relatively short duration of training may contribute, at least partly, to the lack of cardiac remodelling in our study. Moreover, the largest proportion of our training-participants reported ischemic HF etiology. This could be of special importance, since a recent study suggested that cardiac adaptation during outpatient rehabilitation is more prominent in HF patients with non-ischemic etiology [49]. Furthermore, our results are in line with a recent meta-analysis that could not confirm that HIT is superior to CT to induce cardiac adaptations [46]. In our study, we found no superior effect of HIT to improve vascular function, which contrasts with the findings of a recent meta-analysis [50]. However, 4 out the 7 studies included in this meta-analysis showed a superior effect of HIT. Interestingly, these studies were all from the same laboratory and did not follow contemporary guidelines to assess endothelial function. We found no overall effect of exercise training on vascular function. As previous literature has reported a wide range of exercise-induced responses (and also demonstrated non-responders) in vascular function, Green et al. investigated which factors predict this response [51]. They concluded that exercise-induced improvements in vascular function are associated with a lower pre-training vascular function. When comparing the baseline FMD values of our subjects to normal values published previously [52], the endothelial function of the subjects in our study was within the normal range for their age. This may relate to the optimal pharmacological therapy of the HF patients we included [53]. Moreover, we have previously demonstrated that the shear rate pattern during exercise (i.e. an important stimulus for exercise-induced adaptation in vascular function) is less beneficial in HF patients compared to controls [54]. Preserved FMD before training and a suboptimal shear rate stimulus during exercise training may contribute to the absence of a significant training-induced change in vascular function.\n\nBODY.DISCUSSION.QUALITY OF LIFE:\nQuality of life after exercise training in HF patients is previously demonstrated to improve [7,55]. In our study, we indeed found improvement in the subscale for physical functioning after exercise training, but not for total quality of life. The lack of improvement in quality of life may relate to the relatively 'good' quality of life at baseline, which was well above that of previous studies [17,56,57] and consequently, provides little space for further improvement. In support of this idea, we observed a trend for an inverse relation between baseline SF-36 and change in SF-36 in the training group. This indicates that subjects with lower quality of life prior to exercise training demonstrate a larger benefit from the intervention. Furthermore, the inclusion of more relatively old HF patients in our study may also contribute to the smaller effect size of exercise training on quality of life, as demonstrated in a previous study [58]. This latter study found that older HF patients (>60 yrs) demonstrate a smaller effect of exercise training on quality of life compared to younger HF patients (<60 yrs).\n\nBODY.DISCUSSION.CLINICAL RELEVANCE:\nGiven the importance of (even small improvements in) fitness levels for the prognosis of HF patients [5,6,59], finding both a feasible and effective training program is clinically relevant. Another important factor is adherence to exercise training, which often is reported to be low in HF patients due to time-constraints and lack of energy [60]. A HIT training program with lower training frequency and high-intensity intervals of moderate duration might address these two major factors of non-compliance. Therefore, we have studied whether such a program is effective and whether it is superior to CT. The results of this study suggest that low frequency HIT with high-intensity intervals of moderate duration is feasible and successful in improving fitness. Such findings may be of clinical relevance and future studies should therefore focus on finding the optimal exercise protocol for HF patients to achieve long-term benefits and adherence.\n\nBODY.DISCUSSION.LIMITATIONS:\nAlthough we have included a relatively small number of patients, our sample size was in line with previous studies that demonstrated differences in effects of HIT and CT on physical fitness [16,17] and vascular function [50]. Moreover, we have used state-of-the-art techniques for measuring physical fitness and vascular function, in contrast to some previous studies that used suboptimal techniques to assess endothelial function. Therefore, we a priori expected to have sufficient power to detect significant differences between HIT and CT. Post-hoc power analysis revealed a power of 54% to detect differences in change in physical fitness between the two types of training. Finally, we did not provide a comparison between HIT with short high-intensity bouts and HIT with long high-intensity bouts. We encourage future studies to investigate whether different HIT-protocols render different results and to elucidate the optimal HIT-protocol. In conclusion, we have demonstrated that 12-weeks of exercise training in HF patients is associated with improvements in parameters of physical fitness, whilst no improvements in cardiovascular function at rest or (total) quality of life are observed. Moreover, our data does not provide strong evidence for a potentially superior improvement in physical fitness, cardiovascular function or quality of life after 12-weeks of HIT compared to CT in HF patients NYHA class II-III.\n\nBODY.SUPPORTING INFORMATION:\nS1 TREND ChecklistTREND statement checklist.(PDF)Click here for additional data file. S1 ProtocolResearch protocol.(PDF)Click here for additional data file. S1 TableResults of the control group.Data is presented as mean ±SD. †Data missing for 1 control subject. VO2peak; peak oxygen uptake. AT; anaerobic threshold. BA; brachial artery. SFA; superficial femoral artery. GTN; glyceryl trinitrate. CADC; conduit artery dilating capacity. IMT; intima-media thickness. SRAUC; shear rate area-under-the-curve. CADC; conduit artery dilating capacity. LVEDV; left ventricular end-diastolic volume. LVESV; left-ventricular end-systolic volume. IVCT-L/S: isovolumetric contraction time, lateral/septal. IVRT-L/S; isovolumetric relaxation time, lateral/septal. E/A ratio; peak mitral flow velocity during early filling/peak mitral flow velocity during atrial contraction. S/D; systolic flow velocity pulmonary vein/diastolic flow velocity pulmonary vein. E/E'-L/S; peak mitral flow velocity during early filling/peak mitral annulus velocity during early filling, lateral/septal. MLHFQ; Minnesota living with heart failure questionnaire.(DOCX)Click here for additional data file.\n\nQuestion:* Compared to continuous training (CT) 12-weeks inpatients NYHA II-III what was the result of high-intensity interval training (HIT) for 12-weeks in patients NYHA II-III on VO2peak tended?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1010	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Comparing the Hemodynamic Effects of Spinal Anesthesia in Preeclamptic and Healthy Parturients During Cesarean Section\n\n ABSTRACT.BACKGROUND:\nDespite controversies about the safest anesthetic technique for cesarean delivery in severely preeclamptic women, there is evidence that supports the use of spinal anesthesia in this group of patients.\n\nABSTRACT.OBJECTIVES:\nThis prospective randomized clinical trial was designed to determine the hemodynamic effects of low-dose spinal bupivacaine and the incidence of spinal anesthesia-associated hypotension in severely preeclamptic and healthy parturients undergoing cesarean sections.\n\nABSTRACT.PATIENTS AND METHODS:\nSpinal anesthesia was performed with 10 mg (= 2 mL) hyperbaric 0.5% bupivacaine plus 2.5 μg sufentanil in two groups of patients after they received 500 mL of IV lactated Ringer's solution. Heart rate and blood pressure were recorded before spinal anesthesia and at two minutes intervals for 15 minutes after the block, and then every five minutes until the end of the surgery. Hypotension was defined as more than 25% of decline in the mean arterial blood pressure compared to the baseline in both groups (or systolic blood pressure < 100 mmHg in healthy parturients) and was treated with 5 mg IV ephedrine. The total amounts of intravenous administered fluid and the total doses of ephedrine were recorded for each patient as well.\n\nABSTRACT.RESULTS:\nThe incidence rate of hypotension among the preeclamptic patients was lower than that of the healthy parturients, despite the former group receiving smaller volumes of intravenous fluids (P < 0.05). The total doses of IV ephedrine for treating hypotension were significantly lower among the preeclamptic patients (3.2 mg in preeclamptic patients versus 7.6 mg in normotensive patients) (P = 0.02). The one-minute Apgar score was significantly lower for the preeclamptic parturients (8.4 ± 0.7 versus 7.2 ± 1.5) (P = 0.001), but there was no significant difference in the five-minute Apgar scores between the two groups.\n\nABSTRACT.CONCLUSIONS:\nOur results confirm that low-dose bupivacaine spinal anesthesia is associated with a lower risk of hypotension than previously believed, and it can therefore be safely used in severe preeclamptic women undergoing cesarean delivery.\n\nBODY.1. BACKGROUND:\nPregnancy-induced hypertension is a major cause of morbidity and mortality in obstetrics, complicating 3% - 8% of pregnancies. Severe preeclampsia poses a dilemma for anesthesiologists, and there is some controversy about the best anesthetic technique for cesarean delivery in such cases (1, 2). Because of the risks related to airway edema, difficulty with the airway or failed intubation, hypertensive response to direct laryngoscopy, and aspiration pneumonitis, general anesthesia is associated with more untoward outcomes in this particular group of patients (3, 4). When there is no contraindication for performing regional anesthesia, risk-benefit considerations strongly favor neuraxial techniques over general anesthesia for cesarean delivery in cases of severe preeclampsia. Regional anesthesia techniques have been widely used recently, however, spinal anesthesia, once considered contraindicated due to the common belief that the sudden and extensive sympathetic blockade following the subarachnoid block would result in severe hypotension and compromise uteroplacental blood flow in this group of patients (5-8). Although controversial, some studies have shown the effectiveness of colloid loading on reducing the incidence of hypotension in spinal anesthesia (9, 10), but vasopressor agents and volume loading, which are commonly used to manage spinal anesthesia-induced hypotension, could put the preeclamptic patients at increased risk of hypertension and pulmonary edema (6). Recent evidence has challenged this view, suggesting that spinal anesthesia may in fact be an appropriate choice for preeclamptic women when cesarean delivery is planned, as long as neuraxial anesthesia is not contraindicated (e.g., coagulopathy, eclampsia with persistent neurologic deficits) (2, 5, 8). Although the relative safety of the subarachnoid block in these patients has been demonstrated, there are few studies that compare the differences in the hemodynamic changes and newborn well-being after single-shot spinal anesthesia between preeclamptic and healthy parturients\n\nBODY.2. OBJECTIVES:\nThis prospective randomized clinical trial was designed to compare the hemodynamic effects and the incidence of spinal anesthesia-associated hypotension after spinal anesthesia with bupivacaine plus sufentanil in severely preeclamptic versus healthy parturients undergoing cesarean sections.\n\nBODY.3. PATIENTS AND METHODS:\nAfter obtaining institutional ethics committee approval, 80 parturients (37 healthy and 43 severely preeclamptic parturients) that were being cared for in our unit from April 2011 to July 2012 were enrolled in the study after providing informed consent. Severe preeclampsia was defined as a systolic arterial blood pressure of 160 mmHg or higher, or a diastolic blood pressure of 110 mmHg or higher, associated with proteinuria > 5 g in 24 hours. Patients who were excluded were those with coagulopathy (including those with platelet counts < 50,000), placental abruption, severe fetal distress, a history of allergy to local anesthetics, oliguria of less than 500 mL in 24 hours or persistently < 30 mL/hour, cerebral or visual disturbances, pulmonary edema, hemodynamic instability, local infection of the spinal injection site, or refusal of a spinal block. All patients in the preeclampsia group received a 4 g loading dose of intravenous magnesium sulfate (Mg SO4) followed by a 1 g/hour infusion for 24 hours for seizure prophylaxis. Intravenous hydralazine of 5 mg was given at 20-minute intervals to decrease diastolic blood pressure to approximately 90 mmHg. Before performing spinal anesthesia on each patient, preoperative fluid administration equal to 10 mL/kg of Ringer's lactate solution was administered over the course of 15 - 20 minutes. All patients received 1500 - 2000 mL lactated Ringer's solution after spinal anesthesia and during the operation. The volume of administered fluid was not restricted in the preeclamptic patients because of the contracted intravascular volume in this group of patients and the high incidence of hypotension caused by spinal anesthesia-induced sympathetic blockade. Patients were monitored with standard monitoring devices including automated blood pressure cuffs, electrocardiogram, and pulse oximetry. Spinal anesthesia was performed with 10 mg hyperbaric 0.5% bupivacaine plus 2.5 - 3 μg sufentanil (2.5 mL volumes) in two groups in the sitting position in the L3-L4 or L4-L5 vertebral interspaces. Each patient was then placed in the supine position with a left lateral tilt of 15-20 degrees. The height of the sensory block was assessed using a pinprick test, and a 10°-15° head down-tilt (Trendelenburg position) was initiated if a T4 sensory level was not achieved at 10 minutes after the spinal injection. After achieving an adequate sensory block (T4 level), the patient was prepared for surgery. Heart rate and blood pressure were recorded before performing spinal anesthesia at two-minute intervals for 15 minutes after the block, and then every five minutes until the end of the surgery. Hypotension was defined as more than 25% decline in mean arterial blood pressure (MAP) compared to the baseline in both groups (or systolic blood pressure (SBP) < 100 mmHg in healthy parturients) and was treated with 5 mg IV ephedrine. The total amounts of intravenous administered fluid and the total doses of ephedrine were recorded as well. Based on the findings of previous studies, we calculated that at least 38 patients per group were required to show a 25% difference in the incidence of hypotension, with 80% power at the 5% level. Data are presented as number, median and range, mean ± SD, or percentage as appropriate. Fisher's exact test was used for intergroup comparisons of the incidence of hypotension. Mean values of most of the quantitative study variables were compared by using the unpaired Student's t-test. A P value of less than 0.05 was considered to indicate statistical significance. Data entry and analysis were performed using SPSS software version 16.\n\nBODY.4. RESULTS:\nEighty patients (severe preeclampsia = 43 and healthy = 37) were studied. Demographic data, the times from spinal injection to delivery, the median sensory blocked levels at the time of incision, the volumes of estimated blood loss, and the surgical durations were similar between the two groups (Table 1). Table 1. Maternal, Neonatal, and Anesthetic Considerations a Variable Healthy Preeclampsia P Value \n n \n 37 43 \n Age, y \n 28.1 ± 5 29.3 ± 6.6 0.12 \n Gestational age, week \n 38.8 ± 1.2 34.3 ± 3.8 0.00 \n Base line MAP \n 101.1±10.1 119.5±15.9 0.02 \n Upper Sensory Level (Median, Range) \n T4 (T2-T5) T4 (T2-T5) 0.32 \n IV fluid, mL \n 2500 ± 0.1 2400 ± 0.2 0.000 \n Spinal puncture to delivery interval, minute \n 17.5 ± 2.5 17.1 ± 2.5 0.83 \n Ephedrine dose, mg \n 7.5 ± 9.2 3.2 ± 7.8 0.04 \n APGAR score 1-min (Range) \n 8.4 ± 0.7, (5 - 10) 7.2 ± 1.5, (2 - 10) 0.001 \n APGAR score 5-min (Range) \n 9.4 ± 0.7, (7 - 10) 8.6 ± 1.1, (5 - 10) 0.35 a Values are expressed as mean ± SD unless otherwise indicated. The mean gestational age and mean one-minute Apgar scores in the patients with severe preeclampsia were significantly lower than those of the healthy parturients (Table 1). However, there was no significant difference in the five-minute APGAR score between the two groups. The incidence rate of hypotension in the preeclamptic patients (55.8%) was less than that of the healthy parturients (89.2%) (Table 2), despite the former receiving smaller volumes of intravenous fluids (2.4 versus 2.5 lit) (Table 1) (P = 0.001). Table 2. Incidence of Hypotension and Changes in Blood Pressure After Spinal Anesthesia in the Two Groups Variable Healthy Preeclampsia P Value \n Incidence of MAP hypotension (%) \n 33 (89.2%) 24 (55.8%) 0.001 \n Lowest SBP mmHg \n 98 ± 12.9 116 ± 18.6 0.02 \n Lowest DBP mmHg \n 47.5 ± 9.5 66.3 ± 14.1 0.03 \n Lowest MAP mmHg \n 64.9 ± 10.1 83.7 ± 14.9 0.008 The SBP, DBP, and MAP measured at the baseline were higher for the patients with preeclampsia, and the mean lowest SBP and MAP measured among the preeclamptic patients were consistently higher than the corresponding values among the healthy parturients (Table 2). Furthermore, the total doses of IV ephedrine for treating hypotension were significantly lower for the preeclamptic patients than for the normotensive patients (3.2 ± 7.8 mg versus 7.5 ± 9.2 mg) (P = 0.04).\n\nBODY.5. DISCUSSION:\nSpinal anesthesia-associated hypotension may occur in up to 64% - 100% of pregnant women undergoing cesarean delivery (2). Severely preeclamptic patients have been considered to be at higher risk of severe hypotension (1, 2, 5-8), and the concern of severe hypotension caused by subarachnoid block may often deter the anesthesiologist from choosing this technique for this group of patients. Epidural anesthesia has traditionally been regarded to be safer for preeclamptic parturients as it does not produce sudden hypotension. However, some studies have shown that the two techniques produce a similar incidence and severity of hypotension in preeclamptic parturients (6, 7, 11). There is growing interest in using spinal anesthesia on preeclamptic patients because of its simplicity, faster onset, lower dose of injected local anesthetic (which decreases the probability of systemic toxicity), and less tissue trauma caused by the use of a smaller gauge spinal needle (12-14). As a result of this interest, a number of studies have been conducted to show the hemodynamic consequences of spinal anesthesia in patients with preeclampsia. A prospective study by Aya et al. found that the risk of hypotension following spinal anesthesia in preeclamptic patients was significantly lower than the risk among healthy term parturients (17% in preeclamptic parturients and 53% in healthy parturients) (2). In another study, the same author suggested that the risk of hypotension following a subarachnoid block in preeclampsia was related to preeclampsia-associated factors rather than a small uterine size (15). Similar to the studies by Aya et al., the incidence of hypotension in severely preeclamptic patients undergoing spinal anesthesia for cesarean delivery was found to be significantly lower in comparison to the rate among healthy parturients (55% versus 89%) in our study. Factors such as difference in gestational age, the carrying of a smaller fetus, less aortocaval compression, sympathetic hyperactivity, and high vascular tone might have led to this finding (1, 2, 8, 16). The injection of different doses of bupivacaine (10 mg versus 8 - 12 mg) for the induction of the subarachnoid block and the different criteria for defining hypotension (a 25% versus 30% decline to baseline MAP) might explain why the incidence of hypotension was higher in both groups in our study compared to the corresponding rates in Aya et al.'s study. According to two other studies conducted by Mendes et al. (17) and Saha et al. (8), the hemodynamic changes and newborn well-being appeared to be comparable in severely preeclamptic and healthy parturients submitted to spinal anesthesia for cesarean section, and spinal anesthesia seemed to be a safe option for patients with severe preeclampsia. The ephedrine requirement for treatment of spinal anesthesia-induced hypotension in preeclampsia has been reported to be lower than that required by healthy parturients (2, 18). Preeclamptics have been reported as requiring significantly less phenylephrine to treat hypotension as well (8). These results were comparable to our findings, in that the total doses of IV ephedrine for treating hypotension were significantly lower for the preeclamptic patients (3.2 ± 7.8 mg) than for the normotensive patients (7.5 ± 9.2 mg) (P = 0.04). There is little evidence in the current literature supporting the use of phenylephrine as the vasopressor of choice in high-risk pregnancies such as those involving preeclampsia (19), so we chose to use ephedrine for treating hypotension in our patients. More studies are needed to investigate the effects of vasopressors while considering the influence on feto-maternal physiology in patients with preeclampsia. The results of a review by Dyer et al. showed that after spinal anesthesia for cesarean section, patients with preeclampsia had a lower susceptibility to hypotension and less impairment of cardiac output than healthy parturients (20). In a prospective observational study on 15 parturients with severe preeclampsia, no clinically significant change in cardiac output was shown after the subarachnoid block (21). The focus of our study was on the blood pressure changes during spinal anesthesia in the preeclamptic patients, and therefore we did not measure the cardiac output fluctuations in our patients. Further studies with larger sample sizes evaluating cardiac output are needed for better understanding of hemodynamic changes during spinal anesthesia in this group of patients. It is believed that the incidence of spinal anesthesia-induced hypotension is related to the local anesthetic dose, so one particular strategy to minimize the hemodynamic disruption after spinal anesthesia involves using small intrathecal local anesthetic doses. In a pilot study which compared the hemodynamic consequences of two doses of spinal bupivacaine (7.5 mg versus 10 mg) for cesarean delivery in those with severe preeclampsia, pre-delivery MAP was lower and the ephedrine requirements were greater in the 10 mg group (22). In another study, Roofthoof and Van de Velde have shown that when low-dose spinal anesthesia (6.5 mg bupivacaine) was administered with sufentanil as part of a combined spinal-epidural (CSE) technique in shorter surgeries (less than 60 minutes), the need for epidural supplementation was rare (23). The ED95 of intrathecal bupivacaine coadministered with intrathecal 2.5 μg sufentanil using CSE anesthesia for cesarean section in severely preeclamptic patients was reported to be 8.82 mg in another study, and using smaller doses of intrathecal bupivacaine in the patients resulted in a decrease of incidences of maternal hypotension and vasopressor requirements (24). However, no studies have compared CSE with single-shot spinal anesthesia in severe preeclampsia, and further research is needed to elucidate the best strategy to optimize the hemodynamics and uteroplacental perfusion in this particular group of patients. Considering the neonatal outcomes after various anesthesia techniques in cesarean delivery among preeclamptic patients, no statistically significant difference was found in the one- and five-minute Apgar scores and the umbilical artery blood gas markers between the two groups of patients receiving spinal or general anesthesia (25). Other studies in support of subarachnoid block have also shown that transient neonatal depression and birth asphyxia are more common among preeclamptic women who have received general anesthesia (26). Comparing umbilical arterial fetal base deficit and other markers of maternal and neonatal well-being in 70 preeclamptic patients undergoing cesarean delivery who were randomized into groups receiving either spinal or general anesthesia, the spinal group had a higher mean umbilical arterial base deficit and a lower median umbilical arterial pH, but other markers of a compromised neonatal condition, including the requirement for neonatal resuscitation, an Apgar score < 7, an umbilical arterial pH < 7.2, and the need for neonatal intermittent positive pressure ventilation were the same among the two groups (27). In comparison with healthy subjects, patients with severe preeclampsia had a younger gestational age (34 weeks versus 39 weeks) in our study, which is one of the likely causes of the lower one-minute Apgar scores of the neonates among the first group. Although there was evidence as early as 1950 that preeclampsia attenuates spinal anesthesia-induced hypotension, it has taken a long time for clinical trials to demonstrate the safety of spinal and CSE anesthesia in preeclamptic parturients. Recently, after five decades of research, the relationship between spinal anesthesia, pre-eclampsia, and hypotension can be properly acknowledged and put into clinical practice (28). Because of an altered balance of vascular tone, reduced responses to endogenous pressors, and increased synthesis of vasodilator prostaglandins and nitric oxide, the normal pregnant patient is very sensitive to spinal anesthesia. These effects increase dependence on sympathetic vascular tone in normal pregnancy, and this can be the main cause of spinal anesthesia-induced hypotension in healthy parturients, while damaged vascular epithelium results in persistent vasoconstriction in preeclampsia (8, 16). There is a dramatic increase in the use of spinal anesthesia for cesarean delivery in severe preeclampsia that could be related to the documented safety of subarachnoid block in this group of patients. Therefore, single-shot subarachnoid block may be a good choice for cesarean delivery in patients with severe preeclampsia, since it has been shown to be safe for both the mother and the neonate (28).\n\nBODY.5. DISCUSSION.5.1. CONCLUSION:\nOur results have also confirmed that single-shot low-dose bupivacaine spinal anesthesia is associated with a lower risk of hypotension and vasopressor requirements in comparison to the rates of healthy subjects, and could be safely used in patients with severe preeclampsia undergoing cesarean delivery. However, more studies with the CSE technique using smaller doses of local anesthetics and larger sample sizes are suggested. Further research is needed to find the best strategies to optimize hemodynamics and uteroplacental perfusion in severely preeclamptic parturients during spinal anesthesia for cesarean delivery.\n\nQuestion: Compared to Low-dose bupivacaine spinal anesthesia in healthy parturients what was the result of Low-dose bupivacaine spinal anesthesia in pre-eclamptic parturients on Risk of hypotension?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1140	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy and Safety of Tiropramide in the Treatment of Patients With Irritable Bowel Syndrome: A Multicenter, Randomized, Double-blind, Non-inferiority Trial, Compared With Octylonium\n\n ABSTRACT.BACKGROUND/AIMS:\nAntispasmodics such as octylonium are widely used to manage irritable bowel syndrome (IBS) symptoms. However, the efficacy and safety of another antispasmodic, tiropramide, remain uncertain. We aimed to evaluate the efficacy and safety of tiropramide compared with octylonium in patients with IBS.\n\nABSTRACT.METHODS:\nIn this multicenter, randomized, non-inferiority trial, 287 patients with IBS (143 receiving tiropramide and 144 octylonium) were randomly allocated to either tiropramide 100 mg or octylonium 20 mg t.i.d (means 3 times a day) for 4 weeks. Primary endpoint was the mean change of abdominal pain from baseline assessed by visual analogue scales (VAS) score after 4 weeks of treatment. Secondary endpoints were the changes in abdominal pain from baseline at week 2 and in abdominal discomfort at weeks 2 and 4, using VAS scores, patient-reported symptom improvement including stool frequency and consistency, using symptom diaries, IBS-quality of life (IBS-QoL), and depression and anxiety, at week 4.\n\nABSTRACT.RESULTS:\nThe VAS scores of abdominal pain at week 4, were significantly decreased in both tiropramide and octylonium groups, but the change from baseline did not differ between the 2 groups (difference,-0.26 mm; 95% CI,-4.33-3.82; P = 0.901). Abdominal pain and discomfort assessed using VAS scores, diaries, and IBS-QoL were also improved by both treatments, and the changes from baseline did not differ. The incidence of adverse events was similar in the 2 groups, and no severe adverse events involving either drug were observed.\n\nABSTRACT.CONCLUSIONS:\nTiropramide is as effective as octylonium in managing abdominal pain in IBS, with a similar safety profile.\n\nBODY.INTRODUCTION:\nIrritable bowel syndrome (IBS) is a functional bowel disorder characterized by abdominal pain or discomfort relieved by defecation and accompanied by a change in bowel habit.1 According to epidemiologic studies in Korea, the prevalence of IBS was reported to be 6.6% overall, 7.1% in men and 6.0% in women.2 Patients with IBS are reported to seek healthcare frequently, have poor health-related quality of life (QoL) and be responsible for high societal costs.3-5 Like other functional gastrointestinal (GI) disorders, the development of IBS and its symptoms are associated with multifactorial pathophysiology.6 Moreover, symptoms even in an individual patient with IBS may have a different pathophysiology depending on various factors such as diet or emotional status. Therefore, therapy targeting a specific pathophysiology in IBS has been difficult, and symptom treatment focusing on major complaints of IBS or drug combination covering multiple pathophysiology has usually been applied to the management of IBS. Of multifactorial pathophysiology in IBS, colonic smooth muscle spasm has long been postulated to be responsible for abdominal pain in IBS from clinical observations as well as some experimental evidences.7 Therefore, pharmacologic agents directly acting on smooth muscle or on cholinergic receptors, called as antispasmodics, have been developed and used to control abdominal pain and discomfort in IBS. They may be classified as smooth muscle relaxants or agents with anti-cholinergic or anti-muscarinic property. One of the antispasmodics, tiropramide, is a derivative of tyrosine, and exerts a spasmolytic effect on the intestine through reducing Ca2+ release into intestinal smooth muscle, rather than acting on the enteric nervous system.8,9 In a double-blind, placebo-controlled, randomized trial, tiropamide led to symptom improvement in terms of total symptom scores for 4 weeks, compared with 3 weeks in the placebo group; in addition, at week 4 abdominal pain was only improved in the tiropramide group.10 Also in a Korean study of similar design involving 63 patients with IBS, tiropramide improved overall symptom scores and decreased abdominal pain at weeks 2 and 4 (78.2% of the treatment group with tiropramide and 40.5% of placebo group).10 Another antispasmodic, octylonium, also modifies Ca2+ fluxes in the intestinal smooth muscle, with direct myolytic properties similar to tiropramide.11,12 Previously, octylonium has already been proven to be more effective in reducing IBS symptoms than placebo.13-15 However, there have been few large-scale clinical trials comparing tiropamide with antispasmodics of proven efficacy in IBS patients. Therefore, this study aimed at evaluating the efficacy and safety profile of tiropamide in IBS patients compared with octylonium.\n\nBODY.MATERIALS AND METHODS.STUDY PATIENTS:\nEligible patients were 20 to 75 years of age; had been diagnosed with IBS (as assessed according to the Rome III diagnostic criteria for IBS); complained of abdominal pain or discomfort at least 2 times per week for the 2-week run-in period; had visual analogue scale (VAS) scores over 30 mm for abdominal pain during the randomization period. Patients who fit the study criteria had a run-in period of at least 2 weeks during which all IBS-related medications, and concomitant medications were stopped. Exclusion criteria included a history of inflammatory bowel disease, lactose intolerance, uncontrolled diabetes (haemoglobin A1C > 8%) or hypertension (systolic or diastolic blood pressure of ≥ 140/90 mmHg), psychiatric disorder requiring medication, malignancy of organs other than digestive (except for cases with no recurrence for over 5 years since treatment), laparoscopic or open abdominal surgery (except for appendectomy), renal or hepatic disease, glaucoma, and prostate hyperplasia. Those with a history of the following diseases within the previous 6 months were also excluded; peptic ulcer disease, GI bleeding, gastroesophageal reflux disease, intestinal stenosis or obstruction, infectious diarrhea, and pancreatic insufficiency. Patients were excluded if they were intolerable of or sensitive to, study drug, had a history of alcohol or drug addiction, or were expected to take any contraindicated medication during the study period. Pregnant or lactating women and women of childbearing age not using contraception, were also excluded.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis was a multicenter (20 centers), randomized, double-blind, parallel-group, non-inferiority comparative study conducted in South Korea from May 2012 to April 2013. The study protocol was approved by the Institutional Review Board of each study center and conducted in accordance with the ethical principles based on the Declaration of Helsinki and Good Clinical Practice guidelines. For a run-in period of about 2 weeks, eligible subjects for screening were instructed to stop IBS-related medications and prohibited from other drugs. Following the screening phase of 2 to 4 weeks, eligible patients were randomly assigned to either tiropramide (Tiropa; Dae Woong Pharma Korea Inc., Seoul, South Korea) 100 mg or octylonium (Menoctyl; DONG HWA PHARM, Seoul, South Korea) 20 mg, taken 3 times daily before meals for 4 weeks. Treatment assignments were carried out by a computer-generated randomization schedule that was designed to allocate patients to the 2 treatment arms in a 1:1 ratio. The subjects were assigned to sequential allocation numbers at each site, and the medications were presented as 2 identically-appearing tablets containing 1 active drug and 1 placebo of each comparative drug to maintain the double blind condition. Follow-up visits during the study period were scheduled at weeks 2 and 4 to assess abdominal pain/discomfort using VAS, IBS quality of life, IBS symptoms including bowel habits using diaries, the Beck depression inventory (BDI) and the Beck anxiety inventory (BAI), drug compliance and adverse events (Fig. 1). Written, informed consent was obtained from all subjects before enrollment.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.EFFICACY:\nThe primary endpoint was the change in abdominal pain from baseline assessed by VAS scores after 4 weeks of treatment. The secondary endpoints included the change in abdominal pain from baseline by VAS scores at week 2, the change in abdominal discomfort from baseline by VAS scores at weeks 2 and 4, improvement of patients' overall assessment at weeks 2 and 4, the change in IBS QoL from baseline at 4 weeks, the change in symptom improvement in abdominal pain and discomfort from baseline using symptom diaries (severity of symptoms and days of no symptoms), and stool frequency and form assessed by Bristol stool form scale and according to IBS subtypes. Symptom improvement was defined as \"completely improved,\" \"considerably improved\" or \"slightly improved.\" Percentages of symptom improvement include \"completely, considerably and slightly improved.\" Symptom diaries assessed daily symptoms of abdominal pain and discomfort using VAS of 0 to 100 with 100 representing extreme symptom. The number of defecation per day and the most common stool consistency during the day were recorded using the Bristol stool form scale. IBS-QoL was assessed by asking patients to answer each question using a 5-point Likert scale (0 = none, 1 = mild, 2 = moderate, 3 = severe, 4 = extremely severe). Exploratory end points were the changes in BDI and BAI from baseline. Each BDI or BAI was composed of 21 questions and assessed as \"0 = do not feel at all,\" \"1 = feel a bit,\" \"2 = feel significantly,\" and \"3 = feel badly.\" Confounding factors were baseline factors of efficacy including BDI and BAI.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.SAFETY:\nSafety assessments included adverse events, and abnormalities in laboratory findings and vital signs.\n\nBODY.MATERIALS AND METHODS.STATISTICAL METHODS:\nWe estimated the required sample size for this study from the data of a previous study which found a change in VAS for abdominal pain from baseline as 23.6 mm with standard deviation (SD) of 25.0 mm.14 The margin of non-inferiority was assumed to be 11 mm, approximately half of 22.7 mm, which was the difference of the changes observed between the octylonium and the placebo groups. Based on these assumptions, a sample of 129 patients was needed for each study arm in order to have a power of 90%, and α of 0.025 (one-sided), while allowing for a 15% dropout rate. The analyses were performed using full analysis set (FAS) and per protocol set (PPS). All efficacy analyses were conducted in the FAS population, which consisted of all randomized patients satisfying the inclusion and exclusion criteria who received at least one dose of study medication and had at least one post-baseline efficacy measurement. The primary efficacy analysis was based on the PPS, which included all patients within the FAS population who took more than 80% of their assigned drugs and had no major protocol violations such as violations of scheduled visits or administration of contraindicated medication. The change in VAS for abdominal pain from baseline was evaluated by 2 sample t test. Seconday outcomes were compared by 2 sample t test or Wilcoxon's rank sum test. Rates of symptom improvement were described as frequencies and percentages, and compared between groups by Pearson's chi-square test or Fisher's exact test. For safety variables including treatment emrgent adverse event (TEAE), adverse drug reaction, and serious adverse event, Pearson's chi-square test or Fisher's exact test was used to evaluate differences in incidence between groups. Changes in continuous variables from baseline after treatment were analyzed by 2 sample t test or Wilcoxon's rank sum test, while categorical variables, by Pearson's chi-square test or Fisher's exact test. Confounding factors such as BDI, BAI and baseline values of the efficacy variables were further analysed by ANCOVA or multiple logistic regression. A P-value of 0.05 was considered statistically significant. Statistical analyses were performed using SAS (Enterprise Guide 4.3).\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nTotal of 356 patients were evaluated for study inclusion. After exclusion of 61 patients during the screening period, 295 patients were randomized to either tiropramide or octylonium. Three percent of patients in the tiropramide group (4/143) and octylonium group (4/144) did not complete the study. Data on the remaining 287 patients were available for the FAS analysis: 143 for tiropramide vs. 144 for octylonium. Data on 245 patients were available for the PPS analysis: 117 for tiropramide vs. 128 for octylonium. A flowchart of patient progression through the study with reasons for premature discontinuation is presented in Fig. 2. Demographic and baseline characteristics of patients are presented in Table 1. Both treatment arms were well balanced for gender, age and severity of symptoms at baseline.\n\nBODY.RESULTS.EFFICACY:\nThe PPS population comprised of 245 patients (117 in the test group and 128 in the control group). The mean changes of VAS scores for abdominal pain from baseline were-23.49 ± 17.51 mm in the tiropramide group and-23.13 ± 17.61 in the octylonium group. The mean difference between the 2 groups was-0.26 mm in the FAS and-0.35 mm in the PPS, and the upper limit of the 97.5% CI at one-sided was 3.82 mm in the FAS and 4.07 mm in the PPS; these are below the margin of inferiority of 11 mm, indicating that tiropramide is not inferior to octylonium (Table 2). In secondary outcome analyses, VAS scores for abdominal pain at week 2 were significantly decreased in both groups (Table 3). Significant improvement in abdominal pain and discomfort at weeks 2 and 4 using symptom diaries, and in IBS-QoL, BDI and BAI at week 4 were observed in both groups, however the differences between the groups were not significant. In the subgroup of IBS-D, stool frequency was decreased and stool consistency was improved by treatment. Furthermore, the degree of symptom reduction in abdominal pain using symptom diaries was higher in the tiropramide group than in the octylonium group from week 1 (P = 0.033). After adjusting the baseline values of related factors, our analysis showed that all the factors based on symptom diaries, except the change of IBS symptoms, did not differ in the 2 groups. IBS symptoms at week 4 using symptom diaries were reduced further compared to baseline in the tiropramide group than the octylonium group.\n\nBODY.RESULTS.SAFETY:\nAdverse events reported during the study are shown in Table 4. TEAE was 10.88% (16/147) in the tiropramide group and 12.24% (18/147) in the octylonium group, which included 28 each. The safety profile of tiropramide was similar to that of octylonium. Adverse drug reactions were reported in 7 patients in the tiropramide group and 6 patients in the octylonium group, which included 17 and 9, respectively. Serious adverse events developed in one patient in each group, idiopathic thrombocytopenic purpura in the tiropramide group and intervertebral disc protrusion in the octilonium group, but were not related to the study drugs, and were improved without any sequelae. Laboratory test results, when comparing those at screening period with those at last visit, showed no violation of safety regarding normal values, or the changes of direction and quantity. Vital signs did not change significantly from baseline in either group at weeks 2 and 4.\n\nBODY.DISCUSSION:\nThe present study was designed to assess the non-inferiority of tiropramide compared to the proven antispasmodic, octylonium, for managing IBS symptoms. This multicenter, randomized, double-blind, non-inferiority trial showed that 4-week treatment with tiropramide improved abdominal pain and discomfort, patient-reported overall assessments of IBS symptoms, IBS-QoL, depression and anxiety, with no significant differences from octylonium. These results demonstrate non-inferiority of tiropramide in efficacy and safety, compared with otiolonium. Tiropramide effectively and safely managed abdominal pain in the IBS patients. Our results showed that the change in VAS scores for abdominal pain from baseline was about 23.5 mm after 4-week treatment with tiropramide, similar to 23.6 mm observed after 4-week treatment with octylonium. The changes from baseline between the 2 groups were not significantly different, and the upper limit of 95% CI was lower than the margin of inferiority in both the FAS and PPS populations, indicating non-inferiority of tiropramide compared to octylonium. In a previous study comparing tiroparmide with octylonium in IBS patients, the proportion of patients whose abdominal pain was relieved by treatment was higher in tiropramide group than in octylonium group at days 3 and 5 of medication, suggesting rapid drug action of tiropramide.16 Also, at the end of 30-day treatment, normal gut motility was restored in 88% of the tiropramide group compared with 47% of octylonium group.16 The presumed mechanism of tiropramide in improving abdominal pain is its antispasmodic effect on the intestine. In an animal study using the isolated smooth muscle, tiropramide inhibited Ca2+ influx for the most part and, to a lesser extent, increased the intracellular cyclic adenosine monophosphate (cAMP) levels.9 This study using rabbit also found that tiropamide increased Ca2+ absorption into microvesicles and decreased the amount of Ca2+ released to stimulate the contraction of the smooth muscle by increasing cAMP; as a consequence the smooth muscle relaxed.9 In terms of the distribution of tiropramide, a study showed that the radioactivity of tiropramide lasted longer in the colon than in other organs after intravenous or oral administration,17 indicating relative colonic selectivity. Furthermore, the effect of tiropramide were more evident in the smooth muscle of the digestive, urinary and female genital tract than in those of the vessel, and in stimulated contractions rather than in spontaneous ones.17 In the present study, other advantages of tiropramide were observed compared with octylonium: tiropramide was effective earlier than octylonium; in the assessment using symptom diaries, the severity and degree of abdominal discomfort tended to be reduced further in the tiropramide group than in the octylonium group. Since this study was designed to evaluate the non-inferiority of tiropramide over octylonium, we could not conclude that tiropramide is more effective than octylonium, but we may at least speculate about this possibility, considering that assessment using symptom diaries is less biased than that using VAS, which is based on patients' rememberance of symptoms from the previous week. Taken together, there may be some advantage of tiroparmide over octylonium for managing IBS symptoms; this could be due to its colonic selectivity. Regarding the safety of tiropramide, percentages of patients reporting adverse events were similar in both groups. Vital signs and labortory test results did not significantly change after a 4-week treatment with either drug. It has been known that it does not affect neurotransmitters such as histamine, acetylcholine, and adrenaline, thus leading to a lower incidence of side effects than other antispasmodic agents. It was also found that tiropramide did not affect esophageal motility, including the pressure of the low esophageal sphincter, and the coordinated movements of the esophagus.18 Actually, both tiropramide and octylonium have been safely prescribed over the past ten years. Similarly, the present study raised no safety concern. In the subgroup of patients with diarrhea predominant IBS (IBS-D), tiropramide improved bowel habits. Its spasmolytic effect of the drug may be related to the improvement of bowel habits in terms of stool frequency and consistency. These improvements may also be explained by the fact that tiropramide can restore normal intestinal transit in patients with IBS-D having rapid intestinal transit, and are consistent with observations in a study on octylonium demonstrating improvements of bowel habit and abdominal pain and discomfort.14 Moreover, as previously mentioned, gut motility was normalized in 88% of the tiropramide group after 30-day treatment with tiropramide, against 47% of the octylonium group.16 Considering the effect on bowel habit improvement in the subgroup of patients with IBS-D, there may be an additional benefit of tiropramide in patients with IBS-D, although the small number of patients with constipation predominant IBS (IBS-C) in our study might preclude us from concluding that the study drug is effective in patients with IBS-C. In this study, levels of depression and anxiety in the IBS patients were also improved by tiropramide. This may be interpreted in terms of the brain-gut axis.19 Relief of abdominal pain may affect positively the emotional status of study patients. IBS-QoL was also improved. However, theses secondary outcomes should be cautiously interpreted because there may be a variety of confounding factors. Placebo effects are known to be relatively high in IBS, ranging from 20% to 70%. This is believed to be partly due to a variety of physical and psychological factors affecting the brain-gut axis, which is thought to be involved in IBS pathophysiology. Therefore, studies of the treatment of IBS should be designed as randomized, double-blind, and placebo-controlled trials.20 The present study lacks a placebo control therefore could be limited in directly showing the superiority of tiropramide to placebo. However, this limitation in our study may be sufficiently compensated by previous evidence to demonstrate the superiority of octylonium to placebo.13,14,21 Other limitations of our study include the relatively short period of treatment (only 4 weeks) and the lower dose of octylonium than that used in the reference study (20 mg vs. 40 mg, t.i.d). However, the efficacy of both tiropramide and octylonium in improving symptoms of IBS was clearly demonstrated by our study results with statistical differences between pre-and post-treatments. In conclusion, our study demonstrates that treatment with tiropramide is effective and safe for managing IBS symptoms such as abdominal pain and discomfort, stool frequency and consistency, IBS-QoL, depression and anxiety. Considering not enough data fully show the efficacy and safety of tiropramide in IBS patients, the present study should be a useful reference in IBS research and clinical practice for managing IBS patients. Further studies are required to elucidate the mechanism of action of tiropramide on intestine, particularly its pharmacodynamic and pharmacokinetic properties.\n\nQuestion: Compared to octylonium 20 mg what was the result of tiropramide 100 on Abdominal pain and discomfort assessed using VAS scores, diaries, and IBS-QoL?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1014	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The Effect of Desmopressin on the Amount of Bleeding in Patients Undergoing Coronary Artery Bypass Graft Surgery with a Cardiopulmonary Bypass Pump After Taking Anti-Platelet Medicine\n\n ABSTRACT.BACKGROUND:\nCoronary artery bypass grafting (CABG) is a common surgical intervention at the end-stages of coronary artery occlusion disease. Despite the effectiveness of CABG, it may have particular complications, such as bleeding during and after surgery. So far, there have been many drugs used to reduce bleeding.\n\nABSTRACT.OBJECTIVES:\nThis study aimed at investigating the effects of desmopressin on the amount of bleeding in patients undergoing CABG with a cardiopulmonary bypass pump (CPBP) who were taking anti-platelet medicine.\n\nABSTRACT.METHODS:\nOne hundred patients scheduled for elective CABG with a CPBP were included in a prospective, placebo-controlled, double-blinded clinical trial study. They were randomly divided into two groups. One group received desmopressin (40 μg) and the other group received a placebo (isotonic saline). Seven patients were excluded from the study, and 47 and 46 patients participated in the desmopressin and control groups, respectively. The methods of monitoring and the anesthetic techniques were similar in both groups, and all surgeries were performed by one surgeon. Variables including age, gender, pump time, aortic clamp time, duration of surgery, complications (e.g., nausea and vomiting, blood pressure changes), the necessity to receive blood products, and coagulation tests (prothrombin time, partial thromboplastin time, international normalized ratio, and bleeding time) were assessed. Data were statistically analyzed with SPSS software version 17.\n\nABSTRACT.RESULTS:\nThere was no significant difference between the groups regarding age, gender, pump time, clamp time, duration of surgery, complications, and the changes in hemoglobin and coagulation test measurements (P > 0.05). No significant difference was noted between the groups regarding the rate of bleeding after surgery (359.3 ± 266.2 in group D vs. 406.3 ± 341.6 in group P (control group); P = 0.208). However, the platelet changes after surgery in both groups were significantly different. The analysis revealed that the rate of thrombocytopenia after surgery was higher in the control group (P = 0.012).\n\nABSTRACT.CONCLUSIONS:\nOur study showed that desmopressin could not reduce the amount of blood loss after CABG. Also, desmopressin did not have a significant effect on coagulation status. Therefore, based on the results of our study, it seems that the use of this medication cannot be a helpful for patients with any indication for CABG.\n\nBODY.1. BACKGROUND:\nCoronary artery disease (CAD) is one of the leading causes of death worldwide. Patients with CAD require coronary artery revascularization as well as other medical treatments (1). Coronary artery bypass grafting (CABG) is a common interventional surgery in order to treat end-stage coronary artery occlusion disease. Although CABG is an effective method, it may also come with particular complications during and after the surgery (1, 2). CABG may lead to disorders in platelet count, coagulation, and fibrinolysis. Excessive amounts of bleeding after surgery is a common problem that sometimes requires blood transfusions or even reoperation (3-6). Desmopressin is an artificial form of vasopressin which is commonly used to prevent bleeding in hemophilia and Von Willebrand disease (7, 8). Previous investigations have shown that desmopressin can decrease the amount of blood products needed in transfusion for cardiac surgery (9). However, some studies have indicated that desmopressin was not effective when used as a prophylaxis (10, 11). Still, some other studies have shown that using desmopressin could reduce bleeding in post-CABG patients, patients with long cardiopulmonary bypass pump (CPBP) times, and high-risk patients who had taken anti-platelet medication (9, 12-16).\n\nBODY.2. OBJECTIVES:\nAccording to the general importance of the issue and the conflicting results on the effects of desmopressin on bleeding after cardiac surgery, and also concerning the lack of previous studies which have assessed the effects of intranasal desmopressin on bleeding after cardiac surgery, we aimed to investigate the effects of desmopressin on the bleeding rates in patients who had undergone CABG with a CPBP after taking anti-platelet medicine.\n\nBODY.3. METHODS:\nWe conducted a randomized double-blind clinical trial in the anesthesiology research center of Guilan University of Medical Sciences (GUMS) in Rasht, Iran. This study was approved by the ethics committee of GUMS with the reference number of 1930252810 and registered in the Iranian registry of clinical trials (IRCT) under the number IRCT201409304345N3. Inclusion criteria were Class II-III status according to the American society of anesthesiologists' physical status classification system, 3-vessel coronary artery disease, ejection fraction of ≥ 40%, reception of anti-platelet medicines including aspirin of 80 mg/day and clopidogrel of 75 mg/day before surgery, no history of coagulopathy or renal impairment, and having been scheduled for CABG with a CPBP. Exclusion criteria were a pump time > 120 minutes, concomitant valve procedure and CABG, inotrope administration for separating the patient from the cardiopulmonary pump, need for anticoagulant therapy during and/or in the post-operative period, and coronary endarterectomy. The sample size was determined according to the following formula derived from the study by Gratz et al. (17): α = 0.05 Z1-α/2 = 1.96 (95% confidence interval was noted) β = 0.20 Z1-β = 0.85 μ1 = 1176, S1 = 674 μ2 = 833, S2 = 311 Equation 1.n=(Z1-α2+Z1\n- β)2(S12+S22)(μ1\n-μ2)2 n = 50 Patients in each group. Using the method of random blocking, 100 patients were divided into two groups (desmopressin: group D and placebo: group P) with 50 patients in each group. At the time of hospitalization, the type of surgery and anesthesia method were explained for patients, and written informed consent was obtained. In the preoperative period, blood levels of hemoglobin (Hb), platelets, prothrombin time (PT), partial thromboplastin time (PTT), international normalized ratio (INR), and fibrinogen were measured and recorded. The anesthesiologist advised patients to fast the night before surgery. For premedication, oral lorazepam of 1 mg was administered the night before and one hour prior to surgery. An hour before induction of anesthesia, intramuscular morphine sulfate of 0.1 mg/kg was injected into all patients. Thirty minutes before anesthesia, the desmopressin or placebo was administered. In group D, two puffs of intranasal desmopressin (Sina Vista Daroo manufacturing, Tehran, Iran) were sprayed. Each puff contained 10 μg of desmopressin. In group P, 2 puffs of intranasal saline (normal saline in a desmopressin container) were sprayed. The patients and the anesthesiologist had no awareness about the drug type administered during and after surgery. Also, the laboratory technician was unaware of the drug type. The researcher was the only one who was aware of the medication so that he could take any necessary actions if complications occurred. Patients were monitored under standard protocols including 7-lead electrocardiography (EKG), pulse oximetry, and bispectral indexing (BIS) in the operating room. Before induction of anesthesia, the cardiac anesthesiologist inserted one peripheral venous catheter, a left radial artery catheter, and a central venous catheter under local anesthesia with lidocaine of 1%. Patients received 5 - 7 ml/kg isotonic saline before induction of anesthesia. After preoxygenation, anesthesia was induced by slow injection of midazolame of 0.05 mg/kg and sufentanil of 1 μg/kg (over the course of 10 minutes) intravenously, followed by infusion of 0.2 mg/kg cisatracurium for muscle relaxation. After intubation, anesthesia was maintained by propofol of 50 - 75 μg/kg/min, sufentanil of 0.2 μg/kg/h, and atracurium of 0.6 μg/kg/h. Then, a nasopharyngeal thermometer was inserted, and in order to maintain the depth of anesthesia, BIS during surgery was maintained between 40 and 60. Then, patients underwent median sternotomy, a standard technique was used to establish a CPBP. Activated clotting time (ACT) was also measured following the administration of 300 μg/kg heparin. Cardiopulmonary bypass was initiated if ACT ≥ 480 seconds. Upon completion of the grafts, if vital signs were stable, patients were separated from the pump, and the circulating heparin was antagonized by protamine sulfate. After the surgery, patients were transferred to the intensive care unit (ICU), resuming ventilation under close observation. Patients were extubated about six to eight hours after operation if they were awake, calm, had normal arterial blood gas analysis, and acceptable breathing status. If the patients had VAS > 3, intravenous morphine of 0.1 mg/kg was injected. Six hours after transferring the patients to the ICU, in group D, two puffs of intranasal desmopressin equivalent to 20 μg, and in group P, two puffs of intranasal placebo (isotonic saline), were sprayed. If the patients had nausea and vomiting (desmopressin complications), metoclopramide of 0.1 mg/kg was injected. In the ICU, the amount of blood in the chest bottle, Hb level, and platelet count were observed. If the Hb level reduced to less than 10gr/dL, or if the platelet level was less than 100,000/mm3, packed red blood cells (PRBC) or platelet concentrate were injected, respectively. Investigators measured the levels of Hb, platelets, fibrinogen, PT, PTT, and BT 24 hours after surgery.\n\nBODY.3. METHODS.3.1. STATISTICAL ANALYSIS:\nAfter collection, data were entered into SPSS software version 17. Data were reported by descriptive statistics (number, percent, mean, and standard deviation) and analyzed with a chi-squared test, an independent T-test, a Mann-Whitney U test, and a paired T-test. For intragroup comparison of variables after surgery, ANCOVA was used. A P value < 0.05 was considered as statistically significant, and a 95% confidence interval was noted.\n\nBODY.4. RESULTS:\nOf the 100 patients initially enrolled in this study, seven patients were excluded. Therefore, 47 and 46 patients participated in groups D and P, respectively. Two patients in group D and two patients in group P were excluded as a result of bleeding and reoperation required to control it. A prolonged cardiopulmonary pump time resulted in the exclusion of one patient in group D and two patients in group P (Figure 1). Figure 1.Enrollment and Outcomes There were no significant differences between the groups regarding age, gender, body mass index (BMI), ejection fraction (Table 1), duration of surgery, pump time, and aortic clamp time (Table 2). Also, there was no significant difference between the groups regarding the outbreak of complications such as nausea, vomiting, blood pressure alteration, and the amount of bleeding (P > 0.05). Table 1. Demographic Characteristics of the Patients Variables Group D Group P P Value \n Age, y \n 54.1 ± 7.58 56.92 ± 7.33 0.074 a \n Height, cm \n 166.3 ± 9.48 167.46 ± 3.04 0.215 a \n Weight, kg \n 71.8 ±7.63 72.4 ± 5.3 0.65 a \n BMI \n 25.93 ± 2.29 25.82 ± 1.66 0.79 a \n Ejection fraction (EF) \n 47.19 ± 4.18 47.86 ± 4.81 0.47 a \n Gender \n 0.217 b Male 35 (74.5%) 39 (84.8%) Female 12 (25.5%) 7 (15.2%) a Independent T-test. b Chi-squared test. Table 2. The Surgery Times, Pump Times, and Clamp Times of the Patients Variables Group D Group P P Value a \n Duration of surgery, h \n 2.89 ± 0.42 2.92 ± 0.44 0.73 \n Pump time, min \n 57.2 ± 9.01 56.7 ± 8.83 0.79 \n Aortic clamp time, min \n 37.34 ± 9.43 36.08 ± 9 0.51 a Independent T-test. Thirty-nine patients received PRBC, and 13 patients received platelet concentrate. The results showed no significant difference between these groups (p=0.472) (Table 3). Table 3. Frequency of Complications in the Two Groups Variables Group D Group P P Value \n Hypotension \n 0.533 a Yes 6 (12.8%) 8 (17.4%) No 41 (87.2%) 38 (82.6%) \n Nausea \n 0.109 a Yes 11 (23.4%) 5 (10.9%) No 36 (76.6%) 41 (89.1%) \n Vomiting \n 0.57 a Yes 2 (4.3%) 1 (2.2%) No 45 (95.7%) 45 (97.8%) \n Bleeding volume, mL \n 359.3 ± 266.2 406.3 ± 341.6 0.208 b \n Blood transfusion, packed cell \n 0.472 a Yes 18 (38.3%) 21 (45.7%) No 29 (61.7%) 25 (54.3%) \n Platelet transfusion \n 0.797 a Yes 7 (14.9%) 6 (13%) No 40 (85.1%) 40 (87%) \n Packed red blood cell transfusion, U \n 0.65 ± 1.06 0.82 ± 1.32 0.596 b a Chi-squared test. b Mann-Whitney U test. Table 4. Changes in Hemoglobin, Platelet, and Coagulation Results Before and After Surgery in the Two Groups Variables Group D Group P Estimate Within Group , P Value a Estimates Between Groups b \n Hemoglobin \n 0.134 Preoperative 13.63 ± 1.78 13.12 ± 2.18 0.221 Postoperative 11.71 ± 1.45 11.15 ± 1.31 0.058 Estimate within group, value c 0.0001 0.0001 \n Platelets \n 0.012 Preoperative 243489 ± 74577 240239 ± 46991 0.802 Postoperative 226176 ± 91502 194456 ± 46514 0.038 Estimate within group, P value c 0.042 0.0001 \n INR \n 0.665 Preoperative 1.0 ± 0.21 1.05 ± 0.14 0.86 Postoperative 1.11 ± 0.19 1.14 ± 0.22 0.964 Estimate within group, P value c 0.005 0.011 \n PT \n 0.463 Preoperative 12.85 ± 0.71 12.82 ± 0.62 0.88 Postoperative 13.28 ± 1.29 13.55 ± 2.12 0.941 Estimate within group, P value c 0.017 0.011 \n PTT \n 0.588 Preoperative 30.97 ± 5.96 30.98 ± 7.47 0.134 Postoperative 29.73 ± 8.63 28.77 ± 8.55 0.517 Estimate within group, P value c 0.029 0.085 \n BT \n 0.129 Preoperative 1.3 ± 0.39 1.42 ± 0.42 0.223 Postoperative 1.69 ± 0.56 1.55 ± 0.58 0.173 Estimate within group, P valuec 0.0001 0.285 \n Fibrinogen \n 0.265 Preoperative 302.9 ± 34.3 288.7 ± 45.6 0.091 Postoperative 261.4 ± 37.4 247.8 ± 35.1 0.075 Estimate within group, P value c 0.0001 0.0001 Abbreviation: BT, bleeding time; INR, international normalized ratio; PT, prothrombin time; PTT, partial thromboplastin time. a Independent T-test. b ANCOVA. c Paired T-test. A paired T-test revealed that the Hb levels decreased significantly in each group after surgery (P = 0.0001), but the difference was not statistically significant between the groups (0.134). The alterations of platelets in the D and P groups were statistically significant (P = 0.042, P = 0.0001, respectively). A T-test showed no significant difference in mean platelet levels between the groups before surgery (P = 0.802), but there was a significant difference between the groups in terms of the mean platelet levels after surgery (P = 0.038). The PT, PTT, INR, BT, and fibrinogen changes before and after surgery showed no significant differences between the groups (P > 0.05).\n\nBODY.5. DISCUSSION:\nSevere bleeding after cardiac surgery consistently remains a challenge for cardiac surgeons and anesthesiologists. Using a cardiopulmonary pump in cardiac surgery may induce blood coagulation disorders and platelet dysfunction, requiring transfusion of proper functioning platelets or the administration of other medicines (3-6). Up until now, diverse products including desmopressin, albumin, recombinant factor VII, and tranexamic acid have been used to reduce bleeding after cardiac surgery (12, 15, 18-20). Desmopressin is an artificial form of vasopressin or an antiduretic hormone (ADH) analogue that exerts its anti-hemorrhagic effects through increased plasma levels of factor VΙΙΙ and increased activity of the Von Willebrand factor. It also has a direct effect on the blood vessel. Our study showed no significant differences between the groups regarding the demographic characteristics, pump times, clamp times, and durations of surgery. Also, the frequency of complications such as nausea, vomiting, and hypotension was not significantly different between the groups. Furthermore, no significant difference was noted between the groups regarding the amount of blood collected in the chest bottle and the number of transfused PRBC units. Pleym et al. observed no significant difference in the amount of blood loss after prescribing 0.3 mcg/kg of desmopressin in patients undergoing CABG (21). They reported 606 and 601 cc of blood loss in the desmopressin and saline groups, respectively. They finally declared that taking desmopressin had no significant effect on bleeding after CABG in patients treated with aspirin the day before surgery. Their finding was consistent with our study, but with increasing doses of desmopressin, different results might be achieved. Cattaneo et al. showed that although the use of desmopressin reduced postoperative bleeding, it did not reduce the need for blood transfusions (12). In both groups, the same amount of blood was transfused. Also, in this study, researchers noted that the effectiveness of desmopressin depended on the amount of bleeding, and by an increase in bleeding of about 1.1 liters, the effect of desmopressin on reducing blood loss could be more apparent (12). It seems that low rates of bleeding could indicate the supposed ineffectiveness of desmopressin in our study (359.3 ± 266.2 mL in group D, and 406.3 ± 341.6 in Group P). In our study, it was observed that Hb levels dropped after surgery in each group, and this amount was significant. However, comparing Hb levels before and after surgery in both groups indicated no significant difference. Also, Pleym et al. noted similar results (21). Furthermore, platelet counts after surgery decreased significantly in both groups in our study. Platelet counts in group P were lower than those of group D, but this difference was not clinically considerable, and in both groups, postoperative platelet counts were enough to maintain homeostasis. In contrast to our study, Pleym et al. reported a different result (21). They indicated that despite a decrease in platelets after surgery in both groups, the rate of thrombocytopenia was higher in the desmopressin group. This different result might be due to other factors such as the cardiopulmonary pump effect. In addition, there was no significant difference between groups in BT before and after surgery (P = 0.129). In a study by Keyl et al. which examined the effects of aspirin and intravenous desmopressin of 0.4 μg/kg on platelet function in patients undergoing CABG, they observed that desmopressin did not affect platelet activity (22). In our study, 40 μg of intranasal desmopressin in the form of four puffs was administered before (two puffs) and six hours (two puffs) after surgery. Intranasal desmopressin at high dosages may produce an elevation of blood pressure, which disappears with reduction in dosage. Therefore, this drug should be used with caution in patients with coronary artery insufficiency and/or hypertensive cardiovascular disease and heart failure. For this reason, in our study, the lower dosage of desmopressin was used. In Keyl et al.'s study, similar to ours, desmopressin did not improve platelet function. However, their study focused on platelet activity more than platelet count. In our study, platelet count and BT were also investigated. Our results showed that PT and INR increased after surgery, but this difference was not significant when comparing the two groups. The only variable with a downward trend in coagulation parameters was PTT. However, a significant difference in this variable was not observed between the groups. Generally, desmopressin did not improve platelet count or function, nor did it improve coagulation status. In a review study, Wademan and Galvin (23) examined the effects of desmopressin in reducing bleeding after heart surgery. They announced that desmopressin could not induce beneficial effects either before or after heart surgery. In their study, desmopressin improved the hemostatic status in those patients consuming aspirin for seven days prior surgery, having a pump time of more than 140 minutes, or having preoperative platelet dysfunction. Also, in a meta-analysis, Levi et al. (24) showed that desmopressin might cause a slight reduction in the amount of bleeding after heart surgery without any clinical improvements.\n\nBODY.5. DISCUSSION.5.1. LIMITATIONS:\nIn this study, we investigated the platelet counts and BT. It is recommended that in future studies, further platelet function tests such as optical aggregometry, flow cytometry, or PFA-100 could be used. Also, it seems that measuring the Von Willebrand factor and factor VΙΙΙ levels before and after surgery could prove to be valuable.\n\nBODY.5. DISCUSSION.5.2. CONCLUSION:\nOur study showed that desmopressin could not reduce the amount of blood loss after CABG surgery. Also, desmopressin did not have a significant effect on coagulation status. Therefore, based on our study, it seems that the use of this medication cannot be considered as helpful in candidates for CABG surgery.\n\nQuestion: Compared to Placebo what was the result of Desmopressin on Thrombocytopenia rate?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1143	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: School Age Effects of the Newborn Individualized Developmental Care and Assessment Program for Medically Low-Risk Preterm Infants: Preliminary Findings\n\n ABSTRACT.BACKGROUND:\nBy school-age, even low-risk moderately preterm-born children show more neuro-cognitive deficits, motor impairments, academic underachievement, behavioral problems, and poor social adaptation than full-term peers.\n\nABSTRACT.AIM:\nTo evaluate the outcomes at school-age for moderately preterm-born children (29-33 weeks gestational age), appropriate in growth for gestational age (AGA) and medically at low-risk, randomized to Newborn Individualized Developmental Care and Assessment Program (NIDCAP) or standard care in the Newborn Intensive Care Unit. At school-age, the experimental (E) group will show better neuropsychological and neuro-electrophysiological function, as well as improved brain structure than the control (C) group.\n\nABSTRACT.MATERIALS AND METHODS:\nThe original sample consisted of 30 moderately preterm-born infants (29 to 33 weeks), 23 (8C and 15E) of them were evaluated at 8 years of age, corrected-for-prematurity with neuropsychological, EEG spectral coherence, and diffusion tensor magnetic resonance imaging (DT-MRI) measures.\n\nABSTRACT.RESULTS:\nE-performed significantly better than C-group children on the Kaufman Assessment Battery for Children-Second Edition (KABC-II) and trended towards better scores on the Rey-Osterrieth Complex Figure Test. They also showed more mature frontal and parietal brain connectivities, and more mature fiber tracts involving the internal capsule and the cingulum. Neurobehavioral results in the newborn period successfully predicted neuropsychological functioning at 8 years corrected age.\n\nABSTRACT.CONCLUSION:\nModerately preterm infants cared for with the NIDCAP intervention showed improved neuropsychological and neuro-electrophysiological function as well as improved brain structure at school-age.\n\nBODY.INTRODUCTION:\nPreterm compared to full-term children perform more poorly in working memory, planning, visual spatial organization, and mental flexibility,[12] and are over-represented among early intervention and special education service recipients.[3] Early brain-based differences[45] contribute to long-term disabilities. Poor executive function appears related to basal ganglia/cerebellar volume reduction and sub-cortical white matter circuit disruptions between frontal, striatal, and thalamic regions.[67] Cumulative effects of medical complications[8] are compounded by the Newborn Intensive Care Unit (NICU) experience (exposure to bright lights, heightened sound, frequent interventions), which alters brain development.[91011] The Newborn Individualized Developmental Care and Assessment Program (NIDCAP)[12] provides a system of NICU care and environmental structure that supports preterm infants' early brain development. Several randomized, controlled NIDCAP trials reported significant neurobehavioral and neuro-electrophysiological improvement for high-risk preterm infants.[1314151617181920] School-age follow-up studies[2122] showed continued significant neurodevelopmental improvement. The current study tests NIDCAP-effectiveness into school-age for medically low-risk, appropriate for gestational age (AGA), moderately preterm infants and evaluates prediction by newborn-period neurobehavioral measures of school-age neuropsychological performance.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN AND ETHICS:\nChildren born preterm, who had been studied in-NICU during a randomized control trial[23] (control-C and experimental-E), were assessed in follow-up at 8 years (y) of age corrected-for-prematurity (CA). The study protocol was approved by the hospital's Institutional Review Board for Research with Human Subjects. All school-age assessment personnel (neuropsychology, interviews, EEG, and MRI) were kept blind to original subject group assignments.\n\nBODY.MATERIALS AND METHODS.SUBJECTS:\nThe original sample[23] consisted of 30 study infants (14C; 16E), recruited from the 46-bed level-III NICU, with an inborn population at a large urban tertiary care center. Family selection criteria included: Maternal age >14 years; no major medical or psychiatric illness, chronic medication treatment, and/or history of substance abuse; telephone accessibility; and English-language facility. Infant criteria included: Gestational birth-age 28 weeks 4 days (d) to 33 weeks 3 days; 5-minute Apgar >7; at birth AGA (5th-95th percentile)[24] in weight and head circumference; normal initial cranial ultrasound (s), MRI, and/or electroencephalogram (EEG); <72 hours ventilator and/or vasopressor support; prenatal care; absence of congenital/chromosomal abnormalities, congenital/acquired infections, prenatal brain lesions, and seizures. Of the 30 subjects, 23 (8C; 15E) returned at school-age [Figure 1]. Figure 1Consort chart\n\nBODY.MATERIALS AND METHODS.SUMMARY OF NEWBORN INTERVENTION AND STUDY RESULTS:\nE-infants received NIDCAP[12] from NICU-admission to 2 weeks corrected age. C-group care was the study NICU's standard care. At 2 weeks corrected age, E-infants showed significantly better neurobehavioral functioning (Assessment of Preterm Infants' Behavior-APIB[25]), increased brain functionality (EEG) with increased frontal to occipital brain connectivities,[4] and improved brain structure (MRI) with more mature internal capsule and frontal white matter fiber tracts. The relationship among neurobehavior, EEG, and MRI was significant. Nine-months corrected age E-group neurodevelopmental functioning (Bayley Scales of Infant Development, Second Edition[26]) was significantly improved.\n\nBODY.MATERIALS AND METHODS.PRIMARY AND SECONDARY SCHOOL-AGE HYPOTHESES:\nSignificant E-group-favoring effects were hypothesized for visual-spatial planning, executive function and working memory, spectral coherence increase between long-distance bi-hemispheric frontal and parietal brain system, and improved fiber tract development in internal capsule and optic radiations. Significant relationships were hypothesized among school-age neuropsychological function, spectral coherence, and diffusion-tensor magnetic-resonance-imaging, and between newborn neurobehavioral and school-age neuropsychological function.\n\nBODY.MATERIALS AND METHODS.SAMPLE DESCRIPTION:\nNewborn background information was compared between the children who returned for school-age follow-up and those who did not. Newborn background information was also compared between returning school-age C-and E-group children. School-age anthropometric, medical, and academic history indices were measured or obtained by parent interview.[27] Parent-IQ, reportedly correlating with child functioning,[28] was measured with the Kaufman Brief Intelligence Test, Second Edition (KBIT-2),[29] yielding a Verbal IQ, Non-Verbal IQ, and Mental Processing Composite (Mean-x: 100; standard deviation-SD: 15). Should parent-IQ, hypothesized to be comparable between groups, correlate with child-IQ, all outcome measures would be corrected for parent-IQ.\n\nBODY.MATERIALS AND METHODS.SCHOOL-AGE NEURODEVELOPMENTAL OUTCOMES.NEUROPSYCHOLOGICAL MEASURES:\nThe small sample size necessitated limited neuropsychological assessment. An experienced neuropsychologist performed the Kaufman Assessment Battery for Children, Second Edition (KABC-II)[30] yielding a Mental Processing Composite Index (x=100; SD=15), four Scale Indexes, (Sequential, Simultaneous, Planning, Learning), and two language subscales (Expressive Vocabulary, Verbal Knowledge); the Woodcock-Johnson III Tests of Achievement (WJIII)[31] with two Standard Cluster Scores (x=100; SD=15) (Broad Reading-Letter/Word Identification, Reading Fluency, Passage Comprehension; Academic Skills-Letter/Word Identification, Calculation, Spelling); and the Rey-Osterrieth Complex Figure Test (Rey),[323334] Copy, Immediate Recall and Delayed (20 minutes) Recall conditions assessing gestalt integration, executive function, spatial planning, and memory. The Rey Developmental Scoring System[3536] yields per condition 3 mutually exclusive scores, Organization; Structural Elements Accuracy; and Incidental Elements Accuracy.\n\nBODY.MATERIALS AND METHODS.SCHOOL-AGE NEURODEVELOPMENTAL OUTCOMES.NEUROPHYSIOLOGICAL MEASURES:\nEEG and MRI studies were conducted within 1 week of neuropsychological testing. A pediatric EEG-technologist collected thirty-two-channel EEG at a 256 Hz sampling rate (with 1-50 Hz bandpass filtering with 60 Hz mains filter) for 12 minutes of Eyes Closed alert state EEG. Paroxysmal eye, muscle, and body movements were visually identified and excluded. Figure 2 shows standard EEG electrode names and positions [Figure 2]. Analysis used the Laplacian reference-electrode-free format, sensitive to underlying cortex and insensitive to deep/remote EEG sources.[37] Residual eye blink/movement artifacts were removed with source component techniques.[3839] (BESATM software package). Spectral analysis, including spectral coherence calculation,[40] was performed (NicoletTM software package). Two Hz/data point (16 points/32 Hz) spectral resolution for 32 channels yielded 7936 individual coherence variables. Remaining low amplitude, artifactual contributions were removed by multivariate regression analysis,[41] utilizing signals proportional to known artifact sources. Coherence variable number was reduced by using in-house-developed[42] principal components analysis software suited to factoring large asymmetrical matrices. Forty coherence factors, previously created on an independent age-comparable normative sample (n=219) and reflecting 48% of total coherence variance,[4344] were formed on the current school-age subjects utilizing the previous principal-components-analysis-generated rule. Given the sample size, the first 20 factors were utilized in the subsequent analyzes. Figure 2Standard EEG electrode names and positions. Head in vertex view, nose above, left ear to left. EEG electrodes: Z: Midline: FZ: Midline Frontal; CZ: Midline Central; PZ: Midline parietal; OZ: Midline occipital. Even numbers, right hemisphere locations; odd numbers, left hemisphere locations: Fp: Frontopolar; F: Frontal; C: Central; T: Temporal; P: Parietal; O: Occipital. The standard 19, 10-20 electrodes are shown as black circles. An additional subset of 17, 10-10 electrodes are shown as open circles\n\nBODY.MATERIALS AND METHODS.SCHOOL-AGE NEURODEVELOPMENTAL OUTCOMES.NEUROSTRUCTURAL MEASURES:\nDiffusion-tensor-MRI evaluated underlying brain structure by quantitative assessment of brain connectivity to delineate relevant white matter pathways and measure myelination and axon integrity parameters. Data were acquired at 3Tesla (Siemens Tim Trio, Siemens, Erlangen, Germany) with an MR imager using a 32-channel head coil. High spatial resolution echo-planar diffusion-weighted images were acquired (24 cm FOV, matrix 128 × 128, 2 mm thick contiguous slices). Geometric distortion from magnetic susceptibility differences was minimized with a short echo time (TE=78 ms) and parallel imaging (iPAT 2). Thirty b=1000 s/mm2 images were acquired at directions evenly spaced on the sphere along with 5 baseline (b=0) images. Diffusion tensors were reconstructed, and 5 major fiber pathways were identified with a previously validated automated procedure.[45] Summary diffusion scalar measures of mean diffusivity, axial diffusivity, radial diffusivity, and fractional anisotropy were averaged in a streamline-density-weighted fashion.[46] along 5 major pathways: Arcuate Fasciculus (connecting posterior brain areas with Broca's area involved in complex language processing[47]); Corpus Callosum (thick white nerve band deep within the brain connecting the two hemispheres, supporting their communication and activity coordination); Cingulum (tracts receiving inputs from thalamus and neocortex; projecting to the entorhinal cortex; integral to limbic system; involving emotion, learning, memory, and executive function); Internal Capsule (massive white matter layer, major route inter-connecting cerebral cortex with brainstem and spinal cord); and Optic Radiations (axons carrying visual information from lateral geniculate nucleus relay neurons of thalamus to visual cortex). Children were scanned unsedated, awake, watching a cartoon or movie. Broad language processing tracts (arcuate fasciculus)[48] and early-developing basic hemispheres-connecting structures were thought to be least affected by NIDCAP; cingulum, internal capsule, and optic radiations related to memory, executive function, and visual-motor processing were hypothesized to be improved for E-children.\n\nBODY.MATERIALS AND METHODS.DATA ANALYSIS:\nThe Biomedical Data Package 2007TM (BMDP)[49] supported statistical analyzes. Continuous variables were submitted to univariate analysis of variance (ANOVA) (BMDP-7D).[50] In cases of unequal variance, the Browne-Forsythe test of variance (F) was used. Categorical variables were submitted to Fisher's exact probability test (FET) for 2 × 2, and Pearson's Chi-square (χ2) test for all other multiple row by column arrays.[4951] Two-tailed values of P<0.05 were considered statistically significant. Sample sizes provided 80% power to detect large between-group-effects, generally effect sizes >1.0.[52] Analyzes included stepwise discriminant analysis (BMDP-7M) for the neuropsychological, electrophysiological, and neurostructural domains; Wilks' lambda[53] and jack-knifed[5455] classification for ascertainment of two-group classification success per domain and across domains; canonical correlation analysis (BMDP-6M) to explore relationships among the neuropsychological, electrophysiological, and neurostructural domains at school-age, and between newborn and school-age neurobehavioral domains.\n\nBODY.RESULTS.SAMPLE.NEWBORN BACKGROUND FOR SUBJECTS WITH VERSUS WITHOUT SCHOOL AGE FOLLOW-UP:\nThe subjects who returned for school-age follow-up were sicker at birth than those who did not return [Table 1].[56575859] Moreover, the school-age E-group had significantly lower 5-minute Apgar scores than the C-group [Table 2].[56575859] This biased results against the E-group. Table 1 Anthropometric, medical, and demographic background variables, participating vs. lost to follow-up subjects Table 2 Anthropometric, medical, and demographic background variables, children seen at follow-up, control vs. experimental group* \n\nBODY.RESULTS.SAMPLE.SCHOOL-AGE BACKGROUND INCLUDING PARENT IQ:\nC-and E-school-age groups were comparable in age-at-testing, parent-IQ,[29] and anthropometric, medical, and demographic characteristics. E-children's head circumferences were somewhat larger [Table 3]. Parent Mental Processing Composite and non-verbal IQ[29] correlated significantly with Child Simultaneous Processing[30] (r=0.4309, P=0.05; r=0.4231, P=0.05, respectively). Therefore, all outcome measures were residualized by partial correlation and multivariate regression analysis (BMDP-6M) for Parent IQ. Table 3 Anthropometric, medical, and demographic variables at time of evaluation* \n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.NEUROPSYCHOLOGICAL RESULTS:\nAll subjects (8C; 15E) completed neuropsychological testing. E-performed significantly better than the C-children on KABC-II Composite Index Simultaneous Processing and on subtest Rover; subtest Triangles showed a trend [Table 4]. Both subtests assess planning, decision-making, executive function, and visual-spatial processing. The groups performed comparably on the WJ-III Broad Reading and Academic Skill Clusters [Table 5], as well as on the 9 Rey scores. However, on the Rey, Basal Level and Organization (Immediate Recall), along with Incidental Accuracy (Delayed Recall), showed a trend towards favoring E-over C-children [Table 6], indicating that E-children showed somewhat better overall gestalt integration, visual-motor planning, visual gestalt and detail memory, and executive function. Figure 3 shows a C-and an E-child's sample drawings. The KABC-II Simultaneous Processing and Rey differences are reminiscent of the earlier school-age study results for high-risk preterms[22] and the poorer visual-spatial planning, executive and memory functions reported for preterms without intervention.[6061] Table 4 Kaufman assessment battery for children, second edition Table 5 Woodcock-Johnson III Table 6 Rey-Osterrieth complex figure test Figure 3Rey-Osterrieth complex figure. The figure represents sample drawings from 2 study children, 1 from the Control group, a 9 year 3 month old born at 31 w 1 d GA; and 1 from the Experimental group, a 8 year 4 month old born at 31 w 4 d GA. The conditions displayed are from left to right: Copy, Immediate Recall, and Delayed Recall Discriminant analysis (10 KABC-II, 7 WJ-III subtests, 9 Rey-measures) identified 3 KABC-II (Rover, Atlantis, and Triangles) and 2 Rey (Organization/Immediate and Delayed Recall) measures that showed significant C-from E-group differentiation [Table 7]. Misclassified were 2 C-and 3 E-subjects. Table 7 Discriminant function analysis of neuropsychological measures \n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.NEUROPHYSIOLOGICAL RESULTS:\nAll school-age subjects completed neurophysiological assessment. Coherence-Factor-15 showed significantly decreased E-over C-group connectivity (P=0.001) between the right medial posterior frontal and right occipital regions from 2-18 Hz. This suggests release of frontal-associative cortex from overly-restricted visual-motor integration, freeing it for higher level functions. Factor-13 showed a trend towards significant group difference (P=0.112) [Figure 4]. Factor-13 (8-12 Hz, i.e., alpha), a broad, long-distance, and interhemispheric set of connectivities, demonstrated strong E-over C-group enhancement of left frontal lobe (typically dominant in motor and sensory processing functions) connectivity with multiple distant regions, especially in the contra-lateral hemisphere, suggesting better information and processing flow to and from left frontal lobe, indicative of better visual-spatial and broad high level judgment, planning, and executive control functions. Figure 4EEG Spectral coherence factors at school age, Control (C) (n = 8), Experimental (E) (n = 15). Head shown in vertex view, nose above, left ear to left. EEG frequency and coherence electrodes shown above head. Arrow color illustrates experimental group coherence; green = decreased, red = increased Discriminant analysis identified 3 coherence factors [Figure 4] significantly differentiating C-from E-children [Table 8]. Jackknifed classification success utilizing the 3 factors showed 91.3% correct subject classification.[5455] The factors included Coherence-Factor-7, increased for the E-subjects, a long distance bi-hemispheric factor (6-20 Hz) connecting parietal-associative regions with bilateral prefrontal cortex, consistent with more mature prefrontal cortex connectivities underlying organization, planning and executive function; Factor-12, (20-30 Hz), involving, similar to Factor-13, E-group connectivity increase of left lateral-frontal regions to homologous, broader, right lateral-frontal and anterior-temporal regions, likely sub-serving working memory; and again Factor-15, as interpreted above. These factors misclassified only 2 C-subjects. Table 8 Discriminant function analysis of EEG coherence factors Overall, the successful group-discriminating factors highlighted two increased bi-hemispheric, connectivities from left frontal to broad temporal and parietal regions and one decreased connectivity, freeing up frontal system function, mirroring earlier results.[222362] NIDCAP, for this population, appears to have increased connectivities strongly supportive of broad executive and complex planning functions as well as of working memory.\n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.BRAIN STRUCTURAL RESULTS:\nTwenty-one (7 C; 14 E) subjects completed MRI study. For internal capsule and optic radiation, as hypothesized, E-showed a significantly stronger trend towards lower diffusivity (mean and radial diffusivity) than C-children. Internal capsule, axial diffusivity was also lower. The cingulum also showed significantly lower E-than C-group mean and radial diffusivity and a trend towards lower axial diffusivity; and the arcuate fasciculus showed a trend towards lower mean and radial diffusivity [Table 9]. Higher E-than C-group fractional anisotropy was observed only at the trend level for the cingulum. Other structures differed in the direction favorable to the E-group. Marginal fractional anisotropy findings were possibly due to the small sample [Table 10 and Figure 5]. Table 9 Diffusion tensor magnetic resonance imaging, diffusivity measures (C=7; E=14) Table 10 Diffusion tensor magnetic resonance imaging factors for fractional anisotropy, (C=7; E=14) Figure 5Mean diffusivity in cortico-spinal tract (internal capsule) at 8 years. Control children, top row, experimental children, bottom row. Mean diffusivity rendered onto trajectories of the cortico-spinal tract, and color coded from red (low) to yellow (high). (Yellow and brighter orange: Higher measure of mean diffusivity; darker orange and red: Lower measure of mean diffusivity Discriminant function analysis accessing all 20 diffusion-tensor-MRI variables identified 3 measures, corpus callosum radial diffusivity, cingulum fractional anisotropy, and internal capsule radial diffusivity, which significantly differentiated C-from E-children [Table 11]. Two C-and 2 E-subjects were misclassified. Despite reduced sample, diffusion-tensor-MRI successfully differentiated the groups. Table 11 Discriminant function analysis of diffusion tensor magnetic resonance imaging measures \n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.CLASSIFICATION SUCCESS UTILIZING ALL THREE NEURODEVELOPMENT DOMAINS:\nWhen examining the relative group classification power of the 3 neurodevelopmental domains, discriminant analysis identified 2 coherence factors (15, 12) and 3 neuropsychological variables including KABC-II Triangles (measuring planning, decision-making, executive function, and visual-spatial processing) and Rey Organization-Immediate and Delayed Recall (assessing gestalt integration, executive function, spatial planning, and memory) measures which significantly differentiated C-from E-children [Table 12]. Two C-and 2 E-subjects were misclassified. Classification success was highly significant despite small sample size. Thus, overall, the EEG measures were most successful in discriminating C-from E-children. Table 12 Discriminant function analysis of neuropsychological, EEG and diffusion tensor magnetic resonance imaging measures \n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.RELATIONSHIP BETWEEN NEUROPSYCHOLOGICAL AND SPECTRAL COHERENCE MEASURES:\nCanonical correlation between the discriminant-analysis- identified neuropsychological measures (KABC-II Rover, Atlantis, Triangles; Rey Immediate/Delayed Recall Organization Scores) and spectral coherence factors (12, 7, 15) showed a significant relationship (Bartlett's test, χ2=38.01, df=15, P<0.0160). One canonical variable described the relationship. KABC-II subtest Atlantis (memory storage/retrieval of verbal information) and Rey Organization-Delayed Recall (long-term storage retrieval of visual-spatial content and executive function) as well as Coherence Factors-12 and-7 correlated highest with the canonical variable. Thus, better verbal and executive function, spatial organization, planning, and memory were associated with stronger broad bilateral frontal and parietal connectivities.\n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.RELATIONSHIP BETWEEN SPECTRAL COHERENCE AND DIFFUSION-TENSOR-MRI MEASURES:\nCanonical correlation between the discriminant-analysis- identified Coherence Factors-7,-12, and-15 and the diffusion-tensor-MRI measures, (corpus callosum radial diffusivity, cingulum fractional anisotropy, and internal capsule radial diffusivity) was marginally significant (χ2=14.79, df=9, P=0.0968). One canonical variable described the relationship. Variables correlating significantly with the canonical variable included Coherence Factors-15 (positive) and-7 (negative), and cingulum fractional anisotropy (positive), and internal capsule radial diffusivity (negative). Thus, measures of integrated central parietal and bilateral frontal connectivities coupled with frontal system functioning unhampered by restrictive visual motor input were associated with better-developed cingulum and internal capsule fiber tracts.\n\nBODY.RESULTS.NEURODEVELOPMENTAL SCHOOL-AGE OUTCOME.RELATIONSHIPS BETWEEN NEWBORN AND SCHOOL-AGE NEUROBEHAVIORAL FUNCTION:\nCanonical correlation showed a significant relationship between the 8 newborn APIB/Prechtl factor scores[23] and 4 KABC-II[30] Scale Indexes (Sequential, Simultaneous, Planning, Learning) (χ2=46.19, df=32 P=0.0501). One canonical variable described the relationship. APIB/Prechtl-Factor-3 (reactivity and hypersensitivity) and KABC-II Simultaneous Scale Index correlated significantly with the canonical variable. Newborns, who were less hypersensitive and over-reactive, had better KABC-II Simultaneous Scale scores at school age. Canonical correlation also identified a highly significant relationship (χ2 = 137.64, df=96, P=0.0034) between the APIB/Prechtl factor scores[23] and 12 school-age Rey[32] measures. One canonical variable described the relationship. APIB/Prechtl-Factors-2 (broad motor organization) and-3 again, (see above) correlated significantly with the canonical variable as did Rey Organization-Copy and Basal Level-Immediate Recall. Thus, the better organized motorically and less hyper-reactive/hypersensitive the newborn, the better the school-age child's overall Rey-production in Copy and Immediate Recall. The relationship between newborn neurobehavioral and 8-year neuropsychological function was strong and internally consistent.\n\nBODY.DISCUSSION:\nResults reported, consistent across the 3 domains tested, support the hypothesis that NIDCAP enhances low-risk AGA moderately preterm infants' long-term neurodevelopment, specifically complex planning, executive function, memory, and simultaneous non-verbal mental processing. E-children showed significantly better neurobehavioral functioning at 2 weeks corrected age[23] and better simultaneous processing and complex planning, memory, and executive function at school-age. Similarly, E-children at 2 weeks corrected age showed a pattern of increased long-distance connectivities between occipital and frontal regions,[23] and at school-age increased bilateral and across-midline broad frontal and parietal connectivities and release from overly connected visual-motor function. The NIDCAP experience supports better-differentiated brain connectivity development. Better developed connectivities between frontal systems and the parietal systems appears more conducive to better mental control, executive and memory functions.[63] This is reflected in Factor-15, supportive of frontal associative cortical functions, and Factor-13, supportive of mental processing, memory, executive function, attention to spatial relationships/location, responsivity to object shape, size, and orientation, and visual spatial working memory.[6465] The school-age neurostructural findings corroborated the neuropsychological and neurophysiological findings. Diffusion-tensor-MRI, which at 2 weeks corrected age showed improved E-group right and left internal capsule and frontal white matter tracts[23] showed at school-age improved internal capsule, cingulum, optic radiation, and arcuate fasciculus fiber tracts. This is the first report of school-age NIDCAP-effectiveness for low-risk AGA moderately preterm infants in terms of neuropsychological, electrophysiological, and brain-structural development. Results are internally consistent. NIDCAP is directed towards reliable reduction in stressful experiences and consistent return to base and restfulness to assure the infants' opportunities for continued behavioral re-integration of experiences, the foundation for increasingly well-differentiated modulation of function and the growth of well-differentiated brain-connectivities. Not all children returned for follow-up testing. It appears that the children who were more compromised at birth with lower Apgar scores at 5 minutes and higher SNAPPE-II, a newborn illness severity and mortality risk score, returned for school-age assessment. Moreover, the returning experimental group children were differentially sicker (lower Apgar scores at 5 minutes) in the newborn period than the returning control children. This emphasizes even more the effectiveness of the in-NICU NIDCAP intervention in improving neurodevelopmental outcomes at school-age. Interpretation of findings, nevertheless, requires caution. The study's most serious limitation is the small sample size. Substantiation by larger, longitudinal school-age follow-up studies is necessary to corroborate the result presented. Advances in newborn intensive care since the time of study also may have implications for result interpretation. The mechanisms underlying NIDCAP effectiveness remain to be discovered. The cost-effectiveness of NIDCAP, as compared to other in-NICU interventions,[66] remains to be evaluated. The long-term goal of the research is the wider dissemination of the NIDCAP approach. Given the encouraging findings, preterm infants and their families benefit when those responsible for NICU care are knowledgeable and well-educated in early brain development and provide opportunities for individualized developmental care. The highly dependent, sensitive, and rapidly developing preterm infants and their hopeful and vulnerable parents have little choice but to fully trust NICU staff. Professionals and NICU systems must live up to and warrant this trust.\n\nQuestion: Compared to C-group - the Newborn Intensive Care Unit (NICU) experience (exposure to bright lights, heightened sound, frequent interventions), which alters brain development. what was the result of E-group - The Newborn Individualized Developmental Care and Assessment Program (NIDCAP) provides a system of NICU care and environmental structure that supports preterm infants' early brain development. on performed on KABC-II Composite Index Simultaneous Processing and on subtest Rover?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1023	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of \n\n ABSTRACT.INTRODUCTION:\nPrevalence of diabetes and its complications have been a burden to the society from the ancient times, in the present and also will be in the future unless proper measures are taken to prevent its manifestation. There have been an increasing number of death associated-amputation cases which are mainly caused by nonhealing wounds. These facts urge researchers to develop new, more effective wound treatments for diabetic patients.\n\nABSTRACT.AIM:\nTo evaluate and compare the effect of Katupila Kalka (Securinega leucopyrus [Willd.] Muell. leaf paste) and Tila Taila (Sesamum indicum oil) in Madhumehajanya Vrana (diabetic wounds/ulcers) with Betadine ointment.\n\nABSTRACT.MATERIALS AND METHODS:\nA total of 23 patients of Madhumehajanya Vrana were chosen and randomly divided into two groups (Group A and B). Patients of Group A were treated with local application of Katupila Kalka with Tila Taila, whereas, in Group B, Betadine ointment was applied on the affected parts, once a day in the morning for 30 days. The relief in signs and symptoms were assessed on scoring pattern.\n\nABSTRACT.RESULTS:\nIn Group A, diabetic wounds treated with Katupila paste got healed within 28 days with minimal scar formation without any complications, whereas in Group B, wound was healed completely only in two patients within 28 days. In both the groups, no patients reported any adverse drug reaction during the entire course of treatment as well as in follow-up period.\n\nABSTRACT.CONCLUSION:\nStudy concluded that the drug Katupila Kalka possesses Vrana Ropana (wound healing) activity with fine scaring.\n\nBODY.INTRODUCTION:\nIn 2011, it was estimated that 366 million people worldwide had diabetes, representing roughly 8.3% of the adult population (20–79 years of age group). The number is expected to reach 552 million by 2030, representing 9.9% of the adult population. Diabetes is associated with various short and long-term complications, many of which, if left untreated, can be fatal. All these also have the potential to reduce the quality of life of people with diabetes and their families. The most common long-term complications affect the heart, eyes, kidneys, and feet.[1] Foot infections in persons with diabetes are a common and complex.[23] In addition to causing severe morbidities, they now account for the largest number of diabetes-related hospital bed-days[4] and are the most common proximate, nontraumatic cause of amputations.[56] Diabetic foot infections require careful attention and coordinated management, preferably by a multidisciplinary foot-care team.[7] Ayurveda has its own principles, but it is incorporating new theories and drugs in it and is presenting them according to its principles. Number of drugs known to Ayurveda since Vedic era is increasing with the time. Acharya Charaka says that a physician can add new drugs to these Mahakashayas by his own intelligence that will help him to treat the patients.[8] He also states that one should get the knowledge about plants from tribal people or cowherds as they know and use the plants in a better way.[9] However, after Acharya Bhavamishra, the process of addition of new drugs to science has diminished or somewhat ceased. It is said that the wounds/ulcers of the diabetic patient are cured with difficulty.[10] Even with the latest technology and modern medicine in hand, highly trained medical team around, yet the majority of the diabetic ulcers end up with more or less amputation of the concerned major or minor part of the lower limb. Securinega leucopyrus (Willd.) Muell. is known as Humari in India, Katupila in Sri Lanka and Spinous Fluggea in English. It is a desert climatic plant used topically in paste form for the healing of chronic and nonhealing wounds. Hence, in the light of the above references from classics, Katupila Kalka (paste) was selected for this study with an aim to assess its effect in the management of Madhumehajanya Vrana (diabetic ulcer).\n\nBODY.MATERIALS AND METHODS:\nDiagnosed patients of diabetic wounds were selected from outpatient and inpatient departments of Shalya Tantra irrespective of the age, sex, religion, caste, occupation, etc. The study was started after obtaining approval from the Institutional Ethics Committee (PGT/7-A/2012-2013/1964 dated 21/09/2012) and study has been registered under Clinical Trial Registry of India (No.: CTRI/2013/09/004020). Informed written consent from each patient was obtained before starting treatment course.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nDiagnosed cases of Madhumehajanya Vrana with Type I and Type II diabetes mellitus of 18–70 years age of either sex.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nThe patients with a history of tuberculosis, wounds other than diabetic wounds, uncontrolled hypertension, cardiac diseases, such as myocardial infarction, coronary artery disease, and ischemic heart disease were excluded in this study. Patients with human immune virus (HIV), venereal disease research laboratory (VDRL) and hepatitis-B test positive were also excluded from the study.\n\nBODY.MATERIALS AND METHODS.LABORATORY INVESTIGATIONS:\nRoutine hematological parameters such as hemoglobin percentage, total leukocyte count, differential leucocyte count, bleeding time, clotting time, erythrocyte sedimentation rate; blood biochemical parameters such as fasting blood sugar, postprandial blood sugar, hepatitis B surface antigen, VDRL, and HIV; urine examination (routine and microscopic) was done to find out any other pathological condition.\n\nBODY.MATERIALS AND METHODS.RADIOLOGICAL EXAMINATION:\nX-ray of the affected foot (dorsoventral and lateral view) was done to rule out the osteomylitis of bone.\n\nBODY.MATERIALS AND METHODS.GROUPING AND POSOLOGY:\nTotally 23 patients of the diabetic wound were allocated randomly into two groups (Group A and B). \nGroup A (n = 13): In this group, Katupila Kalka (paste of S. leucopyrus leaves) with Tila Taila (sesame oil) was applied locally on the affected part. The dressing was done once in the morning up to 1 month or healing of wound which is earlierGroup B (n = 10): In this group, patients were treated with dressing of Betadine ointment once daily in the morning and treated as the standard control group.\n The leaves of Katupila were obtained from Sri Lanka and authenticated[11] at Pharmacognosy Laboratory, IPGT and RA, Jamnagar. Patients were advised to continue their anti-diabetic and anti-hypertensive medications (Allopathic/Ayurvedic) during treatment.\n\nBODY.MATERIALS AND METHODS.ASSESSMENT OF THERAPY:\nThe assessment of results was carried out mainly on the basis of relief in the signs and symptoms of the ulcers that are odor (Gandha), peri-wound skin (Varna), exudates level (Srava), type of exudates, pain (Vedana), wound measurement in cm (Akruti), and signs of infection [Table 1]. Table 1 Gradation for assessment of results Effect of therapy was statistically analysed by using student 't' test.\n\nBODY.MATERIALS AND METHODS.OVERALL EFFECT OF THERAPY:\n\nCured: 100% improvement in subjective and objective parametersMarked improvement: 70–99%Moderate improvement: 50–69%Mild improvement: 30–49%Unchanged: <30%.\n\n\nBODY.OBSERVATIONS:\nThe demographic data reveal that maximum patients were from the age group of 46 to 65 years (57%). Male patients were more that is 78.3% may be due to their irregular eating habits, addiction, excess standing work, and less care. Maximum patients were following Hindu religion (78%) and married (87%). Socioeconomically middle-class patients were in the majority (78.2%). The 78.27% of patients were having a history of diabetes and 21.73% of patients found with a history of both diabetes and hypertension. The 69.5% of patients had family history of diabetes. For the management of diabetic wound, 39.1% of patients had received medical treatment in past and 52.1% of patients had undergone surgery, whereas 8.6% of patients had both medical and surgical treatment. The majority of the patients that is 56.5% were suffering from wounds since 1 to 6 months, 34.7% of patients noted traumatic onset and maximum 73.9% were found with single wound. The 82.6% of patients were having Puya Srava (purulent exudates) and 95.6% of patients had Ghana Srava with 43.4% were having moderate Srava (discharge). Maximum numbers of patients presented without pain whereas only 34.9% of patients were found with pain. Bad odor was noted in all wounds and fever was found in maximum 73.91% of patients. In maximum 47.81% of patients the location of wound was at foot, as this part of the body more often gets trauma.\n\nBODY.RESULTS:\nIn this study, infection was controlled within 3–4 days and foul smell was controlled after 3 days in patients of Group A. In Group B, foul smell from ulcer continues until the wound was healed. The surrounded skin color became normal skin color within 7 days in maximum patients (76%) of Group A, whereas only 32% patients showed normal peri-wound skin color in Group B. In Group A, 55% of patients showed a complete cessation of discharge within 7 days whereas in Group B, exudation found reduced in 34% of patients at the end of 28th day. In all patients, pain sensation at wound site regained by 7th day in Group A, due to neo-vascularization and restored pain sensation in nerve fibers. In Group A, 12 patients wound size was reduced completely within 28 days, whereas in Group B, only 29% of patients wound size was reduced completely within 28 days. In Group A, signs of infections relieved 61% by the 7th day and totally relieved at the end of 28th day, whereas in Group B, patients infection was relieved 41% by the end of 28th day [Tables 2 and 3]. Table 2 Effect of therapy on signs and symptoms of wound in Group A Table 3 Effect of therapy on signs and symptoms of wound in Group B In Group A, 92.3% of patients were completely cured, whereas in Group B, 20% of patients were completely cured [Figure 1]. Wound healing effect of Katupila in four cases is depicted in Figure 2. Figure 1Overall effect of therapy Figure 2Before and after treatment wound status of Katupila treated cases\n\nBODY.DISCUSSION:\nIn this study, foul smell was controlled after 3 days in Group A patients, which was found statistically significant (P < 0.001). In Group B, foul smell from ulcer continues until the wound was healed. The Krimighna, Vishaghna, Rakshoghna (antimicrobial) properties of the Katupila helped to control the local infection and ultimately the bad odor.[12] In Group A, 100% normal skin coloration was achieved which was found statistically significant (P < 0.001). In 32% of patients of Group B, peri-wound skin color became normal which was found statistically significant (P > 0.05). Katupila may have Rakta Shodhana, Pittashamana, Varnya, Twaka Prasadana properties which helped to improve the surrounding wound skin color. Complete cessation of discharge within 7 days was observed in 55% of patients of Group A, while in remaining patients discharge was reduced by 28th day which was statistically significant (P < 0.001). Krimighna property of drug helped to control the infection. Hence, it can be said that Katupila paste had a better role than Betadine to reduce exudates level. In Group A, 77% of patients presented without pain while the pain was reported in 23% of patients due to diabetic neuropathy. After treating with Katupila, pain sensation regained by 7th day due to neo-vascularization and restored pain sensation in nerve fibers. The statistically insignificant result in pain relief was seen due to the restoration of pain sensation by correcting neuropathy. The Snigdha Guna of Tila Taila helped in control the vitiation of Vata and helped to relief in pain.[13] In Group B, there was minimal neovascularization, but the pain was relieved in 25% of patients due to the healed wounds which were statistically significant (P > 0.05). Hence, it can be inferred that Katupila is better than Betadine ointment to regain pain sensation (initial stage) as well as to relieve pain (in later stage). Complete wound healing was observed within 28 days in 92% cases so wound size reduction was found statistically highly significant (P < 0.001) which may be due to Katupila which may have Lekhana (scraping), Shodhana (cleaning) and Ropana (healing) properties. Madhura Rasa, Prinana (nourishment), Dhatuvardhana (tissue strength) and Dhatuposhana (nutrition) actions of Katupila helped to reduce the wound size by promoting healing and the rate of contraction. The infection at the wound site was assessed on the basis of odor, exudate level, local temperature, and swelling in both the groups. In Group A, signs of infections relieved 61% by the 7th day and totally relieved at the end of 28th day. Local application of Katupila reduces the discharge, swelling, pain by controlling the bacterial load, so wound became Shuddha (clean or healthy). Whereas in Group B, infection was relieved in 41% by the end of 28th day. Both drugs have shown statistically highly significant (P < 0.001) result in controlling infection. However, on the comparison, the duration of infection control by Katupila paste (that is 1st week) was found earlier than Betadine which took longer duration in controlling infections. The strength and positive finding of this study is Katupila Kalka had the potential to cure the diabetic wounds early than Betadine ointment. Findings in previously published case reports also showed the good potential in wound healing by Katupila.[1415] None of the adverse drug reaction noted during the treatment period. A reverse pharmacological study in the suitable animal model is a further scope of this work. As this drug is being used by traditional people and of herbal origin, there is a need to generate safety and toxicity profile of Katupila. The limitation of this research work is less number of patients due to the limited time of the postgraduate study.\n\nBODY.CONCLUSION:\nThe study concluded that Katupila Kalka (paste) possesses highly qualitative efficacy in \"Vrana Ropana\" with fine scaring. Therefore, it may be recommended that this low cost, easily preparable application may be prescribed for continuous use for the healing purposes.\n\nBODY.CONCLUSION.FINANCIAL SUPPORT AND SPONSORSHIP:\nIPGT & RA, Gujarat Ayurved University, Jamnagar.\n\nBODY.CONCLUSION.CONFLICTS OF INTEREST:\nThere are no conflicts of interest.\n\nQuestion: Compared to Betadine ointment what was the result of Katupila Kalka with Tila Taila on Control of foul smell?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1024	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of \n\n ABSTRACT.INTRODUCTION:\nPrevalence of diabetes and its complications have been a burden to the society from the ancient times, in the present and also will be in the future unless proper measures are taken to prevent its manifestation. There have been an increasing number of death associated-amputation cases which are mainly caused by nonhealing wounds. These facts urge researchers to develop new, more effective wound treatments for diabetic patients.\n\nABSTRACT.AIM:\nTo evaluate and compare the effect of Katupila Kalka (Securinega leucopyrus [Willd.] Muell. leaf paste) and Tila Taila (Sesamum indicum oil) in Madhumehajanya Vrana (diabetic wounds/ulcers) with Betadine ointment.\n\nABSTRACT.MATERIALS AND METHODS:\nA total of 23 patients of Madhumehajanya Vrana were chosen and randomly divided into two groups (Group A and B). Patients of Group A were treated with local application of Katupila Kalka with Tila Taila, whereas, in Group B, Betadine ointment was applied on the affected parts, once a day in the morning for 30 days. The relief in signs and symptoms were assessed on scoring pattern.\n\nABSTRACT.RESULTS:\nIn Group A, diabetic wounds treated with Katupila paste got healed within 28 days with minimal scar formation without any complications, whereas in Group B, wound was healed completely only in two patients within 28 days. In both the groups, no patients reported any adverse drug reaction during the entire course of treatment as well as in follow-up period.\n\nABSTRACT.CONCLUSION:\nStudy concluded that the drug Katupila Kalka possesses Vrana Ropana (wound healing) activity with fine scaring.\n\nBODY.INTRODUCTION:\nIn 2011, it was estimated that 366 million people worldwide had diabetes, representing roughly 8.3% of the adult population (20–79 years of age group). The number is expected to reach 552 million by 2030, representing 9.9% of the adult population. Diabetes is associated with various short and long-term complications, many of which, if left untreated, can be fatal. All these also have the potential to reduce the quality of life of people with diabetes and their families. The most common long-term complications affect the heart, eyes, kidneys, and feet.[1] Foot infections in persons with diabetes are a common and complex.[23] In addition to causing severe morbidities, they now account for the largest number of diabetes-related hospital bed-days[4] and are the most common proximate, nontraumatic cause of amputations.[56] Diabetic foot infections require careful attention and coordinated management, preferably by a multidisciplinary foot-care team.[7] Ayurveda has its own principles, but it is incorporating new theories and drugs in it and is presenting them according to its principles. Number of drugs known to Ayurveda since Vedic era is increasing with the time. Acharya Charaka says that a physician can add new drugs to these Mahakashayas by his own intelligence that will help him to treat the patients.[8] He also states that one should get the knowledge about plants from tribal people or cowherds as they know and use the plants in a better way.[9] However, after Acharya Bhavamishra, the process of addition of new drugs to science has diminished or somewhat ceased. It is said that the wounds/ulcers of the diabetic patient are cured with difficulty.[10] Even with the latest technology and modern medicine in hand, highly trained medical team around, yet the majority of the diabetic ulcers end up with more or less amputation of the concerned major or minor part of the lower limb. Securinega leucopyrus (Willd.) Muell. is known as Humari in India, Katupila in Sri Lanka and Spinous Fluggea in English. It is a desert climatic plant used topically in paste form for the healing of chronic and nonhealing wounds. Hence, in the light of the above references from classics, Katupila Kalka (paste) was selected for this study with an aim to assess its effect in the management of Madhumehajanya Vrana (diabetic ulcer).\n\nBODY.MATERIALS AND METHODS:\nDiagnosed patients of diabetic wounds were selected from outpatient and inpatient departments of Shalya Tantra irrespective of the age, sex, religion, caste, occupation, etc. The study was started after obtaining approval from the Institutional Ethics Committee (PGT/7-A/2012-2013/1964 dated 21/09/2012) and study has been registered under Clinical Trial Registry of India (No.: CTRI/2013/09/004020). Informed written consent from each patient was obtained before starting treatment course.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nDiagnosed cases of Madhumehajanya Vrana with Type I and Type II diabetes mellitus of 18–70 years age of either sex.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nThe patients with a history of tuberculosis, wounds other than diabetic wounds, uncontrolled hypertension, cardiac diseases, such as myocardial infarction, coronary artery disease, and ischemic heart disease were excluded in this study. Patients with human immune virus (HIV), venereal disease research laboratory (VDRL) and hepatitis-B test positive were also excluded from the study.\n\nBODY.MATERIALS AND METHODS.LABORATORY INVESTIGATIONS:\nRoutine hematological parameters such as hemoglobin percentage, total leukocyte count, differential leucocyte count, bleeding time, clotting time, erythrocyte sedimentation rate; blood biochemical parameters such as fasting blood sugar, postprandial blood sugar, hepatitis B surface antigen, VDRL, and HIV; urine examination (routine and microscopic) was done to find out any other pathological condition.\n\nBODY.MATERIALS AND METHODS.RADIOLOGICAL EXAMINATION:\nX-ray of the affected foot (dorsoventral and lateral view) was done to rule out the osteomylitis of bone.\n\nBODY.MATERIALS AND METHODS.GROUPING AND POSOLOGY:\nTotally 23 patients of the diabetic wound were allocated randomly into two groups (Group A and B). \nGroup A (n = 13): In this group, Katupila Kalka (paste of S. leucopyrus leaves) with Tila Taila (sesame oil) was applied locally on the affected part. The dressing was done once in the morning up to 1 month or healing of wound which is earlierGroup B (n = 10): In this group, patients were treated with dressing of Betadine ointment once daily in the morning and treated as the standard control group.\n The leaves of Katupila were obtained from Sri Lanka and authenticated[11] at Pharmacognosy Laboratory, IPGT and RA, Jamnagar. Patients were advised to continue their anti-diabetic and anti-hypertensive medications (Allopathic/Ayurvedic) during treatment.\n\nBODY.MATERIALS AND METHODS.ASSESSMENT OF THERAPY:\nThe assessment of results was carried out mainly on the basis of relief in the signs and symptoms of the ulcers that are odor (Gandha), peri-wound skin (Varna), exudates level (Srava), type of exudates, pain (Vedana), wound measurement in cm (Akruti), and signs of infection [Table 1]. Table 1 Gradation for assessment of results Effect of therapy was statistically analysed by using student 't' test.\n\nBODY.MATERIALS AND METHODS.OVERALL EFFECT OF THERAPY:\n\nCured: 100% improvement in subjective and objective parametersMarked improvement: 70–99%Moderate improvement: 50–69%Mild improvement: 30–49%Unchanged: <30%.\n\n\nBODY.OBSERVATIONS:\nThe demographic data reveal that maximum patients were from the age group of 46 to 65 years (57%). Male patients were more that is 78.3% may be due to their irregular eating habits, addiction, excess standing work, and less care. Maximum patients were following Hindu religion (78%) and married (87%). Socioeconomically middle-class patients were in the majority (78.2%). The 78.27% of patients were having a history of diabetes and 21.73% of patients found with a history of both diabetes and hypertension. The 69.5% of patients had family history of diabetes. For the management of diabetic wound, 39.1% of patients had received medical treatment in past and 52.1% of patients had undergone surgery, whereas 8.6% of patients had both medical and surgical treatment. The majority of the patients that is 56.5% were suffering from wounds since 1 to 6 months, 34.7% of patients noted traumatic onset and maximum 73.9% were found with single wound. The 82.6% of patients were having Puya Srava (purulent exudates) and 95.6% of patients had Ghana Srava with 43.4% were having moderate Srava (discharge). Maximum numbers of patients presented without pain whereas only 34.9% of patients were found with pain. Bad odor was noted in all wounds and fever was found in maximum 73.91% of patients. In maximum 47.81% of patients the location of wound was at foot, as this part of the body more often gets trauma.\n\nBODY.RESULTS:\nIn this study, infection was controlled within 3–4 days and foul smell was controlled after 3 days in patients of Group A. In Group B, foul smell from ulcer continues until the wound was healed. The surrounded skin color became normal skin color within 7 days in maximum patients (76%) of Group A, whereas only 32% patients showed normal peri-wound skin color in Group B. In Group A, 55% of patients showed a complete cessation of discharge within 7 days whereas in Group B, exudation found reduced in 34% of patients at the end of 28th day. In all patients, pain sensation at wound site regained by 7th day in Group A, due to neo-vascularization and restored pain sensation in nerve fibers. In Group A, 12 patients wound size was reduced completely within 28 days, whereas in Group B, only 29% of patients wound size was reduced completely within 28 days. In Group A, signs of infections relieved 61% by the 7th day and totally relieved at the end of 28th day, whereas in Group B, patients infection was relieved 41% by the end of 28th day [Tables 2 and 3]. Table 2 Effect of therapy on signs and symptoms of wound in Group A Table 3 Effect of therapy on signs and symptoms of wound in Group B In Group A, 92.3% of patients were completely cured, whereas in Group B, 20% of patients were completely cured [Figure 1]. Wound healing effect of Katupila in four cases is depicted in Figure 2. Figure 1Overall effect of therapy Figure 2Before and after treatment wound status of Katupila treated cases\n\nBODY.DISCUSSION:\nIn this study, foul smell was controlled after 3 days in Group A patients, which was found statistically significant (P < 0.001). In Group B, foul smell from ulcer continues until the wound was healed. The Krimighna, Vishaghna, Rakshoghna (antimicrobial) properties of the Katupila helped to control the local infection and ultimately the bad odor.[12] In Group A, 100% normal skin coloration was achieved which was found statistically significant (P < 0.001). In 32% of patients of Group B, peri-wound skin color became normal which was found statistically significant (P > 0.05). Katupila may have Rakta Shodhana, Pittashamana, Varnya, Twaka Prasadana properties which helped to improve the surrounding wound skin color. Complete cessation of discharge within 7 days was observed in 55% of patients of Group A, while in remaining patients discharge was reduced by 28th day which was statistically significant (P < 0.001). Krimighna property of drug helped to control the infection. Hence, it can be said that Katupila paste had a better role than Betadine to reduce exudates level. In Group A, 77% of patients presented without pain while the pain was reported in 23% of patients due to diabetic neuropathy. After treating with Katupila, pain sensation regained by 7th day due to neo-vascularization and restored pain sensation in nerve fibers. The statistically insignificant result in pain relief was seen due to the restoration of pain sensation by correcting neuropathy. The Snigdha Guna of Tila Taila helped in control the vitiation of Vata and helped to relief in pain.[13] In Group B, there was minimal neovascularization, but the pain was relieved in 25% of patients due to the healed wounds which were statistically significant (P > 0.05). Hence, it can be inferred that Katupila is better than Betadine ointment to regain pain sensation (initial stage) as well as to relieve pain (in later stage). Complete wound healing was observed within 28 days in 92% cases so wound size reduction was found statistically highly significant (P < 0.001) which may be due to Katupila which may have Lekhana (scraping), Shodhana (cleaning) and Ropana (healing) properties. Madhura Rasa, Prinana (nourishment), Dhatuvardhana (tissue strength) and Dhatuposhana (nutrition) actions of Katupila helped to reduce the wound size by promoting healing and the rate of contraction. The infection at the wound site was assessed on the basis of odor, exudate level, local temperature, and swelling in both the groups. In Group A, signs of infections relieved 61% by the 7th day and totally relieved at the end of 28th day. Local application of Katupila reduces the discharge, swelling, pain by controlling the bacterial load, so wound became Shuddha (clean or healthy). Whereas in Group B, infection was relieved in 41% by the end of 28th day. Both drugs have shown statistically highly significant (P < 0.001) result in controlling infection. However, on the comparison, the duration of infection control by Katupila paste (that is 1st week) was found earlier than Betadine which took longer duration in controlling infections. The strength and positive finding of this study is Katupila Kalka had the potential to cure the diabetic wounds early than Betadine ointment. Findings in previously published case reports also showed the good potential in wound healing by Katupila.[1415] None of the adverse drug reaction noted during the treatment period. A reverse pharmacological study in the suitable animal model is a further scope of this work. As this drug is being used by traditional people and of herbal origin, there is a need to generate safety and toxicity profile of Katupila. The limitation of this research work is less number of patients due to the limited time of the postgraduate study.\n\nBODY.CONCLUSION:\nThe study concluded that Katupila Kalka (paste) possesses highly qualitative efficacy in \"Vrana Ropana\" with fine scaring. Therefore, it may be recommended that this low cost, easily preparable application may be prescribed for continuous use for the healing purposes.\n\nBODY.CONCLUSION.FINANCIAL SUPPORT AND SPONSORSHIP:\nIPGT & RA, Gujarat Ayurved University, Jamnagar.\n\nBODY.CONCLUSION.CONFLICTS OF INTEREST:\nThere are no conflicts of interest.\n\nQuestion: Compared to Betadine ointment what was the result of Katupila Kalka with Tila Taila on Control of infection?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1025	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: A randomised controlled trial to prevent smoking relapse among recently quit smokers enrolled in employer and health plan sponsored quitlines\n\n ABSTRACT.OBJECTIVE:\nTo test adding an interactive voice response (IVR)-supported protocol to standard quitline treatment to prevent relapse among recently quit smokers.\n\nABSTRACT.DESIGN:\nParallel randomised controlled trial with three arms: standard quitline, standard plus technology enhanced quitline with 10 risk assessments (TEQ-10), standard plus 20 TEQ assessments (TEQ-20).\n\nABSTRACT.SETTING:\nQuit For Life (QFL) programme.\n\nABSTRACT.PARTICIPANTS:\n1785 QFL enrolees through 19 employers or health plans who were 24+ h quit.\n\nABSTRACT.INTERVENTIONS:\nQFL is a 5-call telephone-based cessation programme including medications and web-based support. TEQ interventions included 10 or 20 IVR-delivered relapse risk assessments over 8 weeks with automated transfer to counselling for those at risk.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nSelf-reported 7-day and 30-day abstinence assessed at 6-month and 12-month post-enrolment (response rates: 61% and 59%, respectively). Missing data were imputed.\n\nABSTRACT.RESULTS:\n1785 were randomised (standard n=592, TEQ-10 n=602, TEQ-20 n=591). Multiple imputation-derived, intent-to-treat 30-day quit rates (95% CI) at 6 months were 59.4% (53.7% to 63.8%) for standard, 62.3% (57.7% to 66.9%) for TEQ-10, 59.4% (53.7% to 65.1%) for TEQ-20 and 30-day quit rates at 12 months were 61.2% (55.6% to 66.8%) for standard, 60.6% (56.0% to 65.2%) for TEQ-10, 54.9% (49.0% to 60.9%) for TEQ-20. There were no significant differences in quit rates. 73.3% of TEQ participants were identified as at-risk by IVR assessments; on average, participants completed 0.41 IVR-transferred counselling calls. Positive risk assessments identified participants less likely (OR=0.56, 95% CI 0.42 to 0.76) to be abstinent at 6 months.\n\nABSTRACT.CONCLUSIONS:\nStandard treatment was highly effective, with 61% remaining abstinent at 12 months using multiple imputation intent-to-treat (intent-to-treat missing=smoking quit rate: 38%). TEQ assessments identified quitters at risk for relapse. However, adding IVR-transferred counselling did not yield higher quit rates. Research is needed to determine if alternative designs can improve outcomes.\n\nABSTRACT.TRIAL REGISTRATION NUMBER:\nNCT00888992.\n\nBODY:\nStrengths and limitations of this studyFirst large randomised controlled trial to examine the use of interactive voice response (IVR) technology for prevention of smoking relapse.Large sample of participants recruited from employer and health plan quitline programmes serving tobacco users across the USA.Protocol used an innovative and potentially cost-effective technology to connect those at risk for relapse to immediate counselling.We compared two risk assessment intensities over the first 8 weeks following successful abstinence.Although participants rated the IVR system positively, fewer accepted immediate risk-focused counselling than anticipated; thus, the increase in treatment exposure was small. Smoking continues to be the leading preventable cause of premature death and disease in the USA and worldwide.1\n2 Quitting tobacco is one of the most important steps a tobacco user can take to improve their health.3 Free publicly (state and government) and privately (eg, employer and health plan) funded telephone-based tobacco cessation quitlines are available throughout the USA and increasingly around the world to help tobacco users quit. With the advent of the Affordable Care Act in the USA, telephone-based tobacco cessation services offer an important resource to ensure that tobacco users have access to the empirically supported tobacco treatments that are required components of coverage. Although extensive evidence exists regarding the efficacy and cost-effectiveness of tobacco cessation quitlines,4–6 as with other behavioural and pharmacological tobacco treatment options, little is known about how best to intervene with callers at the time of greatest risk for relapse. A recent Cochrane Review concluded that previously tested behavioural relapse prevention interventions, which primarily included skills training or extended therapeutic contact, did not provide additional benefit over no treatment or intervention without a relapse prevention component.7 Survival studies have identified that the highest relapse risk, on average, is in the first 2 weeks after a quit attempt; however, there is considerable between-individual and within-individual variability in risk-related symptom patterns.8 Relapse prevention interventions may be most effective if provided at the time of relapse risk given the multifaceted and individualised nature of withdrawal and environmentally induced relapse risks over time.8 Interactive voice response (IVR) technology offers a resource-efficient solution for connecting tobacco users with relapse prevention interventions at the time of need, especially those already enrolled in phone-based tobacco cessation treatment. IVR is increasingly incorporated into some tobacco treatment protocols,9\n10 and has been used in chronic disease management, posthospital discharge management, medication compliance monitoring, and in a small number of addiction and depression self-help interventions.11 IVR has been piloted as a smoking relapse prevention tool following a single group counselling call and 12 weeks of varenicline,12 but was insufficiently powered to draw meaningful conclusions about the effectiveness of the nine-call and nurse call-back intervention. The purpose of this present study is to examine the effectiveness of augmenting standard multisession tobacco quitline treatment with repeated IVR assessments to monitor recent quitters' relapse risk, and transfer those at risk to a Quit Coach for a brief, focused, intervention targeting the identified relapse trigger. We hypothesised that smokers receiving IVR risk assessments during the first 2 months after quitting would be more likely to stay quit than those receiving standard quitline treatment, and that more frequent assessments (20 vs 10) would be more beneficial.\n\nBODY.METHODS.STUDY DESIGN:\nIn this parallel randomised controlled trial, tobacco users enrolled in the Quit For Life (QFL) programme who achieved abstinence for at least 24 h after their quit date were randomised into one of three study groups: (1) standard treatment, (2) Technology Enhanced Quitline-10 (TEQ-10): standard treatment plus 10 IVR-delivered relapse risk assessments which triggered a transfer to a Quit Coach for participants exceeding risk thresholds and (3) Technology Enhanced Quitline-20 (TEQ-20): same as the TEQ-10 condition except with 20 relapse risk assessments rather than 10. Participants were randomised using blocked randomisation to ensure similar group sizes throughout the study; every nine participants within each employer or health plan contract were randomly assigned with an allocation ratio for the three groups of 3:3:3. These random allocation tables were generated by the study management team and integrated into the QFL computer system where they were not accessible to coaches or participants. Once study eligibility was confirmed, the Quit Coach clicked a 'Randomise' button and the system automatically assigned the participant to the group listed in the next available cell of the allocation table. The planned and final sample size was 1785 and was determined a priori to achieve at least 80% power to detect 30-day point prevalence quit rate differences of 8% between any pair of three arms for intent-to-treat (ITT) analyses, including the traditional penalised imputation approach in which non-responders to data collection are considered relapsed13 and the state-of-the-art multiple imputation method14 (assuming quit rates of 29.6%, 37.6% and 45.6% at 6 months and 26.6%, 34.6% and 42.6% at 12 months for standard care, TEQ-10 and TEQ-20, respectively; n=595) and of 10% for a responder analysis between standard care and either intervention at 6 or 12 months (assuming quit rates of 52.1% standard care, 62.1% TEQ-10, 62.1% TEQ-20; assuming 25% attrition, with 446 responders per arm). The primary analysis using ITT multiple imputation has slightly greater than 80% power because, like ITT using penalised imputation (missing=smoking), it uses all persons with baseline data. However, compared with penalised imputation, or responder-only analysis, multiple imputation ITT uses more information and produces results with greater power, less bias, and greater accuracy.13\n14 Participants gave informed consent prior to study enrolment and received a US$25 gift card for completed 6-month and 12-month follow-up surveys (potential for US$50 total).\n\nBODY.METHODS.PARTICIPANTS:\nTobacco users were eligible for the study if they had enrolled in the QFL programme between April 2010 and October 2012 through 1 of 19 employers or health plans who offered QFL as part of their benefits package. Because the purpose of this study was to examine the potential benefit of IVR assessments, and their triggering of counselling at the point of need to reduce relapse, tobacco users were screened for study criteria and invited to participate after reporting they had been quit for 24 h or more after their quit date. This typically occurred during their second or third call (their quit date call or the call after) of the five-call programme. Additional eligibility criteria included being English-speaking, 18 years of age or older, and having access to a touch-tone phone. Tobacco users were excluded if they exclusively used smokeless tobacco, were actively participating in another tobacco cessation programme, had previously enrolled in the QFL programme during the past 6 months, or had limited phone access (eg, incarceration). Of the 3723 tobacco users who received the study offer, 1840 (49.4%) agreed to participate and 1785 completed the baseline survey and were randomised to one of the three study groups (figure 1). Figure 1CONSORT Diagram. 36 participants did not receive all of their relapse risk assessments due to a programming error in the interactive voice response (IVR) code.\n\nBODY.METHODS.THE QFL PROGRAMME:\nQFL, operated by Alere Wellbeing (formerly Free & Clear), has been commercially available for nearly 30 years, and its effectiveness and cost-effectiveness has been demonstrated in various studies.5\n15–19 The QFL programme includes five counselling calls (an initial assessment and planning call plus four additional proactive outbound calls from an expert Quit Coach). Quit Coaches are required to have a bachelor's degree in a related field, complete more than 200 h of training, and receive ongoing supervision and feedback. The call schedule and content is tailored to each participant's needs. The default call schedule includes the initial planning and assessment call, a quit date call (QDC), a quit date follow-up call 7 days after the QDC, and two additional follow-up calls that take place approximately every 3 weeks after the previous call. Participants are also encouraged to call in for support as needed (ie, participant-initiated inbound calls). Calls vary in length: the planning and assessment call is 25–30 min, while other calls are 15–20 min. Calls focus on creating a quit plan, developing problem-solving and coping skills, identifying social support, and using cessation medications to achieve and maintain abstinence. Participants may receive over-the-counter nicotine replacement products directly via mail (or other prescription cessation medications depending upon their cessation benefit with their employer or health plan). They also receive a printed quit guide, and access to Web Coach, an online interactive web-based programme designed to complement the phone programme.\n\nBODY.METHODS.IVR INTERVENTION:\nIn the two TEQ groups, participants were contacted for relapse risk assessments through automated IVR calls over their first 8 weeks postquit. Two intensities of IVR monitoring were examined. TEQ-10 participants were contacted twice weekly for the first 2 weeks, then weekly for 6 weeks. TEQ-20 participants were contacted daily for the first 2 weeks, then weekly for 6 weeks. An IVR service contractor programmed and delivered the risk assessments (approximately 5 min), which included questions to identify relapse risk on five factors: lapses, cravings, negative affect, self-efficacy and motivation to remain quit. An algorithm was used to flag participants as 'at risk' if they answered any of the screening questions over an established threshold, based on previous research.20–22 Participants who exceeded the threshold were then transferred directly to a Quit Coach for a brief intervention (approximately 15 min) specifically addressing the risk factor(s) that triggered their transfer. Intervention fidelity was monitored by study staff and investigators. Randomly sampled recordings of IVR-triggered telephone counselling sessions were rated for compliance with the study protocol (the primary criterion being whether the counsellor focused the call on identified relapse risk(s)) by two independent reviewers (a study staff member and a Quit Coach supervisor). Reviews revealed some Quit Coaches did not receive information about the risk factor that triggered a participant's transfer due to technological issues. These programming errors were corrected by the IVR vendor. In these circumstances, participants still received empirically based tobacco cessation support at the time of need. As part of quality monitoring, any protocol deviations were addressed with individual feedback from Quit Coach supervisors and ongoing training for all Quit Coaches.\n\nBODY.MEASURES.BASELINE MEASURES:\nDuring registration and the first Quit Coach call, participants completed standard assessment questions regarding demographic characteristics (age, gender, health comorbidities) and tobacco use (tobacco type, time to first use, cigarettes per day, number of previous quit attempts, social contact with smokers). After study recruitment, participants completed an additional baseline measure assessing age, race, ethnicity, education, depressive symptoms (PHQ-2; 2-item measure21), and stress (Perceived Stress Scale; 4-item measure23).\n\nBODY.MEASURES.IVR-POSITIVE SCREENS AND PROGRAM CALL COMPLETION:\nThe IVR system stored the number of relapse risk assessments participants answered, participants' responses to the relapse risk questions, and the number of IVR assessments on which a participant had a positive risk screen. Counselling calls completed as a result of a positive IVR screen and successful transfer to a Quit Coach (ie, IVR-transferred counselling calls) were tracked in addition to standard programme calls (5 planned calls plus participant-initiated inbound calls).\n\nBODY.MEASURES.OUTCOMES MEASURED AT 6 AND 12 MONTHS:\nAt 6 and 12 months after randomisation, participants completed telephone interviewsi administered by outcomes evaluators from the Indiana University Center for Survey Research who were blind to study condition to measure abstinence. All participants rated their satisfaction with the QFL service, and those in the TEQ groups were asked their opinions of the IVR system during the 6-month survey. When participants could not be reached after repeated phone attempts, we also mailed a brief paper survey with only the smoking abstinence questions. Survey response rates were 61% and 59% at 6 and 12 months, respectively. The primary study outcomes were quit rates at 6 and 12 months, defined as 7-day and 30-day self-reported point prevalence abstinence measured by the question, 'In the last [7/30] days, have you smoked a cigarette, even a puff?'. Time to relapse was examined as a secondary outcome and was identified using three questions: 'Since [end of two-week grace period], have you ever smoked at least a part of a cigarette on 7 days in a row?'; 'Since [end of two-week grace period], have you ever smoked any in each of two consecutive weeks (at least 1 day for 2 weeks in a row)?', and [if yes to either of the 2 previous questions] 'What was the first day of that 7-day or two-week period that you smoked?'.16\n\nBODY.MEASURES.STATISTICAL ANALYSES:\nMissing values on all 6-month and 12-month outcomes were imputed using the state-of-the-art imputation method called 'multiple imputation'24 with sequential regression.25 Multiple imputation allows all cases (N=1785) to be included in the analysis. Two imputation models were performed: one for 7-day and one for 30-day point prevalence abstinence. With this approach, variables with no missing values served as independent variables. The variable with the least amount of missing data was imputed first, and used as the dependent variable. Once imputation was carried out, the next variable with the least amount of missing data was imputed using all variables with non-missing values as independent variables including the variable imputed on the previous step. This cycle continued until all missing values were imputed resulting in a series of regressions, hence the name sequential regression. Variables used to provide information for imputation (and to be imputed themselves if missing) included intervention group (no data missing), baseline characteristics listed in table 1 (with the exception of years of tobacco use and stress, due to high correlations with age and depression, respectively), and number of planned calls plus participant-initiated inbound counselling calls completed. These variables had a minimal amount of missing data with, at most, 3.5% missing for the motivation variable. Abstinence outcomes measured at both 6 and 12 months were included in each imputation model and had the greatest amount of missing data. Ten multiple-imputed data sets were generated and analysed. Table 1 Baseline characteristics (N=1785) Variable Overall (N=1785) Standard (N=592) Standard plus TEQ-10 (N=602) Standard plus TEQ-20 (N=591) Demographics Age, mean (SD) 43.4 (11.9) 43.3 (12.2) 44.0 (11.5) 43.0 (12.0) Gender, N (%) Female 967 (54.2) 321 (54.2) 326 (54.1) 320 (54.2) Male 818 (45.8) 271 (45.8) 276 (45.9) 271 (45.8) Race, N (%) Caucasian 1489 (83.4) 497 (84.0) 501 (83.2) 491 (83.1) African-American 204 (11.4) 63 (10.6) 71 (11.8) 70 (11.8) Other 51 (2.9) 16 (2.7) 19 (3.2) 16 (2.7) Missing 43 (2.3) 16 (2.7) 11 (1.8) 14 (2.4) Education, N (%) High school or less 667 (37.4) 229 (38.7) 225 (37.4) 213 (36.0) More than high school 1117 (62.6) 363 (61.3) 376 (62.6) 378 (64.0) Comorbidities, N (%) Asthma 176 (9.9) 62 (10.5) 61 (10.1) 53 (9.0) COPD 108 (6.0) 39 (6.6) 32 (5.3) 37 (6.3) CAD 75 (4.2) 27 (4.6) 25 (4.2) 23 (3.9) Diabetes 138 (7.7) 53 (8.9) 46 (7.6) 39 (6.6) Any chronic comorbidity 395 (22.1) 136 (23.0) 136 (22.6) 123 (20.8) Tobacco use Time to first cigarette, N (%), min 5 539 (30.2) 165 (27.9) 197 (32.7) 177 (30.0) 6–30 618 (34.6) 213 (36.0) 201 (33.4) 204 (34.5) 31–60 285 (16.0) 89 (15.0) 101 (16.8) 95 (16.1) >60 289 (16.2) 105 (17.7) 88 (14.6) 96 (16.2) Missing 54 (3.0) 20 (3.4) 15 (2.5) 19 (3.2) Cigarettes per day, mean (SD) 16.8 (9.0) 16.8 (9.1) 17.2 (8.9) 16.4 (9.1) Number of quit attempts, N (%) 0–1 377 (21.1) 116 (19.6) 127 (21.1) 134 (22.7) 2–5 1033 (57.9) 371 (62.7) 335 (55.7) 327 (55.3) 6+ 347 (19.4) 97 (16.4) 127 (21.3) 122 (20.6) Missing 28 (1.6) 8 (1.4) 12 (2.0) 8 (1.4) Tobacco use ≥20 years, N (%) Yes 1098 (61.5) 361 (61.0) 383 (63.6) 354 (59.9) No 671 (37.6) 227 (38.3) 211 (35.1) 233 (39.4) Missing 16 (0.9) 4 (0.7) 8 (1.3) 4 (0.7) Social contact with smokers, N (%) No 470 (26.3) 146 (24.7) 179 (29.7) 145 (24.5) Work 572 (32.0) 192 (32.4) 188 (31.2) 192 (32.5) Home 342 (19.2) 122 (20.6) 104 (17.3) 116 (19.6) Both work and home 344 (19.3) 112 (18.9) 111 (18.4) 121 (20.5) Missing 57 (3.2) 20 (3.4) 20 (3.3) 17 (2.9) Scale scores Motivation to quit, mean (SD) 9.1 (1.3) 9.0 (1.3) 9.0 (1.2) 9.1 (1.2) Depression, mean (SD) 1.0 (1.3) 1.0 (1.3) 1.0 (1.3) 1.0 (1.3) Perceived stress, mean (SD) 4.3 (2.8) 4.3 (2.9) 4.2 (2.8) 4.5 (2.8) Defined as having asthma or COPD or CAD or diabetes. CAD, coronary artery disease; COPD, chronic obstructive pulmonary disease; TEQ-10, Technology Enhanced Quitline-10; TEQ-20, Technology Enhanced Quitline-20. Logistic regression models were used to model intervention efficacy on the 6-month and 12-month outcomes of abstinence, while adjusting for theoretically important potentially confounding baseline covariates.26 There were four main outcomes (7-day and 30-day point prevalence quit rates assessed at 6 and 12 months) and each was analysed with a separate logistic regression model. The multiple imputation quit rate results were our primary outcome metric. However, outcomes were reported using three methods: (1) for all survey respondents (responder analysis), (2) using penalised imputation reporting (assumes non-respondents are treatment failures) which is the traditional ITT analysis used in the smoking literature and (3) with results imputed for participants with missing data using the state-of-the-art multiple imputation method. Although ITT outcomes using penalised imputation are commonly reported in cessation trials, methodological research, including simulation studies, have shown that multiple imputation ITT uses more information and produces greater power, less bias, and more accuracy compared with simpler ad hoc methods for handling missing data such as traditional penalised imputation ITT, or responder-only analysis.13\n14 Missing values for relapse date were imputed using the procedures described above. Using this relapse date and the baseline date, proportional hazards regression was used to examine factors associated with time to relapse. The variables representing number of calls (table 2) were generally skewed to the right with a large number of zeroes. These data were complete and did not require imputation. To compare study groups on these count variables, a generalised linear model with log link function and negative binomial distribution was used. Six-month satisfaction data were also analysed (without imputation) to determine levels of satisfaction with the QFL programme and IVR protocol. The satisfaction variable was not imputed since it was not a primary outcome. Satisfaction comparisons between intervention groups were made using a χ2 test. Mplus software for Windows (V.7.2) was used to generate imputed data and PROC MIANALYZE from SAS/STAT software (V.9.3) was used to pool results and analyse the imputed data sets. All other statistical comparisons were performed using SAS/BASE and SAS/STAT software for Windows (V.9.3). Table 2 Descriptives for number of phone calls (N=1785) Variable Overall (N=1785) Standard (N=592) Standard plus TEQ-10 (N=602) Standard plus TEQ-20 (N=591) p Value (1) Planned programme counselling calls (1–5), mean (SD); range 3.29 (1.09); 1–5 3.29 (1.09); 1–5 3.32 (1.09); 1–5 3.25 (1.08); 1–5 0.8085 (2) Participant-initiated inbound calls, mean (SD); range 0.38 (1.05); 0–14 0.37 (0.92); 0–8 0.40 (1.13); 0–14 0.37 (1.08); 0–12 0.9082 ≥1 vs 0, N (%) 284 (15.9) 99 (16.7) 96 (16.0) 89 (15.1) 0.7361† (1+2) Sum of planned and participant-initiated inbound calls, mean (SD); range 3.67 (1.53); 2–17 3.66 (1.48); 2–13 3.72 (1.62); 2–17 3.62 (1.48); 2–13 0.6851 (3) IVR-transferred counselling calls, mean (SD); range 0.41 (0.75); 0–6 N/A 0.39 (0.72); 0–6 0.43 (0.79); 0–6 0.2791‡ ≥1 vs 0, N (%) 361 (30.3) N/A 175 (29.1) 186 (31.5) 0.3665†‡ (1+2+3) Sum of all calls, mean (SD); range 3.94 (1.71); 2–19 3.66 (1.48); 2–13 4.11 (1.82); 2–19 4.06 (1.77); 2–17 <0.0001 p Value obtained from generalised linear model for a count outcome except where indicated. †p Value obtained from χ 2 test. ‡p Value is for comparison between TEQ-10 and TEQ-20 groups. IVR, interactive voice response; TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.PARTICIPANTS:\nBaseline characteristics across the three intervention groups are shown in table 1. Overall, the average age of study participants was 43 years (range 18–85). A little over half (54%) were women. A majority of the sample was Caucasian (83%) and reported having a high school education or more (62%). Just under a quarter of the sample reported having ≥1 chronic comorbidity (22%). The average number of reported cigarettes used per day was 17 (range 0–60) with about two-thirds of the sample reporting having had a cigarette within 30 min from the time they wake in the morning. About 20% of the sample reported 0 or one quit attempts, with a similar percentage reporting six or more quit attempts. A little over 60% reported using tobacco for 20 or more years, and about three-quarters reported having contact with smokers at work, home, or both. Overall, participants reported feeling motivated to quit smoking, with an average rating of 9 on a 1–10 scale (1=low, 10=high). The average PHQ-2 depression score was 1.0 (possible range 0–6, with high scores indicating higher levels of depression,21 and the average perceived stress score was 4.3 (possible range 0–16, with higher scores indicating higher perceived stress.23 At the time of study offer, 56.5% of participants had been quit for 1–6 days, 40% had been quit for 7–29 days, and 3.5% had been quit for 30 days or more.\n\nBODY.RESULTS.PROGRAMME ENGAGEMENT AND POSITIVE RISK SCREENS:\nProgramme engagement was measured as the number of counselling calls completed by participants:1 planned programme counselling calls,2 participant-initiated inbound calls, or3 IVR-transferred counselling calls (table 2). Overall, the average number of total calls completed was 3.9 (SD=1.7; range 2–19). There was a statistical difference between groups; the TEQ-10 and TEQ-20 groups completed slightly more calls than the standard study group due to the additional IVR-transferred counselling calls they received after a positive screen (p<0.001). There were no statistical differences between participant-initiated (p=0.91) or planned programme calls completed (p=0.81). Also, there was no statistical difference in IVR-transferred counselling calls between the TEQ-10 and TEQ-20 groups (p=0.28). There was a statistical difference in the number of positive screens between the two intervention groups, with TEQ-20 having slightly more positive screens than TEQ-10 (on average, 1.52 (SD=1.66) for TEQ-10 and 1.82 (SD=1.99) for TEQ-20, p=0.003). The percentage of one or more positive screens was also larger in the TEQ-20 group (76% vs 70%; p=0.03).\n\nBODY.RESULTS.SIX-MONTH AND 12-MONTH OUTCOMES:\nSeven-day and 30-day point prevalence abstinence rates at 6-month and 12-month follow-up are shown in table 3. As aforementioned, outcomes are reported using three methods: (1) for all survey respondents (responder analysis), (2) using a crude ITT analysis based on penalised imputation reporting (assumes non-respondents are treatment failures) and (3) using state-of-the-art ITT based on multiple imputation for participants with missing data. Since we had missing data, we used the multiple imputation quit rate as our primary outcome. Table 3 Estimates of abstinence at 6 and 12 months, N=1785 Intervention group 6-Month survey outcomes 12-Month survey outcomes N Did not smoke in last 7 days N Did not smoke in the last 30 days N Did not smoke in last 7 days N Did not smoke in the last 30 days Responders Standard 368 66.0 (61.2 to 70.9) 368 60.6 (55.6 to 65.6) 363 65.3 (60.4 to 70.2) 362 61.6 (56.6 to 66.6) Standard plus TEQ-10 368 69.6 (64.9 to 74.3) 368 65.2 (60.4 to 70.1) 370 67.0 (62.2 to 71.8) 371 63.1 (58.2 to 68.0) Difference compared to standard 3.5 (−3.2 to 10.3) p=0.3051 4.6 (−2.4 to 11.6) p=0.1946 1.7 (−5.1 to 8.6) p=0.6191 1.5 (−5.5 to 8.5) p=0.6812 Standard plus TEQ-20 352 67.3 (62.4 to 72.2) 352 61.1 (56.0 to 66.2) 310 62.6 (57.2 to 68.0) 311 56.6 (51.1 to 62.1) Difference compared to standard 1.3 (−5.6 to 8.2) p=0.7121 0.5 (−6.6 to 7.6) p=0.8947 −2.7 (−10.0 to 4.6) p=0.4655 −5.0 (−12.5 to 2.4) p=0.1871 Intent-to-treat penalised imputation (missing=smoking)† Standard 592 41.1 (37.1 to 45.0) 592 37.6 (33.8 to 41.6) 592 40.0 (36.1 to 44.0) 592 37.7 (33.8 to 41.6) Standard plus TEQ-10 602 42.5 (38.6 to 46.5) 602 39.9 (36.0 to 43.8) 602 41.2 (37.3 to 45.1) 602 38.9 (35.0 to 42.8) Difference compared to standard 1.5 (−4.1 to 7.1) p=0.6047 2.2 (−3.3 to 7.7) p=0.4357 1.2 (−4.4 to 6.7) p=0.6827 1.2 (−4.3 to 6.7) p=0.6693 Standard plus TEQ-20 591 40.1 (36.2 to 44.1) 591 36.4 (32.5 to 40.3) 591 32.8 (29.0 to 36.6) 591 29.8 (26.1 to 33.5) Difference compared to standard −1.0 (−6.5 to 4.7) p=0.7405 −1.3 (−6.8 to 4.2) p=0.6459 −7.2 (−12.7 to −1.7) p=0.0100 −7.9 (−13.3 to −2.5) p=0.0041 Multiple imputation‡ Standard 592 64.2 (59.5 to 68.9) 592 59.4 (53.7 to 63.8) 592 63.3 (58.4 to 68.4) 592 61.2 (55.6 to 66.8) Standard plus TEQ-10 602 67.8 (63.0 to 72.7) 602 62.3 (57.7 to 66.9) 602 65.1 (60.3 to 69.9) 602 60.6 (56.0 to 65.2) Difference compared to standard 3.6 (−3.3 to 10.5) p=0.2980 3.6 (−3.2 to 10.4) p=0.2969 1.7 (−4.4 to 7.7) p=0.5831 −0.6 (−7.6 to 6.4) p=0.8647 Standard plus TEQ-20 591 64.7 (59.2 to 70.2) 591 59.4 (53.7 to 65.1) 591 60.9 (56.4 to 65.5) 591 54.9 (49.0 to 60.9) Difference compared to standard 0.5 (−7.0 to 8.0) p=0.8982 0.7 (−6.4 to 7.8) p=0.8468 −2.5 (−9.4 to 4.5) p=0.4808 −6.3 (−14.9 to 2.3) p=0.1471 Percentage of participants reporting abstinence is shown in table above with 95% CIs in parentheses. p Values obtained from χ 2 test for difference between proportions. Estimates were obtained among participants having completed a 6-month or 12-month survey. †Estimates were obtained assuming participants missing a 6-month or 12-month survey were not abstinent. ‡Estimates were obtained by pooling results across 10 multiply imputed data sets. TEQ-10, Technology Enhanced Quitline-10. ITT-penalised imputation quit rates at 12 months were significantly lower for the TEQ-20 group compared with the standard and TEQ-10 groups. However, there were no significant differences in responder or imputed quit rates at 6 or 12 months, or rates of relapse. The quit rates based on multiple imputation at 6 and 12 months ranged from 55% to 68% depending on intervention group, follow-up time point, and outcome measure. Controlling for baseline characteristics, logistic regression models further illustrated no statistical difference between intervention groups for either primary outcome and either time point (table 4). A few baseline characteristics were statistically associated with the outcomes. Across the four models shown in table 4, a higher number of counselling calls, and being motivated to quit, were consistently associated with higher odds of being abstinent (all p<0.05). Depression also played a role in three of the models, with higher depression scores being associated with lower odds of being abstinent (all p<0.05). Older age resulted in higher odds of abstinence for 6-month outcomes only (both p<0.01). Having at least one comorbid chronic condition was associated with lower odds of abstinence in three of the models (all p<0.05). Table 4 ORs from adjusted logistic models of multiple imputation quit rates at 6 and 12 months, N=1785 6-Month survey outcomes 12-Month survey outcomes Variable Did not smoke in the last 7 days Did not smoke in the last 30 days Did not smoke in the last 7 days Did not smoke in the last 30 days Randomisation groups Standard plus TEQ-10 vs standard 1.15 (0.83 to 1.59) 1.14 (0.85 to 1.54) 1.07 (0.82 to 1.41) 0.96 (0.71 to 1.30) Standard plus TEQ-20 vs standard 1.00 (0.71 to 1.42) 1.01 (0.74 to 1.37) 0.87 (0.64 to 1.19) 0.75 (0.52 to 1.09) Number of programme counselling calls Planned+participant−initiated 1.10 (1.02 to 1.18) 1.10 (1.02 to 1.19)* 1.12 (1.02 to 1.22)* 1.10 (1.02 to 1.19)* Demographics Gender Female vs male 0.92 (0.70 to 1.21) 1.00 (0.80 to 1.25) 1.17 (0.91 to 1.49) 1.16 (0.92 to 1.46) Age 1.02 (1.01 to 1.03)* 1.02 (1.00 to 1.03) 1.01 (0.99 to 1.02) 1.01 (0.99 to 1.02) Race African–American vs Caucasian 1.32 (0.89 to 1.96) 1.41 (0.91 to 2.21) 1.16 (0.75 to 1.80) 1.12 (0.72 to 1.76) Other vs Caucasian 0.73 (0.34 to 1.56) 0.72 (0.32 to 1.66) 1.09 (0.55 to 2.16) 0.98 (0.53 to 1.81) Education High school or less vs more than high school 1.12 (0.84 to 1.50) 1.05 (0.77 to 1.43) 0.86 (0.65 to 1.13) 1.01 (0.76 to 1.33) Comorbidities Any chronic comorbidity 0.69 (0.51 to 0.94)* 0.65 (0.46 to 0.92)* 0.72 (0.53 to 0.98)* 0.76 (0.56 to 1.03) Tobacco use Cigarettes per day 0.98 (0.97 to 0.99)* 0.99 (0.97 to 1.00) 0.98 (0.97 to 1.00) 0.99 (0.98 to 1.00) Time to first cigarette 5 min vs all others 0.92 (0.68 to 1.24) 1.10 (0.82 to 1.48) 0.88 (0.64 to 1.20) 0.85 (0.65 to 1.12) Number of quit attempts 2–5 vs 0–1 0.96 (0.69 to 1.34) 0.98 (0.75 to 1.29) 0.80 (0.58 to 1.10) 0.93 (0.69 to 1.24) 6+ vs 0–1 0.88 (0.57 to 1.35) 0.85 (0.56 to 1.28) 0.68 (0.47 to 0.99)* 0.79 (0.55 to 1.13) Social contact with smokers Work or home vs all others 0.74 (0.56 to 0.97)* 0.95 (0.73 to 1.24) 0.98 (0.74 to 1.30) 0.89 (0.68 to 1.17) Scale scores Motivation to quit 1.24 (1.12 to 1.36)* 1.24 (1.11 to 1.39)* 1.22 (1.11 to 1.34)* 1.23 (1.12 to 1.35)* Depression 0.87 (0.78 to 0.96) 0.88 (0.80 to 0.97) 0.94 (0.83 to 1.06) 0.89 (0.80 to 0.99)* All variables shown were included in each model. Estimates for each model were obtained by combining results across 10 multiply imputed data sets; 95% CIs are shown in parentheses. p<0.05; p<0.01; p<0.001. TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.TIME TO RELAPSE:\nThere was no significant association between time to relapse and randomisation group (table 5). Other factors related to time to relapse included number of counselling calls, having comorbid health condition, number of quit attempts, motivation to quit and depression. Higher number of counselling calls and higher levels of motivation to quit were associated with being less likely to relapse sooner (HR=0.87, p<0.001; HR=0.84, p<0.001, respectively). By contrast, participants reporting higher levels of depression were more likely to relapse sooner (HR=1.07, p=0.02). Compared to those with no chronic comorbidities, participants reporting one or more chronic comorbidities were more likely to relapse sooner (HR=1.29, p=0.04). Those reporting six or more quit attempts were also more likely to relapse sooner compared to those with 0–1 attempts (HR=1.32, p=0.04). Table 5 HRs from adjusted proportional hazard models of time to relapse, N=1785 Variable HR (95% CI) p Value Randomisation groups Standard plus TEQ-10 vs standard 0.85 (0.69 to 1.04) 0.1171 Standard plus TEQ-20 vs standard 1.05 (0.85 to 1.31) 0.6282 Number of programme counselling calls Planned+participant−initiated 0.87 (0.82 to 0.92)* <0.0001 Demographics Gender Female vs male 0.90 (0.75 to 1.09) 0.2838 Age 1.00 (0.99 to 1.01) 0.5278 Race African–American vs Caucasian 0.97 (0.75 to 1.26) 0.8400 Other vs White 1.11 (0.67 to 1.84) 0.6762 Education High school or less vs more than high school 1.06 (0.87 to 1.30) 0.5368 Comorbidities Any chronic comorbidity 1.29 (1.01 to 1.64)* 0.0430 Tobacco use Cigarettes per day 1.01 (0.99 to 1.02) 0.0639 Time to first cigarette 5 min vs all others 1.08 (0.88 to 1.34) 0.4430 Number of quit attempts 2–5 vs 0–1 1.14 (0.90 to 1.43) 0.2657 6+ vs 0–1 1.32 (1.02 to 1.72)* 0.0345 Social contact with smokers Work or home vs all others 0.99 (0.80 to 1.24) 0.9713 Scale scores Motivation to quit 0.84 (0.79 to 0.90)*** <0.0001 Depression 1.07 (1.01 to 1.13)* 0.0198 All variables shown were included in each model. Estimates for each model were obtained by combining results across 10 multiply imputed data sets; 95% CIs are shown in parentheses. p<0.05; p<0.01; p<0.001. TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.USING IVR TO IDENTIFY RISK:\nFigure 2 presents quit outcomes for TEQ-10 and TEQ-20 groups (separately in panel A and combined in panel B) according to their positive screen status (≥1 positive screen vs no positive screen); 70.4% in TEQ-10 and 76.1% in TEQ-20 had ≥1 positive screen during the study. Compared with participants who screened positive in either TEQ group, participants who did not screen positive were more likely to be abstinent at 6 (OR=1.69, p=0.01 for 7-day point prevalence; OR=1.77, p≤0.001 for 30-day point prevalence) and 12 months (OR=1.47, p=0.03 for 7-day point prevalence; OR=1.50, p=0.01 for 30-day point prevalence). Figure 2Abstinence rates for intervention and positive screen groups, N=1785. Estimates for each model were obtained by combining results across 10 multiple-imputed data sets. Error bars indicate 95% CIs. (A) Displays results for the TEQ-10 and TEQ-20 groups separately. (B) Displays data for the two TEQ-groups combined. '1+ positive screen' is defined as exceeding the predetermined risk threshold on any of the IVR assessment questions (topics: lapses, cravings, negative effect, self-efficacy, and motivation to remain quit) on any IVR assessment call. IVR, interactive voice response; TEQ-10, Technology Enhanced Quitline-10; TEQ-20, Technology Enhanced Quitline-20.\n\nBODY.RESULTS.SATISFACTION WITH QFL AND THE IVR PROTOCOL:\nSatisfaction was measured at 6 months after enrolment. Participants completing the 6-month survey (n=1091, 61.1%) were generally satisfied with the overall QFL programme and the counselling they received (96% and 98%, respectively, were somewhat satisfied, satisfied, or very satisfied at 6 months). A similar percentage (98%) would recommend the programme to others. There were no differences in QFL programme satisfaction between the three study groups. Compared to TEQ-10 participants, those receiving TEQ-20 were more likely to report the number of relapse risk assessments were too many (36% vs 23%, p≤0.001) and also were marginally more likely to agree that the risk assessments took too much time (28% vs 23%, p=0.09). The majority of participants reported it was easy to answer questions through the IVR system (95%), that the system was helpful (87%), and that they would recommend the IVR system to others trying to stay quit (86%), with no significant differences between the TEQ-10 and TEQ-20 groups.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial investigating the use of an automated, IVR-supported protocol to identify risk and prevent smoking relapse among recently quit tobacco users enrolled in the QFL programme, there were no differences in tobacco abstinence rates between the control (standard QFL) and technology-enhanced (IVR-delivered risk assessments and transfer for counselling) groups at 6-month and 12-month follow-up. Although the risk assessment and transfer protocols did not yield better abstinence rates, the IVR-delivered screenings did successfully identify participants who were less likely to be quit at follow-up. Participants who did not screen positive during the relapse risk assessments were 77% more likely to be abstinent at 6-month follow-up. We tested two risk screening and transfer protocols of varying intensities. The more intensive screening protocol with 20 IVR-delivered assessments did not demonstrate any benefit over the 10-assessment group, and the TEQ-20 respondents were more likely to indicate there were too many IVR assessments. In addition, we explored whether the TEQ intervention was more effective for certain populations in this study with regard to quit outcomes, by testing interaction effects, but did not identify any significant moderating relationships. There are several possible explanations for why the intervention did not reduce relapse rates. The TEQ interventions were designed to immediately transfer participants who met risk thresholds for tobacco counselling to target the identified relapse risk. About three-quarters (73.3%) of the TEQ participants were identified as being at risk at least one time over the 8-week intervention period. Having a positive screen was predictive of relapse; however, it is possible that other risk factors are more predictive of risk than those included in the assessment. Also, participants identified as at risk by the IVR assessments and automatically transferred to a coach failed to remain on the line to receive cessation counselling at the anticipated rate. That is, less than one third of those in the TEQ arms completed an IVR-transferred counselling call and 41.3% of those with a positive risk screen completed one or more IVR-transferred counselling calls, resulting in participants in the TEQ conditions completing only 0.41 calls, on average, more than the planned programme calls from the standard programme. Thus, it is possible that we failed to observe an effect because we did not increase the actual treatment exposure much above the base rate of calls. It remains unclear why some callers did not accept these additional calls when the satisfaction data showed positive perceptions of the IVR automated assessment system (87% felt it was helpful when they need to talk to a Quit Coach; 86% would recommend). Most callers were still receiving planned standard programme calls at the time of their risk assessments; perhaps callers who had recently spoken to a coach did not feel they needed another call at that time. Future studies should assess reasons for lack of counselling uptake and consider an automated system that would allow participants to schedule a call in the near future or would initiate outbound calls to participants identified as at risk who do not immediately transfer to a counsellor. The study had high quit outcomes, in spite of the fact that the TEQ intervention did not significantly improve outcomes. The 61% respondent and 38% ITT penalised imputation (missing=smoking) 30-day point prevalence quit rates at 6 months in the standard treatment group indicated that tobacco users who receive a multiple-call phone counselling programme, have access to cessation medication benefits, and successfully achieve at least a 24 h abstinence period early in treatment do quite well. These quit rates are high compared to studies focusing on all commercial quitline enrolees (eg, 34.3–41.1% responder quit rate at 6 months27\n28). The relatively strong performance and engagement in standard treatment for this study may have made achieving improvements with a low intensity relapse prevention intervention even more challenging. This finding also aligns with previous recommendations that increasing quit attempts may be one of the most important factors for increasing cessation at the population level,29 and demonstrates the importance of achieving at least 24 h of abstinence. More counselling calls completed, higher motivation to quit, lower depression scores, and not having chronic health condition were consistently related to greater likelihood of being abstinent at follow-up. These variables were also associated with time to relapse; additionally, callers with a greater number of previous quit attempts (6+) were more likely to relapse sooner. These findings are consistent with previous quitline studies which have demonstrated the importance of programme engagement (ie, number of calls completed15\n30\n31). Callers in this study had a high motivation to quit (9 out of 10, on average); a previous study has linked high motivation to quit with making a quit attempt but not with likelihood of remaining quit.32 Moreover, previous work has identified that callers with depressive symptoms33 and chronic health conditions31 may have more difficulty quitting. Dependence level (time to first use and cigarettes per day) was not consistently related to outcomes in this study, which differs from previous literature that has often linked baseline dependence and outcomes.31\n32 Compared with other behavioural relapse prevention research, strengths of this study included a relatively large sample size, use of an innovative and potentially cost-effective technology that could be disseminated to large populations if shown to be effective, and attempting to connect those at risk to immediate counselling. Most previous behavioural relapse prevention studies have focused on skills training and have not yielded significant effects.7 As noted by Hajek et al,7 future relapse prevention research efforts may be best applied in examining new and alternative approaches to those previously studied. One recent small pilot study examined extended IVR assessments following varenicline treatment, and also did not find significant effects for the extended IVR group.12 That article did not report on whether those who screened positive during IVR assessments were more likely to have returned to smoking at follow-up, and likely had too small of sample size to meaningfully do so. Additionally, the McNaughton et al's12 study included an intensive IVR contact schedule with 80 contacts over 40 weeks; low IVR assessment completion rates (37% of IVR calls and 16% of assessments were completed) in that study align with our findings that more contact is not necessarily better. Identifying the most effective and cost-effective number of contacts should continue to be a focus in future studies using IVR technology. The response rates to our 6-month and 12-month outcome surveys were 61% and 59%, respectively, which may limit the validity of our findings. Multiple imputation, a preferred method for ITT analysis, was used to reduce potential non-response bias, and the findings from these analyses agreed closely with results from a sensitivity analysis using respondent-only data. Another potential limitation to our study design is the lack of biochemical verification of abstinence, particularly in light of the high reported abstinence rates. However, our study procedures were consistent with recommendations of the SRNT Subcommittee on Biochemical Verification,34 and the results should be considered with respect to this. Additionally, we have no reason to believe there was a systematic bias in reporting abstinence across groups. Third, the protocol aimed for IVR-triggered counselling calls to focus on the specific risk factor(s) identified by the IVR assessment; all participants received empirically based support at the time of need, but not all calls were focused on the identified risk factor(s). Finally, as with other research on prevention of smoking relapse, the time frame for intervention and data collection poses limitations. The IVR-delivered risk assessments in this study were limited to the first 8 weeks following successful abstinence. Although previous research has identified the first weeks as being the greatest risk for relapse, callers also relapse at later dates. Ongoing plans for prevention of relapse, or risk intervention, may be needed; future research may be able to identify those in need of ongoing relapse risk monitoring and intervention. Augmenting tobacco quitline treatment with IVR-delivered relapse risk screening assessments was acceptable to participants, and successfully identified recently quit tobacco users who may be in need of more intensive or different intervention. More research is needed to identify how to engage at-risk participants in additional treatment. Using a technology-based screening for relapse risk to connect recent tobacco users to cessation counselling at the time of risk could offer a scalable, cost-effective approach for delivering tailored services to those in need, if future research can identify the appropriate services to deliver at that time of need.\n\nQuestion:** Compared to Standard quitline treatment what was the result of Technology Enhanced Quitline-10 and Technology Enhanced Quitline-20 on Programme engagement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1028	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: A randomised controlled trial to prevent smoking relapse among recently quit smokers enrolled in employer and health plan sponsored quitlines\n\n ABSTRACT.OBJECTIVE:\nTo test adding an interactive voice response (IVR)-supported protocol to standard quitline treatment to prevent relapse among recently quit smokers.\n\nABSTRACT.DESIGN:\nParallel randomised controlled trial with three arms: standard quitline, standard plus technology enhanced quitline with 10 risk assessments (TEQ-10), standard plus 20 TEQ assessments (TEQ-20).\n\nABSTRACT.SETTING:\nQuit For Life (QFL) programme.\n\nABSTRACT.PARTICIPANTS:\n1785 QFL enrolees through 19 employers or health plans who were 24+ h quit.\n\nABSTRACT.INTERVENTIONS:\nQFL is a 5-call telephone-based cessation programme including medications and web-based support. TEQ interventions included 10 or 20 IVR-delivered relapse risk assessments over 8 weeks with automated transfer to counselling for those at risk.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nSelf-reported 7-day and 30-day abstinence assessed at 6-month and 12-month post-enrolment (response rates: 61% and 59%, respectively). Missing data were imputed.\n\nABSTRACT.RESULTS:\n1785 were randomised (standard n=592, TEQ-10 n=602, TEQ-20 n=591). Multiple imputation-derived, intent-to-treat 30-day quit rates (95% CI) at 6 months were 59.4% (53.7% to 63.8%) for standard, 62.3% (57.7% to 66.9%) for TEQ-10, 59.4% (53.7% to 65.1%) for TEQ-20 and 30-day quit rates at 12 months were 61.2% (55.6% to 66.8%) for standard, 60.6% (56.0% to 65.2%) for TEQ-10, 54.9% (49.0% to 60.9%) for TEQ-20. There were no significant differences in quit rates. 73.3% of TEQ participants were identified as at-risk by IVR assessments; on average, participants completed 0.41 IVR-transferred counselling calls. Positive risk assessments identified participants less likely (OR=0.56, 95% CI 0.42 to 0.76) to be abstinent at 6 months.\n\nABSTRACT.CONCLUSIONS:\nStandard treatment was highly effective, with 61% remaining abstinent at 12 months using multiple imputation intent-to-treat (intent-to-treat missing=smoking quit rate: 38%). TEQ assessments identified quitters at risk for relapse. However, adding IVR-transferred counselling did not yield higher quit rates. Research is needed to determine if alternative designs can improve outcomes.\n\nABSTRACT.TRIAL REGISTRATION NUMBER:\nNCT00888992.\n\nBODY:\nStrengths and limitations of this studyFirst large randomised controlled trial to examine the use of interactive voice response (IVR) technology for prevention of smoking relapse.Large sample of participants recruited from employer and health plan quitline programmes serving tobacco users across the USA.Protocol used an innovative and potentially cost-effective technology to connect those at risk for relapse to immediate counselling.We compared two risk assessment intensities over the first 8 weeks following successful abstinence.Although participants rated the IVR system positively, fewer accepted immediate risk-focused counselling than anticipated; thus, the increase in treatment exposure was small. Smoking continues to be the leading preventable cause of premature death and disease in the USA and worldwide.1\n2 Quitting tobacco is one of the most important steps a tobacco user can take to improve their health.3 Free publicly (state and government) and privately (eg, employer and health plan) funded telephone-based tobacco cessation quitlines are available throughout the USA and increasingly around the world to help tobacco users quit. With the advent of the Affordable Care Act in the USA, telephone-based tobacco cessation services offer an important resource to ensure that tobacco users have access to the empirically supported tobacco treatments that are required components of coverage. Although extensive evidence exists regarding the efficacy and cost-effectiveness of tobacco cessation quitlines,4–6 as with other behavioural and pharmacological tobacco treatment options, little is known about how best to intervene with callers at the time of greatest risk for relapse. A recent Cochrane Review concluded that previously tested behavioural relapse prevention interventions, which primarily included skills training or extended therapeutic contact, did not provide additional benefit over no treatment or intervention without a relapse prevention component.7 Survival studies have identified that the highest relapse risk, on average, is in the first 2 weeks after a quit attempt; however, there is considerable between-individual and within-individual variability in risk-related symptom patterns.8 Relapse prevention interventions may be most effective if provided at the time of relapse risk given the multifaceted and individualised nature of withdrawal and environmentally induced relapse risks over time.8 Interactive voice response (IVR) technology offers a resource-efficient solution for connecting tobacco users with relapse prevention interventions at the time of need, especially those already enrolled in phone-based tobacco cessation treatment. IVR is increasingly incorporated into some tobacco treatment protocols,9\n10 and has been used in chronic disease management, posthospital discharge management, medication compliance monitoring, and in a small number of addiction and depression self-help interventions.11 IVR has been piloted as a smoking relapse prevention tool following a single group counselling call and 12 weeks of varenicline,12 but was insufficiently powered to draw meaningful conclusions about the effectiveness of the nine-call and nurse call-back intervention. The purpose of this present study is to examine the effectiveness of augmenting standard multisession tobacco quitline treatment with repeated IVR assessments to monitor recent quitters' relapse risk, and transfer those at risk to a Quit Coach for a brief, focused, intervention targeting the identified relapse trigger. We hypothesised that smokers receiving IVR risk assessments during the first 2 months after quitting would be more likely to stay quit than those receiving standard quitline treatment, and that more frequent assessments (20 vs 10) would be more beneficial.\n\nBODY.METHODS.STUDY DESIGN:\nIn this parallel randomised controlled trial, tobacco users enrolled in the Quit For Life (QFL) programme who achieved abstinence for at least 24 h after their quit date were randomised into one of three study groups: (1) standard treatment, (2) Technology Enhanced Quitline-10 (TEQ-10): standard treatment plus 10 IVR-delivered relapse risk assessments which triggered a transfer to a Quit Coach for participants exceeding risk thresholds and (3) Technology Enhanced Quitline-20 (TEQ-20): same as the TEQ-10 condition except with 20 relapse risk assessments rather than 10. Participants were randomised using blocked randomisation to ensure similar group sizes throughout the study; every nine participants within each employer or health plan contract were randomly assigned with an allocation ratio for the three groups of 3:3:3. These random allocation tables were generated by the study management team and integrated into the QFL computer system where they were not accessible to coaches or participants. Once study eligibility was confirmed, the Quit Coach clicked a 'Randomise' button and the system automatically assigned the participant to the group listed in the next available cell of the allocation table. The planned and final sample size was 1785 and was determined a priori to achieve at least 80% power to detect 30-day point prevalence quit rate differences of 8% between any pair of three arms for intent-to-treat (ITT) analyses, including the traditional penalised imputation approach in which non-responders to data collection are considered relapsed13 and the state-of-the-art multiple imputation method14 (assuming quit rates of 29.6%, 37.6% and 45.6% at 6 months and 26.6%, 34.6% and 42.6% at 12 months for standard care, TEQ-10 and TEQ-20, respectively; n=595) and of 10% for a responder analysis between standard care and either intervention at 6 or 12 months (assuming quit rates of 52.1% standard care, 62.1% TEQ-10, 62.1% TEQ-20; assuming 25% attrition, with 446 responders per arm). The primary analysis using ITT multiple imputation has slightly greater than 80% power because, like ITT using penalised imputation (missing=smoking), it uses all persons with baseline data. However, compared with penalised imputation, or responder-only analysis, multiple imputation ITT uses more information and produces results with greater power, less bias, and greater accuracy.13\n14 Participants gave informed consent prior to study enrolment and received a US$25 gift card for completed 6-month and 12-month follow-up surveys (potential for US$50 total).\n\nBODY.METHODS.PARTICIPANTS:\nTobacco users were eligible for the study if they had enrolled in the QFL programme between April 2010 and October 2012 through 1 of 19 employers or health plans who offered QFL as part of their benefits package. Because the purpose of this study was to examine the potential benefit of IVR assessments, and their triggering of counselling at the point of need to reduce relapse, tobacco users were screened for study criteria and invited to participate after reporting they had been quit for 24 h or more after their quit date. This typically occurred during their second or third call (their quit date call or the call after) of the five-call programme. Additional eligibility criteria included being English-speaking, 18 years of age or older, and having access to a touch-tone phone. Tobacco users were excluded if they exclusively used smokeless tobacco, were actively participating in another tobacco cessation programme, had previously enrolled in the QFL programme during the past 6 months, or had limited phone access (eg, incarceration). Of the 3723 tobacco users who received the study offer, 1840 (49.4%) agreed to participate and 1785 completed the baseline survey and were randomised to one of the three study groups (figure 1). Figure 1CONSORT Diagram. 36 participants did not receive all of their relapse risk assessments due to a programming error in the interactive voice response (IVR) code.\n\nBODY.METHODS.THE QFL PROGRAMME:\nQFL, operated by Alere Wellbeing (formerly Free & Clear), has been commercially available for nearly 30 years, and its effectiveness and cost-effectiveness has been demonstrated in various studies.5\n15–19 The QFL programme includes five counselling calls (an initial assessment and planning call plus four additional proactive outbound calls from an expert Quit Coach). Quit Coaches are required to have a bachelor's degree in a related field, complete more than 200 h of training, and receive ongoing supervision and feedback. The call schedule and content is tailored to each participant's needs. The default call schedule includes the initial planning and assessment call, a quit date call (QDC), a quit date follow-up call 7 days after the QDC, and two additional follow-up calls that take place approximately every 3 weeks after the previous call. Participants are also encouraged to call in for support as needed (ie, participant-initiated inbound calls). Calls vary in length: the planning and assessment call is 25–30 min, while other calls are 15–20 min. Calls focus on creating a quit plan, developing problem-solving and coping skills, identifying social support, and using cessation medications to achieve and maintain abstinence. Participants may receive over-the-counter nicotine replacement products directly via mail (or other prescription cessation medications depending upon their cessation benefit with their employer or health plan). They also receive a printed quit guide, and access to Web Coach, an online interactive web-based programme designed to complement the phone programme.\n\nBODY.METHODS.IVR INTERVENTION:\nIn the two TEQ groups, participants were contacted for relapse risk assessments through automated IVR calls over their first 8 weeks postquit. Two intensities of IVR monitoring were examined. TEQ-10 participants were contacted twice weekly for the first 2 weeks, then weekly for 6 weeks. TEQ-20 participants were contacted daily for the first 2 weeks, then weekly for 6 weeks. An IVR service contractor programmed and delivered the risk assessments (approximately 5 min), which included questions to identify relapse risk on five factors: lapses, cravings, negative affect, self-efficacy and motivation to remain quit. An algorithm was used to flag participants as 'at risk' if they answered any of the screening questions over an established threshold, based on previous research.20–22 Participants who exceeded the threshold were then transferred directly to a Quit Coach for a brief intervention (approximately 15 min) specifically addressing the risk factor(s) that triggered their transfer. Intervention fidelity was monitored by study staff and investigators. Randomly sampled recordings of IVR-triggered telephone counselling sessions were rated for compliance with the study protocol (the primary criterion being whether the counsellor focused the call on identified relapse risk(s)) by two independent reviewers (a study staff member and a Quit Coach supervisor). Reviews revealed some Quit Coaches did not receive information about the risk factor that triggered a participant's transfer due to technological issues. These programming errors were corrected by the IVR vendor. In these circumstances, participants still received empirically based tobacco cessation support at the time of need. As part of quality monitoring, any protocol deviations were addressed with individual feedback from Quit Coach supervisors and ongoing training for all Quit Coaches.\n\nBODY.MEASURES.BASELINE MEASURES:\nDuring registration and the first Quit Coach call, participants completed standard assessment questions regarding demographic characteristics (age, gender, health comorbidities) and tobacco use (tobacco type, time to first use, cigarettes per day, number of previous quit attempts, social contact with smokers). After study recruitment, participants completed an additional baseline measure assessing age, race, ethnicity, education, depressive symptoms (PHQ-2; 2-item measure21), and stress (Perceived Stress Scale; 4-item measure23).\n\nBODY.MEASURES.IVR-POSITIVE SCREENS AND PROGRAM CALL COMPLETION:\nThe IVR system stored the number of relapse risk assessments participants answered, participants' responses to the relapse risk questions, and the number of IVR assessments on which a participant had a positive risk screen. Counselling calls completed as a result of a positive IVR screen and successful transfer to a Quit Coach (ie, IVR-transferred counselling calls) were tracked in addition to standard programme calls (5 planned calls plus participant-initiated inbound calls).\n\nBODY.MEASURES.OUTCOMES MEASURED AT 6 AND 12 MONTHS:\nAt 6 and 12 months after randomisation, participants completed telephone interviewsi administered by outcomes evaluators from the Indiana University Center for Survey Research who were blind to study condition to measure abstinence. All participants rated their satisfaction with the QFL service, and those in the TEQ groups were asked their opinions of the IVR system during the 6-month survey. When participants could not be reached after repeated phone attempts, we also mailed a brief paper survey with only the smoking abstinence questions. Survey response rates were 61% and 59% at 6 and 12 months, respectively. The primary study outcomes were quit rates at 6 and 12 months, defined as 7-day and 30-day self-reported point prevalence abstinence measured by the question, 'In the last [7/30] days, have you smoked a cigarette, even a puff?'. Time to relapse was examined as a secondary outcome and was identified using three questions: 'Since [end of two-week grace period], have you ever smoked at least a part of a cigarette on 7 days in a row?'; 'Since [end of two-week grace period], have you ever smoked any in each of two consecutive weeks (at least 1 day for 2 weeks in a row)?', and [if yes to either of the 2 previous questions] 'What was the first day of that 7-day or two-week period that you smoked?'.16\n\nBODY.MEASURES.STATISTICAL ANALYSES:\nMissing values on all 6-month and 12-month outcomes were imputed using the state-of-the-art imputation method called 'multiple imputation'24 with sequential regression.25 Multiple imputation allows all cases (N=1785) to be included in the analysis. Two imputation models were performed: one for 7-day and one for 30-day point prevalence abstinence. With this approach, variables with no missing values served as independent variables. The variable with the least amount of missing data was imputed first, and used as the dependent variable. Once imputation was carried out, the next variable with the least amount of missing data was imputed using all variables with non-missing values as independent variables including the variable imputed on the previous step. This cycle continued until all missing values were imputed resulting in a series of regressions, hence the name sequential regression. Variables used to provide information for imputation (and to be imputed themselves if missing) included intervention group (no data missing), baseline characteristics listed in table 1 (with the exception of years of tobacco use and stress, due to high correlations with age and depression, respectively), and number of planned calls plus participant-initiated inbound counselling calls completed. These variables had a minimal amount of missing data with, at most, 3.5% missing for the motivation variable. Abstinence outcomes measured at both 6 and 12 months were included in each imputation model and had the greatest amount of missing data. Ten multiple-imputed data sets were generated and analysed. Table 1 Baseline characteristics (N=1785) Variable Overall (N=1785) Standard (N=592) Standard plus TEQ-10 (N=602) Standard plus TEQ-20 (N=591) Demographics Age, mean (SD) 43.4 (11.9) 43.3 (12.2) 44.0 (11.5) 43.0 (12.0) Gender, N (%) Female 967 (54.2) 321 (54.2) 326 (54.1) 320 (54.2) Male 818 (45.8) 271 (45.8) 276 (45.9) 271 (45.8) Race, N (%) Caucasian 1489 (83.4) 497 (84.0) 501 (83.2) 491 (83.1) African-American 204 (11.4) 63 (10.6) 71 (11.8) 70 (11.8) Other 51 (2.9) 16 (2.7) 19 (3.2) 16 (2.7) Missing 43 (2.3) 16 (2.7) 11 (1.8) 14 (2.4) Education, N (%) High school or less 667 (37.4) 229 (38.7) 225 (37.4) 213 (36.0) More than high school 1117 (62.6) 363 (61.3) 376 (62.6) 378 (64.0) Comorbidities, N (%) Asthma 176 (9.9) 62 (10.5) 61 (10.1) 53 (9.0) COPD 108 (6.0) 39 (6.6) 32 (5.3) 37 (6.3) CAD 75 (4.2) 27 (4.6) 25 (4.2) 23 (3.9) Diabetes 138 (7.7) 53 (8.9) 46 (7.6) 39 (6.6) Any chronic comorbidity 395 (22.1) 136 (23.0) 136 (22.6) 123 (20.8) Tobacco use Time to first cigarette, N (%), min 5 539 (30.2) 165 (27.9) 197 (32.7) 177 (30.0) 6–30 618 (34.6) 213 (36.0) 201 (33.4) 204 (34.5) 31–60 285 (16.0) 89 (15.0) 101 (16.8) 95 (16.1) >60 289 (16.2) 105 (17.7) 88 (14.6) 96 (16.2) Missing 54 (3.0) 20 (3.4) 15 (2.5) 19 (3.2) Cigarettes per day, mean (SD) 16.8 (9.0) 16.8 (9.1) 17.2 (8.9) 16.4 (9.1) Number of quit attempts, N (%) 0–1 377 (21.1) 116 (19.6) 127 (21.1) 134 (22.7) 2–5 1033 (57.9) 371 (62.7) 335 (55.7) 327 (55.3) 6+ 347 (19.4) 97 (16.4) 127 (21.3) 122 (20.6) Missing 28 (1.6) 8 (1.4) 12 (2.0) 8 (1.4) Tobacco use ≥20 years, N (%) Yes 1098 (61.5) 361 (61.0) 383 (63.6) 354 (59.9) No 671 (37.6) 227 (38.3) 211 (35.1) 233 (39.4) Missing 16 (0.9) 4 (0.7) 8 (1.3) 4 (0.7) Social contact with smokers, N (%) No 470 (26.3) 146 (24.7) 179 (29.7) 145 (24.5) Work 572 (32.0) 192 (32.4) 188 (31.2) 192 (32.5) Home 342 (19.2) 122 (20.6) 104 (17.3) 116 (19.6) Both work and home 344 (19.3) 112 (18.9) 111 (18.4) 121 (20.5) Missing 57 (3.2) 20 (3.4) 20 (3.3) 17 (2.9) Scale scores Motivation to quit, mean (SD) 9.1 (1.3) 9.0 (1.3) 9.0 (1.2) 9.1 (1.2) Depression, mean (SD) 1.0 (1.3) 1.0 (1.3) 1.0 (1.3) 1.0 (1.3) Perceived stress, mean (SD) 4.3 (2.8) 4.3 (2.9) 4.2 (2.8) 4.5 (2.8) Defined as having asthma or COPD or CAD or diabetes. CAD, coronary artery disease; COPD, chronic obstructive pulmonary disease; TEQ-10, Technology Enhanced Quitline-10; TEQ-20, Technology Enhanced Quitline-20. Logistic regression models were used to model intervention efficacy on the 6-month and 12-month outcomes of abstinence, while adjusting for theoretically important potentially confounding baseline covariates.26 There were four main outcomes (7-day and 30-day point prevalence quit rates assessed at 6 and 12 months) and each was analysed with a separate logistic regression model. The multiple imputation quit rate results were our primary outcome metric. However, outcomes were reported using three methods: (1) for all survey respondents (responder analysis), (2) using penalised imputation reporting (assumes non-respondents are treatment failures) which is the traditional ITT analysis used in the smoking literature and (3) with results imputed for participants with missing data using the state-of-the-art multiple imputation method. Although ITT outcomes using penalised imputation are commonly reported in cessation trials, methodological research, including simulation studies, have shown that multiple imputation ITT uses more information and produces greater power, less bias, and more accuracy compared with simpler ad hoc methods for handling missing data such as traditional penalised imputation ITT, or responder-only analysis.13\n14 Missing values for relapse date were imputed using the procedures described above. Using this relapse date and the baseline date, proportional hazards regression was used to examine factors associated with time to relapse. The variables representing number of calls (table 2) were generally skewed to the right with a large number of zeroes. These data were complete and did not require imputation. To compare study groups on these count variables, a generalised linear model with log link function and negative binomial distribution was used. Six-month satisfaction data were also analysed (without imputation) to determine levels of satisfaction with the QFL programme and IVR protocol. The satisfaction variable was not imputed since it was not a primary outcome. Satisfaction comparisons between intervention groups were made using a χ2 test. Mplus software for Windows (V.7.2) was used to generate imputed data and PROC MIANALYZE from SAS/STAT software (V.9.3) was used to pool results and analyse the imputed data sets. All other statistical comparisons were performed using SAS/BASE and SAS/STAT software for Windows (V.9.3). Table 2 Descriptives for number of phone calls (N=1785) Variable Overall (N=1785) Standard (N=592) Standard plus TEQ-10 (N=602) Standard plus TEQ-20 (N=591) p Value (1) Planned programme counselling calls (1–5), mean (SD); range 3.29 (1.09); 1–5 3.29 (1.09); 1–5 3.32 (1.09); 1–5 3.25 (1.08); 1–5 0.8085 (2) Participant-initiated inbound calls, mean (SD); range 0.38 (1.05); 0–14 0.37 (0.92); 0–8 0.40 (1.13); 0–14 0.37 (1.08); 0–12 0.9082 ≥1 vs 0, N (%) 284 (15.9) 99 (16.7) 96 (16.0) 89 (15.1) 0.7361† (1+2) Sum of planned and participant-initiated inbound calls, mean (SD); range 3.67 (1.53); 2–17 3.66 (1.48); 2–13 3.72 (1.62); 2–17 3.62 (1.48); 2–13 0.6851 (3) IVR-transferred counselling calls, mean (SD); range 0.41 (0.75); 0–6 N/A 0.39 (0.72); 0–6 0.43 (0.79); 0–6 0.2791‡ ≥1 vs 0, N (%) 361 (30.3) N/A 175 (29.1) 186 (31.5) 0.3665†‡ (1+2+3) Sum of all calls, mean (SD); range 3.94 (1.71); 2–19 3.66 (1.48); 2–13 4.11 (1.82); 2–19 4.06 (1.77); 2–17 <0.0001 p Value obtained from generalised linear model for a count outcome except where indicated. †p Value obtained from χ 2 test. ‡p Value is for comparison between TEQ-10 and TEQ-20 groups. IVR, interactive voice response; TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.PARTICIPANTS:\nBaseline characteristics across the three intervention groups are shown in table 1. Overall, the average age of study participants was 43 years (range 18–85). A little over half (54%) were women. A majority of the sample was Caucasian (83%) and reported having a high school education or more (62%). Just under a quarter of the sample reported having ≥1 chronic comorbidity (22%). The average number of reported cigarettes used per day was 17 (range 0–60) with about two-thirds of the sample reporting having had a cigarette within 30 min from the time they wake in the morning. About 20% of the sample reported 0 or one quit attempts, with a similar percentage reporting six or more quit attempts. A little over 60% reported using tobacco for 20 or more years, and about three-quarters reported having contact with smokers at work, home, or both. Overall, participants reported feeling motivated to quit smoking, with an average rating of 9 on a 1–10 scale (1=low, 10=high). The average PHQ-2 depression score was 1.0 (possible range 0–6, with high scores indicating higher levels of depression,21 and the average perceived stress score was 4.3 (possible range 0–16, with higher scores indicating higher perceived stress.23 At the time of study offer, 56.5% of participants had been quit for 1–6 days, 40% had been quit for 7–29 days, and 3.5% had been quit for 30 days or more.\n\nBODY.RESULTS.PROGRAMME ENGAGEMENT AND POSITIVE RISK SCREENS:\nProgramme engagement was measured as the number of counselling calls completed by participants:1 planned programme counselling calls,2 participant-initiated inbound calls, or3 IVR-transferred counselling calls (table 2). Overall, the average number of total calls completed was 3.9 (SD=1.7; range 2–19). There was a statistical difference between groups; the TEQ-10 and TEQ-20 groups completed slightly more calls than the standard study group due to the additional IVR-transferred counselling calls they received after a positive screen (p<0.001). There were no statistical differences between participant-initiated (p=0.91) or planned programme calls completed (p=0.81). Also, there was no statistical difference in IVR-transferred counselling calls between the TEQ-10 and TEQ-20 groups (p=0.28). There was a statistical difference in the number of positive screens between the two intervention groups, with TEQ-20 having slightly more positive screens than TEQ-10 (on average, 1.52 (SD=1.66) for TEQ-10 and 1.82 (SD=1.99) for TEQ-20, p=0.003). The percentage of one or more positive screens was also larger in the TEQ-20 group (76% vs 70%; p=0.03).\n\nBODY.RESULTS.SIX-MONTH AND 12-MONTH OUTCOMES:\nSeven-day and 30-day point prevalence abstinence rates at 6-month and 12-month follow-up are shown in table 3. As aforementioned, outcomes are reported using three methods: (1) for all survey respondents (responder analysis), (2) using a crude ITT analysis based on penalised imputation reporting (assumes non-respondents are treatment failures) and (3) using state-of-the-art ITT based on multiple imputation for participants with missing data. Since we had missing data, we used the multiple imputation quit rate as our primary outcome. Table 3 Estimates of abstinence at 6 and 12 months, N=1785 Intervention group 6-Month survey outcomes 12-Month survey outcomes N Did not smoke in last 7 days N Did not smoke in the last 30 days N Did not smoke in last 7 days N Did not smoke in the last 30 days Responders Standard 368 66.0 (61.2 to 70.9) 368 60.6 (55.6 to 65.6) 363 65.3 (60.4 to 70.2) 362 61.6 (56.6 to 66.6) Standard plus TEQ-10 368 69.6 (64.9 to 74.3) 368 65.2 (60.4 to 70.1) 370 67.0 (62.2 to 71.8) 371 63.1 (58.2 to 68.0) Difference compared to standard 3.5 (−3.2 to 10.3) p=0.3051 4.6 (−2.4 to 11.6) p=0.1946 1.7 (−5.1 to 8.6) p=0.6191 1.5 (−5.5 to 8.5) p=0.6812 Standard plus TEQ-20 352 67.3 (62.4 to 72.2) 352 61.1 (56.0 to 66.2) 310 62.6 (57.2 to 68.0) 311 56.6 (51.1 to 62.1) Difference compared to standard 1.3 (−5.6 to 8.2) p=0.7121 0.5 (−6.6 to 7.6) p=0.8947 −2.7 (−10.0 to 4.6) p=0.4655 −5.0 (−12.5 to 2.4) p=0.1871 Intent-to-treat penalised imputation (missing=smoking)† Standard 592 41.1 (37.1 to 45.0) 592 37.6 (33.8 to 41.6) 592 40.0 (36.1 to 44.0) 592 37.7 (33.8 to 41.6) Standard plus TEQ-10 602 42.5 (38.6 to 46.5) 602 39.9 (36.0 to 43.8) 602 41.2 (37.3 to 45.1) 602 38.9 (35.0 to 42.8) Difference compared to standard 1.5 (−4.1 to 7.1) p=0.6047 2.2 (−3.3 to 7.7) p=0.4357 1.2 (−4.4 to 6.7) p=0.6827 1.2 (−4.3 to 6.7) p=0.6693 Standard plus TEQ-20 591 40.1 (36.2 to 44.1) 591 36.4 (32.5 to 40.3) 591 32.8 (29.0 to 36.6) 591 29.8 (26.1 to 33.5) Difference compared to standard −1.0 (−6.5 to 4.7) p=0.7405 −1.3 (−6.8 to 4.2) p=0.6459 −7.2 (−12.7 to −1.7) p=0.0100 −7.9 (−13.3 to −2.5) p=0.0041 Multiple imputation‡ Standard 592 64.2 (59.5 to 68.9) 592 59.4 (53.7 to 63.8) 592 63.3 (58.4 to 68.4) 592 61.2 (55.6 to 66.8) Standard plus TEQ-10 602 67.8 (63.0 to 72.7) 602 62.3 (57.7 to 66.9) 602 65.1 (60.3 to 69.9) 602 60.6 (56.0 to 65.2) Difference compared to standard 3.6 (−3.3 to 10.5) p=0.2980 3.6 (−3.2 to 10.4) p=0.2969 1.7 (−4.4 to 7.7) p=0.5831 −0.6 (−7.6 to 6.4) p=0.8647 Standard plus TEQ-20 591 64.7 (59.2 to 70.2) 591 59.4 (53.7 to 65.1) 591 60.9 (56.4 to 65.5) 591 54.9 (49.0 to 60.9) Difference compared to standard 0.5 (−7.0 to 8.0) p=0.8982 0.7 (−6.4 to 7.8) p=0.8468 −2.5 (−9.4 to 4.5) p=0.4808 −6.3 (−14.9 to 2.3) p=0.1471 Percentage of participants reporting abstinence is shown in table above with 95% CIs in parentheses. p Values obtained from χ 2 test for difference between proportions. Estimates were obtained among participants having completed a 6-month or 12-month survey. †Estimates were obtained assuming participants missing a 6-month or 12-month survey were not abstinent. ‡Estimates were obtained by pooling results across 10 multiply imputed data sets. TEQ-10, Technology Enhanced Quitline-10. ITT-penalised imputation quit rates at 12 months were significantly lower for the TEQ-20 group compared with the standard and TEQ-10 groups. However, there were no significant differences in responder or imputed quit rates at 6 or 12 months, or rates of relapse. The quit rates based on multiple imputation at 6 and 12 months ranged from 55% to 68% depending on intervention group, follow-up time point, and outcome measure. Controlling for baseline characteristics, logistic regression models further illustrated no statistical difference between intervention groups for either primary outcome and either time point (table 4). A few baseline characteristics were statistically associated with the outcomes. Across the four models shown in table 4, a higher number of counselling calls, and being motivated to quit, were consistently associated with higher odds of being abstinent (all p<0.05). Depression also played a role in three of the models, with higher depression scores being associated with lower odds of being abstinent (all p<0.05). Older age resulted in higher odds of abstinence for 6-month outcomes only (both p<0.01). Having at least one comorbid chronic condition was associated with lower odds of abstinence in three of the models (all p<0.05). Table 4 ORs from adjusted logistic models of multiple imputation quit rates at 6 and 12 months, N=1785 6-Month survey outcomes 12-Month survey outcomes Variable Did not smoke in the last 7 days Did not smoke in the last 30 days Did not smoke in the last 7 days Did not smoke in the last 30 days Randomisation groups Standard plus TEQ-10 vs standard 1.15 (0.83 to 1.59) 1.14 (0.85 to 1.54) 1.07 (0.82 to 1.41) 0.96 (0.71 to 1.30) Standard plus TEQ-20 vs standard 1.00 (0.71 to 1.42) 1.01 (0.74 to 1.37) 0.87 (0.64 to 1.19) 0.75 (0.52 to 1.09) Number of programme counselling calls Planned+participant−initiated 1.10 (1.02 to 1.18) 1.10 (1.02 to 1.19)* 1.12 (1.02 to 1.22)* 1.10 (1.02 to 1.19)* Demographics Gender Female vs male 0.92 (0.70 to 1.21) 1.00 (0.80 to 1.25) 1.17 (0.91 to 1.49) 1.16 (0.92 to 1.46) Age 1.02 (1.01 to 1.03)* 1.02 (1.00 to 1.03) 1.01 (0.99 to 1.02) 1.01 (0.99 to 1.02) Race African–American vs Caucasian 1.32 (0.89 to 1.96) 1.41 (0.91 to 2.21) 1.16 (0.75 to 1.80) 1.12 (0.72 to 1.76) Other vs Caucasian 0.73 (0.34 to 1.56) 0.72 (0.32 to 1.66) 1.09 (0.55 to 2.16) 0.98 (0.53 to 1.81) Education High school or less vs more than high school 1.12 (0.84 to 1.50) 1.05 (0.77 to 1.43) 0.86 (0.65 to 1.13) 1.01 (0.76 to 1.33) Comorbidities Any chronic comorbidity 0.69 (0.51 to 0.94)* 0.65 (0.46 to 0.92)* 0.72 (0.53 to 0.98)* 0.76 (0.56 to 1.03) Tobacco use Cigarettes per day 0.98 (0.97 to 0.99)* 0.99 (0.97 to 1.00) 0.98 (0.97 to 1.00) 0.99 (0.98 to 1.00) Time to first cigarette 5 min vs all others 0.92 (0.68 to 1.24) 1.10 (0.82 to 1.48) 0.88 (0.64 to 1.20) 0.85 (0.65 to 1.12) Number of quit attempts 2–5 vs 0–1 0.96 (0.69 to 1.34) 0.98 (0.75 to 1.29) 0.80 (0.58 to 1.10) 0.93 (0.69 to 1.24) 6+ vs 0–1 0.88 (0.57 to 1.35) 0.85 (0.56 to 1.28) 0.68 (0.47 to 0.99)* 0.79 (0.55 to 1.13) Social contact with smokers Work or home vs all others 0.74 (0.56 to 0.97)* 0.95 (0.73 to 1.24) 0.98 (0.74 to 1.30) 0.89 (0.68 to 1.17) Scale scores Motivation to quit 1.24 (1.12 to 1.36)* 1.24 (1.11 to 1.39)* 1.22 (1.11 to 1.34)* 1.23 (1.12 to 1.35)* Depression 0.87 (0.78 to 0.96) 0.88 (0.80 to 0.97) 0.94 (0.83 to 1.06) 0.89 (0.80 to 0.99)* All variables shown were included in each model. Estimates for each model were obtained by combining results across 10 multiply imputed data sets; 95% CIs are shown in parentheses. p<0.05; p<0.01; p<0.001. TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.TIME TO RELAPSE:\nThere was no significant association between time to relapse and randomisation group (table 5). Other factors related to time to relapse included number of counselling calls, having comorbid health condition, number of quit attempts, motivation to quit and depression. Higher number of counselling calls and higher levels of motivation to quit were associated with being less likely to relapse sooner (HR=0.87, p<0.001; HR=0.84, p<0.001, respectively). By contrast, participants reporting higher levels of depression were more likely to relapse sooner (HR=1.07, p=0.02). Compared to those with no chronic comorbidities, participants reporting one or more chronic comorbidities were more likely to relapse sooner (HR=1.29, p=0.04). Those reporting six or more quit attempts were also more likely to relapse sooner compared to those with 0–1 attempts (HR=1.32, p=0.04). Table 5 HRs from adjusted proportional hazard models of time to relapse, N=1785 Variable HR (95% CI) p Value Randomisation groups Standard plus TEQ-10 vs standard 0.85 (0.69 to 1.04) 0.1171 Standard plus TEQ-20 vs standard 1.05 (0.85 to 1.31) 0.6282 Number of programme counselling calls Planned+participant−initiated 0.87 (0.82 to 0.92)* <0.0001 Demographics Gender Female vs male 0.90 (0.75 to 1.09) 0.2838 Age 1.00 (0.99 to 1.01) 0.5278 Race African–American vs Caucasian 0.97 (0.75 to 1.26) 0.8400 Other vs White 1.11 (0.67 to 1.84) 0.6762 Education High school or less vs more than high school 1.06 (0.87 to 1.30) 0.5368 Comorbidities Any chronic comorbidity 1.29 (1.01 to 1.64)* 0.0430 Tobacco use Cigarettes per day 1.01 (0.99 to 1.02) 0.0639 Time to first cigarette 5 min vs all others 1.08 (0.88 to 1.34) 0.4430 Number of quit attempts 2–5 vs 0–1 1.14 (0.90 to 1.43) 0.2657 6+ vs 0–1 1.32 (1.02 to 1.72)* 0.0345 Social contact with smokers Work or home vs all others 0.99 (0.80 to 1.24) 0.9713 Scale scores Motivation to quit 0.84 (0.79 to 0.90)*** <0.0001 Depression 1.07 (1.01 to 1.13)* 0.0198 All variables shown were included in each model. Estimates for each model were obtained by combining results across 10 multiply imputed data sets; 95% CIs are shown in parentheses. p<0.05; p<0.01; p<0.001. TEQ-10, Technology Enhanced Quitline-10. \n\nBODY.RESULTS.USING IVR TO IDENTIFY RISK:\nFigure 2 presents quit outcomes for TEQ-10 and TEQ-20 groups (separately in panel A and combined in panel B) according to their positive screen status (≥1 positive screen vs no positive screen); 70.4% in TEQ-10 and 76.1% in TEQ-20 had ≥1 positive screen during the study. Compared with participants who screened positive in either TEQ group, participants who did not screen positive were more likely to be abstinent at 6 (OR=1.69, p=0.01 for 7-day point prevalence; OR=1.77, p≤0.001 for 30-day point prevalence) and 12 months (OR=1.47, p=0.03 for 7-day point prevalence; OR=1.50, p=0.01 for 30-day point prevalence). Figure 2Abstinence rates for intervention and positive screen groups, N=1785. Estimates for each model were obtained by combining results across 10 multiple-imputed data sets. Error bars indicate 95% CIs. (A) Displays results for the TEQ-10 and TEQ-20 groups separately. (B) Displays data for the two TEQ-groups combined. '1+ positive screen' is defined as exceeding the predetermined risk threshold on any of the IVR assessment questions (topics: lapses, cravings, negative effect, self-efficacy, and motivation to remain quit) on any IVR assessment call. IVR, interactive voice response; TEQ-10, Technology Enhanced Quitline-10; TEQ-20, Technology Enhanced Quitline-20.\n\nBODY.RESULTS.SATISFACTION WITH QFL AND THE IVR PROTOCOL:\nSatisfaction was measured at 6 months after enrolment. Participants completing the 6-month survey (n=1091, 61.1%) were generally satisfied with the overall QFL programme and the counselling they received (96% and 98%, respectively, were somewhat satisfied, satisfied, or very satisfied at 6 months). A similar percentage (98%) would recommend the programme to others. There were no differences in QFL programme satisfaction between the three study groups. Compared to TEQ-10 participants, those receiving TEQ-20 were more likely to report the number of relapse risk assessments were too many (36% vs 23%, p≤0.001) and also were marginally more likely to agree that the risk assessments took too much time (28% vs 23%, p=0.09). The majority of participants reported it was easy to answer questions through the IVR system (95%), that the system was helpful (87%), and that they would recommend the IVR system to others trying to stay quit (86%), with no significant differences between the TEQ-10 and TEQ-20 groups.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial investigating the use of an automated, IVR-supported protocol to identify risk and prevent smoking relapse among recently quit tobacco users enrolled in the QFL programme, there were no differences in tobacco abstinence rates between the control (standard QFL) and technology-enhanced (IVR-delivered risk assessments and transfer for counselling) groups at 6-month and 12-month follow-up. Although the risk assessment and transfer protocols did not yield better abstinence rates, the IVR-delivered screenings did successfully identify participants who were less likely to be quit at follow-up. Participants who did not screen positive during the relapse risk assessments were 77% more likely to be abstinent at 6-month follow-up. We tested two risk screening and transfer protocols of varying intensities. The more intensive screening protocol with 20 IVR-delivered assessments did not demonstrate any benefit over the 10-assessment group, and the TEQ-20 respondents were more likely to indicate there were too many IVR assessments. In addition, we explored whether the TEQ intervention was more effective for certain populations in this study with regard to quit outcomes, by testing interaction effects, but did not identify any significant moderating relationships. There are several possible explanations for why the intervention did not reduce relapse rates. The TEQ interventions were designed to immediately transfer participants who met risk thresholds for tobacco counselling to target the identified relapse risk. About three-quarters (73.3%) of the TEQ participants were identified as being at risk at least one time over the 8-week intervention period. Having a positive screen was predictive of relapse; however, it is possible that other risk factors are more predictive of risk than those included in the assessment. Also, participants identified as at risk by the IVR assessments and automatically transferred to a coach failed to remain on the line to receive cessation counselling at the anticipated rate. That is, less than one third of those in the TEQ arms completed an IVR-transferred counselling call and 41.3% of those with a positive risk screen completed one or more IVR-transferred counselling calls, resulting in participants in the TEQ conditions completing only 0.41 calls, on average, more than the planned programme calls from the standard programme. Thus, it is possible that we failed to observe an effect because we did not increase the actual treatment exposure much above the base rate of calls. It remains unclear why some callers did not accept these additional calls when the satisfaction data showed positive perceptions of the IVR automated assessment system (87% felt it was helpful when they need to talk to a Quit Coach; 86% would recommend). Most callers were still receiving planned standard programme calls at the time of their risk assessments; perhaps callers who had recently spoken to a coach did not feel they needed another call at that time. Future studies should assess reasons for lack of counselling uptake and consider an automated system that would allow participants to schedule a call in the near future or would initiate outbound calls to participants identified as at risk who do not immediately transfer to a counsellor. The study had high quit outcomes, in spite of the fact that the TEQ intervention did not significantly improve outcomes. The 61% respondent and 38% ITT penalised imputation (missing=smoking) 30-day point prevalence quit rates at 6 months in the standard treatment group indicated that tobacco users who receive a multiple-call phone counselling programme, have access to cessation medication benefits, and successfully achieve at least a 24 h abstinence period early in treatment do quite well. These quit rates are high compared to studies focusing on all commercial quitline enrolees (eg, 34.3–41.1% responder quit rate at 6 months27\n28). The relatively strong performance and engagement in standard treatment for this study may have made achieving improvements with a low intensity relapse prevention intervention even more challenging. This finding also aligns with previous recommendations that increasing quit attempts may be one of the most important factors for increasing cessation at the population level,29 and demonstrates the importance of achieving at least 24 h of abstinence. More counselling calls completed, higher motivation to quit, lower depression scores, and not having chronic health condition were consistently related to greater likelihood of being abstinent at follow-up. These variables were also associated with time to relapse; additionally, callers with a greater number of previous quit attempts (6+) were more likely to relapse sooner. These findings are consistent with previous quitline studies which have demonstrated the importance of programme engagement (ie, number of calls completed15\n30\n31). Callers in this study had a high motivation to quit (9 out of 10, on average); a previous study has linked high motivation to quit with making a quit attempt but not with likelihood of remaining quit.32 Moreover, previous work has identified that callers with depressive symptoms33 and chronic health conditions31 may have more difficulty quitting. Dependence level (time to first use and cigarettes per day) was not consistently related to outcomes in this study, which differs from previous literature that has often linked baseline dependence and outcomes.31\n32 Compared with other behavioural relapse prevention research, strengths of this study included a relatively large sample size, use of an innovative and potentially cost-effective technology that could be disseminated to large populations if shown to be effective, and attempting to connect those at risk to immediate counselling. Most previous behavioural relapse prevention studies have focused on skills training and have not yielded significant effects.7 As noted by Hajek et al,7 future relapse prevention research efforts may be best applied in examining new and alternative approaches to those previously studied. One recent small pilot study examined extended IVR assessments following varenicline treatment, and also did not find significant effects for the extended IVR group.12 That article did not report on whether those who screened positive during IVR assessments were more likely to have returned to smoking at follow-up, and likely had too small of sample size to meaningfully do so. Additionally, the McNaughton et al's12 study included an intensive IVR contact schedule with 80 contacts over 40 weeks; low IVR assessment completion rates (37% of IVR calls and 16% of assessments were completed) in that study align with our findings that more contact is not necessarily better. Identifying the most effective and cost-effective number of contacts should continue to be a focus in future studies using IVR technology. The response rates to our 6-month and 12-month outcome surveys were 61% and 59%, respectively, which may limit the validity of our findings. Multiple imputation, a preferred method for ITT analysis, was used to reduce potential non-response bias, and the findings from these analyses agreed closely with results from a sensitivity analysis using respondent-only data. Another potential limitation to our study design is the lack of biochemical verification of abstinence, particularly in light of the high reported abstinence rates. However, our study procedures were consistent with recommendations of the SRNT Subcommittee on Biochemical Verification,34 and the results should be considered with respect to this. Additionally, we have no reason to believe there was a systematic bias in reporting abstinence across groups. Third, the protocol aimed for IVR-triggered counselling calls to focus on the specific risk factor(s) identified by the IVR assessment; all participants received empirically based support at the time of need, but not all calls were focused on the identified risk factor(s). Finally, as with other research on prevention of smoking relapse, the time frame for intervention and data collection poses limitations. The IVR-delivered risk assessments in this study were limited to the first 8 weeks following successful abstinence. Although previous research has identified the first weeks as being the greatest risk for relapse, callers also relapse at later dates. Ongoing plans for prevention of relapse, or risk intervention, may be needed; future research may be able to identify those in need of ongoing relapse risk monitoring and intervention. Augmenting tobacco quitline treatment with IVR-delivered relapse risk screening assessments was acceptable to participants, and successfully identified recently quit tobacco users who may be in need of more intensive or different intervention. More research is needed to identify how to engage at-risk participants in additional treatment. Using a technology-based screening for relapse risk to connect recent tobacco users to cessation counselling at the time of risk could offer a scalable, cost-effective approach for delivering tailored services to those in need, if future research can identify the appropriate services to deliver at that time of need.\n\nQuestion:** Compared to Standard quitline treatment what was the result of Technology Enhanced Quitline-10 and Technology Enhanced Quitline-20 on Tobacco abstinence?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1038	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Nicotine delivery, tolerability and reduction of smoking urge in smokers following short-term use of one brand of electronic cigarettes\n\n ABSTRACT.BACKGROUND:\nThis randomized, partially single-blinded, 6-period crossover clinical study of adult smokers compared the nicotine pharmacokinetics, impacts on smoking urge and tolerability of various formulations of one brand of e-cigarettes with that of a tobacco cigarette.\n\nABSTRACT.METHODS:\nFive e-cigarettes with different e-liquid formulations containing 1.6 % and 2.4 % nicotine and a conventional tobacco cigarette were randomized among 24 subjects under two exposure sessions consisting of a 30-min controlled and a one-hour ad lib use period to assess plasma nicotine levels, impacts on smoking urge and adverse events. The 30-min controlled use session comprised an intensive use of the e-cigarettes with a total of 50 puffs taken every 30 s for comparison to a single conventional cigarette having a typical machine-measured nicotine yield (~0.8 mg). Ad lib product use conditions provided insight into more naturalistic product use behaviors and their accompanying smoking urge reductions. Adverse events (AEs) were assessed by the Principal Investigator.\n\nABSTRACT.RESULTS:\nSignificant (p < 0.05) increases in plasma nicotine concentrations occurred within 10 min of controlled e-cigarette use and significant (p < 0.001) reductions from baseline smoking urge were observed within 5 min. E-cigarette and cigarette nicotine plasma levels were comparable for up to one hour of use. After both sessions (90 min), nicotine exposure was the highest for the cigarette, with all e-cigarettes showing 23 % to 53 % lower plasma concentrations. During controlled use, peak reduction in smoking urge for e-cigs occurred later than for the cigarette. After completion of both sessions, significant smoking urge reduction persisted for most of the tested e-cigarettes, albeit at levels lower than that provided by the tobacco cigarette. Nicotine content, vehicle differences, and the presence of menthol did not significantly affect smoking urge reduction by the e-cigarettes. No subjects were discontinued due to AEs. The most frequently reported AEs events included cough, throat irritation, headache, and dizziness.\n\nABSTRACT.CONCLUSIONS:\nBlood plasma nicotine levels obtained from short-term use of e-cigarettes containing 1.6 % and 2.4 % nicotine were significant, but lower than those of conventional tobacco cigarettes, yet the reduction in craving symptoms were broadly comparable. The types of AEs were consistent with other research studies of longer duration that have reported that use of e-cigarettes by adult smokers is well-tolerated.\n\nABSTRACT.TRIAL REGISTRATION:\nhttp://ClinicalTrials.gov identifier: NCT02210754. Registered 8 August 2014.\n\nBODY.BACKGROUND:\nSmoking remains the leading preventable cause of premature death in the United States [1]. Electronic cigarettes (e-cigarettes) are rapidly becoming a popular alternative to cigarette smoking worldwide and are garnering significant attention as potentially reduced-exposure replacements for conventional cigarettes (cigarettes) [2–6]. E-cigarettes consist of a battery, heating component, and a cartridge containing tobacco-derived nicotine in a solution composed of glycerin and/or propylene glycol (PG), and flavorings. Upon activation, the heating element heats the solution to generate an aerosol that is inhaled by the consumer in a manner that mimics smoking. Pharmacokinetic studies with early-generation e-cigarettes found that they delivered markedly lower levels of plasma nicotine than conventional cigarettes [7, 8]. More recent studies have reported that experienced subjects using later-generation e-cigarettes containing 9 to 24 mg/mL of nicotine attain significant increases in plasma nicotine concentrations over baseline values that can be similar to those obtained from conventional cigarette smoking [9–11]. These results suggest that an acclimation to the product may be necessary for naïve smokers to become familiar with the characteristics of the specific e-cigarettes in order to effectively use them in a subjectively enjoyable manner. Moreover, these studies also demonstrated a reduction in smoking urge or abstinence symptoms following e-cigarette use, even for products that deliver less nicotine than conventional tobacco cigarettes. This is quite consistent with a perspective that the substantial sensory and behavioral aspects of cigarette smoking that are mimicked by e-cigarettes may provide meaningful relief of the cigarette cravings commonly reported by abstinent smokers. Surveys and clinical studies evaluating the impacts, tolerability and adverse events (AEs) associated with e-cigarette use suggest that they are generally well-tolerated following short-term use [1, 9, 12–16]. Commonly reported AEs include symptoms such as mouth and throat irritation, light-headedness, dizziness and dry cough. The primary objective of this study was to examine the nicotine blood plasma levels and smoking urge impacts of various formulations of one brand of e-cigarette with that of a tobacco cigarette. The tested products contained different flavorings, aerosol forming excipients (i.e., propylene glycol, glycerin) and nicotine levels. The secondary objectives were to assess the tolerability and any adverse events associated with the study products following short-term use under intensive controlled use conditions, as well as under more natural ad-lib use conditions.\n\nBODY.METHODS.PARTICIPANTS:\nThe study protocol and the informed consent forms were approved by Chesapeake IRB, Columbia, MD. A total of 107 potential subjects were recruited from the Lincoln, NE area using standard advertising methods (i.e., print and radio advertisements) and from a database of subjects who had previously participated a clinical research study or who had expressed interest in participating in a study. All potential subjects were provided details regarding the study and written informed consent was obtained prior to completion of any study procedures. Sixty-one subjects were excluded for not meeting the predefined inclusion/exclusion criteria, while five subjects declined to participate prior to enrollment and three subjects were excluded because the study had reached the recruitment target of 38 eligible subjects. The 38 subjects meeting the eligibility criteria participated in a 7-day at-home lead-in period during which they used and became familiar with two of e-cigarette study products (non-menthol and menthol, 2.4 % nicotine with glycerin). All subjects who participated in the at-home lead-in period were allowed to check in at the start of clinical conduct. Two subjects chose not to participate further after the lead-in period and one subject failed further screening requirements at check-in. A final study population of 24 subjects were enrolled into the study and randomized into one of six product usage sequences with four subjects per sequence. One subject withdrew consent after completion of the first product use on Day 1 of the trial due to a personal reason (family emergency). All subjects participating in the study from the time of the lead-in period were paid for their participation. The main criteria for inclusion were as follows: healthy adult male and female smokers, 21 to 65 years of age, inclusive; smoker for at least 12 months and currently smoked an average of 10 or more manufactured cigarettes per day (no restriction on brand-style); positive urine cotinine at screening (≥ 500 ng/mL); and exhaled carbon monoxide CO > 10 ppm at screening. Exclusion criteria included: history or presence of clinically significant mental or physical health conditions; females who were pregnant or breastfeeding; high blood pressure; body mass index < 18 kg/m2 or > 40 kg/m2; acute illnesses (e.g., upper respiratory infection, viral infection) requiring treatment within 2 weeks prior to check-in; use of prescription smoking cessation treatments, anti-diabetic or insulin drugs or medications known to interact with cytochrome P450 2A6; positive urine screen for alcohol or drugs of abuse; and self-reported puffers (i.e., smokers who draw smoke from the cigarette into the mouth and throat but do not inhale). Subjects who had used any tobacco- or nicotine-containing products other than manufactured cigarettes or e-cigarettes within 28 days of in-clinic product use were also excluded.\n\nBODY.METHODS.PRODUCTS TESTED:\nA rechargeable version of an e-cigarette that is currently sold in retail outlets throughout the United States was used in this study. The rechargeable e-cigarette consists of a battery segment and a cartomizer segment comprising the heating unit and a liquid reservoir which can be separated from the battery for recharging or replacement when the e-liquid is depleted. The battery operates at a voltage of 3.7 volts (nominal) and the resistance of the heating element is approximately 3 ohms. The maximum operating temperature is dependent on both the state of reservoir fluid fill and on the manner of use and was not recorded in this study. Two commercial e-cigarette products that contained 16 mg/mL (1.6 %) USP grade nicotine were used in this study. As well, three non-commercial products that contained 24 mg/mL (2.4 %) USP grade nicotine were used in this study to evaluate various product characteristics considered important to further product development. In addition to nicotine, the e-cigarettes used in this study contained USP grade glycerin and/or propylene glycol (as described below), distilled water (<20 %), citric acid (<1.0 %) and natural or artificial flavors (<10 %). The nicotine yield of the conventional cigarette used in the study was approximately 0.8 mg per cigarette [17]. The study products included:Product A: Classic Tobacco flavored e-cigarette (2.4 % nicotine, ~75 % glycerin)Product B: Classic Tobacco flavored e-cigarette (2.4 % nicotine, ~50 % glycerin/~20 % propylene glycol)Product C: Menthol flavored e-cigarette (2.4 % nicotine, ~75 % glycerin)Product D: Classic Tobacco flavored e-cigarette (1.6 % nicotine, ~75 % glycerin)Product E: Classic Tobacco flavored e-cigarette (1.6 % nicotine, ~50 % glycerin/~20 % propylene glycol)Product F: Tobacco Cigarette\n\nBODY.METHODS.STUDY DESIGN:\nThis was a randomized, partially single-blinded, six-period crossover study conducted at a single independent research center (Celerion, Lincoln, NE). Twenty-four subjects were randomly selected from the pool of 38 subjects who participated in the at-home lead-in period were enrolled into the testing phase of the trial and randomized to assigned product sequences. The subjects checked into the clinic on Day −2 and abstained from using of nicotine-containing products until product use on Day 1. Days 1, 3, 5, 7, 9, and 11 were designated product use days while Days −1, 2, 4, 6, 8, and 10 were designated wash-out days. The subjects were housed at the test site from the time of check-in through completion of study events on Day 11. The clinic staff monitored the subjects during the confinement period to ensure that no illicit nicotine or tobacco products were used. Study investigators were not blinded, but the subjects were as the all the e-cigarette products appeared the same. The menthol product, however, was easily discernible due to taste. Previous studies have demonstrated that a lack of familiarity with e-cigarette products may result in low nicotine intake with their use [7, 18]. In order to allow study participants to become familiar with the e-cigarette devices, subjects were instructed on the appropriate use of the products and were required to demonstrate the appropriate use to clinic staff. Each subject was then provided with two units of the menthol and non-menthol 2.4 % nicotine products containing glycerin for at-home use prior to the start of the study and instructed to use the products each day during the 7-day lead-in period. Two types of exposures were utilized in the study on each product use day: a controlled use period followed by an ad lib use period. Similar 2-stage designs have been informative in prior studies evaluating the nicotine delivery and subjective effects of e-cigarettes [5–9, 19]. Enrolled subjects were randomized into one of six product usage sequences (Table 1) with four subjects per sequence.Table 1Summary of study demographics and FTCD scores by study product sequence and overallTrait/TestCategory/StatisticStudy product sequenceABFCED (N = 4)BCADFE (N = 4)CDBEAF (N = 4)DECFBA (N = 4)EFDACB (N = 4)FAEBDC (N = 4)Overall (N = 24)SexFemale2 (50 %)2 (50 %)2 (50 %)2 (50 %)2 (50 %)2 (50 %)12 (50 %)Male2 (50 %)2 (50 %)2 (50 %)2 (50 %)2 (50 %)2 (50 %)12 (50 %)RaceAmerican Indian/Alaska Native1 (25 %)0 (0 %)0 (0 %)0 (0 %)0 (0 %)0 (0 %)1 (4 %)Black or African American0 (0 %)1 (25 %)0 (0 %)2 (50 %)0 (0 %)0 (0 %)3 (13 %)White3 (75 %)3 (75 %)4 (100 %)2 (50 %)4 (100 %)4 (100 %)20 (83 %)EthnicityHispanic or Latino1 (25 %)0 (0 %)0 (0 %)0 (0 %)0 (0 %)0 (0 %)1 (4 %)Not Hispanic or Latino3 (75 %)4 (100 %)4 (100 %)4 (100 %)4 (100 %)4 (100 %)23 (96 %)Age (yrs)Mean38.340.538.335.334.045.838.7SD12.0415.7015.444.039.496.1310.77Height (cm)Mean167.25175.75168.75172.75167.00171.75170.54SD3.40310.2436.1313.7758.2069.8117.331Weight (kg)Mean84.179.270.874.780.083.978.8SD16.5225.896.1513.1312.9314.1414.91BMI (kg/m2)Mean30.05025.19824.79825.01528.94828.37527.064SD6.04395.76220.68543.84646.38104.32554.8512Fagerström Test for Cigarette Dependence ScoreMean4.05.35.06.04.07.85.3SD2.160.51.412.162.162.632.18Median3.55.04.55.54.58.55.0Minimum2544141Maximum767961010 Given the wide variability in smoking behaviors, the controlled use period of the study was intended to provide some degree of standardization of the nicotine \"dose\" associated with each of the study products to better understand potential influences of different vehicles, flavor characteristics and nicotine content on measured parameters. As such, the controlled use period of the study consisted of 50 puffs of the assigned e-cigarette product (5-s puffs at 30-s intervals, approximately 24.5 min of use) and smoking one conventional tobacco cigarette (30-s intervals with the subjects' normal puff duration, approximately 4.5 min of use). Fifty e-cigarette puffs was selected as an optimal controlled \"dose\" as it approximated the dose of nicotine delivered by the cigarette used in the study (~0.8 mg) based on machine yields of the e-cigarettes determined previously using a standardized Canadian Intense puffing protocol [20, 21]. Thus, this controlled \"dose\" period was intended to reflect intensive usage of the e-cigarettes for comparison to the tobacco cigarette used in the study. During the controlled use period, subject puff counts were monitored by the clinical staff and all e-cigarettes were weighed before and after use in order determine the amount of solution consumed. Further, evaluation under the ad lib use conditions provided plasma nicotine levels under uncontrolled, natural use conditions and insights into product use behaviors accompanied by subjective self-assessments of smoking urge. During ad lib use, subjects assigned to an e-cigarette or tobacco cigarette product were allowed to use the product as desired for the entire hour (use of the assigned e-cigarette products in an unrestricted manner or smoking as many tobacco cigarettes as they chose) and subjects were responsible for maintaining their own puff counts. All e-cigarette products were weighed before and after use. The ad lib use period was conducted immediately following the end of the controlled product use session. Blood samples for plasma nicotine determinations, smoking urge assessments, blood pressure, pulse rate, and exhaled CO measurements were also obtained at scheduled time points on each product use day.\n\nBODY.METHODS.PHARMACOKINETICS (PK) - PLASMA NICOTINE:\nBlood samples for the measurement of plasma nicotine concentrations were taken by direct venipuncture at 10 min prior to, and at 5, 10, 15, 20, 25, 30, 45, 60, 75, and 90 min following the start of the controlled product usage on Days 1, 3, 5, 7, 9, and 11. Plasma nicotine was analyzed by LC-MS/MS using validated analytical methods with appropriate quality controls in accordance with applicable FDA Good Laboratory Practice regulations (Title 21 CFR Part 58). The limit of quantification for nicotine was 0.200 ng/mL. The following PK parameters were calculated:Cmax0–30 - maximum observed concentration from time zero to 30 min.AUC0–30 - area under the concentration-time curve from time zero to 30 min.tmax0–30 - time of the maximum concentration from time zero to 30 min.AUC30–90 - area under the concentration-time curve from 30 to 90 min.C90 - maximum observed concentration at 90 min.\n\nBODY.METHODS.PHARMACODYNAMICS – SMOKING URGE:\nSmoking urge was assessed using a simple and subjective 100 mm visual analog scale (VAS). Various forms of VAS have been used in e-cigarette studies as a tool for obtaining various subjective effects data associated with e-cigarette use and measuring nicotine and smoking abstinence symptom suppression [6–10]. Participants were asked to rate \"how strong is your urge to smoke right now?\" by placing a line through a 100 mm line where far left indicated: 'not at all' and far right indicated: 'extremely'. Assessments occurred within 1 min prior to the −10 (pre-product use), 5, 15, 25, 30, 60, and 90-min PK blood draws. The smoking urge change-from-baseline was calculated as the difference between the pre-use and post-use smoking urge result for each tested product. The following pharmacodynamic (PD) parameters were calculated:Emax0–30 - Maximum smoking urge change-from-baseline from time zero to 30 min.Emaxreduction0–30 - Maximum smoking urge reduction from baseline from time zero to 30 min.AUEC0–30 - Area under the effect curve (smoking urge change-from-baseline) from time zero to 30 min.tEmax0–30 - Time of the maximum smoking urge change-from-baseline from time zero to 30 min.AUEC30–90 - Area under the effect curve (smoking urge change-from-baseline) from 30 to 90 min.E90 - Observed smoking urge change-from-baseline at 90 min.\n\nBODY.METHODS.TOLERABILITY AND ADVERSE EVENTS (AES):\nTolerability evaluations included assessments of AEs, vital signs and concomitant medications. AEs reported by the subjects or observed by the clinic staff were assessed for severity (mild, moderate, or severe), as serious or not serious, and relationship to the study products (unrelated, unlikely, possible, probable, or definite) by the Principal Investigator. A study product use-emergent AE was defined as an AE that started or intensified at the time of or after study product usage. An AE that occurred during the washout period between study products was considered study product use-emergent for the last study product given. All reported AEs were coded with Medical Dictionary for Regulatory Activities (MedDRA®), Version 17.0. AEs were recorded by frequency by study product and the number of subjects experiencing product use-emergent AEs.\n\nBODY.METHODS.DATA ANALYSES:\nNon-compartmental PK and smoking urge parameters were calculated using Phoenix® WinNonlin® Version 6.3 (Certara, Princeton, NJ) from the individual nicotine concentration and smoking urge change-from-baseline data. All statistical summarizations and comparisons were calculated using SAS® Version 9.3 (SAS, Cary, NC). Analyses of variance were performed on the plasma nicotine AUC0–30, AUC30–90, Cmax0–30, and C90 parameters, and a Wilcoxon Signed Rank Test was used for the tmax0–30 parameter to assess differences between the e-cigarettes and the tobacco cigarette. Usual brand cigarette flavor (menthol or non-menthol) was included in each of the analyses as a covariate to account for any impact that flavor preference might have had on the results. Repeated measures ANOVA with simple contrasts were used to compare the maximum observed concentrations of plasma nicotine within the first 30 min and at 90 min (Cmax0–30 and C90) to the pre-product use concentration. The smoking urge parameters AUEC0–30, AUEC30–90, Emax0–30, E90, and tmax0–30 were compared using methods similar to those used in the PK analyses. Differences were considered statistically significant at an alpha level of 5 %.\n\nBODY.RESULTS AND DISCUSSION.PARTICIPANT CHARACTERISTICS:\nOf the 24 subjects who were enrolled into the testing phase of the study and randomized to study product sequences, 23 subjects completed the study and one subject withdrew due to a family emergency. A summary of the subjects' demographics together with the results of the Fagerström Test for Cigarette Dependence (FTCD) scores [22, 23] for all study participants by study product sequence and overall is presented in Table 1.\n\nBODY.RESULTS AND DISCUSSION.PRODUCT USE:\nThe mean pre-to-post use product weight differences for the e-cigarettes and the mean puffs taken from all products during each period of the study are provided in Table 2. During controlled product administration, all subjects were to take the same number of puffs (50) from the e-cigarette products with a defined inhalation pattern (5-s puffs every 30 s) while monitored by the clinical staff in an attempt to standardize nicotine intake. The resulting mean weight differences were comparable across study products (0.2238 - 0.2570 g), with the highest and lowest estimated nicotine delivery from the 1.6 % nicotine products. During the ad lib product use period, subjects were free to puff as often as they chose with no limitation on puff duration. As a result, the number of puffs from each of the e-cigarette products varied widely across subjects during the ad lib use period. However, the mean puff counts were fairly comparable across products, averaging between 49.5 and 60.3, with the highest and lowest mean puff counts again noted with the 1.6 % nicotine products. Product weight differences followed the same pattern. Hence, there was no clear indication in either period that subjects compensated during use of the lower nicotine-containing products by taking more or deeper puffs in an attempt to self-administer more nicotine.Table 2Product use summaryControlled Use Period\nAd Lib Use PeriodE-CigarettePuffsPre-to-Post Use Weight Difference (g)PuffsPre-to-Post Use Weight Difference (g)2.4 % nic + Gly50.0 (50–51)0.2251 ± 0.040852.3 (5–128)0.1467 ± 0.0843\nN = 232.4 % nic + Gly/PG50.0 (50–51)0.2349 ± 0.063355.4 (4–136)0.1445 ± 0.0880\nN = 232.4 % nic + Gly + menthol50.0 (50–51)0.2421 ± 0.047758.0 (8–140)0.1604 ± 0.0827\nN = 231.6 % nic + Gly50.0 (50–51)0.2238 ± 0.039960.3 (8–112)0.1738 ± 0.0937\nN = 231.6 % nic + Gly/PG50.0 (50–51)0.2570 ± 0.043349.5 (3–118)0.1194 ± 0.0675\nN = 23PuffsCigarettes SmokedPuffsCigarettes SmokedTobacco Cigarette10.5 (9–13)1.0 (NA)38.6 (16–103)3.6 (2–7)\nN = 24Values for puff count and cigarettes smoked are presented as mean (range). Values for the pre-to-post weight differences are presented as mean ± SD\nnic nicotine, Gly glycerine, PG propylene glycol The mean differences in product weights were observed to be smaller for each e-cigarette (~22 % - 54 %) following ad lib product use compared to the controlled product administration despite the subjects having taken similar numbers of puffs, or more, during ad lib product use. This was likely due to shorter puff durations during ad lib product use. For the tobacco cigarettes, subjects smoked only a single cigarette during the controlled product administration, with an average of 10.5 puffs per cigarette taken. During the ad lib phase subjects smoked an average of 3.6 cigarettes, with approximately the same number of puffs taken per cigarette.\n\nBODY.RESULTS AND DISCUSSION.NICOTINE PHARMACOKINETICS AND BLOOD PLASMA LEVELS:\nThe mean plasma nicotine concentration-time profiles are presented in Fig. 1. Baseline nicotine concentrations were below the limit of quantification in the majority of subjects and mean baseline nicotine concentrations were comparable across study products, all representing less than half the limit of quantification of 0.200 ng/mL. During the controlled use period, mean concentrations increased peaked immediately after use of the single tobacco cigarette (p < 0.05 compared to baseline) and then steadily decreased until reaching a minimum at the end of the period. For all e-cigarettes, nicotine plasma absorption was slower, with mean concentrations steadily increasing with continued product use and peaking at the end of the period. Usage of the study e-cigarettes resulted in statistically significant (p < 0.05) increases from baseline in nicotine concentration as soon as 5 min following the start of product use with the exception of the 1.6 % nicotine product with glycerin, which also reached statistical significance after 10 min of use. Plasma nicotine concentrations steadily increased during the one-hour ad lib use of the tobacco cigarettes, whereas ad lib use of the e-cigarettes resulted in plasma nicotine concentrations that increased during the first 45 min and then plateaued during the last 15 min.Fig. 1Mean Plasma Nicotine Concentration Versus Time The summary of nicotine plasma PK parameters is presented in Table 3. The controlled e-cigarette puffing regimen provided peak (Cmax30) and overall (AUC0-30) nicotine exposures comparable to the tobacco cigarette for the two non-menthol 2.4 % nicotine products and the 1.6 % nicotine product containing glycerin and PG (all differences within 15 % of the tobacco cigarette). However, use of 1.6 % nicotine product containing only glycerin provided significantly lower peak (35 %) and overall (39 %) exposures despite having the highest mean puff counts of any of the e-cigarette products. Use of the menthol product (2.4 % nicotine with glycerin) also yielded a significantly lower overall exposure (16 %) compared to the tobacco cigarette, but a comparable peak concentration. Not surprisingly, the use pattern of the e-cigarette during the controlled use period resulted in a significantly longer time to peak nicotine concentration (Tmax0–30) than for the single tobacco cigarette.Table 3Summary of plasma nicotine pharmacokinetic parameters and statistical comparisons to the tobacco cigaretteE-CigarettesPharmacokinetic Parameters2.4 % nic + Gly2.4 % nic + Gly/PG2.4 % nic + Gly + menthol1.6 % nic + Gly1.6 % nic + Gly/PGTobacco Cigarette\nN = 23\nN = 23\nN = 23\nN = 23\nN = 23\nN = 24Cmax0–30 (ng/mL)17.4 ± 5.9718.1 ± 6.4715.3 ± 5.1610.3 ± 3.7015.1 ± 4.6115.8 ± 8.64\np-value0.12420.05080.88580.00020.7776Tmax0–30 (hr)0.50 (0.33, 0.55)0.50 (0.33, 0.52)0.50 (0.33, 0.52)0.50 (0.33, 0.61)0.50 (0.33, 0.62)0.09 (0.08, 0.42)\np-value<0.0001<0.0001<0.0001<0.0001<0.0001AUC0–30 (nghr/mL)4.7 ± 1.844.9 ± 1.754.1 ± 1.633.0 ± 1.184.3 ± 1.394.9 ± 1.79\np-value0.76360.84430.0406<0.00010.0928AUC30–90 (nghr/mL)22.4 ± 5.6124.6 ± 7.9921.6 ± 5.0814.7 ± 5.1519.8 ± 4.7222.1 ± 5.98\np-value0.84630.06020.6319<0.00010.0756C90 (ng/mL)19.7 ± 5.7222.4 ± 7.6519.4 ± 5.8013.7 ± 5.9816.8 ± 4.4429.2 ± 10.86\np-value<0.0001<0.0001<0.0001<0.0001<0.0001Tmax0–30 is presented as median (minimum, maximum), all other values are presented as arithmetic mean ± SD. Statistical significance is based on the differences in least squares means between groups. P-values represent the comparison to the tobacco cigarette\nnic nicotine, Gly glycerine, PG propylene glycol During the ad lib use period, overall nicotine exposure (AUC30–90) was comparable (differences within 11 %) between the tobacco cigarette and all e-cigarette products with the exception of the 1.6 % nicotine product with only glycerin, which provided a 33 % lower overall exposure. However, the nicotine concentration at the end of the ad lib use period was significantly higher following use of the tobacco cigarette compared to the e-cigarettes, with concentrations ranging from 23 % to 53 % lower after 60 min of ad lib use. Overall, the exposure parameters among the e-cigarette products tended to be higher for the 2.4 % nicotine products, higher for the products containing both glycerin and PG, and lower for the product containing menthol compared to the other 2.4 % nicotine products.\n\nBODY.RESULTS AND DISCUSSION.PHARMACODYNAMICS: EFFECTS ON URGE TO SMOKE:\nThe mean smoking urge change from baseline-time profiles are presented in Fig. 2. Mean baseline smoking urge values across all test products were comparable, with the mean visual assessment scale (VAS) responses ranging from 62 to 68 out of 100 (mm).Fig. 2Mean Smoking Urge Change from Baseline versus Time (Note: More Negative Values Indicate a Stronger Urge Reduction) An immediate statistically significant (p < 0.001) reduction in smoking urge was observed at 5 min following the start of controlled use of each study product. Following use of a single tobacco cigarette, the maximum reduction in smoking urge was observed at 5 min, approximately corresponding to the end of use of that study product, and then increased during the remainder of the controlled use period. Continuous use of the e-cigarette products throughout the controlled use period resulted in a maximal reduction in smoking urge also approximately corresponding to the end of product use. During the ad lib use period, use of the tobacco cigarette resulted in a steady decrease in smoking urge, peaking at the final time point, while the response with the e-cigarettes peaked 30 min into ad lib use and stabilized during the final 30 min. Table 4 summarizes the change in smoking urge PD parameters. No statistically significant differences were found in the maximal smoking urge reduction parameters Emax0–30 and Emaxreduction0–30 (all differences within 11 %) or the overall smoking urge reduction parameter AUEC0-30 (all differences within 21 %) between the use of a single tobacco cigarette and each of the e-cigarettes during the controlled use period. The mean time to the maximal reduction in smoking urge was shorter for the tobacco cigarette (15 min) than each of the e-cigarettes (25 – 30 min), but only significantly so for both of the 1.6 % nicotine products and the 2.4 % nicotine product with menthol.Table 4Summary of change in smoking urge parameters and statistical comparisons to the tobacco cigaretteE-CigarettesSmoking Urge Parameters2.4 % nic + Gly2.4 % nic + Gly/PG2.4 % nic + Gly + menthol1.6 % nic + Gly1.6 % nic + Gly/PGTobacco Cigarette\nN = 23\nN = 23\nN = 23\nN = 23\nN = 23\nN = 24Emax0–30 (mm)−41.9 ± 26.56−44.7 ± 26.98−37.0 ± 30.25−40.2 ± 32.47−40.7 ± 24.25−41.5 ± 27.43\np-value0.92850.64270.30230.69720.7450Emaxreduction0–30 (mm)−42.2 ± 26.01−44.7 ± 26.98−39.1 ± 25.86−41.4 ± 30.40−40.7 ± 24.25−41.7 ± 27.08\np-value0.94890.65050.50560.84800.7079AUEC0–30 (hrmm)−14.1 ± 10.56−15.5 ± 10.39−12.2 ± 10.75−13.9 ± 12.09−13.3 ± 8.29−15.4 ± 12.67\np-value0.40540.89120.08820.35900.2225TEmax0–30 (hr)0.41 (0.07, 0.50)0.41 (0.07, 0.50)0.41 (0.08, 0.50)0.42 (0.08, 0.50)0.49 (0.24, 0.50)0.25 (0.07, 0.51)\np-value0.17640.09480.00140.00120.0009AUEC30–90 (hrmm)−44.3 ± 35.39−50.9 ± 33.64−42.7 ± 38.24−46.2 ± 40.23−47.7 ± 34.16−46.9 ± 30.14\np-value0.66790.52750.50460.89190.9395E90 (mm)−37.0 ± 30.69−42.5 ± 29.85−34.3 ± 34.03−37.4 ± 35.08−38.5 ± 30.12−52.2 ± 26.33\np-value0.00600.09210.00100.00660.0122TEmax0–30 is presented as median (minimum, maximum), all other values are presented as arithmetic mean ± SD. Statistical significance is based on the differences in least squares means between groups. P-values represent the comparison to the tobacco cigarette\nnic nicotine, Gly glycerine, PG propylene glycol During the ad lib use period, the overall smoking urge reduction (AUEC30-90) achieved with use of the e-cigarettes were comparable to that of the tobacco cigarette, with all differences less than 10 %. However, at the end of the ad lib period, use of the tobacco cigarette resulted in a 19 % to 34 % greater relief of smoking urge (E90) when compared to the e-cigarettes, with statistically significant differences for all except the 2.4 % nicotine product containing both glycerin and PG. The smoking urge reduction appeared comparable among the e-cigarette products with the exception of the 2.4 % nicotine product with menthol which tended to provide a somewhat lower level of relief compared to the other four products.\n\nBODY.RESULTS AND DISCUSSION.TOLERABILITY AND REPORTED ADVERSE EVENTS:\nDuring the course of the study, a total of 38 subjects were exposed to one or more of the study products. There were no serious adverse events reported and no subjects were discontinued due to AEs. Mild product-use-emergent AEs were reported by 18 of 38 subjects provided a study product (including the lead-in period). The number of subjects reporting AEs was similar among products, ranging from 3 to 10 subjects each, with slightly fewer subjects experiencing AEs following use of the menthol-flavored product. The most frequent AE was cough, reported 20 times by 11 subjects (more commonly with use of an e-cigarette product than the tobacco cigarette), followed by throat irritation (8 reports by 5 subjects) and headache (6 reports by 5 subjects), and dizziness (5 reports by 4 subjects). All AEs resolved without sequelae. The observed acute effects of the study products on blood pressure, heart rate and CO levels were previously reported by the authors under a separate publication [24] where it was noted that heart rate and systolic and diastolic blood pressure were significantly elevated after the use of the tobacco cigarette, but the elevation was less after use of most of the e-cigarettes. Furthermore, it was also observed that the use of the e-cigarettes produced no increase the exhaled CO levels, whereas the cigarette significantly increased the exhaled CO more than eight (8) times above the baseline.\n\nBODY.CONCLUSIONS:\nThe key objectives of this study were to examine the nicotine blood plasma levels and smoking urge impacts of various formulations of one brand of e-cigarette for comparison to a conventional tobacco cigarette, and to assess the tolerability and adverse events associated with the study products following short-term use under intensive and naturalistic use conditions. The study design and results are not intended to support the potential for e-cigarettes as harm-reduction products. While not all puffing parameters can be controlled across all subjects, a product use that includes the same number of puffs, puff duration, and puff interval as utilized in this study allows for standardization of nicotine intake to the extent possible in order to accurately characterize uptake and reduction in smoking urge. The small difference in pre-to-post use weight differences across the e-cigarette products supports this. When compared to a tobacco cigarette, the nicotine PK following a controlled, 50-puff use of the e-cigarettes was characterized by slower absorption than from a single tobacco cigarette, but comparable maximal and overall nicotine exposures for all but the 1.6 % nicotine product with glycerin. Analysis of the mean maximum plasma concentrations attained during the controlled use period showed that the non-menthol e-cigarettes containing 2.4 % nicotine exceeded that of the tobacco cigarette (15.8 ng/mL at approximately 5 min) with approximately 25 min of use (17.8 to 18.1 ng/mL). This observation is most likely attributable to the rather intensive e-cigarette puffing regimen (one puff every 30 s) imposed during the controlled use interval when compared to the single tobacco cigarette regimen (average 10.5 puffs total). However, it also suggests that under an intensive puffing scenario, e-cigarettes are capable of delivering similar amounts of nicotine as a tobacco cigarette. The continuous rise in nicotine concentrations achieved with use of the e-cigarettes during the controlled use period appeared to be matched by a consistent decrease in smoking urge, though at the end of the 30-min controlled use period the urge reduction was comparable across those products. Smoking a single cigarette during the controlled use period produced a predictable nicotine concentration-time curve, with a rapid peak nicotine concentration followed by a gradual elimination. The rise and fall of nicotine concentration was matched by the smoking urge response, with a rapid decrease in urge followed by a gradual return toward baseline. While the time to maximum urge reductions was significantly shorter for the tobacco cigarette during the controlled use period compared to each of the e-cigarettes, there were no significant differences in the maximal or overall urge reduction achieved between the two types of products. Ad lib use of the study products can provide insight into use patterns and nicotine concentrations that will allow consumers to satisfy their smoking urge and provide an overall satisfying product use experience. As should be expected, individual use of the products as measured by puff counts varied widely and followed the amount of nicotine solution that was consumed during use as measured by pre-to-post use product weight difference. Use of the e-cigarettes during the ad lib use period resulted in a relatively small increase in nicotine concentration during the first 45 min, followed by a plateau during the last 15 min. In contrast, use of the cigarette during the ad lib use period resulted in a continuous increase in nicotine concentration and continued reduction in smoking urge through the final time point. Following ad lib use of all products for 60 min, the tobacco cigarette yielded a significantly higher nicotine concentration (C90) compared to each of the e-cigarettes. The higher nicotine concentration coincided with a greater reduction in smoking urge at the end of the ad lib use period (E90) for the tobacco cigarette compared to all e-cigarettes, and significantly greater than all except the 2.4 % nicotine product containing glycerin and PG. However, there was no overall impact on urge as assessed by AUEC30–90. This was likely due to the relatively short duration of the ad lib use. Indeed, as the smoking urge response appeared to have reached a plateau with the e-cigarettes and continued to increase with the cigarette following 60 min of ad lib use, a longer evaluation period may have resulted in a difference in the AUEC parameter as well. Among the e-cigarettes, use of the e-cigarettes containing 1.6 % nicotine resulted in lower nicotine exposure compared to the e-cigarettes containing 2.4 % nicotine. However, this did not translate into significant differences in the smoking urge response. Further, while the suppression of urge to smoke appeared comparable between the 1.6 % and the 2.4 % test formulations in the present study, evaluation of the mean puff counts and the amount of solution consumed did not suggest that the subjects compensated by puffing on the lower-nicotine products consciously or subconsciously more so than the higher-nicotine products to achieve a similar level of satisfaction. In addition, higher nicotine content, the presence of PG in the vehicle, and the absence of menthol in the e-cigarettes were found to increase plasma nicotine levels during both controlled and ad lib use. Such factors, however, did not appear to significantly affect smoking urge. However, consistent with prior research documenting the prominent role of conditioned behavior and nicotine addiction, in addition to the concentration of nicotine, the respiratory tract sensory cues and manipulation of smoking materials that are associated with smoking, and mimicked by e-cigarettes, may have had a role in relieving smoking urges [25]. Thus, the present findings further suggest that some of the substantial sensory and behavioral aspects of smoking that are mirrored by e-cigarettes, may be essential elements in the reduction of craving or abstinence symptoms. To the extent that e-cigarettes may provide some measure of reduction in smoking urges, they may serve as cigarette substitutes for smokers who would otherwise seek to smoke a conventional tobacco cigarette. Despite the aggressive puff regime employed in the controlled use period, there were no SAEs in this study and no subjects were discontinued due to AEs. The incidence of AEs was similar among products, with slightly fewer subjects experiencing AEs following use of the menthol-flavored product. The most frequently reported minor AEs were cough, followed by throat irritation, headache, and dizziness. These findings are consistent with other research studies of longer duration that have reported that use of e-cigarettes by adult smokers is well-tolerated as compared to tobacco cigarette use [2, 26]. This study was not without limitations. It was performed at a single site with a small number of subjects, which might lead to the conclusion that the data is not generalizable to a broader population. However, many initial PK evaluations of tobacco and pharmaceutical products are performed using a similar approach. Further, the comparison to the e-cigarettes was made based on a single product use and a short-term ad lib product use to a single brand of tobacco cigarette. Indeed, the trend we noted at the end of the ad lib use period did show that nicotine concentrations appeared to be continuing to rise and smoking urge appeared to be continuing to decrease. Hence, a longer term comparison in future studies would be beneficial. Finally, while the product use data did not provide a clear indication that subjects compensated by using the products with less nicotine more intensively, use of topography measurements providing insight into puff volume and inhalation rate coupled with product evaluation questionnaires in future studies might lend additional information regarding product use behaviors leading to PK and smoking urge responses. Overall, the findings of this study indicate that nicotine uptake from short-term use of e-cigarettes containing 1.6 % and 2.4 % nicotine are significant, but lower than those of tobacco cigarettes, yet the reduction in urge-to-smoke or craving symptoms are broadly comparable. Moreover, it was also found that the short-term use of e-cigarettes by adult smokers is well-tolerated as compared to tobacco cigarette use.\n\nQuestion:* Compared to Conventional tobacco cigarette what was the result of E-cigarettes on Serious adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1041	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy of Web-Based Weight Loss Maintenance Programs: A Randomized Controlled Trial Comparing Standard Features Versus the Addition of Enhanced Personalized Feedback over 12 Months\n\n ABSTRACT:\nFew randomized controlled trials (RCT) have evaluated the efficacy of web-based programs targeting maintenance of lost weight. The aims of this study were to evaluate two versions of a commercially available web-based weight loss maintenance (WLM) program and examine whether the provision of enhanced feedback was associated with better WLM. The study was an assessor-blinded RCT of change in body mass index (BMI) over 12 months WLM. Participants were 227 adults (44% male, 42.3 ± 10.1 years, BMI 30.4 ± 4.1 kg/m2) randomized to either a basic (Basic WLM) or enhanced program with additional support (Enhanced WLM). Analysis was intention-to-treat with imputation using last observation carried forward. There was no significant weight rebound from the start of weight loss maintenance to 12 months for either group (mean: basic 1.3%, enhanced 1.5%) and limited change in secondary outcomes for either program. There were no significant between-group differences in the primary outcome of change in BMI (basic −0.5 (1.9) kg/m2, enhanced −0.5 (1.6) kg/m2, p = 0.93). In conclusion, a web-based WLM program was effective in preventing weight regain over one year following weight loss. However, the addition of personalized e-feedback provided limited additional benefits compared to a standard program. Given the potential reach of web-based approaches, further research examining which web-based program components optimize weight outcomes long-term is required.\n\nBODY.1. INTRODUCTION:\nObesity rates are continuing to rise globally [1] in contrast to the limited access to treatment programs. While web-based approaches to treatment could potentially have broad reach, especially as households gain access to broadband internet, their evaluation in the context of longer-term follow-up has been limited. Studies have shown that passive follow-up with no active intervention after weight loss is associated with weight gain [2], with 50–80% of participants gradually regaining weight lost following treatment, with most regain occurring in the first year [3,4,5,6]. A systematic review of weight loss maintenance (WLM) trials found that active WLM interventions facilitated a 1.56 kg (95% CI −2.27 to −0.86 kg) lower weight regain compared with passive follow-up after 12 months. Most WLM studies have required attendance at group sessions and have been hampered by methodological issues, such as mainly recruiting females or mid-aged adults and including only those with a good response to an initial weight loss phase, while excluding those with low adherence. [7]. Few studies have evaluated the use of eHealth technologies (e.g., websites, smartphone applications, text messages) to deliver WLM interventions. Furthermore, most research in this area has looked at short-term interventions (<6 months) without longer-term follow-up [8,9]. The small number of longer-term studies have reported a gradual regain of weight lost following treatment, with regain occurring after the first six months [10,11]. A recent randomized controlled trial examined the effectiveness of a 12-week short message service (SMS) based WLM program following an initial 12-week commercial weight loss program. At three and nine months follow-up, there was no significant difference in weight maintenance between the usual care control group who received a brief telephone call providing lifestyle information and a mailed leaflet with advice on weight loss maintenance and the intervention group who received a weekly SMS to remind them to self-weigh in addition to the call [12]. A systematic review published in 2017, evaluated the efficacy of web-based interventions on weight loss or WLM in adults with overweight or obesity and found web-based interventions were more effective than minimal treatments but less effective than face-to-face interventions [13]. Furthermore, a recent systematic review concluded that there was insufficient evidence to recommend the use of eHealth interventions for WLM [14]. There were however promising results from the eHealth weight loss trials with the addition of newer technologies including text messages, self-monitoring devices, and mobile applications, with meta-analysis demonstrating significantly greater weight loss (1.46 kg [0.80, 2.13], p < 0.001) in interventions with enhanced behavioral features (e.g., individualized counselling, feedback on dietary intake or weight change) or technologies (e.g., addition of text messaging) than standard eHealth interventions. There is some evidence to suggest that these 'enhanced' interventions positively impact participant engagement, retention, and behavior change. We have previously published results of an online commercially available weight loss maintenance (WLM) program which demonstrated limited between-group differences for the basic and enhanced versions of the program after six months [15]. While the enhanced version resulted in greater retention (81.0% vs. 68.5%) and usage of the web-program, it did not result in a difference in weight loss [15]. A study using a 12-month intervention program (6-month weight loss plus a 6-month WLM) compared a self-directed web-based commercial program to a therapist-led behavioral web-based program and found greater weight loss in the behavioral web-based program than the therapist-led program at 12 months [16]. We have previously reported that adults randomized to this therapist-led web-based weight loss program initially lost more weight compared to wait list controls [17], and that there was no difference in weight loss between basic or enhanced versions of the weight loss program after either 12 weeks [17] or after 24 weeks [15] of participation. To date, no WLM trials have specifically evaluated the inclusion of enhanced behavioral features in an eHealth WLM program, including those outlined in Table S1, such as automatically-generated personalized reports; personalized feedback on diet, physical activity, and weight loss, as well as reminders to use the online diary, visit the website, and weigh-in. Therefore, the aim of the current study was to evaluate the impact of two versions of a WLM program on BMI in adults with overweight or obesity who had previously completed a weight loss program. The secondary aim was to compare differences in waist circumference and clinical measures including cholesterol, triglycerides, glucose and insulin between a standard version of a web-based WLM program (basic) and an enhanced version that provided additional personalized e-support.\n\nBODY.2. MATERIALS AND METHODS.2.1. PARTICIPANTS:\nAdults (BMI 25–40 kg/m2), aged 18–60 years were initially recruited into a weight loss trial in 2009 from the Hunter community in NSW, Australia [18]. Written informed consent was obtained from all participants for the weight loss maintenance trial. The study was approved by the University of Newcastle Human Ethics Research Committee (H-2009-0245) on 10 September 2009. The trial was registered with the Australian New Zealand Clinical Trials Registry, anzctr.org.au ACTRN12610000197033.\n\nBODY.2. MATERIALS AND METHODS.2.2. STUDY DESIGN:\nParticipants who completed an initial 24-week web-based weight loss intervention (The Biggest Loser Club, SP Health Co Pty Ltd., North Sydney, Australia) were randomly assigned into one of two weight loss maintenance groups for 12 months using a stratified randomized block design. Participants were allocated to either a basic weight loss maintenance program (Basic WLM) or an enhanced version of the weight loss maintenance program (Enhanced WLM) (see Figure 1). Both participants and the outcome assessors were blinded to group allocation. Detailed methods of the RCT have been published elsewhere [18]. The WLM programs were developed to follow on directly after completion of 24 weeks of a web-based weight loss program [15]. Program features and differences between groups are summarized in Table S1 and also described in detail elsewhere [18]. The Basic WLM group received free access to the weight loss program, but the weekly meal plans were based on an energy intake target equivalent to weight maintenance. The Enhanced WLM group received access to these same meal plans and dietary information, but they also received personalized system-generated feedback on their progress. The feedback on progress was provided using system-generated personalized reports that were populated with the data entered into the platform by the participant. Feedback included progress in relation to weight maintenance goals; usage of the online diet and physical activity diary (which was recommended but not mandated); usage patterns for website features; and level of success with weight loss. Those allocated to the enhanced group also received an escalating scale of email reminders followed by SMS text message reminders (if no response) to use the diary, visit the website, to 'weigh-in' by recording their weekly weight in the online program, and a relapse phone call if their recorded weight rebounded by ≥3% to remind them to return to weight loss mode (Table S1).\n\nBODY.2. MATERIALS AND METHODS.2.3. MEASURES:\nParticipants were assessed at baseline and 12 months [18] by blinded research assistants. Height, weight, waist circumference, and blood pressure were measured using standardized procedures [18] and BMI calculated. Following an overnight fast, blood samples were collected and analyzed for total cholesterol, low density lipoprotein (LDL), high density lipoprotein (HDL) cholesterol, triglycerides, glucose, and insulin by a single National Association of Testing Authorities accredited pathology service using standard automated techniques.\n\nBODY.2. MATERIALS AND METHODS.2.4. DATA ANALYSIS:\nBaseline variables were compared between treatment groups using analysis of variance (ANOVA) for continuous variables and chi-square tests for categorical variables. Analysis of covariance (ANCOVA) was used to test for group differences in outcomes at 12 months after adjusting for the baseline values of the outcome and sex. Analyses were performed in Stata v11 or SAS v9.2 (StataCorp, College Station, TX, USA). Intention-to-treat (ITT) analyses included all participants randomized at the weight loss management phase baseline, with missing follow-up data imputed using the last observation carried forward (LOCF).\n\nBODY.3. RESULTS:\nAt entry into WLM 227 participants were randomized to Basic WLM (n = 114) or Enhanced WLM (n = 113) program versions, with demographic data summarized in Table 1. Mean age was 43.3 (±9.7) years, with a mean BMI of 30.6 (±4.1) kg/m2, 42% were male and 95% were Australian-born (Table 1). There was no significant between-group difference in attrition after 12 months, basic 18.4% and enhanced 23.9%, p = 0.31. Both the Basic and Enhanced WLM groups successfully achieved WLM after 12 months with no significant rebound in weight. There were no significant between-group differences (p > 0.05) for the primary outcome of BMI with mean weight change (12 months—baseline) similar between the basic (−0.5 (1.9) kg/m2) and enhanced groups (−0.5 (1.6) kg/m2), p > 0.05 (Table 2). Table 2 shows that there were no significant differences in secondary outcomes between groups up to 12 months (p > 0.05).\n\nBODY.4. DISCUSSION:\nWhilst participants in both intervention arms of the current trial successfully maintained weight over one year of participating in a web-based program design to support maintenance of lost weight, those with access to the additional features designed to provide support and personalized feedback on diet, physical activity, and weight loss did not achieve better outcomes compared to those receiving access to the online program with minimal support. Both groups regained approximately one-and-a-half kilograms over the 12-month maintenance period, which was not significantly different between groups. This is comparable to results of the active intervention arms from a recent systematic review of all WLM intervention modes that included both food intake and physical activity advice, including group programs, face-to-face, and internet interventions [7]. The review included almost 3000 participants across 25 comparisons and found that the active intervention arms were associated with less weight regain of approximately 1.56 kg, up to 12 months [7]. This suggests that both active intervention arms in the current study were successful in achieving WLM. In our study, it appears that doing 'anything' was enough to support WLM, compared to the no-intervention arms in the systematic review, which also found no evidence that specific modes of intervention delivery were more effective than others. This suggests that having access to the level support provided in both the basic and enhanced versions of the current web-based WLM intervention, following a weight loss intervention did facilitate maintenance of lost weight. Given that it is well established that weight regain is common following initial weight loss [19], the results of the current study are important. Our systematic review evaluating effectiveness of 56 interventions that included a specific dietary component within the WLM intervention found that 14 achieved significant between-group differences at follow-up [2]. Furthermore, our recent systematic review and meta-analysis which evaluated the effectiveness of 84 e-Health interventions, found that e-Health weight loss interventions that include extra support strategies including counselling, personalized feedback, motivational interviewing and/or personal contact, appear to achieve significantly greater weight loss compared with standard eHealth interventions [13]. However, five studies which focused specifically on WLM interventions found no significant difference in weight change between eHealth WLM programs vs. control [14]. The authors concluded that there is currently insufficient evidence to recommended eHealth interventions for WLM and that further high-quality research is required to determine their effectiveness [14]. Although the included studies were heterogeneous the typical intervention characteristics were WLM interventions that lasted 39 weeks on average, had approximately 180 participants and attrition of 26% compared to the current WLM study which lasted 52 weeks had 227 participants and an attrition rate of 21%. The current study is important because individual studies to date suggest that face-to-face contact involving either weekly or monthly individual or group counseling sessions are more likely to achieve WLM than internet support in studies lasting 18 to 30 months. Recent systematic reviews on WLM interventions [7,14] suggest that there is a need for extended support for weight management following participation in weight loss programs internationally, as in-person attendance is not likely to be viable long-term. Hence, prolonged WLM support using eHealth technologies need to be evaluated for both feasibility, engagement, and cost-effectiveness in the long-term. Limitations include the lack of a wait list control group, which is similar to the majority of WLM maintenance studies to date [2]. Although the small sample size and attrition likely reduced the power to detect significant differences between groups for the secondary outcomes, it is similar to other WLM trials lasting 12 or more months which had an average drop-out of 20% [7]. Furthermore. results from the current study need to be interpreted with caution given the meta-analysis within the systematic review [14] indicates that there is no significant difference between the support methods during WLM. This is also supported by our review of web-based interventions which also reported no difference between these two methods of delivery [20]. Strengths include the RCT design, use of blinded assessors, and the comparison of two versions of the WLM program for 12 months, following an initial period of weight loss. Future studies should consider evaluating cost-effectiveness and efficacy in specific population groups for whom access services may be a challenge, based on a range of issues related to time, cost, convenience, rurality, health conditions, or other socio-economic factors. In conclusion, a commercial web-based weight loss maintenance program, with a specific intervention component targeting maintenance of lost weight can be effective at preventing weight re-gain up to one year following 24 weeks of weight loss. While the addition of enhanced features that provide additional feedback and social support did not provide additional benefits during maintenance, health professionals should advise clients that a specific WLM strategy does facilitate WLM up to one year following weight loss. Further research addressing level of feedback and support required to optimize weight status long-term in an online environment is required.\n\nQuestion: Compared to Basic weight loss maintenance program what was the result of Enhanced weight loss maintenance program on Weight rebound after 12 months?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1042	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy of Web-Based Weight Loss Maintenance Programs: A Randomized Controlled Trial Comparing Standard Features Versus the Addition of Enhanced Personalized Feedback over 12 Months\n\n ABSTRACT:\nFew randomized controlled trials (RCT) have evaluated the efficacy of web-based programs targeting maintenance of lost weight. The aims of this study were to evaluate two versions of a commercially available web-based weight loss maintenance (WLM) program and examine whether the provision of enhanced feedback was associated with better WLM. The study was an assessor-blinded RCT of change in body mass index (BMI) over 12 months WLM. Participants were 227 adults (44% male, 42.3 ± 10.1 years, BMI 30.4 ± 4.1 kg/m2) randomized to either a basic (Basic WLM) or enhanced program with additional support (Enhanced WLM). Analysis was intention-to-treat with imputation using last observation carried forward. There was no significant weight rebound from the start of weight loss maintenance to 12 months for either group (mean: basic 1.3%, enhanced 1.5%) and limited change in secondary outcomes for either program. There were no significant between-group differences in the primary outcome of change in BMI (basic −0.5 (1.9) kg/m2, enhanced −0.5 (1.6) kg/m2, p = 0.93). In conclusion, a web-based WLM program was effective in preventing weight regain over one year following weight loss. However, the addition of personalized e-feedback provided limited additional benefits compared to a standard program. Given the potential reach of web-based approaches, further research examining which web-based program components optimize weight outcomes long-term is required.\n\nBODY.1. INTRODUCTION:\nObesity rates are continuing to rise globally [1] in contrast to the limited access to treatment programs. While web-based approaches to treatment could potentially have broad reach, especially as households gain access to broadband internet, their evaluation in the context of longer-term follow-up has been limited. Studies have shown that passive follow-up with no active intervention after weight loss is associated with weight gain [2], with 50–80% of participants gradually regaining weight lost following treatment, with most regain occurring in the first year [3,4,5,6]. A systematic review of weight loss maintenance (WLM) trials found that active WLM interventions facilitated a 1.56 kg (95% CI −2.27 to −0.86 kg) lower weight regain compared with passive follow-up after 12 months. Most WLM studies have required attendance at group sessions and have been hampered by methodological issues, such as mainly recruiting females or mid-aged adults and including only those with a good response to an initial weight loss phase, while excluding those with low adherence. [7]. Few studies have evaluated the use of eHealth technologies (e.g., websites, smartphone applications, text messages) to deliver WLM interventions. Furthermore, most research in this area has looked at short-term interventions (<6 months) without longer-term follow-up [8,9]. The small number of longer-term studies have reported a gradual regain of weight lost following treatment, with regain occurring after the first six months [10,11]. A recent randomized controlled trial examined the effectiveness of a 12-week short message service (SMS) based WLM program following an initial 12-week commercial weight loss program. At three and nine months follow-up, there was no significant difference in weight maintenance between the usual care control group who received a brief telephone call providing lifestyle information and a mailed leaflet with advice on weight loss maintenance and the intervention group who received a weekly SMS to remind them to self-weigh in addition to the call [12]. A systematic review published in 2017, evaluated the efficacy of web-based interventions on weight loss or WLM in adults with overweight or obesity and found web-based interventions were more effective than minimal treatments but less effective than face-to-face interventions [13]. Furthermore, a recent systematic review concluded that there was insufficient evidence to recommend the use of eHealth interventions for WLM [14]. There were however promising results from the eHealth weight loss trials with the addition of newer technologies including text messages, self-monitoring devices, and mobile applications, with meta-analysis demonstrating significantly greater weight loss (1.46 kg [0.80, 2.13], p < 0.001) in interventions with enhanced behavioral features (e.g., individualized counselling, feedback on dietary intake or weight change) or technologies (e.g., addition of text messaging) than standard eHealth interventions. There is some evidence to suggest that these 'enhanced' interventions positively impact participant engagement, retention, and behavior change. We have previously published results of an online commercially available weight loss maintenance (WLM) program which demonstrated limited between-group differences for the basic and enhanced versions of the program after six months [15]. While the enhanced version resulted in greater retention (81.0% vs. 68.5%) and usage of the web-program, it did not result in a difference in weight loss [15]. A study using a 12-month intervention program (6-month weight loss plus a 6-month WLM) compared a self-directed web-based commercial program to a therapist-led behavioral web-based program and found greater weight loss in the behavioral web-based program than the therapist-led program at 12 months [16]. We have previously reported that adults randomized to this therapist-led web-based weight loss program initially lost more weight compared to wait list controls [17], and that there was no difference in weight loss between basic or enhanced versions of the weight loss program after either 12 weeks [17] or after 24 weeks [15] of participation. To date, no WLM trials have specifically evaluated the inclusion of enhanced behavioral features in an eHealth WLM program, including those outlined in Table S1, such as automatically-generated personalized reports; personalized feedback on diet, physical activity, and weight loss, as well as reminders to use the online diary, visit the website, and weigh-in. Therefore, the aim of the current study was to evaluate the impact of two versions of a WLM program on BMI in adults with overweight or obesity who had previously completed a weight loss program. The secondary aim was to compare differences in waist circumference and clinical measures including cholesterol, triglycerides, glucose and insulin between a standard version of a web-based WLM program (basic) and an enhanced version that provided additional personalized e-support.\n\nBODY.2. MATERIALS AND METHODS.2.1. PARTICIPANTS:\nAdults (BMI 25–40 kg/m2), aged 18–60 years were initially recruited into a weight loss trial in 2009 from the Hunter community in NSW, Australia [18]. Written informed consent was obtained from all participants for the weight loss maintenance trial. The study was approved by the University of Newcastle Human Ethics Research Committee (H-2009-0245) on 10 September 2009. The trial was registered with the Australian New Zealand Clinical Trials Registry, anzctr.org.au ACTRN12610000197033.\n\nBODY.2. MATERIALS AND METHODS.2.2. STUDY DESIGN:\nParticipants who completed an initial 24-week web-based weight loss intervention (The Biggest Loser Club, SP Health Co Pty Ltd., North Sydney, Australia) were randomly assigned into one of two weight loss maintenance groups for 12 months using a stratified randomized block design. Participants were allocated to either a basic weight loss maintenance program (Basic WLM) or an enhanced version of the weight loss maintenance program (Enhanced WLM) (see Figure 1). Both participants and the outcome assessors were blinded to group allocation. Detailed methods of the RCT have been published elsewhere [18]. The WLM programs were developed to follow on directly after completion of 24 weeks of a web-based weight loss program [15]. Program features and differences between groups are summarized in Table S1 and also described in detail elsewhere [18]. The Basic WLM group received free access to the weight loss program, but the weekly meal plans were based on an energy intake target equivalent to weight maintenance. The Enhanced WLM group received access to these same meal plans and dietary information, but they also received personalized system-generated feedback on their progress. The feedback on progress was provided using system-generated personalized reports that were populated with the data entered into the platform by the participant. Feedback included progress in relation to weight maintenance goals; usage of the online diet and physical activity diary (which was recommended but not mandated); usage patterns for website features; and level of success with weight loss. Those allocated to the enhanced group also received an escalating scale of email reminders followed by SMS text message reminders (if no response) to use the diary, visit the website, to 'weigh-in' by recording their weekly weight in the online program, and a relapse phone call if their recorded weight rebounded by ≥3% to remind them to return to weight loss mode (Table S1).\n\nBODY.2. MATERIALS AND METHODS.2.3. MEASURES:\nParticipants were assessed at baseline and 12 months [18] by blinded research assistants. Height, weight, waist circumference, and blood pressure were measured using standardized procedures [18] and BMI calculated. Following an overnight fast, blood samples were collected and analyzed for total cholesterol, low density lipoprotein (LDL), high density lipoprotein (HDL) cholesterol, triglycerides, glucose, and insulin by a single National Association of Testing Authorities accredited pathology service using standard automated techniques.\n\nBODY.2. MATERIALS AND METHODS.2.4. DATA ANALYSIS:\nBaseline variables were compared between treatment groups using analysis of variance (ANOVA) for continuous variables and chi-square tests for categorical variables. Analysis of covariance (ANCOVA) was used to test for group differences in outcomes at 12 months after adjusting for the baseline values of the outcome and sex. Analyses were performed in Stata v11 or SAS v9.2 (StataCorp, College Station, TX, USA). Intention-to-treat (ITT) analyses included all participants randomized at the weight loss management phase baseline, with missing follow-up data imputed using the last observation carried forward (LOCF).\n\nBODY.3. RESULTS:\nAt entry into WLM 227 participants were randomized to Basic WLM (n = 114) or Enhanced WLM (n = 113) program versions, with demographic data summarized in Table 1. Mean age was 43.3 (±9.7) years, with a mean BMI of 30.6 (±4.1) kg/m2, 42% were male and 95% were Australian-born (Table 1). There was no significant between-group difference in attrition after 12 months, basic 18.4% and enhanced 23.9%, p = 0.31. Both the Basic and Enhanced WLM groups successfully achieved WLM after 12 months with no significant rebound in weight. There were no significant between-group differences (p > 0.05) for the primary outcome of BMI with mean weight change (12 months—baseline) similar between the basic (−0.5 (1.9) kg/m2) and enhanced groups (−0.5 (1.6) kg/m2), p > 0.05 (Table 2). Table 2 shows that there were no significant differences in secondary outcomes between groups up to 12 months (p > 0.05).\n\nBODY.4. DISCUSSION:\nWhilst participants in both intervention arms of the current trial successfully maintained weight over one year of participating in a web-based program design to support maintenance of lost weight, those with access to the additional features designed to provide support and personalized feedback on diet, physical activity, and weight loss did not achieve better outcomes compared to those receiving access to the online program with minimal support. Both groups regained approximately one-and-a-half kilograms over the 12-month maintenance period, which was not significantly different between groups. This is comparable to results of the active intervention arms from a recent systematic review of all WLM intervention modes that included both food intake and physical activity advice, including group programs, face-to-face, and internet interventions [7]. The review included almost 3000 participants across 25 comparisons and found that the active intervention arms were associated with less weight regain of approximately 1.56 kg, up to 12 months [7]. This suggests that both active intervention arms in the current study were successful in achieving WLM. In our study, it appears that doing 'anything' was enough to support WLM, compared to the no-intervention arms in the systematic review, which also found no evidence that specific modes of intervention delivery were more effective than others. This suggests that having access to the level support provided in both the basic and enhanced versions of the current web-based WLM intervention, following a weight loss intervention did facilitate maintenance of lost weight. Given that it is well established that weight regain is common following initial weight loss [19], the results of the current study are important. Our systematic review evaluating effectiveness of 56 interventions that included a specific dietary component within the WLM intervention found that 14 achieved significant between-group differences at follow-up [2]. Furthermore, our recent systematic review and meta-analysis which evaluated the effectiveness of 84 e-Health interventions, found that e-Health weight loss interventions that include extra support strategies including counselling, personalized feedback, motivational interviewing and/or personal contact, appear to achieve significantly greater weight loss compared with standard eHealth interventions [13]. However, five studies which focused specifically on WLM interventions found no significant difference in weight change between eHealth WLM programs vs. control [14]. The authors concluded that there is currently insufficient evidence to recommended eHealth interventions for WLM and that further high-quality research is required to determine their effectiveness [14]. Although the included studies were heterogeneous the typical intervention characteristics were WLM interventions that lasted 39 weeks on average, had approximately 180 participants and attrition of 26% compared to the current WLM study which lasted 52 weeks had 227 participants and an attrition rate of 21%. The current study is important because individual studies to date suggest that face-to-face contact involving either weekly or monthly individual or group counseling sessions are more likely to achieve WLM than internet support in studies lasting 18 to 30 months. Recent systematic reviews on WLM interventions [7,14] suggest that there is a need for extended support for weight management following participation in weight loss programs internationally, as in-person attendance is not likely to be viable long-term. Hence, prolonged WLM support using eHealth technologies need to be evaluated for both feasibility, engagement, and cost-effectiveness in the long-term. Limitations include the lack of a wait list control group, which is similar to the majority of WLM maintenance studies to date [2]. Although the small sample size and attrition likely reduced the power to detect significant differences between groups for the secondary outcomes, it is similar to other WLM trials lasting 12 or more months which had an average drop-out of 20% [7]. Furthermore. results from the current study need to be interpreted with caution given the meta-analysis within the systematic review [14] indicates that there is no significant difference between the support methods during WLM. This is also supported by our review of web-based interventions which also reported no difference between these two methods of delivery [20]. Strengths include the RCT design, use of blinded assessors, and the comparison of two versions of the WLM program for 12 months, following an initial period of weight loss. Future studies should consider evaluating cost-effectiveness and efficacy in specific population groups for whom access services may be a challenge, based on a range of issues related to time, cost, convenience, rurality, health conditions, or other socio-economic factors. In conclusion, a commercial web-based weight loss maintenance program, with a specific intervention component targeting maintenance of lost weight can be effective at preventing weight re-gain up to one year following 24 weeks of weight loss. While the addition of enhanced features that provide additional feedback and social support did not provide additional benefits during maintenance, health professionals should advise clients that a specific WLM strategy does facilitate WLM up to one year following weight loss. Further research addressing level of feedback and support required to optimize weight status long-term in an online environment is required.\n\nQuestion: Compared to Basic weight loss maintenance program what was the result of Enhanced weight loss maintenance program on Change in body mass index?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1046	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomised controlled trial to evaluate the efficacy and usability of a computerised phone-based lifestyle coaching system for primary and secondary prevention of stroke\n\n ABSTRACT.BACKGROUND:\nOne of the most effective current approaches to preventing stroke events is the reduction of lifestyle risk factors, such as unhealthy diet, physical inactivity and smoking. In this study, we assessed the efficacy and usability of the phone-based Computer-aided Prevention System (CAPSYS) in supporting the reduction of lifestyle-related risk factors.\n\nABSTRACT.METHODS:\nA single-centre two-arm clinical trial was performed between January 2013 and February 2014, based on individual follow-up periods of six months with 94 patients at high risk of stroke, randomly assigned to an intervention group (IC: 48; advised to use the CAPSYS system) or a standard care group (SC: 46). Study parameters, such as blood pressure, blood values (HDL, LDL, HbA1c, glycaemia and triglycerides), weight, height, physical activity as well as nutrition and smoking habits were captured through questionnaires and medical records at baseline and post-intervention and analysed to detect significant changes. The usability of the intervention was assessed based on the standardised System Usability Scale (SUS) complemented by a more system-specific user satisfaction and feedback questionnaire.\n\nABSTRACT.RESULTS:\nThe statistical evaluation of primary measures revealed significant decreases of systolic blood pressure (mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]), LDL (pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]) and triglyceride values (pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]) in the intervention group, while no such changes could be observed in the control group. Furthermore, we detected a statistically significant increase in self-reported fruit and vegetable consumption (pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]) and a decrease in sweets consumption (pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]) in the intervention group. The usability assessment showed that the CAPSYS system was, in general, highly accepted by the users (average SUS score: 80.1).\n\nABSTRACT.CONCLUSIONS:\nThe study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is well applicable in practice.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov Identifier: NCT02444715\n\nBODY.BACKGROUND:\nLifestyle risk factors, such as unhealthy diet, physical inactivity and smoking, have a strong influence on the personal risk of stroke. Reducing such risk factors is currently one of the most effective approaches to preventing stroke events. According to the World Health Organization (WHO), \"most cardiovascular diseases can be prevented by addressing risk factors such as tobacco use, unhealthy diet and obesity, physical inactivity, high blood pressure, diabetes and raised lipids\" [1–3]. However, many individuals have difficulties adhering to recommendations concerning a healthy lifestyle, and long-term compliance with such lifestyle changes is usually low. Early findings in behavioural research support the assumption that the mere task of self-monitoring increases habit awareness, induces reflection on habits, and thus can provoke a positive change of the monitored behaviour [4]. Furthermore, experience has shown that sustained contact is necessary in order to support people in establishing and maintaining lifestyle changes [5]. In this context, the recently developed Computer-aided Prevention System (CAPSYS) offers a cost-effective automated solution combining remote surveillance of individual cerebro-cardiovascular risk factors with tailored advice [6]. Registered patients can access CAPSYS through a phone interface, simply by dialling a landline number. In an automated dialog, patients are asked to provide information about a predefined number of risk factors (current nutrition, physical activity, smoking, weight and blood pressure) by typing in the corresponding answers using the phone keypad. Based on the patient's answers, CAPSYS issues tailored feedback aiming at motivating a positive change towards or maintenance of healthy, risk-reducing habits. The system has been designed as a multi-language tool, in which the languages German and French have already been implemented and used within the trial. Clearly, a telephone as a user interface requires sufficient hearing abilities by the patients as well as the ability to understand and follow the instructions and advice issued by the virtual lifestyle coach. Consequently, this system is not appropriate for use by persons with severe hearing impairments or cognitive limitations. In cases of doubt, a patient's cognitive abilities can be evaluated by means of the Folstein mini-mental state test [7]. On the other hand, there is no problem for patients with difficulties in articulation or speech impediments to use CAPSYS, due to the fact that patient interaction does not involve any speech input but is purely limited to pressing buttons on the telephone keypad. In order to assess the efficacy of the CAPSYS approach concerning the reduction of stroke-related risk factors as well as the usability of the system, a dedicated study was designed and carried out, the results of which are presented in this article.\n\nBODY.METHODS:\nIn 2013 and 2014, a single-centre randomised controlled trial was carried out at the Department of Neurology of the Centre Hospitalier de Luxembourg. The study was designed as a six-month, parallel-group two-arm trial involving an intervention and a control group. Within this six-month study with a relatively limited number of participants, it was not possible to focus on the registration of severe events, such as stroke or death. Instead, the study concentrates on changes in different surrogate parameters for stroke (systolic blood pressure, BMI, HDL, LDL, HbA1c, glycaemia and triglycerides). A draft of the study design has already been presented in [8].\n\nBODY.METHODS.PARTICIPANTS:\nPatients aged 20 and over were eligible for the study if they had already suffered from a stroke or were at high risk of stroke (at least two risk factors according to the criteria described in [2, 9, 10]). The eligibility criteria are summarised in Table 1. Patients' stroke risk and thus their suitability to participate in the CAPSYS study were evaluated by the treating neurologist based on the patients' individual risk factor profiles.\nTable 1Eligibility criteria for the CAPSYS studyInclusion criteriaExclusion criteriaAge: 20 and over; At high risk of stroke:Inability to fill out or to understand the informed consent;∙ Already suffered a stroke or Transient Ischemic Attack (TIA) orNo signed informed consent;∙ At least two risk factors for stroke:– High blood pressure (systolic blood pressure ≥ 140 mmHg)Dementia– Overweight (BMI ≥ 25 kg/m2)– Low physical activity (less than 30 min. of moderate-intensity physical exercise per week)– Smoking– Unhealthy diet\n\nBODY.METHODS.RECRUITMENT AND RANDOMISATION:\nPotential study participants were approached in the course of their regular consultations with their neurologist, where they were screened for eligibility. Prior to their enrolment in the study, all participants signed a written informed consent; 94 participants were randomised by lot to one of two groups: Interventional Care (IC: 48, 34 [71 %] male) or Standard Care (SC: 46, 29 [63 %] male). Participants were aged between 32 and 86 (SC: mean = 59.6; SD = 12.1; median = 59) (IC: mean = 60.7; SD = 11.3; median = 61). The major characteristics of the study cohort are summarised in Table 2. Due to the specific design of the intervention, the study had to be carried out in an only partially blinded manner. It is inherent to the CAPSYS approach that the treating neurologist performs regular reviews of the data collected in the intervention group. The need to have access to patient histories and the possibility to contact patients at any time in case of emerging situations has limited the use of blinding methods within the trial. However, in order to ensure the validity of the study, the CAPSYS study team was separated into three different groups: a) principal investigator and treating neurologist responsible for the initial eligibility check of potential study participants, b) hospital research nurse responsible for patient recruitment and randomisation, and c) healthcare researchers who performed the statistical evaluation of the collected data by using pseudonymised data sets. During the recruitment meeting, patients were informed about the purpose of the study and about the study approach. The CAPSYS study design was approved by the Luxembourg National Research Ethics Committee (CNER) (N° 201205/08) and the National Commission for Data Protection (CNPD) (T007990).\nTable 2Descriptive statistics of the study cohortSC (n = 46)IC (n = 48)Mean age [years] (±SD)59.6 (±12.1)60.7 (±11.3)Men29 (63 %)34 (71 %)Mean BMI [ kg/m2] (±SD)27 (±4.3)28 (±4.3)Smokers2 (4 %)6 (13 %)Hypertension36 (78 %)43 (90 %)Hyper-/Dyslipidemia39 (85 %)44 (92 %)Diabetes mellitus5 (11 %)8 (17 %)Previous stroke/TIA37 (80 %)31 (65 %)\n\nBODY.METHODS.INTERVENTION:\nIn addition to the usual care, participants in the IC group were advised to regularly call the phone-based prevention system CAPSYS (preferably twice a week). In the course of the recruitment process, they were carefully instructed in the proper use of the system, and they were provided a corresponding user manual in form of a leaflet. The participants could access the CAPSYS system by calling a specific land line number with their stationary or mobile phones. After choosing their preferred language (French or German) and authenticating themselves with their individual patient number and PIN code, the participants were posed the following questions: \nHow many servings of fruits and vegetables have you consumed yesterday?How many servings of whole-grain food have you consumed yesterday?How many servings of sweets have you consumed yesterday?Please enter your current weight.How many cigarettes have you smoked yesterday? [removed for non-smokers]How many minutes have you been physically active yesterday? [moderate or high intensity]Please enter your current systolic blood pressure. The participants could answer to these questions by typing in the numerical values (number of servings, weight, minutes etc.) using the phone key pad. During the recruitment meeting at the beginning of the study, participants were instructed on how to estimate the size of one portion for the relevant food groups, and they were advised to measure their current blood pressure and weight, and to write down all necessary values prior to calling the CAPSYS system. Depending on the data provided by the patient, he or she received immediate customized feedback after each answer concerning his or her progress and advice on how to proceed reducing the corresponding risk factor or motivation on maintaining some observed healthy behaviour respectively. The phone call was closed with a concluding statement summing up the feedback issued before by the system. The questions and feedback were automatically generated by CAPSYS and were issued to the patients in spoken natural language by means of a text-to-speech software (TTS). The system was implemented to run fully automatically and could be accessed at any time of day. In case of systolic blood pressure higher than 140 mmHg, the patient was advised to rest for a while and then repeat the measurement. The system also advised the patients to contact a doctor in case of constantly high blood pressure. Patients with values above 140 mmHg were also particularly marked in the web interface when the treating physician accessed the system. Apart from that, all participants have been informed that there were no direct alerts in cases of high blood pressure provided within the study. The treating neurologist could access the data provided by his patients through a web interface, offering both a numerical as well as an adaptable graphical representation of the patient data for a certain period of time. The use of CAPSYS within the study has not replaced or reduced the existing information exchange between the neurologist and the corresponding referring physicians, which was proceeded according to the practices of the Luxembourgish healthcare system. Technically, CAPSYS offers the possibility for further physicians, e.g. the treating general practitioner, to access and monitor the data gathered from their patients. However, in the scope of this study, this option was deliberately discarded in order to avoid potential bias caused by the general practitioner accessing and interpreting the CAPSYS data. In contrast to the IC group, SC participants received only the usual care including blood analyses, blood pressure controls and individual advice on healthy lifestyle during the outpatient treatment given by the neurologist, by the general practitioner and by other physicians. Information material concerning a healthy lifestyle was provided to both groups.\n\nBODY.METHODS.DATA COLLECTION:\nDemographic and medical information of each participant was recorded by the study personnel in a predefined form, including body weight and height, medical history, current medication, smoking habits, blood pressure and heart rate as well as recent blood test results (HDL, LDL, HbA1c, glycaemia and triglycerides). Furthermore, participants were asked to fill in three questionnaires exploring their nutritional habits, physical activity and quality of life. The latter was measured using the standardised EQ-5D-5L instrument provided by the EuroQol Group [11]. Six months after enrolment, participants were asked to fill in the same questionnaires again, and current medical data (weight, blood pressure, heart rate, blood test results, smoking habits and medication) were again recorded by the study personnel. In addition, IC participants were asked to share their experiences with using CAPSYS and to provide their opinions about the system in a predefined questionnaire, which encompasses the well-established System Usability Scale (SUS) [12] and some further more specific questions concerning the usage of CAPSYS and its particular features. There was also space left for open-ended comments and suggestions at the end of the questionnaire.\n\nBODY.METHODS.DEPENDENT MEASURES:\nThe impact of the intervention was assessed based on the changes of cerebro-cardiovascular risk parameters during the six-month trial period, whereby changes in the IC group were compared to those in the control group (SC). Changes in systolic blood pressure, HDL, LDL, HbA1c, glycaemia, triglycerides and BMI were considered as primary dependent measures (see Table 3). Changes in self-reported weekly consumption of fruits and vegetables, whole grain food and sweets as well as changes in self-reported weekly duration of physical activity and quality of life were analysed as secondary measures. Due to the low number of smokers among the study participants (SC: 2, IC: 6), smoking habits were not evaluated.\nTable 3Overview of baseline values and evaluation of primary dependent measures in SC and IC groupsSCICBaselineEvaluationBaselineEvaluation\nParametric data\n\nMean (±SD)\n\nT-test\n\nMean (±SD)\n\nT-test\nSystolic BP [mmHg]139.6 (±21)mean of diff. =0.19145 (±19.4)mean of diff. =−9p =0.96\np\n= 0.03\n95 % CI = [–7.5, 7.88]95 % CI = [–17.29, –0.71]Cohen's d =0.42BMI [ kg/m2]27 (±4.3)mean of diff. =0.0328 (±4.3)mean of diff. =−0.18p =0.9p =0.4395 % CI = [–0.49, 0.55]95 % CI = [–0.65, 0.28]\nNon-parametric data\n\nMedian [IQR]\n\nWilcoxon\n\nMedian [IQR]\n\nWilcoxon\nHDL [ mg/dl]57 [45, 51]pseudo-median of diff =1.553 [47, 74]pseudo-median of diff =−1.5p =0.53p =0.4495 % CI = [–2.5, 4.5]95 % CI = [–4.5, 2]LDL [ mg/dl]96 [71, 114]pseudo-median of diff =−195 [76, 117]pseudo-median of diff =−7.9p =0.76\np\n= 0.04\n95 % CI = [–10.5, 6]95 % CI = [–18.5, –0.5]r =0.24HbA1c [ %]5.8 [5.6, 5.9]pseudo-median of diff =05.9 [5.5, 6.25]pseudo-median of diff =0.1p =0.92p =0.3795 % CI = [–0.25, 0.2]95 % CI = [–0.1, 0.25]Glycaemia [ mg/dl]98 [89, 106.75]pseudo-median of diff =0.5102 [92.5, 114.5]pseudo-median of diff =2.5p =0.78p =0.1995 % CI = [–5.5, 5]95 % CI = [–2, 6]Triglycerides [ mg/dl]95 [73, 134.25]pseudo-median of diff =−6105 [78, 132.5]pseudo-median of diff =−12.5p =0.39\np\n= 0.04\n95 % CI = [–21, 10]95 % CI = [–26, –0.5]r =0.25(statistically significant values are marked in bold) Statistical analyses were carried out on an intention-to-treat basis using RStudio (Version 0.98.978) with a significance level of 0.05. Parametric data (paired and unpaired samples) were evaluated with the Student's t-test approach, and the corresponding effect size was calculated with Cohen's d. Non-parametric data were evaluated using the Wilcoxon signed-rank test (for paired samples) or the Mann-Whitney U test (for unpaired samples) respectively, and effect size was calculated as \\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym} \n\t\t\t\t\\usepackage{amsfonts} \n\t\t\t\t\\usepackage{amssymb} \n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$r = \\frac {Z}{\\sqrt {N}}$\\end{document}r=ZN. For non-parametric paired samples, the pseudo-median is computed as the Hodges-Lehmann estimate.\n\nBODY.RESULTS.EFFICACY OF THE INTERVENTION:\nFinal questionnaires on nutritional habits, physical activity and quality of life could be collected from 68 participants (SC: 36; IC: 32) at the end of the study. This results in an overall dropout rate of 28 % (SC: 22 %; IC: 33 %). Further participant data, such as blood test values, could be retrieved from medical records. Out of the 48 recruited IC participants, 11 (23 %) did not use CAPSYS at all. The remaining 37 IC subjects (77 %) called the system up to 55 times during the study period (mean = 23.32; SD = 14.1; median = 24). Within-subjects analyses of primary dependent measures showed the following statistically significant changes between baseline and post-intervention: \nDecrease of systolic blood pressure in IC group (two-sided paired-samples t-test: mean of the differences = –9 mmHg; p = 0.03; 95 % CI = [–17.29, –0.71]; Cohen's d = 0.42: large effect size) (see Fig. 1), with no corresponding significant difference in SC group (p = 0.96);\nFig. 1Systolic blood pressure. Significant decrease of systolic blood pressure in IC groupDecrease of low-density lipoprotein (LDL) levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –7.9 mg/dl; p = 0.04; 95 % CI = [–18.5, –0.5]; r = 0.24: medium effect size), with no corresponding significant difference in SC group (p = 0.76) (see Fig. 2);\nFig. 2LDL. Significant decrease of LDL levels in IC groupDecrease of triglyceride levels in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –12.5 mg/dl; p = 0.04; 95 % CI = [–26, –0.5]; r = 0.25: medium effect size), with no corresponding significant difference in SC group (p = 0.39) (see Fig. 3);\nFig. 3Triglycerides. Significant decrease of triglyceride levels in IC groupNo statistically significant changes could be found for any of the other primary measures (BMI, HDL, HbA1c and glycaemia). In this context, it needs to be stated that, at baseline, there were no statistical differences between both groups concerning the proportions of patients taking antihypertensives (SC: 36 [78 %]; IC: 43 [90 %]; p = 0.22), antidiabetic drugs (SC: 5 [11 %]; IC: 8 [17 %]; p = 0.61) or cholesterol-lowering medication (SC: 39 [85 %]; IC: 44 [92 %]; p = 0.47). Concerning the secondary dependent measures, we could observe the following statistically significant results: \nIncrease of self-reported fruit and vegetable consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = 5.4 servings/week; p = 0.04; 95 % CI = [0.5, 10.5]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.67);Decrease of self-reported sweets consumption in IC group (Wilcoxon signed-rank test: pseudo-median of the differences = –2 servings/week; p = 0.04; 95 % CI = [–4, –0.00001]; r = 0.26: medium effect size), with no corresponding significant difference in SC group (p = 0.06);Difference between SC and IC groups concerning the change of self-reported whole-grain food consumption (Mann-Whitney U test: difference in location = 3.26 servings/week; p = 0.04; 95 % CI = [0.00006, 7]; r = 0.24: medium effect size);No statistically significant changes for self-reported physical activity and quality of life.\n\nBODY.RESULTS.USABILITY AND USER ACCEPTANCE OF THE INTERVENTION:\nAssessments of the intervention based on the System Usability Scale (SUS) were provided by 28 participants of the IC group, 2 of which were declared invalid, as these participants have demonstrably never used CAPSYS during the trial period, and consequently, they were considered unable to assess the intervention. The average SUS score for CAPSYS was 80.1 (SD = 16.22; median = 78.75; min = 37.5; max = 100; 95 % CI = [73.54, 86.65]). According to Sauro and Lewis, this average score corresponds to an \"A–\" school grade and a percentile of 85–89, meaning that CAPSYS scored better than 85 to 89 % of all systems considered in the Sauro and Lewis study (see [13], chapter 8, page 204, table 8.6). Using the simplified regression equation proposed by Lewis [14], the Likelihood to Recommend for each CAPSYS user was derived from the corresponding SUS scores as LTR = SUS/10. With these values, we could identify 10 promoters (38 %; LTR ≥ 9) and 4 detractors (23 %; LTR ≤ 6) among the 26 participants who provided valid SUS scores, which results in a positive Net Promoter Score (NPS) of 23 [15], meaning that there are 23 % more users who would recommend CAPSYS (promoters) than users who would argue against using the system (detractors). Beside the standardised SUS questionnaire, IC participants were also asked to asses the voice of the text-to-speech module applied in CAPSYS and the automatically generated utterances issued by the system. The results concerning these questions are presented in Table 4.\nTable 4Evaluation of CAPSYS's voice and utterancesScaleResultsVoice1: pleasant – 5: unpleasantmean =1.77;median =1.5;SD =0.991: difficult to understand – 5: easy to understandmean =4.28;median =5;SD =1.141: natural – 5: unnaturalmean =2.15;median =2;SD =1.121: too fast – 5: too slowmean =3.2;median =3;SD =0.5Utterances1: diversified – 5: unvariedmean =3.28;median =4;SD =1.241: inappropriate – 5: appropriatemean =3.46;median =3;SD =1.071: too short – 5: too longmean =3.2;median =3;SD =0.5 Concerning the frequency of use, the majority of the 26 IC participants who answered to the usability questionnaire indicated that they would prefer using CAPSYS once (11; 42 %) or twice (9; 35 %) per week. None of the respondents was willing to use the system more than twice a week, 2 (8 %) preferred to use it less than once a week and 4 (15 %) expressed that they would not use it at all. The approach of connecting to CAPSYS by calling the system whenever they wish was favoured by most of the respondents (18; 69 %) over the potential alternatives of being called by the system (3; 12 %) or receiving reminders to call the system (2; 8 %). Although CAPSYS does not offer speech recognition, we asked users if they prefer to have such an input option instead or in combination with the implemented keypad input. In this context, using the phone keypad was identified as the most preferred way of communication with such a system (20; 77 %) as compared to speech input (1; 4 %) or a combination of both (4; 15 %). The majority of the respondents were interested in having insight into the data history gathered by CAPSYS, either online (9; 35 %) or in a printed version (11; 42 %). Concerning a potential alternative interface for CAPSYS beside the phone interface, 10 (38 %) participants were interested in a corresponding website and 4 (15 %) fancied the idea of having a CAPSYS smartphone app. Regarding the question if the use of CAPSYS has motivated them to a healthier lifestyle, 5 (19 %) of the respondents stated that through the intervention they started eating healthier, 3 (12 %) reported to have become physically more active and 12 (46 %) claimed to have achieved both healthier eating and increased physical activity. This means that, in total, 20 (77 %; 95 % CI = [59 %, 95 %]) of the respondents expressed an improvement of their health-related lifestyle (improved nutrition or increased physical activity or both) through the use of CAPSYS.\n\nBODY.DISCUSSION:\nThe positive effects that could be observed in the IC group concerning systolic blood pressure, LDL and triglyceride levels as well as the self-reported improvements of nutritional habits can be regarded as an indicator that a computerised phone-based intervention, such as CAPSYS, can support the reduction of cerebro-cardiovascular risk when offered in addition to usual care. An average decrease in systolic blood pressure of 9 mmHg among CI participants can be regarded as clinically significant [16]. The same also holds for the observed average decreases of 7.9 mg/dl for LDL [17] and 12.5 mg/dl for triglycerides [18]. Though, the relatively wide 95 % confidence intervals retrieved in the statistical analysis indicate that the cohort size was probably too small to be able to demonstrate strong clinical effects. The evaluation of BMI, HDL, HbA1c and glycaemia values showed no significant changes in the two groups. Our results are to some extent supported by the recently published Australian CLIP study, which found that telephone coaching performed by human health care professionals can result in a significant reduction of LDL and total cholesterol values in the intervention group [19]. A systematic review by Goode et al. also underlines the efficacy of telephone-based lifestyle coaching. In 20 out of 26 studies, telephone support by health professionals have led to significant improvements concerning physical exercises and healthy nutrition [20]. However, personal telephone coaching by health experts requires intensive use of human resources and is associated with enormous costs, which limits its widespread distribution to larger patient groups. CAPSYS is a system that supports prevention initiatives by supporting individuals in daily life settings. It can be assumed that a large percentage of the total target group is not willing to perform any lifestyle changes at all, no matter which kind of support they will receive. So, it has to be taken into account that our study participants are a selected subgroup of the target population with a potentially higher motivation to change risk factors and lifestyle. However, this selection bias in general concerns all prevention initiatives, and the randomisation process should ensure that the general motivation is balanced across both study arms. Compared to therapy studies, participants in prevention studies mostly do not see any direct measurable advantages in their actual health status. Missing short-term improvements are therefore often a reason for higher dropout rates. However, compared to other studies in secondary prevention, the moderate and balanced dropout rates of both CAPSYS arms should not have significantly affected the study results. On the other hand, self-reported consumptions of fruits, vegetables or sweets have a high potential for reporting bias. Therefore, in our study, this kind of information is only considered as secondary depended measures. The improvements of nutritional habits in the IC group (5 servings of fruits and vegetables more per week; 2 servings of sweets less per week) are significant, but have to be treated with caution as they are based on self-reported values and thus less reliable. As the dropout rates were not significantly different for both groups (SC: 22 %; IC: 33 %; p = 0.31), it can be supposed that the withdrawal of IC patients from the clinical trial was not substantially influenced by the intervention itself, but it was due to common reasons, like lack of time, forgetting appointments or just lack of motivation. Furthermore, it remains open how the observed positive effects will evolve after the study period and if they actually are of a long-term nature. The usability evaluation revealed that the CAPSYS approach was well accepted by the study participants. In particular, the large proportion of respondents (77 %) expressing a positive change of health-related behaviour due to the use of CAPSYS is remarkable. One might argue that this result is strongly biased due to the fact that users who have a positive experience with a system are more likely to finish a study and provide corresponding feedback than users with negative experiences. However, even if we consider all dropout IC participants as non-beneficiaries, the success rate concerning a positive health behaviour change would still be 42 % (95 % CI = [27 %, 57 %]). Unfortunately, our cohort was not large enough to perform subgroup analyses in order to evaluate the characteristics of beneficiaries and non-beneficiaries. A follow-up study focussing on such aspects might help to identify appropriate target groups for which a system like CAPSYS might be most beneficial and most accepted. During informal interviews at the end of the study, many of the IC participants explained that they often could not find the time or simply forgot to call CAPSYS. Taking this into account, the implementation of a call reminder functionality seems beneficial, even though in the feedback questionnaire, the majority of the respondents did not favour the concepts of being called or reminded by the system. Another important issue concerning risk factor reduction in the stroke prevention context is the topic of medication adherence. In order to support users in regularly taking their antihypertensive or cholesterol-lowering medication, CAPSYS could be extended to incorporate prompts in its automatically generated feedback messages asking the users if they have taken their prescribed medication according to their individual medication plan. Concerning the technical implementation of CAPSYS, it could be observed that, on average, the artificial voice applied in CAPSYS was perceived as rather pleasant, easy to understand and natural, and the speech rate was perceived as appropriate. The length of the utterances was, on average, perceived as adequate, but the feedback text might also be shortened to some extent. The results also show that there is some space for improvement concerning the diversity and adequacy of the automatically generated feedback. The offered keypad interface for data input was highly accepted by the users, and the need for an alternative input method, such as speech, was detected to be low. Unsurprisingly, only few users were currently interested in a mobile app version of CAPSYS. However, with increasing spread of smartphones, a mobile solution will certainly gain in importance in the future. What is already important for most users is to have access to their own self-monitored data, even if due to technical reasons they might only be able to access them in a printed form.\n\nBODY.CONCLUSION:\nIn summary, the present study provided encouraging results indicating that a computerised phone-based lifestyle coaching system, such as CAPSYS, can support the usual treatment in reducing cerebro-cardiovascular risk factors and that such an approach is in general well accepted by the affected patients. In a next step, CAPSYS could be extended to a disease management tool, involving health professionals from different disciplines, such as neurologists, cardiologists, dieticians, physiotherapists etc., in the treatment of patients. One aspect that could be explored in future research is if the motivational effect of CAPSYS could be strengthened through an increased involvement of the treating physician and through incorporation of social interaction.\n\nQuestion:* Compared to Standard care what was the result of CAPSYS system on Triglyceride levels?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1054	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomized comparison of etoposide pharmacokinetics after oral etoposide phosphate and oral etoposide.\n\n ABSTRACT:\nEtoposide phosphate is a water-soluble prodrug of etoposide. The plasma pharmacokinetics of etoposide following oral administration of etoposide phosphate or oral etoposide were compared. Seventeen patients with solid tumours were enrolled to receive oral etoposide phosphate 125 mg m(-2) on days 1-5 every 3 weeks, with escalation to 175 mg m(-2) from course 3 when possible. Patients were randomized to receive oral etoposide phosphate or oral etoposide on day 1 of course 1 and the alternative compound on day 1 of course 2. Fifteen patients received two or more courses and were evaluable for pharmacokinetic comparisons. The median AUC(inf) (area under the concentration vs time curve from zero to infinity) of etoposide was 77.7 mg l(-1) h after etoposide phosphate (95% CI 61.3-100.5) and 62.0 mg l(-1) h after oral etoposide (95% CI 52.2-76.9). The difference in favour of etoposide phosphate was borderline significant: median 9.9 mg l(-1) h (95% CI 0.1-32.8 mg l(-1) h; P = 0.05). However, the inter-patient variability of etoposide AUC(inf) was not improved (coefficients of variation 42.3% and 48.4%). Etoposide phosphate was undetectable in plasma after oral administration. Toxicities of oral etoposide phosphate were not different from those known for etoposide. In conclusion, oral etoposide phosphate does not offer a clinically relevant benefit over oral etoposide.\n\nBODY:\n\nQuestion: Compared to Oral etoposide what was the result of Oral etoposide phosphate on Median AUC(inf)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1057	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of Neuromuscular Electrical Stimulation Combined with Exercises versus an Exercise Program on the Pain and the Function in Patients with Knee Osteoarthritis: A Randomized Controlled Trial\n\n ABSTRACT:\n\nObjectives. To investigate the effect of 8 weeks of NMES + Ex (neuromuscular electrical stimulation combined with exercises) on pain and functional improvement in patients with knee osteoarthritis (OA) compared to exercise (Ex) alone. Design. Randomized controlled trial. Setting. A specialty outpatient clinic. Participants. Patients (N = 100; women = 86, men = 14; age range, 50–75 years) with knee OA. Interventions. Participants were randomly assigned to NMES + Ex or Ex group. Outcome Measures. Numerical Rating Scale 0 to 10 (NRS) and the Timed Up and Go (TUG) test were the primary outcomes. The secondary outcomes used were the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Results. Following the interventions, a statistically significant improvement in both groups was observed in all outcomes assessed. For the comparison between the groups, no statistically significant difference was found between the NMES + Ex and the Ex groups in NRS (P = 0.52), TUG test (P = 0.12), and aspects of WOMAC: pain (P = 0.26), function (P = 0.23), and stiffness (P = 0.63). Conclusion. The addition of NMES to exercise did not improve the outcomes assessed in knee OA patients. This study was registered at the Australian Clinical Trials Registry (ACTRN012607000357459).\n\nBODY.1. INTRODUCTION:\nOsteoarthritis (OA) is the most common form of arthritis. It affects one-third of adults and tends to increase with age [1]. Knee OA is associated with symptoms of pain, swelling, instability, and reduced range of motion (ROM). These symptoms lead to functional impairment, increasing the risk of morbidity and mortality [2, 3]. The synovium is infiltrated with inflammatory cells and secretes excess synovial fluid, leading to capsular swelling [4]. Through a spinal reflex, the capsular swelling inhibits muscle activation, which, combined with disuse, may cause muscle weakness and atrophy [1]. Because the quadriceps muscle acts as shock absorber for the knee joint, weakness in the thigh muscle reduces joint protection, resulting in overload [4]. Exercises strengthen the muscles, reduce pain, improve physical function, and are therefore considered a major intervention in the conservative treatment of patients with knee OA [5]. In addition to muscle strengthening exercises, stretching exercises are commonly used to increase ROM and are often prescribed in rehabilitation protocols as part of routine warm-up to prepare the muscles and joints for other types of exercise, such as aerobic and strengthening programs [6, 7]. Stretching of the hamstring muscles may improve knee extension ROM in OA patients. Neuromuscular electrical stimulation (NMES) is defined as the application of electrical stimulation using surface electrodes placed over skeletal muscles to produce visible muscle contraction through the activation of intramuscular nerve branches [8]. This technique can also be used as a form of physical therapy in the treatment of patients with knee OA. The goals of rehabilitation protocols that include NMES are to provide additional stimulus to increase muscle strength in patients with knee OA [9]. The methods and findings of previous studies on the effectiveness of NMES in knee OA differ in the modulation of NMES parameters, choice of the outcomes used to evaluate the patients, and characteristics of the control groups. This leads to a lack of consensus regarding the effectiveness attained from including NMES in conventional rehabilitation protocols. Major flaws with regard to methodological quality were found in clinical trials testing the use of NMES in the conservative treatment of patients with knee OA. Only one of these studies reported using allocation concealment, blinded assessment, and intention-to-treat analysis [10]. Thus, the objective of this study was to conduct a randomized clinical trial following methodological criteria, including allocation concealment, blinding of the examiner, and application of intention-to-treat analysis to assess the role of NMES in improving pain and physical function in patients with knee OA. It is important to study interventions with the potential to improve functional status in this patient population [11]. \n\nBODY.2. METHODS:\nThe study was conducted at the Interlagos Specialty Outpatient Clinic, São Paulo, Brazil. Patients were referred from the Rheumatology Department according to the inclusion and exclusion criteria and randomly allocated into groups using a computer-generated randomization chart. The allocation codes were sealed in opaque envelopes by a third person not involved in the study to avoid selection bias. Written informed consent was obtained from all participants. The study was approved by the Research Ethics Committee of the Universidade Federal de São Paulo (UNIFESP), Brazil, no. 0141/07, and registered with the Australian Clinical Trials Registry, no. ACTRN012607000357459. Setting the significance level at 5% and the power of the sample at 80%, a sample size of 40 patients per group was estimated to be necessary to detect a difference of at least 1 minute ± 3 seconds in the Timed Up and Go (TUG) test, which was considered to be the minimum clinically significant difference for the present trial [12]. Paired Student's t-test and analysis of covariance (ANCOVA) were used for comparisons between groups; the covariant was obtained from a previous study [13]. One hundred patients were recruited according to inclusion and exclusion criteria. Eligibility criteria were age 50 to 75 years, OA grade 2 or greater according to the radiographic classification of OA proposed by Kellgren and Lawrence [14], and diagnosis of knee OA based on the American College of Rheumatology (ACR) criteria. Exclusion criteria were use of a pacemaker, unstable heart conditions, participation in another physical activity program, inability to exercise on a stationary bicycle ergometer, inability to walk, previous hip or knee arthroplasty, diagnosis of fibromyalgia, epilepsy, and skin tumor or lesion at the NMES application site. Patients were divided into two groups of 50 each: (1) the NMES combined with exercises (NMES + Ex) group and (2) exercise (Ex) group. Patient medication was standardized and not modified during the study period. Paracetamol was prescribed for pain, and diacerein and chloroquine for OA control. Interventions were delivered for both groups by the same physical therapist, twice a week, for 8 weeks, with each session lasting about 40 minutes. All patients received a manual including guidelines on how not to overload the knee during daily activities and instructions on the use of ice packs in case of pain and inflammation and warm compresses in case of pain without inflammation as follows. \nManual for Patients with Osteoarthritis of the Knee. The purpose of this manual is to explain osteoarthritis and to teach how you can adjust yourself to your daily activities, according to the knee symptoms. Try to seriously follow our orientations for your own benefit! \nThe Knee. The knee joint is composed of 3 bones—the femur (thigh bone), the patella (kneecap) and the tibia (leg bone). It has muscles, capsule, ligaments, meniscus, and the cartilage that lines the bones and protects them from the impact. The knee joint supports nearly the whole weight of our body. \nWhat Is Osteoarthritis? It is a disease caused by the breakdown of cartilage in the joints. The layers in the cartilage become damaged and with time they lose the function of smoothing the contact between the bone surface and the joints. The pain is a result of the attrition of one bone against the other in the absence or decreased cartilage in the joints. \nWhat Are the Signs and Symptoms? Patients with osteoarthritis may have some pain mainly when starting a movement, as in morning stiffness or after immobilization. With time, the pain might be intensified and be permanent. The presence of crepitation when moving the knees is often. \nWhat Kind of Difficulties Might I Have in My Daily Life? Difficulties found in daily live vary according to the patients' symptoms. In general, however, the patient has pain and difficulty when supporting the body weight using the affected knee, going up and down the stairs, or when walking. \nWhat Should I Do When It Is Painful? A doctor can prescribe the treatment for osteoarthritis. However, a simple form of improving the pain is to use warm to hot water bottle over the knee joint (be careful not to burn the skin, use a protection, and test the water temperature before using it. \nWhat If It Is Swollen? To manage the swollen, you can combine rest, use of ice pack, and elevating the leg above the level of the heart. The ice pack should be placed over the knee joint for 20 minutes. \nWhat Are the Other Recommendations?\nIf you are overweight, losing some kilos will reduce the stress over the joint. Wear comfortable shoes with a rubber sole and no heels.In case of pain when walking, use a cane as an aid tool.Try to have a good night sleep.\n\n\nBODY.2. METHODS.2.1. NMES COMBINED WITH EXERCISE GROUP:\nTreatment for patients in the NMES + Ex included 10 minutes on a stationary bicycle, stretching of hamstring muscles (3 repetitions of 30 seconds) with the aid of an elastic band, and loaded quadriceps strengthening exercises combined with NMES. The strengthening exercise with NMES was performed in the sitting position with the knee and hip flexed to 90 degrees; patients contracted their quadriceps at each NMES stimulus. NMES was applied using an electrical stimulator (Globus ACTIVA 600 Pro, Globus, Italia) with two 7.5 × 13 cm self-adhesive electrodes (ValuTrode electrodes, Axelgaard Manufacturing Co. Ltd., Fallbrook, CA) placed over the region of the quadriceps muscle (rectus femoris and vastus medialis). NMES parameters were as follows: pulsed current, biphasic, asymmetrical, rectangular waveform, frequency 50 Hz, pulse duration 250 μs, contraction time 10 s, rest time 30 s every 20 minutes; current intensity was the maximum tolerated by each patient [15]. \n\nBODY.2. METHODS.2.2. EXERCISE GROUP (EX):\nPatients in the Ex group performed the same exercise program as those in the NMES group but without NMES. The exercise protocol included 10 minutes of warm-up on a stationary bicycle ergometer, stretching of hamstrings muscles with the aid of an elastic band, and knee extension exercises performed for 3 sets of 15 repetitions with rest intervals of 30–45 seconds between sets. For both groups, the training load for the strengthening exercises was established based on 50–60% of the 10-repetition maximum (RM) instead of 1 RM to avoid injury by excessive muscle contraction [16].\n\nBODY.2. METHODS.2.3. OUTCOMES:\nPatients were evaluated before and after intervention by a physical therapist blinded to group assignment. The primary outcomes were the TUG test results [12] and pain walking on a flat surface in the last 72 h measured on an 11-point Numerical Rating Scale (NRS) [17]. The secondary outcomes were scores on the pain, physical function, and stiffness subscales of the culturally validated Brazilian-Portuguese version of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) [18, 19]. In this study, WOMAC pain, physical function, and stiffness scores were analyzed separately. \n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nPaired Student's t-test was performed to compare pre- and postintervention values at a significance level of 0.05 (P < 0.05). Statistical analysis was performed on an intent-to-treat (ITT) basis and included all patients who were randomized to treatment. Mixed model analysis of variance with repeated measures was used with occasion measures as within-group factors and intervention as between-group factor. Relations between the observations were analyzed using an unstructured covariance matrix. Missing-data imputation was not performed to evaluate pre- and postintervention differences between the two groups, because Chakraborty and GU [20] showed that mixed model analysis without missing-data imputation always provides equal or more power than does mixed model analysis with missing-data imputation. Effect size was calculated as the difference between the means divided by the standard deviation using Cohen's d [21]. The analyses were performed using the General Linear Model (GLM), and mixed analyses were carried out using the Statistical Analysis Software (SAS) version 9.2 for Windows [22].\n\nBODY.3. RESULTS:\nThe demographic and clinical characteristics of patients, including age, sex, side treated, and body mass index (BMI), as well as TUG test values, NRS pain scores, and WOMAC scores on the pain, physical function, and stiffness subscales, are shown in Table 1. Eighty-seven patients completed the study. Of the 13 dropouts, 6 (12%) patients were in the NMES + Ex group and 7 (14%) in the Ex group (Figure 1). \n\nBODY.3. RESULTS.3.1. PRIMARY OUTCOMES:\nNo significant differences between groups were found in NRS pain scores and TUG test time on ITT analysis. A significant decrease in pain intensity (NRS scores) and TUG test time was observed after intervention compared with baseline in the NMES + Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001) and Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001). The primary outcomes are listed in Table 2. \n\nBODY.3. RESULTS.3.2. SECONDARY OUTCOMES:\nNo significant differences between groups were found on the pain, physical function, and stiffness subscales of the WOMAC index on ITT analysis. There was a significant improvement in all WOMAC subscales in the NMES + Ex group (pain; P < 0.0001; physical function, P < 0.0001; stiffness, P < 0.0001) and in the Ex group (pain, P < 0.0001; physical function, P < 0.0001; stiffness, P = 0.0009). The secondary outcomes are listed in Table 2.\n\nBODY.3. RESULTS.3.3. ADVERSE EFFECT:\nOne patient in the NMES + Ex group exhibited a blood pressure spike, which may have resulted from the use of NMES or from the exercise program itself. The following contraindications to the use of NMES were respected: avoiding the use of NMES over areas of tumor, with open wounds, or bleeding, and in patients with pacemakers [15].\n\nBODY.4. DISCUSSION:\nIn this randomized clinical trial, the NMES combined with exercise did improve pain and physical function, but there was no evidence that it did better than exercise alone. Our results are in agreement with the findings of Rosemffet et al. [23] who conducted a pilot study comparing the treatment results of patients with knee OA (n = 26) treated with either NMES alone or exercises alone or exercises combined with NMES. The authors reported a significant improvement on the WOMAC pain subscale in the three groups, but no significant differences in WOMAC scores were found between groups [23]. The lack of difference in treatment outcome between groups in the present study might be attributed to the fact that the participants had no clinically significant muscle or functional impairment. A finding substantiating this hypothesis is that the mean TUG test values in the two groups were similar to those found in the study of Steffen et al., for elderly patients with no physical limitations categorized under the same mean age group [24]. The TUG test values reported were 8 ± 2 seconds for patients with 60–69 years old and 9 ± 3 seconds for patients with 70–79 years old. In the present study, the baseline values for TUG test were 8.27 + 1.76 for NMES + Ex group and 9.34 ± 2.47 for Ex group. Given that the greater the muscle impairment, the greater the NMES effect, patients with a more advanced stage of OA might obtain greater benefit from NMES [25–27]. With regard to evidence on the effectiveness of NMES in the rehabilitation of patients with knee OA, the Cochrane Collaboration published a systematic review evaluating the pre- and postoperative use of NMES in total knee arthroplasty [28]. The two studies that were evaluated were classified as being at high risk of bias, because randomization and allocation concealment were not described, and no data obtained from the study groups were presented in terms of means and standard deviations. It was not possible to determine whether or not the pre- and postoperative use of NMES was effective in the rehabilitation of knee arthroplasty patients, and therefore further studies are warranted. Regarding lines of evidence on the effectiveness of NMES in the treatment of other conditions, Kim et al. [29] conducted a review of the use of NMES after anterior cruciate ligament (ACL) reconstruction. Based on eight different studies, the authors concluded that the use of NMES combined with exercises can be effective in improving quadriceps strength up to four weeks after surgery. However, there was no sufficient evidence to affirm that NMES has any positive effect on the functional performance of patients who had undergone ACL reconstruction [29]. No literature review could be found on the effectiveness of NMES in patients with knee OA without indication for knee arthroplasty. A limitation of this study is that the current intensity used for electrical stimulation was not recorded. However, the maximum current intensity tolerated by each patient was applied as in previous studies [9, 24, 30]. No participant showed intolerance to electrical stimulation. The questionnaires used in this study have been translated into Brazilian Portuguese, cross-culturally adapted, and validated in previous studies [19, 31, 32]. The assessment of patient-reported pain intensity and physical function was performed according to the international consensus on outcomes measures for phase III clinical trials in OA, in which pain and physical function are identified as the most important outcome measures in randomized clinical trials [18]. The TUG test was chosen because it is a simple and inexpensive test designed to assess the functional mobility of patients based on activities of daily living [12]. Statistical analysis was performed on an intent-to-treat basis to minimize the impact of protocol violations (which may occur after randomization) on the results and conclusions and to avoid an overestimation of the treatment effect. This randomized clinical trial conforms to the Consort Statement (Consolidated Standards of Reporting Trials) [33], whose aim is to improve the quality of reports of randomized clinical trials. Given the predominance of mild and moderate OA cases among the participants, the results of this study can be generalized especially for patients with similar severity levels of OA.\n\nBODY.5. CONCLUSIONS:\nOur results revealed that the application of NMES combined with a conventional exercise program was as effective as the exercise program alone in reducing pain and improving physical function in patients with knee OA, and therefore no therapeutic benefit was observed with the use of NMES. \n\nBODY.6. CLINICAL IMPLICATIONS:\nModerate exercises, including warm-up and muscle stretching and strengthening exercises—combined or not with NMES—are recommended to reduce pain and improve physical function and quality of life in patients with knee OA.\n\nQuestion: Compared to Exercise alone what was the result of NMES plus exercise on Numerical Rating Scale?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1061	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of Neuromuscular Electrical Stimulation Combined with Exercises versus an Exercise Program on the Pain and the Function in Patients with Knee Osteoarthritis: A Randomized Controlled Trial\n\n ABSTRACT:\n\nObjectives. To investigate the effect of 8 weeks of NMES + Ex (neuromuscular electrical stimulation combined with exercises) on pain and functional improvement in patients with knee osteoarthritis (OA) compared to exercise (Ex) alone. Design. Randomized controlled trial. Setting. A specialty outpatient clinic. Participants. Patients (N = 100; women = 86, men = 14; age range, 50–75 years) with knee OA. Interventions. Participants were randomly assigned to NMES + Ex or Ex group. Outcome Measures. Numerical Rating Scale 0 to 10 (NRS) and the Timed Up and Go (TUG) test were the primary outcomes. The secondary outcomes used were the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Results. Following the interventions, a statistically significant improvement in both groups was observed in all outcomes assessed. For the comparison between the groups, no statistically significant difference was found between the NMES + Ex and the Ex groups in NRS (P = 0.52), TUG test (P = 0.12), and aspects of WOMAC: pain (P = 0.26), function (P = 0.23), and stiffness (P = 0.63). Conclusion. The addition of NMES to exercise did not improve the outcomes assessed in knee OA patients. This study was registered at the Australian Clinical Trials Registry (ACTRN012607000357459).\n\nBODY.1. INTRODUCTION:\nOsteoarthritis (OA) is the most common form of arthritis. It affects one-third of adults and tends to increase with age [1]. Knee OA is associated with symptoms of pain, swelling, instability, and reduced range of motion (ROM). These symptoms lead to functional impairment, increasing the risk of morbidity and mortality [2, 3]. The synovium is infiltrated with inflammatory cells and secretes excess synovial fluid, leading to capsular swelling [4]. Through a spinal reflex, the capsular swelling inhibits muscle activation, which, combined with disuse, may cause muscle weakness and atrophy [1]. Because the quadriceps muscle acts as shock absorber for the knee joint, weakness in the thigh muscle reduces joint protection, resulting in overload [4]. Exercises strengthen the muscles, reduce pain, improve physical function, and are therefore considered a major intervention in the conservative treatment of patients with knee OA [5]. In addition to muscle strengthening exercises, stretching exercises are commonly used to increase ROM and are often prescribed in rehabilitation protocols as part of routine warm-up to prepare the muscles and joints for other types of exercise, such as aerobic and strengthening programs [6, 7]. Stretching of the hamstring muscles may improve knee extension ROM in OA patients. Neuromuscular electrical stimulation (NMES) is defined as the application of electrical stimulation using surface electrodes placed over skeletal muscles to produce visible muscle contraction through the activation of intramuscular nerve branches [8]. This technique can also be used as a form of physical therapy in the treatment of patients with knee OA. The goals of rehabilitation protocols that include NMES are to provide additional stimulus to increase muscle strength in patients with knee OA [9]. The methods and findings of previous studies on the effectiveness of NMES in knee OA differ in the modulation of NMES parameters, choice of the outcomes used to evaluate the patients, and characteristics of the control groups. This leads to a lack of consensus regarding the effectiveness attained from including NMES in conventional rehabilitation protocols. Major flaws with regard to methodological quality were found in clinical trials testing the use of NMES in the conservative treatment of patients with knee OA. Only one of these studies reported using allocation concealment, blinded assessment, and intention-to-treat analysis [10]. Thus, the objective of this study was to conduct a randomized clinical trial following methodological criteria, including allocation concealment, blinding of the examiner, and application of intention-to-treat analysis to assess the role of NMES in improving pain and physical function in patients with knee OA. It is important to study interventions with the potential to improve functional status in this patient population [11]. \n\nBODY.2. METHODS:\nThe study was conducted at the Interlagos Specialty Outpatient Clinic, São Paulo, Brazil. Patients were referred from the Rheumatology Department according to the inclusion and exclusion criteria and randomly allocated into groups using a computer-generated randomization chart. The allocation codes were sealed in opaque envelopes by a third person not involved in the study to avoid selection bias. Written informed consent was obtained from all participants. The study was approved by the Research Ethics Committee of the Universidade Federal de São Paulo (UNIFESP), Brazil, no. 0141/07, and registered with the Australian Clinical Trials Registry, no. ACTRN012607000357459. Setting the significance level at 5% and the power of the sample at 80%, a sample size of 40 patients per group was estimated to be necessary to detect a difference of at least 1 minute ± 3 seconds in the Timed Up and Go (TUG) test, which was considered to be the minimum clinically significant difference for the present trial [12]. Paired Student's t-test and analysis of covariance (ANCOVA) were used for comparisons between groups; the covariant was obtained from a previous study [13]. One hundred patients were recruited according to inclusion and exclusion criteria. Eligibility criteria were age 50 to 75 years, OA grade 2 or greater according to the radiographic classification of OA proposed by Kellgren and Lawrence [14], and diagnosis of knee OA based on the American College of Rheumatology (ACR) criteria. Exclusion criteria were use of a pacemaker, unstable heart conditions, participation in another physical activity program, inability to exercise on a stationary bicycle ergometer, inability to walk, previous hip or knee arthroplasty, diagnosis of fibromyalgia, epilepsy, and skin tumor or lesion at the NMES application site. Patients were divided into two groups of 50 each: (1) the NMES combined with exercises (NMES + Ex) group and (2) exercise (Ex) group. Patient medication was standardized and not modified during the study period. Paracetamol was prescribed for pain, and diacerein and chloroquine for OA control. Interventions were delivered for both groups by the same physical therapist, twice a week, for 8 weeks, with each session lasting about 40 minutes. All patients received a manual including guidelines on how not to overload the knee during daily activities and instructions on the use of ice packs in case of pain and inflammation and warm compresses in case of pain without inflammation as follows. \nManual for Patients with Osteoarthritis of the Knee. The purpose of this manual is to explain osteoarthritis and to teach how you can adjust yourself to your daily activities, according to the knee symptoms. Try to seriously follow our orientations for your own benefit! \nThe Knee. The knee joint is composed of 3 bones—the femur (thigh bone), the patella (kneecap) and the tibia (leg bone). It has muscles, capsule, ligaments, meniscus, and the cartilage that lines the bones and protects them from the impact. The knee joint supports nearly the whole weight of our body. \nWhat Is Osteoarthritis? It is a disease caused by the breakdown of cartilage in the joints. The layers in the cartilage become damaged and with time they lose the function of smoothing the contact between the bone surface and the joints. The pain is a result of the attrition of one bone against the other in the absence or decreased cartilage in the joints. \nWhat Are the Signs and Symptoms? Patients with osteoarthritis may have some pain mainly when starting a movement, as in morning stiffness or after immobilization. With time, the pain might be intensified and be permanent. The presence of crepitation when moving the knees is often. \nWhat Kind of Difficulties Might I Have in My Daily Life? Difficulties found in daily live vary according to the patients' symptoms. In general, however, the patient has pain and difficulty when supporting the body weight using the affected knee, going up and down the stairs, or when walking. \nWhat Should I Do When It Is Painful? A doctor can prescribe the treatment for osteoarthritis. However, a simple form of improving the pain is to use warm to hot water bottle over the knee joint (be careful not to burn the skin, use a protection, and test the water temperature before using it. \nWhat If It Is Swollen? To manage the swollen, you can combine rest, use of ice pack, and elevating the leg above the level of the heart. The ice pack should be placed over the knee joint for 20 minutes. \nWhat Are the Other Recommendations?\nIf you are overweight, losing some kilos will reduce the stress over the joint. Wear comfortable shoes with a rubber sole and no heels.In case of pain when walking, use a cane as an aid tool.Try to have a good night sleep.\n\n\nBODY.2. METHODS.2.1. NMES COMBINED WITH EXERCISE GROUP:\nTreatment for patients in the NMES + Ex included 10 minutes on a stationary bicycle, stretching of hamstring muscles (3 repetitions of 30 seconds) with the aid of an elastic band, and loaded quadriceps strengthening exercises combined with NMES. The strengthening exercise with NMES was performed in the sitting position with the knee and hip flexed to 90 degrees; patients contracted their quadriceps at each NMES stimulus. NMES was applied using an electrical stimulator (Globus ACTIVA 600 Pro, Globus, Italia) with two 7.5 × 13 cm self-adhesive electrodes (ValuTrode electrodes, Axelgaard Manufacturing Co. Ltd., Fallbrook, CA) placed over the region of the quadriceps muscle (rectus femoris and vastus medialis). NMES parameters were as follows: pulsed current, biphasic, asymmetrical, rectangular waveform, frequency 50 Hz, pulse duration 250 μs, contraction time 10 s, rest time 30 s every 20 minutes; current intensity was the maximum tolerated by each patient [15]. \n\nBODY.2. METHODS.2.2. EXERCISE GROUP (EX):\nPatients in the Ex group performed the same exercise program as those in the NMES group but without NMES. The exercise protocol included 10 minutes of warm-up on a stationary bicycle ergometer, stretching of hamstrings muscles with the aid of an elastic band, and knee extension exercises performed for 3 sets of 15 repetitions with rest intervals of 30–45 seconds between sets. For both groups, the training load for the strengthening exercises was established based on 50–60% of the 10-repetition maximum (RM) instead of 1 RM to avoid injury by excessive muscle contraction [16].\n\nBODY.2. METHODS.2.3. OUTCOMES:\nPatients were evaluated before and after intervention by a physical therapist blinded to group assignment. The primary outcomes were the TUG test results [12] and pain walking on a flat surface in the last 72 h measured on an 11-point Numerical Rating Scale (NRS) [17]. The secondary outcomes were scores on the pain, physical function, and stiffness subscales of the culturally validated Brazilian-Portuguese version of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) [18, 19]. In this study, WOMAC pain, physical function, and stiffness scores were analyzed separately. \n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nPaired Student's t-test was performed to compare pre- and postintervention values at a significance level of 0.05 (P < 0.05). Statistical analysis was performed on an intent-to-treat (ITT) basis and included all patients who were randomized to treatment. Mixed model analysis of variance with repeated measures was used with occasion measures as within-group factors and intervention as between-group factor. Relations between the observations were analyzed using an unstructured covariance matrix. Missing-data imputation was not performed to evaluate pre- and postintervention differences between the two groups, because Chakraborty and GU [20] showed that mixed model analysis without missing-data imputation always provides equal or more power than does mixed model analysis with missing-data imputation. Effect size was calculated as the difference between the means divided by the standard deviation using Cohen's d [21]. The analyses were performed using the General Linear Model (GLM), and mixed analyses were carried out using the Statistical Analysis Software (SAS) version 9.2 for Windows [22].\n\nBODY.3. RESULTS:\nThe demographic and clinical characteristics of patients, including age, sex, side treated, and body mass index (BMI), as well as TUG test values, NRS pain scores, and WOMAC scores on the pain, physical function, and stiffness subscales, are shown in Table 1. Eighty-seven patients completed the study. Of the 13 dropouts, 6 (12%) patients were in the NMES + Ex group and 7 (14%) in the Ex group (Figure 1). \n\nBODY.3. RESULTS.3.1. PRIMARY OUTCOMES:\nNo significant differences between groups were found in NRS pain scores and TUG test time on ITT analysis. A significant decrease in pain intensity (NRS scores) and TUG test time was observed after intervention compared with baseline in the NMES + Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001) and Ex group (NRS scores, P < 0.0001; TUG test, P < 0.0001). The primary outcomes are listed in Table 2. \n\nBODY.3. RESULTS.3.2. SECONDARY OUTCOMES:\nNo significant differences between groups were found on the pain, physical function, and stiffness subscales of the WOMAC index on ITT analysis. There was a significant improvement in all WOMAC subscales in the NMES + Ex group (pain; P < 0.0001; physical function, P < 0.0001; stiffness, P < 0.0001) and in the Ex group (pain, P < 0.0001; physical function, P < 0.0001; stiffness, P = 0.0009). The secondary outcomes are listed in Table 2.\n\nBODY.3. RESULTS.3.3. ADVERSE EFFECT:\nOne patient in the NMES + Ex group exhibited a blood pressure spike, which may have resulted from the use of NMES or from the exercise program itself. The following contraindications to the use of NMES were respected: avoiding the use of NMES over areas of tumor, with open wounds, or bleeding, and in patients with pacemakers [15].\n\nBODY.4. DISCUSSION:\nIn this randomized clinical trial, the NMES combined with exercise did improve pain and physical function, but there was no evidence that it did better than exercise alone. Our results are in agreement with the findings of Rosemffet et al. [23] who conducted a pilot study comparing the treatment results of patients with knee OA (n = 26) treated with either NMES alone or exercises alone or exercises combined with NMES. The authors reported a significant improvement on the WOMAC pain subscale in the three groups, but no significant differences in WOMAC scores were found between groups [23]. The lack of difference in treatment outcome between groups in the present study might be attributed to the fact that the participants had no clinically significant muscle or functional impairment. A finding substantiating this hypothesis is that the mean TUG test values in the two groups were similar to those found in the study of Steffen et al., for elderly patients with no physical limitations categorized under the same mean age group [24]. The TUG test values reported were 8 ± 2 seconds for patients with 60–69 years old and 9 ± 3 seconds for patients with 70–79 years old. In the present study, the baseline values for TUG test were 8.27 + 1.76 for NMES + Ex group and 9.34 ± 2.47 for Ex group. Given that the greater the muscle impairment, the greater the NMES effect, patients with a more advanced stage of OA might obtain greater benefit from NMES [25–27]. With regard to evidence on the effectiveness of NMES in the rehabilitation of patients with knee OA, the Cochrane Collaboration published a systematic review evaluating the pre- and postoperative use of NMES in total knee arthroplasty [28]. The two studies that were evaluated were classified as being at high risk of bias, because randomization and allocation concealment were not described, and no data obtained from the study groups were presented in terms of means and standard deviations. It was not possible to determine whether or not the pre- and postoperative use of NMES was effective in the rehabilitation of knee arthroplasty patients, and therefore further studies are warranted. Regarding lines of evidence on the effectiveness of NMES in the treatment of other conditions, Kim et al. [29] conducted a review of the use of NMES after anterior cruciate ligament (ACL) reconstruction. Based on eight different studies, the authors concluded that the use of NMES combined with exercises can be effective in improving quadriceps strength up to four weeks after surgery. However, there was no sufficient evidence to affirm that NMES has any positive effect on the functional performance of patients who had undergone ACL reconstruction [29]. No literature review could be found on the effectiveness of NMES in patients with knee OA without indication for knee arthroplasty. A limitation of this study is that the current intensity used for electrical stimulation was not recorded. However, the maximum current intensity tolerated by each patient was applied as in previous studies [9, 24, 30]. No participant showed intolerance to electrical stimulation. The questionnaires used in this study have been translated into Brazilian Portuguese, cross-culturally adapted, and validated in previous studies [19, 31, 32]. The assessment of patient-reported pain intensity and physical function was performed according to the international consensus on outcomes measures for phase III clinical trials in OA, in which pain and physical function are identified as the most important outcome measures in randomized clinical trials [18]. The TUG test was chosen because it is a simple and inexpensive test designed to assess the functional mobility of patients based on activities of daily living [12]. Statistical analysis was performed on an intent-to-treat basis to minimize the impact of protocol violations (which may occur after randomization) on the results and conclusions and to avoid an overestimation of the treatment effect. This randomized clinical trial conforms to the Consort Statement (Consolidated Standards of Reporting Trials) [33], whose aim is to improve the quality of reports of randomized clinical trials. Given the predominance of mild and moderate OA cases among the participants, the results of this study can be generalized especially for patients with similar severity levels of OA.\n\nBODY.5. CONCLUSIONS:\nOur results revealed that the application of NMES combined with a conventional exercise program was as effective as the exercise program alone in reducing pain and improving physical function in patients with knee OA, and therefore no therapeutic benefit was observed with the use of NMES. \n\nBODY.6. CLINICAL IMPLICATIONS:\nModerate exercises, including warm-up and muscle stretching and strengthening exercises—combined or not with NMES—are recommended to reduce pain and improve physical function and quality of life in patients with knee OA.\n\nQuestion: Compared to Exercise alone what was the result of NMES plus exercise on Western Ontario and McMaster Universities Osteoarthritis Index for stiffness?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1062	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Physiological effects of invasive ventilation with neurally adjusted ventilatory assist (NAVA) in a crossover study\n\n ABSTRACT.BACKGROUND:\nNeurally Adjusted Ventilatory Assist (NAVA) is a mode of assisted mechanical ventilation that delivers inspiratory pressure proportionally to the electrical activity of the diaphragm. To date, no pediatric study has focused on the effects of NAVA on hemodynamic parameters. This physiologic study with a randomized cross-over design compared hemodynamic parameters when NAVA or conventional ventilation (CV) was applied.\n\nABSTRACT.METHODS:\nAfter a baseline period, infants received NAVA and CV in a randomized order during two consecutive 30-min periods. During the last 10 min of each period, respiratory and hemodynamic parameters were collected. No changes in PEEP, FiO2, sedation or inotropic doses were allowed during these two periods. The challenge was to keep minute volumes constant, with no changes in blood CO2 levels and in pH that may affect the results.\n\nABSTRACT.RESULTS:\nSix infants who had undergone cardiac surgery (mean age 7.8 ± 4.1 months) were studied after parental consent. Four of them had low central venous oxygen saturation (ScvO2 < 65 %). The ventilatory settings resulted in similar minute volumes (1.7 ± 0.4 vs. 1.6 ± 0.6 ml/kg, P = 0.67) and in similar tidal volumes respectively with NAVA and with CV. There were no statistically significant differences on blood pH levels between the two modes of ventilation (7.32 ± 0.02 vs. 7.32 ± 0.04, P = 0.34). Ventilation with NAVA delivered lower peak inspiratory pressures than with CV: -32.7 % (95 % CI: -48.2 to –17.1 %, P = 0.04). With regard to hemodynamics, systolic arterial pressures were higher using NAVA: +8.4 % (95 % CI: +3.3 to +13.6 %, P = 0.03). There were no statistically significant differences on cardiac index between the two modes of ventilation. However, all children with a low baseline ScvO2 (<65 %) tended to increase their cardiac index with NAVA compared to CV: 2.03 ± 0.30 vs. 1.91 ± 0.39 L/min.m2 (median ± interquartile, P = 0.07).\n\nABSTRACT.CONCLUSIONS:\nThis pilot study raises the hypothesis that NAVA could have beneficial effects on hemodynamics in children when compared to a conventional ventilatory mode that delivered identical PEEP and similar minute volumes.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov Identifier: NCT01490710. Date of registration: December 7, 2011.\n\nBODY.BACKGROUND:\nTo better match the level of ventilator assistance to the patient's needs, manufacturers have developed new modes that deliver a level of assistance proportional either to the patient's inspiratory muscle effort, with proportional assist ventilation (PAV); or to the diaphragmatic electrical activity (EAdi), with neurally adjusted ventilatory assist (NAVA) [1]. For now, only NAVA is usable for infants. With this mode of mechanical ventilation, the collected electrical signal allows synchronization of ventilation to spontaneous breathing efforts of the child, as well as permitting pressure assistance proportional to the electrical signal. NAVA provides both fine synchronization of respiratory support and pressure assistance varying with the needs of the child. To our knowledge, no data have been published on the impact of NAVA on the hemodynamics in children mechanically ventilated. The impact of mechanical ventilation on the circulatory system remains a concern in some infants following surgery for repair of congenital cardiac defects [2]. After the completion of the operation, when there is consensus regarding a good surgical result, many children nowadays are rapidly weaned and successfully separated from mechanical ventilation shortly after the procedure. However, duration of mechanical ventilation is inversely proportional to the patient's age and directly related to the duration of cardiopulmonary bypass and complexity of the surgical procedure [3]. This physiologic study with a randomized cross-over design compared hemodynamic parameters when neurally adjusted ventilatory assist (NAVA) or conventional ventilation (CV) was applied.\n\nBODY.METHODS:\nThis study was performed in the 12-bed PICU of the university hospital center of Nantes (France), between June 2012 and March 2013. Last year, 712 children were admitted in this unit. Among them, 182 underwent a cardiac surgery with cardiopulmonary bypass (55 % were extubated within 8 h). This trial was registered (ClinicalTrials.gov Identifier: NCT01490710). Research has been performed in accordance with the Declaration of Helsinki and has been approved by an appropriate ethics committee (Comité de Protection des Personnes Ouest III de POITIERS, Réference comité: Protocole n°11.07.20). The parents of all the children gave their written consent.\n\nBODY.METHODS.STUDY DESIGN: PROSPECTIVE RANDOMIZED CROSS-OVER STUDY:\nAfter a baseline period, children received conventional ventilation (CV) and NAVA during two consecutive periods of 30 min, in random order. This randomization was performed by contacting a server to define the order in which the two modes of ventilation were administered. There was no washout time between these two periods. During the last 10 min of each period at a steady state, hemodynamic parameters, respiratory parameters, blood gas and cardiac index were collected. No changes in PEEP, FiO2, sedation or inotropic doses were allowed during these two periods. The study protocol is depicted in Fig. 1.Fig. 1Study design. Baseline measures were collected when patient met stability conditions. No changes in PEEP, FiO2, sedation nor inotropic doses were allowed during the two 30-min study periods. NAVA = Neurally Adjusted Ventilatory Assist; CV = Conventional Ventilation\n\n\nBODY.METHODS.PARTICIPANTS:\nChildren hospitalized for postoperative care after cardiac surgery were considered for inclusion. Inclusion criteria were: admission weight >5 kg; invasive ventilatory support ongoing; NAVA ventilation available; sedation status allowing the NAVA ventilation functioning. Non inclusion criteria were: parental refusal; oesophageal disease prohibiting gastric tube; brain damage conflicting with spontaneous ventilation; clinical instability requiring treatment and/or management inconsistent with research.\n\nBODY.METHODS.INTERVENTION:\nChildren were ventilated with a Servo-i ventilator (Maquet Critical Care, Solna, Sweden). During a baseline period, conventional ventilation was applied and adjusted according to blood gases. After the baseline period in which NAVA probe and Doppler monitoring were introduced, all children received conventional ventilation (CV) and NAVA during two consecutive periods of 30 min, in random order. The ventilation settings were supposed to provide the same minute volumes.\n\nBODY.METHODS.INTERVENTION.CONVENTIONAL VENTILATION (CV):\nWith the goal of providing the lowest peak pressures, we used the Volume Control Intermittent Mandatory Ventilation (VC-IMV). Ventilatory parameters were as follows: tidal volume (between 5 and 8 ml/kg), respiratory rate (between 20 and 30 cycles/min). Pressure Support was set at 12 cmH2O above the PEEP. A flow pneumatic trigger was used to synchronize the support to spontaneous breaths. The flow pattern during the volume control ventilation was constant flow. The inspiratory time was initially set at 0.5 s and adjusted according to the inspiratory flow waveforms if needed. The respiratory rate of VC-IMV was set at a high level (between 20 and 30 cycles/min), not allowing many spontaneous cycles. The CV settings were adjusted during the baseline period with no changes allowed during the study period.\n\nBODY.METHODS.INTERVENTION.NEURALLY ADJUSTED VENTILATORY ASSIST (NAVA):\nDuring NAVA, the ventilator delivers a pressure proportional to the electrical activity of the diaphragm (EAdi). The settings in NAVA mode included PEEP, FiO2 and level of NAVA assistance. The NAVA level was set to 1 cmH2O/μV. We had previously observed that children ventilated with NAVA usually adjust their EAdi to maintain a normal blood pH by preserving physiologic tidal volumes and minute volumes. This is no longer true when children are highly sedated. Backup ventilation was Pressure Control set at 12 cmH2O above PEEP in case of failure EAdi signal detection. During NAVA, the positive pressure is triggered when the deflection in the EAdi curve exceeds 0.5 μV, and is cycled-off when the EAdi drops to 70 % of its peak value.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.RESPIRATORY MEASUREMENTS:\nPeak inspiratory pressures (PIP), PEEP, FiO2, Tidal volume (VT), Minute volume, EADI max, Respiratory rate, were recorded for all infants during the last 10 min of each period. Measurements of each parameter were repeated at steady state a total of six times to guarantee reliability and reproducibility. We collected the most representative values rather than gathering data at constant interval because of the variability of the respiratory measurements in NAVA. Hemodynamic and respiratory parameters were collected always in the same time. Respiratory system compliance (Crs) according to the ventilation mode was estimated by the ratio VT/(PIP-PEEP) in ml/kg.cmH2O.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.HEMODYNAMIC MEASUREMENTS:\nCardiac index (CI, L/min.m2) was assessed by transesophageal Doppler ultrasonography (CardioQP, Gamida, France) [4]. Other hemodynamic parameters included heart rate, arterial pressures (by means of an arterial catheter placed before the surgery), and central venous pressure (by means of a central venous catheter inserted into the right internal jugular vein). Cerebral Near InfraRed Spectroscopy (NIRS) was measured with a non invasive optical monitor of regional cerebral oxygen saturation (Invos Oximeter, Covidien, Boulder, CO). The pulse oximeter perfusion index was provided by the monitors (Intellivue MP70 monitor, Philips Medical Systems) [5]. Hemodynamic parameters were collected always in the same time than respiratory parameters. Left cardiac work index [6] was calculated as: LCWI (kg.min/m2) = CI × MAP × 0.0136, with CI for cardiac index and MAP for mean arterial pressure.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.BIOLOGICAL MEASUREMENTS:\nAt the end of each period (CV and NAVA), a blood sample was taken through the internal jugular catheter to measure pH, PCO2, and central venous oxygen saturation (ScvO2). These measurements were performed in the PICU by a blood gases analyser (GEM Premiere 4000, Instrumentation Laboratory UK Ltd).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nEach parameter collected in the last 10 min of each study period was averaged, and compared by a Wilcoxon test for paired samples. Measurements in NAVA and CV are reported as median (interquartile). Changes in parameters during NAVA compared to CV are expressed as mean percentage (95 % CI, P). The P-value taken to indicate significance was P < 0.05. For this pilot study no sample size was calculated.\n\nBODY.RESULTS:\nThe study was concluded after one year. Technical problems were greater than expected: a measure of cardiac output sufficiently accurate, and especially stable in time, was very difficult to reach in children who already had a stomach tube for the NAVA ventilation. We asked the research office of our institution for continuing recruiting more patients. In view of the technical difficulties we had, this request was not accepted. Nine children were randomized. The quality of the surgical repair was always checked by a cardiologist prior to inclusion in the study. Analysis was performed on only six of them. We were unable to start NAVA on one child due to a lack of EAdi signal capture. Thereafter, when the NAVA signal was not stable enough, children were not included. In two other children we were unable to record a Doppler signal likely due to interference between the CardioQP probe and the EAdi probe both intra oesophageal placed. Patient characteristics are provided in Table 1. The mean (± SD) age was 7.8 ± 4.1 months, and weight was 6.7 ± 1.2 kg. Four children had low central venous saturation (ScvO2 < 65 %) at the baseline period: the children 1, 2, 3, 6 in the Table 1.Table 1Children characteristicsChild123456GenderMMMFFFAge (mo)313410611Weight (kg)5.78.97.06.05.87.0CardiopathyAVSDVSD with pulmonary stenosistetralogy of Fallotatrial septal defectcoarctation of the aortapulmonary atresia with VSDCardiopulmonary bypass duration (min)9683130480130Time between PICU entry and study (hours)20720457Baseline cardiac index (L/min.m2)2.002.851.932.602.751.85Milrinone (mcg/kg/min)0.90.50.30.500.5Adrenaline (mcg/kg/min)000000.05ScvO2 (%)646352826852Perfusion index (%)0.313.650.603.621.900.87Random orderCV then NAVANAVA then CVCV then NAVACV then NAVANAVA then CVNAVA then CVAll children were receiving morphine 0.5 mg per kilo per day. All, except the 2 first, were receiving midazolam 40 micrograms per kilo per hour\nAVSD atrioventricular septal defect, VSD ventricular septal defect, NAVA neurally adjusted ventilatory assist, CV conventional ventilation, ScvO\n2: central venous oxygen saturation\n Respiratory parameters, hemodynamic parameters, and blood gases are provided in Table 2. The ventilatory settings resulted in similar minute volumes and in similar tidal volumes in NAVA compared to CV. These similar minute volumes in each periods of the study were supposed when the study was designed. Nevertheless, significant lower peak inspiratory pressures (PIP) were observed during NAVA compared to CV. Apparent respiratory system compliance improved with NAVA in all children. We observed higher systolic arterial pressures during NAVA compared to CV. Pulse oximeter perfusion index were also higher during NAVA.Table 2Respiratory parameters, hemodynamics and biological dataRespiratory parametersCVNAVANAVA versus CV\nP\nRespiratory rate (/min)30 (7)35 (13)+26.4 (-3.6, +56.4)0.17VT (ml/kg)6.6 (0.7)6.9 (0.3)+5.3 (-5.5, +16.1)0.46Minute volume (L/min)1.7 (0.4)1.6 (0.6)+5.4 (-4.3, +15.1)0.67PIP (cm H2O)21 (6)11 (4)-32.7 (-48.2, -17.1)0.04PEEP (cm H2O)4 (2)4 (2)-(a)EAdi max (microVolt)3.9 (3.8)6.3 (1.4)+61.2 (-4.6, +126.9)0.34SpO2 (%)98 (3)96 (3)-1.2 (-2.8, +0.5)0.14FiO2\n30 (4)30 (4)-(a)Crs (ml/kg.cm H2O)0.37 (0.19)0.87 (0.32)+98.4 (+43.8, +153.0)0.04Hemodynamic parametersHeart rate156 (15)156 (22)+2.1 (-0.7, +4.5)0.17Systolic arterial pressure (mmHg)93 (6)99 (13)+8.4 (+3.3, +13.6)0.03Diastolic arterial pressure (mmHg)54 (12)57 (6)+3.6 (-3.0, +10.1)0.46Central venous pressure (mmHg)11 (5)10 (5)+3.9 (-5.3, +13.1)0.92Cerebral NIRS (%)62 (5)61 (3)+1.6 (-2.6, +5.8)0.34Cardiac index (L/min.m2)2.33 (0.84)2.26 (0.70)+1.4 (-3.4, +6.2)0.17Pulse oximeter perfusion index (%)1.50 (2.45)1.78 (2.29)+18.8 (+3.0, +34.7)0.04Venous blood gasespH7.32 (0.04)7.32 (0.02)-0.1 (-0.4, +0.2)0.34PCO2 (mm Hg)47.3 (5.1)45.8 (8.1)+0.6 (-5.1, +6.3)0.50ScvO2 (%)60.1 (20.9)58.4 (15.4)+3.3 (-5.7, +12.2)0.60Measurements in NAVA and CV are reported as median (interquartile). Variations between NAVA versus CV are reported as mean percentage (95 % CI). Statistical analyses between NAVA versus CV were performed by a Wilcoxon test for paired samples(a) No changes in PEEP, FiO2, neither in sedation or inotropic doses were allowed during these study periods\nNAVA Neurally adjusted Ventilatory Assist, CV Conventional Ventilation, V\nT tidal volume, PIP peak inspiratory pressure, Crs respiratory system compliance, EAdi electrical activity of the diaphragm, ScvO\n2 central venous oxygen saturation\n Cardiac index during NAVA compared to CV did not statistically differ. However, all four children with ScvO2 < 65 % tended to have higher cardiac index after 30 min of ventilation with NAVA compared to CV: 2.03 ± 0.30 vs. 1.91 ± 0.39 L/min.m2 (median ± interquartile, P = 0.07). Individual values of cardiac index and ScvO2 of children with low baseline ScvO2 are shown in Fig. 2. Upper values of pulse oximeter perfusion index were also observed. Turning now to left cardiac work index, the increase is +12.4 % (95 % CI: +3.8 % to +20.9 %, P = 0.07).Fig. 2Cardiac index and ScvO2 of the low baseline ScvO2 infants, according to the ventilation mode. White bars are cardiac index when CV is applied; back bars are cardiac index when NAVA is applied. The triangles above the bars indicate the values of the corresponding ScvO2 (%). ScvO2 = central venous oxygen saturation; NAVA = Neurally adjusted Ventilatory Assist; CV = Conventional Ventilation\n\n\nBODY.DISCUSSION:\nNAVA can be used in infants receiving postoperative mechanical ventilation after congenital heart surgery, as previously reported [7–10]. Infants included in this study all weighed less than 10 kg and had been operated less than 24 h before. To deliver a same tidal volume, NAVA required lower inspiratory pressures than conventional ventilation and had some beneficial effects on hemodynamics. Several data validate that the children were not over assisted when ventilated in CV: the delivered volumes, EAdi max, PCO2 and pH are similar in CV compared to NAVA. We suggest that lower EAdi peaks observed in CV are related to the normalization of the blood pH by CV ventilation. If children were over-assisted in CV, EAdi would have been missing, and minute volume would have been high, with a blood alkalosis. In a large randomized controlled trial where NAVA was used as a primary mode of ventilation, lower peak inspiratory pressures were found in the NAVA group [11]. It looks as if gas volume delivery, and probably alveolar expansion, required less pressure. This could be enhanced by an improvement in patient–ventilator interactions with a greater respiratory variability as reported in previous studies [12–16]. The effectiveness of this mode of mechanical ventilation was associated with some beneficial effects on the hemodynamics. Systolic arterial pressures and pulse oximeter perfusion index were significantly higher in NAVA. This pulse oximeter perfusion index provides a monitoring of illness severity in neonates [5]. In fact, we observed that the children with a low cardiac index had also a low perfusion index. This index was significantly higher when the children were ventilated with NAVA compared to CV. The overall values of the cardiac index and of the central venous oxygen saturation during NAVA compared to CV were not significantly higher, but there are possibly no reasons to observe an increase in these two parameters when tissue perfusion is already effective. And actually, the four children with a low ScvO2 trend to have a higher cardiac index after 30 min of ventilation with NAVA (Fig. 2). Moreover, this increase in cardiac index is associated with higher systemic pressures and then higher left cardiac work index. Lower oxygen content in venous blood usually reflects an oxygen balance disrupted between oxygen supply and demand. Ventilation with NAVA could allow the body to increase the cardiac output to ensure adequate oxygen availability. These children had congenital heart disease affecting the right heart: VSD with pulmonary stenosis, tetralogy of Fallot, and pulmonary atresia with VSD. Positive pressure ventilation and PEEP often result in increased right ventricular afterload due to capillary compression [3, 17]. Lower intrathoracic pressures in NAVA than in conventional ventilation could improve the right ventricular function during inspiration by reducing the right ventricular afterload. An improvement in apparent respiratory system compliance was observed when NAVA is applied. Cyclic intrathoracic pressure changes, characteristic of spontaneous breathing, could be preserved. Both fine synchronization of respiratory support and pressure assistance varying with the needs and the spontaneous breathing of the child could improve the pulmonary compliance. Nonetheless, it is important to note that we did not record the transpulmonary pressure. It is likely that, while the airway pressure decreased during NAVA, an increase in esophageal pressure swings occurred because of the patient respiratory efforts. This could have participated in the decrease in apparent compliance improvement [18]. This study has some limitations. Firstly, few children were studied. Many children dropped out due to early extubation in the operation room or immediately on arrival in the intensive care unit. Technical problems were greater than expected: a measure of cardiac output sufficiently accurate, and especially stable in time, was very difficult to reach in children who already had a stomach tube for the NAVA ventilation. Nevertheless the cross-over design of this study has two advantages over both a parallel study and a non-crossover longitudinal study [19]. The influence of confounding covariates is reduced because each cross-over patient serves as his or her own control. Cross-over designs are also statistically efficient and require fewer subjects than do non-crossover designs (even other repeated measures designs). Secondly, the agreement of the cardiac output measurement between the transoesophageal Doppler probe using CardioQP and the thermodilution technique during heart catheterisation in paediatric patients was described as weak [20]. However the CardioQP seems to be capable of detecting slight changes in cardiac output for critically ill children [21, 22]. This bed-side device for cardiac output measurement is minimally invasive, and provides better results in monitoring the slight variations rather than in measuring absolute values. As we were performing a cross-over study, we were interested primarily by changes. Finally, only comparison with CV-SIMV with relatively high preset respiratory rate preventing many spontaneous cycles was made, not with other ventilation strategies.\n\nBODY.CONCLUSION:\nIn conclusion, this cross-over study provides new data on the NAVA ventilation. This pilot study raises the hypothesis that a ventilatory assistance with NAVA could provide improvements in hemodynamics when compared to a conventional ventilatory mode that delivered identical PEEP and similar minute volumes. Thus, because minute volumes were not different between the two modes of ventilation, hemodynamic effects are linked to NAVA mode itself and NOT to incorrect settings in conventional ventilation. Further studies with larger population are needed to confirm these promising results.\n\nQuestion: Compared to Conventional Ventilation what was the result of Neurally Adjusted Ventilatory Assist on Blood pH levels?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1064	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Physiological effects of invasive ventilation with neurally adjusted ventilatory assist (NAVA) in a crossover study\n\n ABSTRACT.BACKGROUND:\nNeurally Adjusted Ventilatory Assist (NAVA) is a mode of assisted mechanical ventilation that delivers inspiratory pressure proportionally to the electrical activity of the diaphragm. To date, no pediatric study has focused on the effects of NAVA on hemodynamic parameters. This physiologic study with a randomized cross-over design compared hemodynamic parameters when NAVA or conventional ventilation (CV) was applied.\n\nABSTRACT.METHODS:\nAfter a baseline period, infants received NAVA and CV in a randomized order during two consecutive 30-min periods. During the last 10 min of each period, respiratory and hemodynamic parameters were collected. No changes in PEEP, FiO2, sedation or inotropic doses were allowed during these two periods. The challenge was to keep minute volumes constant, with no changes in blood CO2 levels and in pH that may affect the results.\n\nABSTRACT.RESULTS:\nSix infants who had undergone cardiac surgery (mean age 7.8 ± 4.1 months) were studied after parental consent. Four of them had low central venous oxygen saturation (ScvO2 < 65 %). The ventilatory settings resulted in similar minute volumes (1.7 ± 0.4 vs. 1.6 ± 0.6 ml/kg, P = 0.67) and in similar tidal volumes respectively with NAVA and with CV. There were no statistically significant differences on blood pH levels between the two modes of ventilation (7.32 ± 0.02 vs. 7.32 ± 0.04, P = 0.34). Ventilation with NAVA delivered lower peak inspiratory pressures than with CV: -32.7 % (95 % CI: -48.2 to –17.1 %, P = 0.04). With regard to hemodynamics, systolic arterial pressures were higher using NAVA: +8.4 % (95 % CI: +3.3 to +13.6 %, P = 0.03). There were no statistically significant differences on cardiac index between the two modes of ventilation. However, all children with a low baseline ScvO2 (<65 %) tended to increase their cardiac index with NAVA compared to CV: 2.03 ± 0.30 vs. 1.91 ± 0.39 L/min.m2 (median ± interquartile, P = 0.07).\n\nABSTRACT.CONCLUSIONS:\nThis pilot study raises the hypothesis that NAVA could have beneficial effects on hemodynamics in children when compared to a conventional ventilatory mode that delivered identical PEEP and similar minute volumes.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov Identifier: NCT01490710. Date of registration: December 7, 2011.\n\nBODY.BACKGROUND:\nTo better match the level of ventilator assistance to the patient's needs, manufacturers have developed new modes that deliver a level of assistance proportional either to the patient's inspiratory muscle effort, with proportional assist ventilation (PAV); or to the diaphragmatic electrical activity (EAdi), with neurally adjusted ventilatory assist (NAVA) [1]. For now, only NAVA is usable for infants. With this mode of mechanical ventilation, the collected electrical signal allows synchronization of ventilation to spontaneous breathing efforts of the child, as well as permitting pressure assistance proportional to the electrical signal. NAVA provides both fine synchronization of respiratory support and pressure assistance varying with the needs of the child. To our knowledge, no data have been published on the impact of NAVA on the hemodynamics in children mechanically ventilated. The impact of mechanical ventilation on the circulatory system remains a concern in some infants following surgery for repair of congenital cardiac defects [2]. After the completion of the operation, when there is consensus regarding a good surgical result, many children nowadays are rapidly weaned and successfully separated from mechanical ventilation shortly after the procedure. However, duration of mechanical ventilation is inversely proportional to the patient's age and directly related to the duration of cardiopulmonary bypass and complexity of the surgical procedure [3]. This physiologic study with a randomized cross-over design compared hemodynamic parameters when neurally adjusted ventilatory assist (NAVA) or conventional ventilation (CV) was applied.\n\nBODY.METHODS:\nThis study was performed in the 12-bed PICU of the university hospital center of Nantes (France), between June 2012 and March 2013. Last year, 712 children were admitted in this unit. Among them, 182 underwent a cardiac surgery with cardiopulmonary bypass (55 % were extubated within 8 h). This trial was registered (ClinicalTrials.gov Identifier: NCT01490710). Research has been performed in accordance with the Declaration of Helsinki and has been approved by an appropriate ethics committee (Comité de Protection des Personnes Ouest III de POITIERS, Réference comité: Protocole n°11.07.20). The parents of all the children gave their written consent.\n\nBODY.METHODS.STUDY DESIGN: PROSPECTIVE RANDOMIZED CROSS-OVER STUDY:\nAfter a baseline period, children received conventional ventilation (CV) and NAVA during two consecutive periods of 30 min, in random order. This randomization was performed by contacting a server to define the order in which the two modes of ventilation were administered. There was no washout time between these two periods. During the last 10 min of each period at a steady state, hemodynamic parameters, respiratory parameters, blood gas and cardiac index were collected. No changes in PEEP, FiO2, sedation or inotropic doses were allowed during these two periods. The study protocol is depicted in Fig. 1.Fig. 1Study design. Baseline measures were collected when patient met stability conditions. No changes in PEEP, FiO2, sedation nor inotropic doses were allowed during the two 30-min study periods. NAVA = Neurally Adjusted Ventilatory Assist; CV = Conventional Ventilation\n\n\nBODY.METHODS.PARTICIPANTS:\nChildren hospitalized for postoperative care after cardiac surgery were considered for inclusion. Inclusion criteria were: admission weight >5 kg; invasive ventilatory support ongoing; NAVA ventilation available; sedation status allowing the NAVA ventilation functioning. Non inclusion criteria were: parental refusal; oesophageal disease prohibiting gastric tube; brain damage conflicting with spontaneous ventilation; clinical instability requiring treatment and/or management inconsistent with research.\n\nBODY.METHODS.INTERVENTION:\nChildren were ventilated with a Servo-i ventilator (Maquet Critical Care, Solna, Sweden). During a baseline period, conventional ventilation was applied and adjusted according to blood gases. After the baseline period in which NAVA probe and Doppler monitoring were introduced, all children received conventional ventilation (CV) and NAVA during two consecutive periods of 30 min, in random order. The ventilation settings were supposed to provide the same minute volumes.\n\nBODY.METHODS.INTERVENTION.CONVENTIONAL VENTILATION (CV):\nWith the goal of providing the lowest peak pressures, we used the Volume Control Intermittent Mandatory Ventilation (VC-IMV). Ventilatory parameters were as follows: tidal volume (between 5 and 8 ml/kg), respiratory rate (between 20 and 30 cycles/min). Pressure Support was set at 12 cmH2O above the PEEP. A flow pneumatic trigger was used to synchronize the support to spontaneous breaths. The flow pattern during the volume control ventilation was constant flow. The inspiratory time was initially set at 0.5 s and adjusted according to the inspiratory flow waveforms if needed. The respiratory rate of VC-IMV was set at a high level (between 20 and 30 cycles/min), not allowing many spontaneous cycles. The CV settings were adjusted during the baseline period with no changes allowed during the study period.\n\nBODY.METHODS.INTERVENTION.NEURALLY ADJUSTED VENTILATORY ASSIST (NAVA):\nDuring NAVA, the ventilator delivers a pressure proportional to the electrical activity of the diaphragm (EAdi). The settings in NAVA mode included PEEP, FiO2 and level of NAVA assistance. The NAVA level was set to 1 cmH2O/μV. We had previously observed that children ventilated with NAVA usually adjust their EAdi to maintain a normal blood pH by preserving physiologic tidal volumes and minute volumes. This is no longer true when children are highly sedated. Backup ventilation was Pressure Control set at 12 cmH2O above PEEP in case of failure EAdi signal detection. During NAVA, the positive pressure is triggered when the deflection in the EAdi curve exceeds 0.5 μV, and is cycled-off when the EAdi drops to 70 % of its peak value.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.RESPIRATORY MEASUREMENTS:\nPeak inspiratory pressures (PIP), PEEP, FiO2, Tidal volume (VT), Minute volume, EADI max, Respiratory rate, were recorded for all infants during the last 10 min of each period. Measurements of each parameter were repeated at steady state a total of six times to guarantee reliability and reproducibility. We collected the most representative values rather than gathering data at constant interval because of the variability of the respiratory measurements in NAVA. Hemodynamic and respiratory parameters were collected always in the same time. Respiratory system compliance (Crs) according to the ventilation mode was estimated by the ratio VT/(PIP-PEEP) in ml/kg.cmH2O.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.HEMODYNAMIC MEASUREMENTS:\nCardiac index (CI, L/min.m2) was assessed by transesophageal Doppler ultrasonography (CardioQP, Gamida, France) [4]. Other hemodynamic parameters included heart rate, arterial pressures (by means of an arterial catheter placed before the surgery), and central venous pressure (by means of a central venous catheter inserted into the right internal jugular vein). Cerebral Near InfraRed Spectroscopy (NIRS) was measured with a non invasive optical monitor of regional cerebral oxygen saturation (Invos Oximeter, Covidien, Boulder, CO). The pulse oximeter perfusion index was provided by the monitors (Intellivue MP70 monitor, Philips Medical Systems) [5]. Hemodynamic parameters were collected always in the same time than respiratory parameters. Left cardiac work index [6] was calculated as: LCWI (kg.min/m2) = CI × MAP × 0.0136, with CI for cardiac index and MAP for mean arterial pressure.\n\nBODY.METHODS.OUTCOMES MEASUREMENTS.BIOLOGICAL MEASUREMENTS:\nAt the end of each period (CV and NAVA), a blood sample was taken through the internal jugular catheter to measure pH, PCO2, and central venous oxygen saturation (ScvO2). These measurements were performed in the PICU by a blood gases analyser (GEM Premiere 4000, Instrumentation Laboratory UK Ltd).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nEach parameter collected in the last 10 min of each study period was averaged, and compared by a Wilcoxon test for paired samples. Measurements in NAVA and CV are reported as median (interquartile). Changes in parameters during NAVA compared to CV are expressed as mean percentage (95 % CI, P). The P-value taken to indicate significance was P < 0.05. For this pilot study no sample size was calculated.\n\nBODY.RESULTS:\nThe study was concluded after one year. Technical problems were greater than expected: a measure of cardiac output sufficiently accurate, and especially stable in time, was very difficult to reach in children who already had a stomach tube for the NAVA ventilation. We asked the research office of our institution for continuing recruiting more patients. In view of the technical difficulties we had, this request was not accepted. Nine children were randomized. The quality of the surgical repair was always checked by a cardiologist prior to inclusion in the study. Analysis was performed on only six of them. We were unable to start NAVA on one child due to a lack of EAdi signal capture. Thereafter, when the NAVA signal was not stable enough, children were not included. In two other children we were unable to record a Doppler signal likely due to interference between the CardioQP probe and the EAdi probe both intra oesophageal placed. Patient characteristics are provided in Table 1. The mean (± SD) age was 7.8 ± 4.1 months, and weight was 6.7 ± 1.2 kg. Four children had low central venous saturation (ScvO2 < 65 %) at the baseline period: the children 1, 2, 3, 6 in the Table 1.Table 1Children characteristicsChild123456GenderMMMFFFAge (mo)313410611Weight (kg)5.78.97.06.05.87.0CardiopathyAVSDVSD with pulmonary stenosistetralogy of Fallotatrial septal defectcoarctation of the aortapulmonary atresia with VSDCardiopulmonary bypass duration (min)9683130480130Time between PICU entry and study (hours)20720457Baseline cardiac index (L/min.m2)2.002.851.932.602.751.85Milrinone (mcg/kg/min)0.90.50.30.500.5Adrenaline (mcg/kg/min)000000.05ScvO2 (%)646352826852Perfusion index (%)0.313.650.603.621.900.87Random orderCV then NAVANAVA then CVCV then NAVACV then NAVANAVA then CVNAVA then CVAll children were receiving morphine 0.5 mg per kilo per day. All, except the 2 first, were receiving midazolam 40 micrograms per kilo per hour\nAVSD atrioventricular septal defect, VSD ventricular septal defect, NAVA neurally adjusted ventilatory assist, CV conventional ventilation, ScvO\n2: central venous oxygen saturation\n Respiratory parameters, hemodynamic parameters, and blood gases are provided in Table 2. The ventilatory settings resulted in similar minute volumes and in similar tidal volumes in NAVA compared to CV. These similar minute volumes in each periods of the study were supposed when the study was designed. Nevertheless, significant lower peak inspiratory pressures (PIP) were observed during NAVA compared to CV. Apparent respiratory system compliance improved with NAVA in all children. We observed higher systolic arterial pressures during NAVA compared to CV. Pulse oximeter perfusion index were also higher during NAVA.Table 2Respiratory parameters, hemodynamics and biological dataRespiratory parametersCVNAVANAVA versus CV\nP\nRespiratory rate (/min)30 (7)35 (13)+26.4 (-3.6, +56.4)0.17VT (ml/kg)6.6 (0.7)6.9 (0.3)+5.3 (-5.5, +16.1)0.46Minute volume (L/min)1.7 (0.4)1.6 (0.6)+5.4 (-4.3, +15.1)0.67PIP (cm H2O)21 (6)11 (4)-32.7 (-48.2, -17.1)0.04PEEP (cm H2O)4 (2)4 (2)-(a)EAdi max (microVolt)3.9 (3.8)6.3 (1.4)+61.2 (-4.6, +126.9)0.34SpO2 (%)98 (3)96 (3)-1.2 (-2.8, +0.5)0.14FiO2\n30 (4)30 (4)-(a)Crs (ml/kg.cm H2O)0.37 (0.19)0.87 (0.32)+98.4 (+43.8, +153.0)0.04Hemodynamic parametersHeart rate156 (15)156 (22)+2.1 (-0.7, +4.5)0.17Systolic arterial pressure (mmHg)93 (6)99 (13)+8.4 (+3.3, +13.6)0.03Diastolic arterial pressure (mmHg)54 (12)57 (6)+3.6 (-3.0, +10.1)0.46Central venous pressure (mmHg)11 (5)10 (5)+3.9 (-5.3, +13.1)0.92Cerebral NIRS (%)62 (5)61 (3)+1.6 (-2.6, +5.8)0.34Cardiac index (L/min.m2)2.33 (0.84)2.26 (0.70)+1.4 (-3.4, +6.2)0.17Pulse oximeter perfusion index (%)1.50 (2.45)1.78 (2.29)+18.8 (+3.0, +34.7)0.04Venous blood gasespH7.32 (0.04)7.32 (0.02)-0.1 (-0.4, +0.2)0.34PCO2 (mm Hg)47.3 (5.1)45.8 (8.1)+0.6 (-5.1, +6.3)0.50ScvO2 (%)60.1 (20.9)58.4 (15.4)+3.3 (-5.7, +12.2)0.60Measurements in NAVA and CV are reported as median (interquartile). Variations between NAVA versus CV are reported as mean percentage (95 % CI). Statistical analyses between NAVA versus CV were performed by a Wilcoxon test for paired samples(a) No changes in PEEP, FiO2, neither in sedation or inotropic doses were allowed during these study periods\nNAVA Neurally adjusted Ventilatory Assist, CV Conventional Ventilation, V\nT tidal volume, PIP peak inspiratory pressure, Crs respiratory system compliance, EAdi electrical activity of the diaphragm, ScvO\n2 central venous oxygen saturation\n Cardiac index during NAVA compared to CV did not statistically differ. However, all four children with ScvO2 < 65 % tended to have higher cardiac index after 30 min of ventilation with NAVA compared to CV: 2.03 ± 0.30 vs. 1.91 ± 0.39 L/min.m2 (median ± interquartile, P = 0.07). Individual values of cardiac index and ScvO2 of children with low baseline ScvO2 are shown in Fig. 2. Upper values of pulse oximeter perfusion index were also observed. Turning now to left cardiac work index, the increase is +12.4 % (95 % CI: +3.8 % to +20.9 %, P = 0.07).Fig. 2Cardiac index and ScvO2 of the low baseline ScvO2 infants, according to the ventilation mode. White bars are cardiac index when CV is applied; back bars are cardiac index when NAVA is applied. The triangles above the bars indicate the values of the corresponding ScvO2 (%). ScvO2 = central venous oxygen saturation; NAVA = Neurally adjusted Ventilatory Assist; CV = Conventional Ventilation\n\n\nBODY.DISCUSSION:\nNAVA can be used in infants receiving postoperative mechanical ventilation after congenital heart surgery, as previously reported [7–10]. Infants included in this study all weighed less than 10 kg and had been operated less than 24 h before. To deliver a same tidal volume, NAVA required lower inspiratory pressures than conventional ventilation and had some beneficial effects on hemodynamics. Several data validate that the children were not over assisted when ventilated in CV: the delivered volumes, EAdi max, PCO2 and pH are similar in CV compared to NAVA. We suggest that lower EAdi peaks observed in CV are related to the normalization of the blood pH by CV ventilation. If children were over-assisted in CV, EAdi would have been missing, and minute volume would have been high, with a blood alkalosis. In a large randomized controlled trial where NAVA was used as a primary mode of ventilation, lower peak inspiratory pressures were found in the NAVA group [11]. It looks as if gas volume delivery, and probably alveolar expansion, required less pressure. This could be enhanced by an improvement in patient–ventilator interactions with a greater respiratory variability as reported in previous studies [12–16]. The effectiveness of this mode of mechanical ventilation was associated with some beneficial effects on the hemodynamics. Systolic arterial pressures and pulse oximeter perfusion index were significantly higher in NAVA. This pulse oximeter perfusion index provides a monitoring of illness severity in neonates [5]. In fact, we observed that the children with a low cardiac index had also a low perfusion index. This index was significantly higher when the children were ventilated with NAVA compared to CV. The overall values of the cardiac index and of the central venous oxygen saturation during NAVA compared to CV were not significantly higher, but there are possibly no reasons to observe an increase in these two parameters when tissue perfusion is already effective. And actually, the four children with a low ScvO2 trend to have a higher cardiac index after 30 min of ventilation with NAVA (Fig. 2). Moreover, this increase in cardiac index is associated with higher systemic pressures and then higher left cardiac work index. Lower oxygen content in venous blood usually reflects an oxygen balance disrupted between oxygen supply and demand. Ventilation with NAVA could allow the body to increase the cardiac output to ensure adequate oxygen availability. These children had congenital heart disease affecting the right heart: VSD with pulmonary stenosis, tetralogy of Fallot, and pulmonary atresia with VSD. Positive pressure ventilation and PEEP often result in increased right ventricular afterload due to capillary compression [3, 17]. Lower intrathoracic pressures in NAVA than in conventional ventilation could improve the right ventricular function during inspiration by reducing the right ventricular afterload. An improvement in apparent respiratory system compliance was observed when NAVA is applied. Cyclic intrathoracic pressure changes, characteristic of spontaneous breathing, could be preserved. Both fine synchronization of respiratory support and pressure assistance varying with the needs and the spontaneous breathing of the child could improve the pulmonary compliance. Nonetheless, it is important to note that we did not record the transpulmonary pressure. It is likely that, while the airway pressure decreased during NAVA, an increase in esophageal pressure swings occurred because of the patient respiratory efforts. This could have participated in the decrease in apparent compliance improvement [18]. This study has some limitations. Firstly, few children were studied. Many children dropped out due to early extubation in the operation room or immediately on arrival in the intensive care unit. Technical problems were greater than expected: a measure of cardiac output sufficiently accurate, and especially stable in time, was very difficult to reach in children who already had a stomach tube for the NAVA ventilation. Nevertheless the cross-over design of this study has two advantages over both a parallel study and a non-crossover longitudinal study [19]. The influence of confounding covariates is reduced because each cross-over patient serves as his or her own control. Cross-over designs are also statistically efficient and require fewer subjects than do non-crossover designs (even other repeated measures designs). Secondly, the agreement of the cardiac output measurement between the transoesophageal Doppler probe using CardioQP and the thermodilution technique during heart catheterisation in paediatric patients was described as weak [20]. However the CardioQP seems to be capable of detecting slight changes in cardiac output for critically ill children [21, 22]. This bed-side device for cardiac output measurement is minimally invasive, and provides better results in monitoring the slight variations rather than in measuring absolute values. As we were performing a cross-over study, we were interested primarily by changes. Finally, only comparison with CV-SIMV with relatively high preset respiratory rate preventing many spontaneous cycles was made, not with other ventilation strategies.\n\nBODY.CONCLUSION:\nIn conclusion, this cross-over study provides new data on the NAVA ventilation. This pilot study raises the hypothesis that a ventilatory assistance with NAVA could provide improvements in hemodynamics when compared to a conventional ventilatory mode that delivered identical PEEP and similar minute volumes. Thus, because minute volumes were not different between the two modes of ventilation, hemodynamic effects are linked to NAVA mode itself and NOT to incorrect settings in conventional ventilation. Further studies with larger population are needed to confirm these promising results.\n\nQuestion: Compared to Conventional Ventilation what was the result of Neurally Adjusted Ventilatory Assist on Systolic arterial pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1074	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The effect of hip abduction on the EMG activity of vastus medialis obliquus, vastus lateralis longus and vastus lateralis obliquus in healthy subjects\n\n ABSTRACT.STUDY DESIGN:\nControlled laboratory study.\n\nABSTRACT.OBJECTIVES:\nThe purposes of this paper were to investigate (d) whether vastus medialis obliquus (VMO), vastus lateralis longus (VLL) and vastus lateralis obliquus (VLO) EMG activity can be influenced by hip abduction performed by healthy subjects.\n\nABSTRACT.BACKGROUND:\nSome clinicians contraindicate hip abduction for patellofemoral patients (with) based on the premise that hip abduction could facilitate the VLL muscle activation leading to a VLL and VMO imbalance\n\nABSTRACT.METHODS AND MEASURES:\nTwenty-one clinically healthy subjects were involved in the study, 10 women and 11 men (aged X = 23.3 ± 2.9). The EMG signals were collected using a computerized EMG VIKING II, with 8 channels and three pairs of surface electrodes. EMG activity was obtained from MVIC knee extension at 90° of flexion in a seated position and MVIC hip abduction at 0° and 30° with patients in side-lying position with the knee in full extension. The data were normalized in the MVIC knee extension at 50° of flexion in a seated position, and were submitted to ANOVA test with subsequent application of the Bonferroni multiple comparisons analysis test. The level of significance was defined as p ≤ 0.05.\n\nABSTRACT.RESULTS:\nThe VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196). There were no statistically significant differences in the VLL EMG activity among the three sets of exercises tested.\n\nABSTRACT.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC hip abduction at 0° and 30° of abduction and MVIC knee extension at 90° of flexion in both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nBODY.INTRODUCTION:\nPatellofemoral pain syndrome (PFPS) presents one of the most perplexing pathologic conditions in orthopedic and sports medicine clinics, as well as in rehabilitation departments, and it was referred to by Dye [1] as the \"black hole of orthopedics\" because of the lack of clarity regarding the etiological factors that contribute to dysfunction or to specific treatment protocols and the causative mechanisms remain imprecisely defined [2]. Dysfunction of the quadriceps muscle has been hypothesized as a cause of patellofemoral pain syndrome (PFPS) with great emphasis placed on the role of VMO and VL muscular imbalance [3,4]. Quadriceps dysfunction in PFPS patients has been assessed in various ways including decreased magnitude of the electromyographic (EMG) activity of the quadriceps [5,6], diminished EMG activity of the VMO in relation to that of the VL [7-9], and the delayed onset of VMO activation in relation to the VL [10-12] caused by the inhibition of pain, effusion and atrophies[13]. Improved control of patella tracking is necessary for symptomatic relief [14] and the recovery of quadriceps function is essential to the resolution of the problem [15]. Consequently, there have been numerous studies that have sought to identify exercises to selectively recruit the VMO in an effort to retrain this muscle [7,16-18]. However, Mirzabeigi et al. [19] suggested that the VMO muscle cannot be significantly isolated during nine sets of different exercises. Since fibers of the VMO attach to the adductor magnus muscle, it has been hypothesized that activation of the VMO may be enhanced by combining active knee extension with volitional hip adduction [4,16,20]. Research in clinical studies on the treatment of PFPS has reported that VL activity may also be enhanced by combining knee extension exercises with hip abduction [21,22]. Fulkerson [23] noted retinacular tenderness in patients with patellofemoral pain, including some who demonstrated histological changes within the perineural tissues of the lateral retinaculum on examination of surgical biopsy specimens. Bevilaqua-Grossi et al. [24] in their anatomical study dissected the thighs of 32 human cadavers and showed that the distal fibers of the Vastus Lateralis Obliquus (VLO) were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, were subsequently joined in a common tendon with the VLL on the superolateral border of the patella (Figure 1) and that tightness of lateral retinaculum could potentially alter the tracking of the patella in the trochlear groove. Based on this anatomic correlation, Hip abduction exercises are often contraindicated by physical therapists because some group of patient with patellofemoral problems may have tight lateral structures and hip abduction exercises would enhance VMO and VL muscular imbalance [21]. Figure 1Lateral view of the right thigh showing the origin of the obliquus portion of the vastus lateralis muscle (vastus lateralis obliquus – VLO) in the lateral intermuscular septum (LIS) and its insertion in the superior -lateral border of the patella (P). VLL – vastus lateralis longus. Bevilaqua-Grossi et al. (2004) 46. Considering that previous few studies have investigated the EMG relationship VMO and VLO with other structures of the lateral compartment (lateral retinaculum and iliotibial tract) and hip abduction strengthening exercises, the aim of this paper was to analyze the EMG activity of the VMO, VLL and VLO muscles and verify whether any difference in activity between these portions occurred during MVIC: 1) knee extension at 90° of flexion, 2) hip abduction at 0° of abduction and 3) hip abduction at 30° of abduction. The data reported in this paper should be useful in future functional studies aimed at a clearer understanding of rehabilitation protocols in PFPS patients.\n\nBODY.METHODS.SUBJECTS:\nTwenty-one healthy volunteers (11 males and 10 females), aged from 19 to 28 (X = 23.3 ± 2.9), participated in this study. They were recruited from Piracicaba Methodist University and all reported no history of orthopedic disorders, surgical procedures, knee pain or other major musculoskeletal injuries. Prior to participation, all subjects read, accepted and signed a consent form that was approved by the Human Research Ethics Committee at the State University of Campinas.\n\nBODY.METHODS.INSTRUMENTATION:\nSilver/silver chloride surface electrodes placed in a bipolar configuration, with a 10 mm contact area and an inter-electrode distance of 2 cm, were used to assess the level of electromyographic activity of the VMO, VLL and VLO muscles. Before the electrode placement the sites were prepared by shaving, abrading and cleaning with isopropyl alcohol to reduce the surface impedance to less than 5 and 10 kΩ for men and women, respectively. A quadriceps line was drawn from the anterior superior iliac spine to the center of the patella for the quadriceps portion placement [24]. A surface electrode for the VMO was placed with a medial inclination of 55° from the quadriceps line [25,26]. The VLL electrode was placed 15 cm from the superior edge of patella at a lateral inclination of 13.6° and the VLO shows its superficial part around 2.2 cm of the lateralis epicondyle with a superficial length of around 8.9 cm with a 50.4° of lateral inclination[27]. A ground electrode was placed over the tibial tubercle of the tested lower limb. The same investigator performed all electrode placements. A calibrated Viking II with eight channels (Nicolet Biomedical Instruments) and a computer were used to collect all EMG data (CMRR of 110 dB, sampling 1000 Hz, gain 200, band pass filter of 10 to 1000 Hz). All signals were viewed on a display screen prior to collection to ensure that there were no visible artifacts.\n\nBODY.METHODS.PROCEDURES:\nFollowing EMG preparation, the subjects were instructed to perform 3 repetitions of the following three sets of exercises: 1) MVIC knee extension at 90° of flexion in a seated position; 2) MVIC hip abduction at 0° of abduction, with patients in side-lying position with the knee in full extension; 3) MVIC hip abduction at 30° of abduction, with patients in side-lying position with the knee in full extension During the MVIC knee extension test, the subjects were positioned seated in a leg extension machine (Queens, São Paulo, BRA) with the knee and hip at 90° of flexion and the ankle in a neutral position (figure 2). For the MVIC hip abduction (0° and 30°) tests, the subjects were positioned on their sides lying on a divan with the test lower limb placed above and with both lower limbs positioned at neutral hip and knee flexions, as measured by the investigator. For the maintenance of these positions the thighs were stabilized with padding and the calves were fixed with a belt applied immediately distal to the knees (Figure 3 and 4). Figure 2Maximum voluntary isometric contraction at 90 degrees of knee extension. Figure 3Maximum voluntary isometric contraction of hip abduction in neutral in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Figure 4Maximum voluntary isometric contraction at 30 degrees of hip abduction in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Before data collection procedures began, each subject received a verbal explanation and a demonstration of the testing activities and practice trials were performed to ensure the subject's comprehension and safety. After familiarization, the subjects randomly performed three MVIC for 5 seconds with a 2 minute rest between repetitions and 10 minutes between each set of exercises to prevent muscle exhaustion. EMG signals were collected throughout each MVIC and verbal encouragement was provided throughout the testing.\n\nBODY.METHODS.DATA ANALYSIS:\nThe normalization of the VMO, VLL and VLO EMG signals for the three exercises (knee extension at 90° of flexion, MVIC hip abduction at 0° of abduction, MVIC hip abduction at 30° of abduction) were obtained dividing the highest EMG value of the MVIC trials by the EMG value of a MVIC knee extension at 50° of flexion in a seated position and multiplied by 100 [16]. The normalization procedure performed at 50° of knee flexion in a seated position followed the same protocol of positioning for the test at 90° of knee flexion in a seated position. Normalized EMG readings were analyzed by two-way analysis of variance with repeated measurements. Post hoc comparisons within the values obtained for each of the muscles were realized by the Bonferroni multiple comparisons analysis. Significance was defined as p ≤ 0.05.\n\nBODY.RESULTS:\nMaximum voluntary isometric contractions for knee extension at 90° of flexion resulted in a significantly higher EMG activity for the VMO muscle compared with hip abduction at 0° and 30° of abduction for both male (p < 0.008) and female (p < 0.0005) subjects (Table 1, Figure 5). Table 1 Summarized results of normalized EMG values of VMO, VLL and VLO muscles during MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction (N = 21) The results are shown as a percentage of MVIC at 50° of knee flexion in a seated position Test procedure VMO (%) VLL (%) VLO (%) Hip abduction at 30° Male 53.70 88.31 75.70 Female 96.07 119.61 103.98 Hip abduction at 0° Male 69.05 110.62 90.25 female 87.09 100.13 92.30 MIVC at 90° of knee flexion Male 144.91 c 115.31 146.72 d female 165.97 b 141.30 162.61 a p ≤ 0,05 Letters demonstrate higher EMG activity of the same muscle in which there were statistically significantly differences between the three exercises a p = 0,02196 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° of abduction b p = 0,008 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction c p = 0,000055 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction d p = 0,000761 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction Figure 5Normalized EMG activity expressed as RMS values from healthy subjects performing MVIC knee extension at 90° of flexion, MVIC hip abduction at 0° and 30° of abduction. A) Significantly higher VMO activity for both male and female subjects performing MVIC knee extension at 90° of flexion when compared to MVIC hip abduction at 0° and 30° of abduction. B) VLL EMG activity without significant differences among the three exercises tested. C) Significantly higher VLO activity for male subjects was observed in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction and for female subjects performing MVIC knee extension at 90° of flexion when compared with MVIC hip abduction at 0° and 30° of abduction. There were no statistically significant differences in the VLL EMG activity among the three types of exercise tested (Table 1, Figure 5). The VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and with MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196) (Table 1, Figure 5). There were no significant differences between gender with respect to the EMG activity of the VMO, VLL and VLO muscles among the three types of exercise tested. No selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction for both male and female subjects.\n\nBODY.DISCUSSION:\nThe primary purpose of this article was to investigate whether VMO, VLL and VLO EMG activity can be influenced by hip abduction. The results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion or MVIC hip abduction at 0° and 30° of abduction for both male and female subjects. These results are in agreement with Hertel et al. [4] who investigated the EMG activity of the VMO, VLL and gluteus medius in eight healthy young adult volunteers with no history of knee injury while performing uniplanar knee extension, knee extension/hip adduction, knee extension/hip abduction and found no significant differences in the VMO/VL ratio between the exercises. It is well established in the literature that the isolation of any of the quadriceps components or selective strengthening is unlikely, especially concerning the VMO/VLL muscles [28,29]. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO in healthy subjects performing maximum voluntary isometric contraction. We are unaware of any studies which have demonstrated the characteristics of EMG activity between VMO, VLL and VLO in subjects performing hip abduction in different positions. The secondary purpose of the present work was investigating the EMG activity of the VMO, VLL and VLO while performing the three exercises tested. The results showed that the VLO presents a significantly different behavior compared with the VLL, whereas the VLO showed a similar motor unit recruitment to the VMO, producing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction. No significant differences were found in the EMG activity of the VLL among the three exercises tested, thus verifying that the VLL and VLO demonstrate not only anatomical but distinct motor unit recruitment characteristics. Bevilaqua-Grossi et al. [27] investigated the EMG activity of the VMO, VLL and VLO muscles in 21 healthy subjects performing open kinetic chain knee extension at 15° and 90° of flexion. The results showed that the VLO and VMO were more active at 90° of flexion compared with the higher activity of the VLL at 15° of flexion, demonstrating that the VMO and VLO muscle have the same behavior suggesting a synchronic antagonist stability role of the patella in healthy people. The striking difference between VLL and VLO behavior concerning the EMG activity observed, could be because the VLL fiber alignment tends to traction the patella, offering greater contribution to knee extension than patella stabilization, different from the VLO which spirally and inclination fibers in relation to femoral dyaphisis promotes patella alignment associated with the VMO [24] Hertel et al. [4] reported that both the VMO and VL are more activated in uniplanar knee extension when compared with knee extension/hip adduction or abduction. These results are not entirely supported by our results, in which the VLL showed no significant differences between MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30°. These conflicting results concerning the VLL recruitment pattern may be because these authors tested the exercises in closed kinetic chain while the three exercises tested in the current work were performed in open kinetic chain. Possible limitations of this study may be related to the non collection of gluteus medius EMG activity during the three exercises tested. Normalization methods using other types of muscle contractions or other angles of the knee joint may result in different VMO/VLL/VLO ratios between studies that use different methods of normalization. The absence of increased EMG activity with hip abduction could have been due limitations in EMG recordings from MVCs. Results might be different when studying submax voluntary contractions. Although normalized EMG data are useful in measuring relative levels of activity between muscles, such information is not indicative of muscular strength or muscular balance [58]. Future studies of this research group will focus on subjects with patellofemoral pain and investigate the recruitment patterns provided from such subjects performing the same task.\n\nBODY.DISCUSSION.CLINICAL IMPLICATIONS:\nBevilaqua-Grossi et al. [24] dissected the thighs of 32 human cadavers and determined the anatomical organizations of the VLL and VLO muscles. The distal fibers of the VLO were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, which subsequently joined in a common tendon with the VLL on the superolateral border of the patella. These results agree with previous anatomical studies which describe the origin [30-34] and insertion of these muscles [35,36]. Thus, tightness of the lateral retinaculum, perhaps as a result of increased tension in the iliotibial tract, could potentially alter the tracking of the patella in the trochlear groove, becoming an important factor in the etiology of patellofemoral pain [37]. Following this theory, some clinicians contraindicate rehabilitation exercises using hip abduction in patients with patellofemoral complaints based on the premise of avoiding excessive tightness of the lateral structures or a VLL and VMO imbalance, since the anatomical origin of the iliotibial tract has a close relation with the iliotibial band and the gluteus medius muscles [21,38]. This theory is not supported by recent works which investigated the role of pelvic control as a contributing factor in the development of anterior knee pain [39-42]. Ireland et al. [39], using hand held dynamometers, investigated hip abduction and external rotation isometric strength in 15 female patients with patellofemoral pain compared with a control group. They found significant weakness of the hip abductors and external rotators of the patellofemoral pain group. It is postulated that in the absence of pelvic control due to hip abductor and external rotator weakness, the femur may adduct and internally rotate, further increasing lateral patellar contact pressure [43]. These findings suggest that hip abduction exercises may be indicated and necessary for patients with patellofemoral pain who present absence of satisfactory pelvic control.\n\nBODY.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC at 30° and 0° of hip abduction and 90° of knee flexion for both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nQuestion: Compared to hip abduction at 0° and 30° what was the result of knee extension at 90° of flexion on vastus medialis obliquus (VMO) EMG activity ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1075	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The effect of hip abduction on the EMG activity of vastus medialis obliquus, vastus lateralis longus and vastus lateralis obliquus in healthy subjects\n\n ABSTRACT.STUDY DESIGN:\nControlled laboratory study.\n\nABSTRACT.OBJECTIVES:\nThe purposes of this paper were to investigate (d) whether vastus medialis obliquus (VMO), vastus lateralis longus (VLL) and vastus lateralis obliquus (VLO) EMG activity can be influenced by hip abduction performed by healthy subjects.\n\nABSTRACT.BACKGROUND:\nSome clinicians contraindicate hip abduction for patellofemoral patients (with) based on the premise that hip abduction could facilitate the VLL muscle activation leading to a VLL and VMO imbalance\n\nABSTRACT.METHODS AND MEASURES:\nTwenty-one clinically healthy subjects were involved in the study, 10 women and 11 men (aged X = 23.3 ± 2.9). The EMG signals were collected using a computerized EMG VIKING II, with 8 channels and three pairs of surface electrodes. EMG activity was obtained from MVIC knee extension at 90° of flexion in a seated position and MVIC hip abduction at 0° and 30° with patients in side-lying position with the knee in full extension. The data were normalized in the MVIC knee extension at 50° of flexion in a seated position, and were submitted to ANOVA test with subsequent application of the Bonferroni multiple comparisons analysis test. The level of significance was defined as p ≤ 0.05.\n\nABSTRACT.RESULTS:\nThe VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196). There were no statistically significant differences in the VLL EMG activity among the three sets of exercises tested.\n\nABSTRACT.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC hip abduction at 0° and 30° of abduction and MVIC knee extension at 90° of flexion in both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nBODY.INTRODUCTION:\nPatellofemoral pain syndrome (PFPS) presents one of the most perplexing pathologic conditions in orthopedic and sports medicine clinics, as well as in rehabilitation departments, and it was referred to by Dye [1] as the \"black hole of orthopedics\" because of the lack of clarity regarding the etiological factors that contribute to dysfunction or to specific treatment protocols and the causative mechanisms remain imprecisely defined [2]. Dysfunction of the quadriceps muscle has been hypothesized as a cause of patellofemoral pain syndrome (PFPS) with great emphasis placed on the role of VMO and VL muscular imbalance [3,4]. Quadriceps dysfunction in PFPS patients has been assessed in various ways including decreased magnitude of the electromyographic (EMG) activity of the quadriceps [5,6], diminished EMG activity of the VMO in relation to that of the VL [7-9], and the delayed onset of VMO activation in relation to the VL [10-12] caused by the inhibition of pain, effusion and atrophies[13]. Improved control of patella tracking is necessary for symptomatic relief [14] and the recovery of quadriceps function is essential to the resolution of the problem [15]. Consequently, there have been numerous studies that have sought to identify exercises to selectively recruit the VMO in an effort to retrain this muscle [7,16-18]. However, Mirzabeigi et al. [19] suggested that the VMO muscle cannot be significantly isolated during nine sets of different exercises. Since fibers of the VMO attach to the adductor magnus muscle, it has been hypothesized that activation of the VMO may be enhanced by combining active knee extension with volitional hip adduction [4,16,20]. Research in clinical studies on the treatment of PFPS has reported that VL activity may also be enhanced by combining knee extension exercises with hip abduction [21,22]. Fulkerson [23] noted retinacular tenderness in patients with patellofemoral pain, including some who demonstrated histological changes within the perineural tissues of the lateral retinaculum on examination of surgical biopsy specimens. Bevilaqua-Grossi et al. [24] in their anatomical study dissected the thighs of 32 human cadavers and showed that the distal fibers of the Vastus Lateralis Obliquus (VLO) were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, were subsequently joined in a common tendon with the VLL on the superolateral border of the patella (Figure 1) and that tightness of lateral retinaculum could potentially alter the tracking of the patella in the trochlear groove. Based on this anatomic correlation, Hip abduction exercises are often contraindicated by physical therapists because some group of patient with patellofemoral problems may have tight lateral structures and hip abduction exercises would enhance VMO and VL muscular imbalance [21]. Figure 1Lateral view of the right thigh showing the origin of the obliquus portion of the vastus lateralis muscle (vastus lateralis obliquus – VLO) in the lateral intermuscular septum (LIS) and its insertion in the superior -lateral border of the patella (P). VLL – vastus lateralis longus. Bevilaqua-Grossi et al. (2004) 46. Considering that previous few studies have investigated the EMG relationship VMO and VLO with other structures of the lateral compartment (lateral retinaculum and iliotibial tract) and hip abduction strengthening exercises, the aim of this paper was to analyze the EMG activity of the VMO, VLL and VLO muscles and verify whether any difference in activity between these portions occurred during MVIC: 1) knee extension at 90° of flexion, 2) hip abduction at 0° of abduction and 3) hip abduction at 30° of abduction. The data reported in this paper should be useful in future functional studies aimed at a clearer understanding of rehabilitation protocols in PFPS patients.\n\nBODY.METHODS.SUBJECTS:\nTwenty-one healthy volunteers (11 males and 10 females), aged from 19 to 28 (X = 23.3 ± 2.9), participated in this study. They were recruited from Piracicaba Methodist University and all reported no history of orthopedic disorders, surgical procedures, knee pain or other major musculoskeletal injuries. Prior to participation, all subjects read, accepted and signed a consent form that was approved by the Human Research Ethics Committee at the State University of Campinas.\n\nBODY.METHODS.INSTRUMENTATION:\nSilver/silver chloride surface electrodes placed in a bipolar configuration, with a 10 mm contact area and an inter-electrode distance of 2 cm, were used to assess the level of electromyographic activity of the VMO, VLL and VLO muscles. Before the electrode placement the sites were prepared by shaving, abrading and cleaning with isopropyl alcohol to reduce the surface impedance to less than 5 and 10 kΩ for men and women, respectively. A quadriceps line was drawn from the anterior superior iliac spine to the center of the patella for the quadriceps portion placement [24]. A surface electrode for the VMO was placed with a medial inclination of 55° from the quadriceps line [25,26]. The VLL electrode was placed 15 cm from the superior edge of patella at a lateral inclination of 13.6° and the VLO shows its superficial part around 2.2 cm of the lateralis epicondyle with a superficial length of around 8.9 cm with a 50.4° of lateral inclination[27]. A ground electrode was placed over the tibial tubercle of the tested lower limb. The same investigator performed all electrode placements. A calibrated Viking II with eight channels (Nicolet Biomedical Instruments) and a computer were used to collect all EMG data (CMRR of 110 dB, sampling 1000 Hz, gain 200, band pass filter of 10 to 1000 Hz). All signals were viewed on a display screen prior to collection to ensure that there were no visible artifacts.\n\nBODY.METHODS.PROCEDURES:\nFollowing EMG preparation, the subjects were instructed to perform 3 repetitions of the following three sets of exercises: 1) MVIC knee extension at 90° of flexion in a seated position; 2) MVIC hip abduction at 0° of abduction, with patients in side-lying position with the knee in full extension; 3) MVIC hip abduction at 30° of abduction, with patients in side-lying position with the knee in full extension During the MVIC knee extension test, the subjects were positioned seated in a leg extension machine (Queens, São Paulo, BRA) with the knee and hip at 90° of flexion and the ankle in a neutral position (figure 2). For the MVIC hip abduction (0° and 30°) tests, the subjects were positioned on their sides lying on a divan with the test lower limb placed above and with both lower limbs positioned at neutral hip and knee flexions, as measured by the investigator. For the maintenance of these positions the thighs were stabilized with padding and the calves were fixed with a belt applied immediately distal to the knees (Figure 3 and 4). Figure 2Maximum voluntary isometric contraction at 90 degrees of knee extension. Figure 3Maximum voluntary isometric contraction of hip abduction in neutral in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Figure 4Maximum voluntary isometric contraction at 30 degrees of hip abduction in side-lying position. The subjects were instructed to maintain an isometric quadriceps contraction at full knee extension while performing the task. Before data collection procedures began, each subject received a verbal explanation and a demonstration of the testing activities and practice trials were performed to ensure the subject's comprehension and safety. After familiarization, the subjects randomly performed three MVIC for 5 seconds with a 2 minute rest between repetitions and 10 minutes between each set of exercises to prevent muscle exhaustion. EMG signals were collected throughout each MVIC and verbal encouragement was provided throughout the testing.\n\nBODY.METHODS.DATA ANALYSIS:\nThe normalization of the VMO, VLL and VLO EMG signals for the three exercises (knee extension at 90° of flexion, MVIC hip abduction at 0° of abduction, MVIC hip abduction at 30° of abduction) were obtained dividing the highest EMG value of the MVIC trials by the EMG value of a MVIC knee extension at 50° of flexion in a seated position and multiplied by 100 [16]. The normalization procedure performed at 50° of knee flexion in a seated position followed the same protocol of positioning for the test at 90° of knee flexion in a seated position. Normalized EMG readings were analyzed by two-way analysis of variance with repeated measurements. Post hoc comparisons within the values obtained for each of the muscles were realized by the Bonferroni multiple comparisons analysis. Significance was defined as p ≤ 0.05.\n\nBODY.RESULTS:\nMaximum voluntary isometric contractions for knee extension at 90° of flexion resulted in a significantly higher EMG activity for the VMO muscle compared with hip abduction at 0° and 30° of abduction for both male (p < 0.008) and female (p < 0.0005) subjects (Table 1, Figure 5). Table 1 Summarized results of normalized EMG values of VMO, VLL and VLO muscles during MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction (N = 21) The results are shown as a percentage of MVIC at 50° of knee flexion in a seated position Test procedure VMO (%) VLL (%) VLO (%) Hip abduction at 30° Male 53.70 88.31 75.70 Female 96.07 119.61 103.98 Hip abduction at 0° Male 69.05 110.62 90.25 female 87.09 100.13 92.30 MIVC at 90° of knee flexion Male 144.91 c 115.31 146.72 d female 165.97 b 141.30 162.61 a p ≤ 0,05 Letters demonstrate higher EMG activity of the same muscle in which there were statistically significantly differences between the three exercises a p = 0,02196 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° of abduction b p = 0,008 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction c p = 0,000055 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction d p = 0,000761 High EMG activity MVIC knee extension at 90° of flexion vs MVIC hip abduction at 0° and 30° of abduction Figure 5Normalized EMG activity expressed as RMS values from healthy subjects performing MVIC knee extension at 90° of flexion, MVIC hip abduction at 0° and 30° of abduction. A) Significantly higher VMO activity for both male and female subjects performing MVIC knee extension at 90° of flexion when compared to MVIC hip abduction at 0° and 30° of abduction. B) VLL EMG activity without significant differences among the three exercises tested. C) Significantly higher VLO activity for male subjects was observed in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction and for female subjects performing MVIC knee extension at 90° of flexion when compared with MVIC hip abduction at 0° and 30° of abduction. There were no statistically significant differences in the VLL EMG activity among the three types of exercise tested (Table 1, Figure 5). The VLO muscle demonstrated a similar pattern to the VMO muscle showing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction for male (p < 0.0007) and with MVIC hip abduction at 0° of abduction for female subjects (p < 0.02196) (Table 1, Figure 5). There were no significant differences between gender with respect to the EMG activity of the VMO, VLL and VLO muscles among the three types of exercise tested. No selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion and MVIC hip abduction at 0° and 30° of abduction for both male and female subjects.\n\nBODY.DISCUSSION:\nThe primary purpose of this article was to investigate whether VMO, VLL and VLO EMG activity can be influenced by hip abduction. The results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC knee extension at 90° of flexion or MVIC hip abduction at 0° and 30° of abduction for both male and female subjects. These results are in agreement with Hertel et al. [4] who investigated the EMG activity of the VMO, VLL and gluteus medius in eight healthy young adult volunteers with no history of knee injury while performing uniplanar knee extension, knee extension/hip adduction, knee extension/hip abduction and found no significant differences in the VMO/VL ratio between the exercises. It is well established in the literature that the isolation of any of the quadriceps components or selective strengthening is unlikely, especially concerning the VMO/VLL muscles [28,29]. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO in healthy subjects performing maximum voluntary isometric contraction. We are unaware of any studies which have demonstrated the characteristics of EMG activity between VMO, VLL and VLO in subjects performing hip abduction in different positions. The secondary purpose of the present work was investigating the EMG activity of the VMO, VLL and VLO while performing the three exercises tested. The results showed that the VLO presents a significantly different behavior compared with the VLL, whereas the VLO showed a similar motor unit recruitment to the VMO, producing higher EMG activity in MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30° of abduction. No significant differences were found in the EMG activity of the VLL among the three exercises tested, thus verifying that the VLL and VLO demonstrate not only anatomical but distinct motor unit recruitment characteristics. Bevilaqua-Grossi et al. [27] investigated the EMG activity of the VMO, VLL and VLO muscles in 21 healthy subjects performing open kinetic chain knee extension at 15° and 90° of flexion. The results showed that the VLO and VMO were more active at 90° of flexion compared with the higher activity of the VLL at 15° of flexion, demonstrating that the VMO and VLO muscle have the same behavior suggesting a synchronic antagonist stability role of the patella in healthy people. The striking difference between VLL and VLO behavior concerning the EMG activity observed, could be because the VLL fiber alignment tends to traction the patella, offering greater contribution to knee extension than patella stabilization, different from the VLO which spirally and inclination fibers in relation to femoral dyaphisis promotes patella alignment associated with the VMO [24] Hertel et al. [4] reported that both the VMO and VL are more activated in uniplanar knee extension when compared with knee extension/hip adduction or abduction. These results are not entirely supported by our results, in which the VLL showed no significant differences between MVIC knee extension at 90° of flexion compared with MVIC hip abduction at 0° and 30°. These conflicting results concerning the VLL recruitment pattern may be because these authors tested the exercises in closed kinetic chain while the three exercises tested in the current work were performed in open kinetic chain. Possible limitations of this study may be related to the non collection of gluteus medius EMG activity during the three exercises tested. Normalization methods using other types of muscle contractions or other angles of the knee joint may result in different VMO/VLL/VLO ratios between studies that use different methods of normalization. The absence of increased EMG activity with hip abduction could have been due limitations in EMG recordings from MVCs. Results might be different when studying submax voluntary contractions. Although normalized EMG data are useful in measuring relative levels of activity between muscles, such information is not indicative of muscular strength or muscular balance [58]. Future studies of this research group will focus on subjects with patellofemoral pain and investigate the recruitment patterns provided from such subjects performing the same task.\n\nBODY.DISCUSSION.CLINICAL IMPLICATIONS:\nBevilaqua-Grossi et al. [24] dissected the thighs of 32 human cadavers and determined the anatomical organizations of the VLL and VLO muscles. The distal fibers of the VLO were interdigitated with the lateral retinaculum and the iliotibial tract in all specimens, which subsequently joined in a common tendon with the VLL on the superolateral border of the patella. These results agree with previous anatomical studies which describe the origin [30-34] and insertion of these muscles [35,36]. Thus, tightness of the lateral retinaculum, perhaps as a result of increased tension in the iliotibial tract, could potentially alter the tracking of the patella in the trochlear groove, becoming an important factor in the etiology of patellofemoral pain [37]. Following this theory, some clinicians contraindicate rehabilitation exercises using hip abduction in patients with patellofemoral complaints based on the premise of avoiding excessive tightness of the lateral structures or a VLL and VMO imbalance, since the anatomical origin of the iliotibial tract has a close relation with the iliotibial band and the gluteus medius muscles [21,38]. This theory is not supported by recent works which investigated the role of pelvic control as a contributing factor in the development of anterior knee pain [39-42]. Ireland et al. [39], using hand held dynamometers, investigated hip abduction and external rotation isometric strength in 15 female patients with patellofemoral pain compared with a control group. They found significant weakness of the hip abductors and external rotators of the patellofemoral pain group. It is postulated that in the absence of pelvic control due to hip abductor and external rotator weakness, the femur may adduct and internally rotate, further increasing lateral patellar contact pressure [43]. These findings suggest that hip abduction exercises may be indicated and necessary for patients with patellofemoral pain who present absence of satisfactory pelvic control.\n\nBODY.CONCLUSION:\nThe results showed that no selective EMG activation was observed when comparison was made between the VMO, VLL and VLO muscles while performing MVIC at 30° and 0° of hip abduction and 90° of knee flexion for both male and female subjects. Our findings demonstrate that hip abduction do not facilitated VLL and VLO activity in relation to the VMO, however, this study included only healthy subjects performing maximum voluntary isometric contraction contractions, therefore much remains to be discovered by future research\n\nQuestion: Compared to hip abduction at 0° and 30° what was the result of knee extension at 90° of flexion on vastus lateralis longus (VLL) EMG activity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1080	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Gabapentin as an adjuvant for postoperative pain management in dogs undergoing mastectomy\n\n ABSTRACT:\nThis study aimed to evaluate the analgesic efficacy of gabapentin as an adjuvant for postoperative pain management in dogs. Twenty dogs undergoing mastectomy were randomized to receive perioperative oral placebo or gabapentin (10 mg/kg). All dogs were premedicated with intramuscular acepromazine (0.03 mg/kg) and morphine (0.3 mg/ kg). Anesthesia was induced with propofol (4 mg/kg) intravenously and maintained with isoflurane. Intravenous meloxicam (0.2 mg/kg) was administered preoperatively. Postoperative analgesia was evaluated for 72 hr. Rescue analgesia was provided with intramuscular morphine (0.5 mg/kg). Dogs in the Placebo group received significantly more morphine doses than the Gabapentin group (P=0.021), despite no significant differences in pain scores. Perioperative gabapentin reduced the postoperative morphine requirements in dogs after mastectomy.\n\nBODY:\nMammary tumors are the most common neoplasias in dogs and are commonly treated by an extensive mastectomy which results in inflammation, edema and moderate to severe postoperative pain [21]. Postoperative pain is not purely nociceptive in nature and may consist of inflammatory, neurogenic and visceral components [17]. Therefore, multimodal analgesic techniques utilizing a number of drugs which act on different analgesic mechanisms are becoming increasingly popular [5, 14, 19, 23]. Gabapentin is a non-opioid medication, structurally analog of gamma-amino butyric acid, which has been used as an anticonvulsant and antinociceptive drug [9]. In humans, several studies have shown that perioperative gabapentin helps to produce a significant opioid-sparing effect and decreases the postoperative pain score compared with placebo groups [3, 4, 6]. In veterinary medicine, two previous reports showed relevant analgesic effects using gabapentin as an adjuvant for the treatment of hyperalgesia and allodynia in dogs and cats [2, 24]. In contrast, in dogs undergoing amputation of a forelimb, perioperative gabapentin did not provide a significant benefit for postoperative pain management [26]. The aim of this\nstudy was to evaluate the analgesic efficacy of gabapentin as an adjuvant for postoperative pain management in dogs. This study was performed following the guidelines of the Brazilian College of Animal Experimentation, and the experimental procedure was approved by an institutional animal care committee (protocol 1182-CEEA). Informed consent was obtained from the owners of all the dogs. Twenty female dogs, aged 6 to 12 years (median, 9.2 years) and weighing between 2.7 and 29.3 kg (median, 10.6 kg), undergoing elective mastectomy of at least 4 mammary glands were enrolled. The preoperative condition of each dog was evaluated through a physical examination and laboratory tests (i.e., complete blood cell count, measurements of the urea, creatinine, alanine aminotransferase and aspartate aminotransferase levels). All the dogs met the following inclusion criteria: American Society of Anesthesiologists physical status of III or less, no arterial hypertension or congestive heart failure, no renal or hepatic dysfunction and no pulmonary metastases. The dogs were randomly assigned to one of the two\ngroups, with 10 animals in each. The dogs were orally (PO) administered with either 10 mg/kg (1 ml/5kg) of gabapentin solution (Neurotin Oral solution, 50 mg/5ml, Pfizer, New York, NY, U.S.A.) (Gabapentin, n=10) or 1 ml/5kg of placebo solution (Placebo, n=10) 120 min prior to surgery. The placebo was produced with the inactive ingredients of the gabapentin oral solution (glycerin, xylitol, purified water and artificial cool strawberry anise flavor.) The postoperative gabapentin or placebo was continued for three days after surgery beginning 12 hr after the preoperative dose. A random number generator (Research Randomizer, Computer software, http://www.randomizer.org/) was used to assign 10 dogs to each of the two groups. After withdrawing food and water for 12 hr and 3 hr, respectively, all dogs were premedicated with 0.03 mg/kg acepromazine (Acepran 0.2%, Univet São Paulo, Brazil) in combination with 0.3 mg/kg morphine (Dimorf, Cristália, Brazil) intramuscularly (IM). Twenty min after the premedication, an intravenous catheter (Insyte, Becton Dickinson, São Paulo, Brazil) was aseptically placed in a cephalic vein, and anesthesia was induced with 4 mg/kg propofol (Propovan, Cristália, Brazil). Orotracheal intubation was performed, and anesthesia was maintained with isoflurane in 100% oxygen using a small animal rebreathing circuit (Samurai, Takaoka, São Paulo, Brazil). Surgical procedures were performed by the same experienced surgeon, using the same surgical technique. The extent of mastectomy was defined as a percentage of mammary tissue excised, an entire mammary gland chain corresponding to a 100% mastectomy [19]. Lactated Ringer's solution (5 to 10\nml/kg/hr) was administered throughout the procedure. All dogs received an initial dose of 0.2 mg/kg meloxicam (Movatec, Roche, São Paulo, Brazil), intravenously, 5 min prior to surgery and additional daily doses of meloxicam (0.1 mg/kg, PO), beginning 24 hr after extubation and continuing for up to 10 days. Based on the anesthetic record, surgery time (time elapsed from the first incision until placement of last suture), extubation time (time elapsed from termination of isoflurane until extubation) and recovery time (time elapsed from the end of anesthesia until standing positon) were recorded for each dog. Extubation was performed when the dog started coughing and/or gagging from the endotracheal tube. The administration of postoperative analgesic drugs was supervised by one anesthesiologist, and the pain assessment was performed by a blinded assessor. The pain level was measured prior to the premedication (baseline scores) and at 0.5, 1, 2, 4, 8, 12, 18, 24, 32, 40, 48, 56, 64 and 72 hr after extubation using the modified Glasgow Composite Measure Pain Scale (GCMPS, 0–10) [15, 23]. In addition, pain was assessed using a Visual Analogue Scale (VAS, 0–100 mm) in which, 0=no pain and 100=worst possible pain, manifested by vocalization, aggression and refusal to allow the examination [18, 19, 23]. Dogs judged to have moderate to severe pain (VAS ≥50 mm or GCMPS ≥3.3) were given morphine (0.5 mg/kg, IM) [23]. At each pain assessment, sedation was\nscored according to a scale that ranged from 0 to 4, as follows: normal behavior (0); mild sedation, some decrease in normal activity, some resistance to handling, responds to name (1); moderate sedation, easy to handle, still spontaneously active, responds to name, but more slowly (2); moderate to heavy sedation, less spontaneous activity, verbal encouragement needed to rise, minimal resistance to handling (3); sternal recumbency, physical stimulus required to rise, depressed, no resistance to handling (4) [12]. A Kolmogorov–Smirnov test was performed to assess the normality of the variables. Body weight, age, time to endotracheal extubation, duration of surgery and recovery time were compared between groups using the Student's t-test. The Mann-Whitney U test was used to compare additional morphine requirement, pain and sedation scores between groups. The Friedman test was used to compare differences in pain and sedation scores over time within each group. All analyses were performed using GraphPad Instat5. Differences were considered significant when P<0.05. There were no significant differences between groups for demographic data. Mean ± standard deviation of weight, age, time to endotracheal extubation, duration of surgery, recovery time and extent of mastectomy were: 13 ± 10 and 8 ± 8 kg; 8 ± 3 and 10 ± 3 years; 7 ± 5 and 6 ± 2 min; 87 ± 20 and 81 ± 26 min; 225 ± 12 and 213 ± 15 min and 70.5 ± 18 and 68 ± 15% (Gabapentin and Placebo groups, respectively). Histopathologic tumor classification was simple mammary carcinoma (50%), complex mammary carcinoma (37.5%) and amelanotic melanoma (12.5%), with varying degrees of inflammation (slight to moderate). The median pain scores (VAS and GCMPS) did not significantly differ between the treatment groups at any time point. The GCMPS pain scores were higher than the corresponding basal values at 2 hr after extubation in both groups (P<0.0001) (Table 1Table 1.Pain and sedation scores (median and lower-upper range) measured prior to surgery (ie, baseline) and at 0.5, 1, 2, 4, 6, 8, 12, 18, 24, 32, 40, 48, 56, 64 and 72 hr after tracheal extubation in dogs undergoing mastectomy treated with gabapentin (Gabapentin) or placebo (Placebo)TimeVASGMCPSSedation scoresGabapentinPlaceboGabapentinPlaceboGabapentinPlaceboBaseline0 (0–0)0 (0–0)0.08 (0.08–0.08)0.08 (0.08–0.87)0 (0–0)0 (0–0)0.5 hr0 (0–20)0 (0–30)2.43 (0.08–3.81)2.43 (0.08–5.56)3 (0–4)a)3 (1–4)a)1 hr0 (0–10)5 (0–50)2.43 (0.08–3.55)1.99 (0.08–3.81)3 (0–4)a)2.5 (0–4)a)2 hr0 (0–30)20 (0–30)2.43 (0.87–3.55)a)2.53 (0.87–3.55)a)1 (0–3)a)1.5 (0–4)a)4 hr5 (0–30)20 (0–60)1.89 (0.08–3.37)3.08 (0.08–4.55)1 (0–3)a)0 (0–1)8 hr10 (0–50)10 (0–30)1.04 (0.08–5.85)1.35 (0.08–3.66)0 (0–1)0 (0–0)12 hr10 (0–50)5 (0–30)1.43 (0.08–4.05)0.6 (0.08–3.58)0 (0–0)0 (0–0)18 hr5 (0–30)0 (0–30)0.6 (0.08–3.56)0.08 (0.08–3.83)0 (0–0)0 (0–0)24 hr0 (0–30)0 (0–80)0.49 (0.08–3.81)0.08 (0.08–4.99)0 (0–0)0 (0–0)32 hr0 (0–10)0 (0–20)0.08 (0.08–1.46)0.08 (0.08–2.64)0 (0–0)0 (0–0)40 hr0 (0–10)0 (0–20)0.08 (0.08–1.20)0.08 (0.08–1.83)0 (0–0)0 (0–0)48 hr0 (0–10)0 (0–10)0.08 (0.08–1.21)0.08 (0.08–0.08)0 (0–0)0 (0–0)56 hr0 (0–20)0 (0–30)0.08 (0.08–1.46)0.08 (0.08–2.43)0 (0–0)0 (0–0)64 hr0 (0–20)0 (0–10)0.08 (0.08–1.20)0.08 (0.08–2.43)0 (0–0)0 (0–0)72 hr0 (0–20)0 (0–10)0.08 (0.08–1.20)0.08 (0.08–2.33)0 (0–0)0 (0–0)a) Differences from baseline in each group (Friedman test, P<0.05). VAS=Visual Analogue scale (0–100 mm); GMCPS= Glasgow Modified Composite Pain Score (0–10).). Requirement for postoperative rescue analgesia was significantly lower in the Gabapentin than the Placebo group. In the first 24-hr period following surgery, 16 rescue doses of morphine were required for 8 dogs treated with the placebo, whereas only 9 rescue doses were needed for 6 dogs treated with gabapentin (P=0.021) (Table 2Table 2.Number of morphine doses administered to each dog, and total number of morphine doses administered to each treatment group over time in dogs undergoing mastectomy treated with gabapentin (Gabapentin) or placebo (Placebo)GroupsPostoperative time (hr)N° doses0.51248121824324048566472Gabapentin /DogsNo. 1000000000000000No. 2000001000000001No. 3000000000000000No. 4000000010000001No. 5000000000000000No. 6000000000000000No. 7000100100000002No. 8010000100000002No. 9001000010000002No. 10001000000000001Total n° of morphine doses9a)Placebo/DogsNo. 1001000000000001No. 2000010010000002No. 3000000000000000No. 4000000000000000No. 5000011000000002No. 6010011000000002No. 7000010010000002No. 8000010000000002No. 9001000100000002No. 10010010100000003Total n° of morphine doses16a)a) Significant difference between groups (Mann-Whitney U test, P=0.021).). The degree of sedation was similar between the groups. However, compared with baseline values, higher scores were observed until 2 and 4 hr after extubation in the Placebo and Gabapentin groups, respectively (P<0.0001) (Table 1). This study showed that the dogs in the Gabapentin group had a significantly lower incidence of rescue medication than the Placebo group, suggesting a superior level of analgesia when gabapentin was administered perioperatively. VAS and GCMPS pain scores did not differ significantly between groups at any time point. Any real differences between gabapentin and placebo treatments may have been attenuated by the administration of rescue analgesics. The perioperative oral administration of gabapentin reduced the requirement of rescue doses of morphine by 44% in the dogs. These results support the reports of a previous study where perioperative administration of gabapentin resulted in a 50% reduction in the postoperative morphine consumption in women undergoing radical mastectomy [4]. With respect to pain assessment in animals, several scoring systems using a variety of scales (e.g., visual analog, numerical rating, simple descriptive and composite) have been developed and correlated specifically for dogs [7, 15, 18]. In the current study, two methods (i.e., the VAS and GCMPS) were used to obtain a more accurate overall impression of pain [20, 23]. The VAS system is a simple method of scoring pain and is commonly used for both humans and animals. The GCMPS system is internationally recognized and is reported to be as reliable and reproducible as the VAS system for assessing pain in dogs [18]. In addition, in the present study, only one observer scored all the dogs to avoid interobserver variability in the subjective evaluation.\nFurthermore, a blinded assessor performed the pain assessment. We believed that the postoperative pain was evaluated objectively with minimum variability in the present study. It has been suggested that central neuronal sensitization may play an important role not only in chronic pain states, such as neuropathic pain, but also in postoperative pain [17]. Although the precise mechanism by which gabapentin produces analgesia is unknown, the compound has a high binding affinity for the α2δ subunit of the presynaptic voltage-gated calcium channels, which inhibits calcium influx and subsequent release of excitatory neurotransmitters including glutamate, substance P and noradrenaline [11, 22]. These channels are upregulated in the dorsal root ganglia and spinal cord after surgical trauma [9]. In animal models, gabapentin has been shown to prevent allodynia and hyperalgesia [8, 11]. Other theories regarding the\nanalgesic effects of gabapentin relate to its inhibitory effect on dorsal horn N-methyl-D-aspartic acid receptors [13]. Postoperative pain following mastectomy may induce an inflammatory response that leads to hyperalgesia of the surgical incision with sensitization of peripheral nociceptive nerve terminals and central neurons [14]. For this reason, all dogs were given meloxicam before and postsurgery. When used to control postoperative pain, both nonsteroidal anti-inflammatory drugs (NSAIDs) and gabapentin have been shown to have a significant opioid-sparing efficacy [3, 4, 23]. NSAIDs (i.e., meloxicam) inhibit peripheral and central nervous system prostaglandin synthesis [16], and gabapentin reduces the hyperexcitability of dorsal horn neurons\nfollowing tissue damage [9]. Clinical trials in humans suggest that the use of the combination of these two non-opioid analgesics promotes superior reduction in opioid requirements [5, 17]. The present study supports these findings and demonstrates that as part of a multimodal analgesic regimen, gabapentin provides a significant effect on analgesic requirements after mastectomy in dogs. Thus, antihyperalgesic drugs, such as gabapentin, may have a role in postoperative pain, and the combination with other antinociceptive drugs may prevent or reduce the peripheral and central sensibilization induced by the surgical procedure, resulting in a decreased need for additional postoperative pain treatment. Unfortunately, there is insufficient information to recommend a specific dose regimen for gabapentin in dogs. In humans, the analgesic efficacy of gabapentin has been associated with 2–3 μg/ml plasma concentrations [25]. Using dogs, Kukanich and Koen [10] studied the pharmacokinetic properties of oral gabapentin at 10–20 mg/kg. The results of this trial showed that plasma concentrations of gabapentin exceeded 2 μg/ml in the majority of dogs only until 8 hr, suggesting that gabapentin was rapidly absorbed and eliminated, and frequent dosing is needed to maintain the minimum targeted plasma concentrations. The dose used in the current study was based on textbook recommendations and recent trials in dogs [1, 26]. Our results showed that 10 mg/kg twice a day of\ngabapentin did not decrease the pain levels when compared with the placebo treatment, which may be associated with an insufficient dose for postoperative pain control in dogs. Using the same dosing regimen in dogs undergoing hemilaminectomy, Aghighi et al. [1] did not find a detectable reduction in pain scores compared to opioid analgesia alone. This study also reported that in 21.5% and 23.1% of the gabapentin treated dogs, serum concentrations fell below 3μg/ml at 24 hr and 72 hr, respectively, suggesting that the dose and dose interval were too low to obtain stable serum concentrations. The design of this study has some limitations. The variability inherent in this type of a clinical study may have contributed to the lack of significant differences in postoperative pain; it was difficult to control the degree of surgical trauma. The randomization of dogs between treatments resulted in groups that were not completely homogeneous. There was a difference with respect to the type of neoplasia and extent of mastectomy, which may also have affected the intensity of postoperative pain. This variability may have confounded the pain scoring in the present study. Moreover, the number of dogs was also limited, because of the inclusion criteria and need for owner consent. In humans, the major side effects reported from the use of gabapentin include sedation, dizziness and nausea [9]. Although there were no statistical differences in sedation scores between groups, compared with the baseline values, greater sedation scores were observed at 2 hr and 4 hr after extubation in the Placebo and Gabapentin groups, respectively. These findings suggest that gabapentin prolonged the sedation effect, and this result is in agreement with previous studies [3, 6]. Nausea and vomiting were observed in the majority of dogs after the premedication, but this effect is associated with morphine [19]. Thus, it appears that gabapentin did not induce relevant adverse effects. In conclusion, at the dose and frequency used in this study, perioperative gabapentin reduced the requirement of postoperative rescue analgesia in dogs after mastectomy.\n\nQuestion: Compared to Placebo what was the result of gabapentin (10 mg/kg) on morphine doses?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1084	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Laser Peripheral Iridotomy versus Trabeculectomy as an Initial Treatment for Primary Angle-Closure Glaucoma\n\n ABSTRACT.PURPOSE:\n To compare laser peripheral iridotomy (LPI) with trabeculectomy as an initial treatment for primary angle-closure glaucoma (PACG) with peripheral anterior synechiae (PAS) ≥ 6 clock hours. \n\nABSTRACT.METHODS:\n Patients were drawn from two randomized controlled trials. 38 eyes of 38 patients (PAS ≥ 6 clock hours) were treated with LPI (group 1) while 111 eyes of 111 PACG patients (PAS ≥ 6 clock hours) underwent primary trabeculectomy (group 2). All patients underwent a comprehensive ophthalmic examination at baseline and at postoperative visits and were followed up for a minimum of one year. \n\nABSTRACT.RESULTS:\n Group 2 had higher baseline IOP (45.7 ± 14.8 mmHg versus 34.3 ± 14.3 mmHg) than group 1 and more clock hours of PAS (10.4 ± 1.9 versus 9.0 ± 2.2). IOPs at all postoperative visits were significantly lower in group 2 than in group 1 (p = 0.000). Five eyes in group 1 required trabeculectomy. 17 of the 38 eyes in group 1 (44.7%) required IOP-lowering medications as compared to seven of the 111 eyes in group 2 (6.3%). Cataract progression was documented in 2 eyes (5.3%) in group 1 and 16 eyes (14.4%) in group 2. \n\nABSTRACT.CONCLUSIONS:\n Primary trabeculectomy for PACG (PAS ≥ 6 clock hours) is more effective than LPI in lowering IOP.\n\nBODY.1. INTRODUCTION:\nPrimary angle-closure glaucoma (PACG) is the major type of primary glaucoma in China [1–4]. The management of PACG in China is different from the recommendations of the American Academy of Ophthalmology Preferred Practice Patterns (PPP) and other published guidelines [5–7]. For primary angle closure (PAC) and PACG, the PPP recommends laser peripheral iridotomy (LPI) to eliminate pupillary block followed by a treatment strategy \"similar to that for POAG\" [8]. Accordingly, LPI is used as the first-line treatment for all patients with PAC or PACG, medication is added as needed, and surgery is considered when the intraocular pressure (IOP) cannot be controlled with maximum tolerated medications. In China, however, trabeculectomy is considered a primary option for PACG and is generally undertaken if peripheral anterior synechiae (PAS) are greater than 6 clock hours [9, 10]. To the best of our knowledge, there is no comparative study of LPI versus primary trabeculectomy in PACG to support such an approach. Using data from patients enrolled in two separate randomized controlled trials [11, 12], we compared the IOP-lowering efficacy and safety of LPI versus trabeculectomy as an initial treatment for PACG with PAS ≥ 6 clock hours.\n\nBODY.2. METHODS:\nPatients included in this study had participated in 2 randomized clinical trials (RCTs) for PACG. Both trials were conducted in accordance with the tenets of the Declaration of Helsinki and approved by the ethics committee of the Tongren Eye Centre, Capital Medical University. Written informed consent was obtained from all subjects for participation in the original trials. Patients undergoing primary trabeculectomy for PACG had participated in a multicenter RCT (registration number: ChiCTR-TCR-00000218) [12]. This RCT was conducted in four clinical collaborative centers of Beijing Tongren Hospital: Handan 3rd Hospital (Hebei Province, China), Anyang Eye Hospital (Henan Province, China), Fushun Eye Hospital (Liaoning Province, China), and the Chenzhou Eye and Optometry Center (Hunan Province, China). PACG was defined as primary angle closure with glaucomatous optic neuropathy and corresponding visual field defects, and patients were recruited from the four centers between April 2006 and November 2007. The primary purpose of the trial was to report the efficacy and complications of trabeculectomy with or without releasable sutures in PACG. Patients who underwent LPI as an initial treatment were part of another RCT (registration number: ChiCTR-TRC-00000034, http://www.chictr.org.cn) conducted at the Handan 3rd Hospital [11]. The purpose of this RCT was to investigate the role of laser iridotomy (with or without iridoplasty) in patients with synechial PAC or PACG. The definition of PACG was the same as that used in the trial mentioned above; consecutive cases of PAC and PACG presenting to the hospital between October 1, 2005, and October 31, 2006, were recruited for this trial.\n\nBODY.2. METHODS.2.1. PATIENT SELECTION:\nThe inclusion criteria for the current study were as follows:\nPACG: defined as primary angle closure with glaucomatous optic neuropathy and visual field defects [13]Age 40 years or morePAS ≥ 6 clock hoursMinimum follow-up of one year. Patients with acute angle-closure glaucoma were excluded. As part of the original clinical trial, all patients had undergone a comprehensive ophthalmic examination including refraction, Goldmann applanation tonometry, static and dynamic gonioscopy (manipulation) using a one-mirror Goldmann gonioscope [14, 15], slit-lamp examination, fundus examination, and automated perimetry (Humphrey Field Analyzer 750i, Carl Zeiss Meditec; Sita Fast strategy; and 24–2 threshold test). These examinations were performed at baseline and at postoperative visits scheduled at month 1, month 3, month 6, month 12, and month 18. Postoperative visits were scheduled on day 1, day 3, week 1, week 2, month 1, month 3, month 6, month 12, and month 18 following the LPI or trabeculectomy.\n\nBODY.2. METHODS.2.2. LASER PERIPHERAL IRIDOTOMY:\nAll laser procedures were performed by one of two senior glaucoma specialists. 2% pilocarpine was applied, and iridotomy was performed under topical anesthesia using a Nd:YAG laser (YL-1600; NIDEK Co. Ltd., Japan) using an Abraham contact lens (Ocular Instruments Inc., Bellevue, USA). A treatment site was selected in the superior nasal iris or in a crypt where present. The treatment was initiated with a single 4 mJ pulse, the power was adjusted, and the treatment was continued to obtain a 0.2 mm opening; patency was determined by direct visualization of the posterior chamber. In accordance with local practice, IOP-lowering medication was initiated if the IOP was greater than 21 mmHg following laser and confirmed by a repeat reading on the same day [11].\n\nBODY.2. METHODS.2.3. TRABECULECTOMY:\nSurgery was performed under topical or peribulbar anesthesia using a standard surgical technique. The eye was prepared using a standard aseptic technique and draped to isolate the lashes. A lid speculum was inserted and a 7/0 superior rectus muscle traction suture was placed. A limbus-based conjunctival flap was created using a 10 mm incision through the conjunctiva and Tenon's capsule approximately 8–10 mm from the limbus. The flap was dissected forwards and hemostasis achieved with monopolar diathermy. A half-thickness 4 × 3 mm2 rectangular scleral flap was fashioned, and cellulose sponges soaked in MMC (0.3 mg/ml) were applied under the scleral flap, conjunctiva, and Tenon's capsule for a duration determined by the surgeon based on an assessment of risk factors. Irrigation with balanced salt solution was performed to wash out residual MMC solution. A paracentesis was created, a 2 × 1.5 mm trabeculectomy block excised, and an iridectomy performed. The scleral flap was sutured with 10-0 monofilament, BSS was injected into the anterior chamber to assess flow, and the conjunctiva was closed with a single running 8/0 vicryl suture [12]. Visual acuity was recorded with a decimal chart and converted to the logarithm of minimum angle of resolution (LogMAR) format. Finger counting, hand movement, and light perception were recorded as 1.5, 2.0, and 2.5 on the LogMAR scale. At each postoperative visit, a trained technician measured the IOP twice using an applanation tonometer and recorded the average. If the difference between the two measurements was more than 2 mmHg, a third measurement was performed, and the average of the two closer results was recorded. All IOP measurements were performed between 8 am and 12 am. At each site, trained observers used standard LOCS III photographs to assess the lens. Cataract progression was defined as an increase of 2 or more units greater than baseline in any LOCS III category (nuclear, cortical, or posterior capsular opacity). Progression was analyzed in all eyes with a minimum follow-up of 12 months; for those whose longer follow-up was available, it was determined at the 18-month visit. The shallow anterior chamber (AC) was categorized as grade I = peripheral iris-cornea touch; grade II = midiris-cornea touch; and grade III = central cornea-lens touch [16]. Hypotony was defined as IOP ≤ 5 mmHg [17]. At each visit, other complications and interventions, if undertaken, were recorded.\n\nBODY.2. METHODS.2.4. STATISTICAL ANALYSIS:\nOne eye of each patient was randomly selected for the analysis. Statistical analysis was carried out using SPSS 15.0 (SPSS Inc., Chicago, USA). Independent t-test was used to compare the difference between the groups, and the chi-square test was used to compare the difference in IOP-lowing medication and cataract progression between the groups. A p value < 0.05 was considered significant.\n\nBODY.3. RESULTS:\n38 eyes of the 38 patients with PACG that underwent primary iridotomy comprised group 1 while group 2 consisted of 111 eyes of the 111 PACG patients who had undergone trabeculectomy. The baseline characteristics of the two groups are summarized in Table 1. Patients in group 2 were slightly younger and had higher baseline IOP and more clock hours of PAS. \nTable 2 shows the postoperative IOP and visual acuity. At each visit, the IOP was significantly lower in group 2 (p < 0.001). Five eyes in group 1 required trabeculectomy: 1 eye at 6 months, 2 eyes at 12 months, and 2 eyes at 18 months. 17 of the 38 eyes (44.7%, CI: 28.9%–60.5%) in group 1 required a mean of 1.8 IOP-lowering medications while seven of the 111 eyes (6.3%, CI: 1.8%–10.8%) in group 2 required a mean of 1.1 medications (Pearson's chi-square value = 30.940, p < 0.001). 19 eyes in group 2 developed a transient shallow anterior chamber (AC), but there was no instance of lens-cornea touch. 16 eyes (including 13 eyes with shallow AC) experienced transient hypotony. Hypotony lasted one day in 14 eyes and one week in 2 eyes and all recovered spontaneously. One eye developed hypotony maculopathy at one month after surgery that was resolved after IOP increased 3 weeks later. In one eye, the IOP increased to 60 mmHg at 3 months postsurgery and required cyclophotocoagulation. Best-corrected visual acuity at 18 months was 0.5 ± 0.5 in group 1 and 0.6 ± 0.7 in group 2. Four eyes (10.5%) in group 1 lost one line of vision, 3 eyes (7.9%) lost 2 lines, and 3 (7.9%) lost more than 2 lines. In group 2, thirteen eyes (11.7%) lost 1 line, 9 eyes (8.1%) lost 2 lines, and 11 eyes (9.9%) lost more than 2 lines. Six eyes in group 1 and 20 eyes in group 2 lost ≥2 lines (Pearson's chi-square value 0.098, p = 0.755). The absolute risk for ≥2 lost lines of vision in the trabeculectomy group was 18% (20 of 111) compared to 16% (6 of 38) in the LPI group. The absolute risk increased with trabeculectomy is 2% and the number needed to harm (NNH) is 50. Cataract progression as defined was documented in 2 eyes (5.3%, CI: −1.8%–12.4%) in group 1 and 16 eyes (14.4%, CI: 7.9%–20.9%) in group 2 (Pearson's chi-square value = 2.232, p = 0.135). The absolute risk increased in cataract formation with trabeculectomy is 9% and translates into a NNH of 11.\n\nBODY.4. DISCUSSION:\nThe PACG treatment strategy formulated by the glaucoma group of the Chinese Ophthalmology Society is different from that formulated by other published guidelines. As per Chinese guidelines, LPI is suggested for \"patients with PAS < 180° without optic disc and visual field damage\" (an indication endorsed without data by a recent publication), while primary trabeculectomy is recommended for PACG with PAS ≥ 180° [9, 18]. A 2005 survey of clinical practice in PACG diagnosis and treatment found that 73% of Chinese glaucoma specialists preferred trabeculectomy as the initial treatment for PACG with PAS ≥ 180° [10]. Evidence for such an approach is however lacking, and to the best of our knowledge, our study is the first study to compare primary LPI with primary trabeculectomy for PACG. LPI is considered a noninvasive, simple, and safe intervention in PACS, PAC, and PACG [19]. The effect of a LPI would depend on the amount of angle that is available for filtration, and this can be estimated clinically by the extent of PAS [18, 20]. IOP control following LPI as reported in the literature varies considerably, and the therapeutic effect seems to decrease over time [21, 22]. In a retrospective analysis of 131 cases (251 eyes) in China, 18 eyes with PACS, 98 eyes with PAC, and 129 eyes with PACG that underwent LPI were followed up for 9.2 ± 3.7 years [23]. Eyes with PAC and PACG had PAS < 6 clock hours. At the final follow up, 16/18 PACS, 38/98 PAC, and 814/129 of PACG eyes were controlled (defined as IOP less than 21 mmHg) without medications. 60% of cases required additional medications and 13% needed filtering surgery. A study from India evaluated the long-term outcome of PACG following laser iridotomy [24]. 70 consecutive patients with PACG whose IOP remained >21 mmHg despite a patent iridotomy had their IOP controlled by medications or trabeculectomy and were followed up over a 6-year period. A trabeculectomy without antimetabolites was performed if IOP was >21 mmHg on maximal tolerable medical therapy, if there was evidence of progression of the disc/visual field, or if the patient was noncompliant. 46 (65.7%) eyes were controlled medically with 26 (57%) eyes requiring two topical medications. 24 (34.3%) eyes required trabeculectomy at various times during follow-up. The extent of PAS was not reported in this study, but reports suggest that the therapeutic effect of LPI decreases over time and many cases need filtering surgery. The results seem consistent with the biologically plausible hypothesis that LPI is more successful in those with relatively undamaged trabecular meshwork [18]. The literature seems to suggest that, despite the presence of a patent LPI, eyes with established PACG and a certain (currently undefined) extent of PAS require further treatment to control IOP and that medical therapy fails in a significant number of cases necessitating filtering surgery [18, 25]. In the current investigation, the IOP during follow-up was significantly lower in the trabeculectomy group. Furthermore, a larger number of patients who underwent LPI needed medical treatment as compared to those who underwent trabeculectomy. In this developing country, setting patients may not be able to afford medical treatment or are generally not adherent or persistent with it. To simulate a real-world condition, we did not provide free IOP-lowering medication and found that 24% of patients could not afford long-term medication. Moreover, 5 eyes (13.2%) of patients who underwent LPI with baseline PAS ≥ 6 clock hours (group 1) had to undergo trabeculectomy during the follow-up period. The poor effectiveness of IOP lowering following LPI for PACG with ≥6 hours of PAS would seem important in selecting treatment within the well-known constraints of a developing country, including a possible one shot at treatment. We therefore suggest that 6 clock hours of PAS can be considered a provisional clinical threshold for LPI in PACG, as this is likely to change with further research and will be different for individual cases. Our findings lend credence to a recently published algorithm for the management of angle-closure disease that recommended a ≥6 clock hour threshold for PAS; that algorithm was based mainly on biological plausibility [18]. Considering the problems of medical treatment in developing countries, a policy of primary trabeculectomy for PACG with ≥6 clock hours of PAS might merit consideration. In fact, even eyes with <6 clock hours of PAS may be considered for a trabeculectomy if the socioeconomic situation so dictates [23]. The choice of initial treatment must also consider the issue of complications. Consistent with most other publications, we did not encounter any significant complications in the LPI group [11]. While complications with trabeculectomy are more frequent, the incidence of severe sight-threatening complications is now less than what it was 20 years ago; we encountered mainly transient shallow chamber and hypotony. It must be kept in mind that in our study, trabeculectomy was undertaken by glaucoma specialists in the context of a clinical trial and the potential for sight-threatening complications remains. Importantly, even in the context of a clinical trial, 18% of eyes undergoing trabeculectomy lost 2 or more lines of vision. However, the number needed to harm for ≥2 lost lines of vision is an acceptable 50. Incision-induced astigmatism as well as progression of cataract was the major reason for visual loss, but both would be considered treatable. 19% of patients in undergoing trabeculectomy had astigmatism of >1D at 6-month visit, and 14.4% had obvious progression of lens opacity. The NNH for progression of cataract with trabeculectomy was 11. While successful intervention is available for cataracts, this low NNH that could lead to an increase in the burden of cataract is a disadvantage with trabeculectomy. The choice for the initial intervention for PACG in China and other developing countries must weigh up effectiveness versus complications as well as the need for additional medications and further interventions. While LPI is safe and easy, there is a more need for intensive medications and surgical intervention. The role of cataract extraction in primary angle-closure disease is evolving but is again more likely to be useful for those with angles less compromised by PAS [18, 26]. Trabeculectomy is better than LPI for lowering the IOP, but it does have the potential for more loss of visual acuity and for serious complications. Accordingly, it is probably best to reserve primary surgical intervention for established PACG with ≥6 clock hours as these are unlikely to do well with laser alone. While not statistically significant in this study, the higher chances for progression of cataract following trabeculectomy raise the question of combining filtration with cataract surgery, an issue not addressed in this study. In addition to clinical factors, any decision will also depend on the availability of lasers and surgeons and costs. One of the limitations in our study is the small sample size in group 1 and the relatively short follow-up time. As few patients progressed during this time, we could not analyze the relationship between IOP and the visual field progression, but IOP would usually be considered an acceptable surrogate. Also, our results are derived from patients enrolled in RCTs, and the effectiveness in the real world is likely to be different. Furthermore, as it was not part of this study, we cannot comment on the increasingly popular role of phacoemulsification or its combination with trabeculectomy in the management of PACG [18]. The low NNH for cataracts with trabeculectomy could however be used as an argument for combining the two surgical procedures. Finally, while the definition of PACG used in both trials was the same, patients for this study were drawn from two separate trials that asked different questions. This could introduce significant bias. The original LPI RCT (registration number: ChiCTR-TRC-00000034, http://www.chictr.org.cn) [11] that randomized patients into two different treatment groups (iridotomy or iridotomy plus iridoplasty) found no significant difference in IOP, medications, need for surgery, or visual function between groups at the 1-year visit. This RCT showed that in eyes with PACG, both iridotomy alone and iridotomy combined with iridoplasty provide a significant and similar reduction in IOP. For the trabeculectomy RCT (registration number: ChiCTR-TCR-00000218) [12], patients were randomly allocated to permanent or releasable sutures. This study too did not demonstrate any significant differences between the groups. Accordingly, we felt that analyzing patients from either arm of the two trials for the current study was acceptable but acknowledge that the possibility of unknown differences does exist and could affect interpretation. However, as the baseline IOP was higher and PAS more extensive in the trabeculectomy group, the conclusion in favor of trabeculectomy is likely to stand. In conclusion, our results support the Chinese guidelines for management of PACG. In PACG with ≥6 clock hours of PAS, primary trabeculectomy is more effective than LPI in lowering IOP and significantly requires less medication but with more progression of cataract and more loss visual acuity. In developing countries, such as China, trabeculectomy can be considered a primary option for PACG with this degree of PAS.\n\nQuestion: Compared to primary trabeculectomy group 2 what was the result of laser peripheral iridotomy (LPI) group 1 on The absolute risk for ?2 lost lines of vision?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1086	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Changes in proprioception and pain in patients with neck pain after upper\nthoracic manipulation\n\n ABSTRACT:\n[Purpose] The purpose of this study was to conduct cervical stability training and upper\nthoracic manipulation for patients with chronic neck pain and then investigate the changes\nof cervical proprioception and pain. [Subjects and Methods] Subjects were 30 workers with\nmechanical neck pain, who were randomly divided into an upper thoracic manipulation group\nand a cervical stability training group. Upper thoracic manipulation after cervical\nstability training was conducted for the upper thoracic manipulation group, and only\nstability training was conducted for the cervical stability training group. The\nintervention period was six weeks, and consisted of three sessions a week, each of which\nlasted for 30 minutes. For proprioception measurement, an electro-goniometer was used to\nmeasure reposition sense before and after the intervention. The visual analogue scale was\nused to assess pain. [Results] After the intervention, the error angle was significantly\nsmaller in flexion and right left side-bending, and pain was significantly reduced in the\nupper thoracic manipulation group. According to the post intervention comparison of the\ntwo groups, there were significant differences in the proprioception and pain values.\n[Conclusion] Conducting both cervical stability training and upper thoracic manipulation\nfor patients with chronic neck pain was more helpful for the improvement of proprioception\nand pain than cervical stability training alone.\n\nBODY.INTRODUCTION:\nNeck pain is a disease that most people experience at least once in their life time. Neck\npain is the main cause of an increase in economic and social health costs. To treat neck\npain, physical therapists often use therapeutic exercise, traction, joint mobilization, and\nmanipulation1, 2). In the case of the patients with chronic neck pain, because of overuse, repetitive trauma,\nserious trauma and muscle weakness, the range of elasticity of the non-contractile tissues\nbecomes enlarged, and stablize the neutral position, and contractile tissues become weak. As\na result, instability increases in the spinal segments, resulting in failure to maintain the\nneutral position. Joint instability is accompanied by loss of somatosensory system function.\nIn addition, joint instability causes hyper-mobility of cervical segments, and restricts the\nmovement of the thoracic segments, which ultimately leads to functional restriction2). Manipulation and mobilization are clinically employed often to improve cervical instability\nand functional movement. Thoracic manipulation and joint mobilization help to increase the\nrestricted mobility of the spinal segments, to improve cervical mobility and stability, and\nto recover functional movement and proprioception, and ultimately reducing pain and\nfunctional disorder3, 4). In order to recover cervical proprioception in patients with chronic neck pain, a\ntherapeutic approach is conducted to improve cervical instability, joint mobility, and\nneuromuscular control. Cranio-cervical flexor (CCF) training aims at recovery of control of\nthe muscular system around the cervical spine and the recovery of cervical proprioception.\nFor improvement in cervical joint mobility, manipulation and mobilization are performed5). Previous studies have reported that direct cervical manipulation is a dangerous cervical\ntreatment, because it can reduce the function of the spinal artery. For that reason, CCF\ntraining is widely employed to improve proprioception, pain and range of motion (ROM), and\nreduce the neck disability index (NDI) score of patients with neck pain4, 6). Recently, indirect thoracic manipulation and mobilization have frequently been used to\ntreat patients with neck pain, because it is safer than direct manipulation. Spinal\nmanipulation elicits immediate effects on recovery of function, such as pain alleviation and\nROM improvement, than conservative physical therapy. In addition, according to previous\nstudies, manipulation is more effective at reducing pain than conservative muscle\ntraining7). Nevertheless, there is still a lack of research evidence supporting the efficacy of\nmanipulation. Therefore, the purpose of this study was to conduct cervical stability\ntraining (CST) and upper thoracic manipulation (UTM) for patients with chronic neck pain and\ninvestigate the changes in cervical proprioception and pain.\n\nBODY.SUBJECTS AND METHODS:\nThe subjects were 30 subjects with chronic mechanical neck pain who agreed to participate\nin this study. The inclusion criteria were: unilateral or bilateral pain in the posterior\nneck or shoulder region, and pain in the cervical region when moving or palpating the\ncervical region, which had lasted for more than 12 weeks, and was rated higher than four on\na visual analogue scale (VAS). The exclusion criteria were: a diagnosis of cervical\nradiculopathy, previous experience of spinal manipulation, a history of fracture or\ndislocation of the cervical or thoracic spine, a history of surgical operation on the\ncervical or thoracic spine, hypertension, heart disease, or pregnancy. The research protocol was approved by the Research Ethics Committee for Human Research of\nKonyang University, Korea. UTM comprised 2 methods. Method 1: Upper thoracic lift manipulation. The subjects were\nasked to lock their fingers together, put their hands on the back of the neck, and sit in a\nchair without a back support. Then, a rolled towel was placed over the target spinal\nsegment. A therapist stood behind the subject, and leant forward toward the rolled towel, or\nthe target spinal segment. The therapist held the forearm of the subject, and flexed the\nsubject's neck and upper thoracic completely up to the spinal segment, creating a force\nagainst the rolled towel using the subject's forearm, and held the subject's elbow in a\nhorizontal adduction motion while lifting the subject toward the therapist in the\nposterior-anterior direction; and then applied thrust manipulation to the subject along with\nhorizontal adduction and expiration4). Method 2: Thoracic manipulation in the supine position. The therapist stood next to the\nsubject. And placed a hand on the subject's transverse process on the inferior segment of\nthe target spinal segment. The subject puts his/her arms on the chest or locked their\nfingers at the back of the head and neck. The therapist held the subject's arms to keep the\nsubject close, then put the manipulation hand on the target spinal segment and used the\nsupporting hand to fix the subject's elbows with the therapist's forearm. After performing\nflexion up to the subject's target segment, the therapist applied thrust manipulation in the\nanterior-to-posterior direction while the subject inhaled and exhaled. The target segments\nwere T1 to T44). CTS consisted of static stability training for re-education and dynamic stability training\nfor muscle endurance and power8). The\nstatic stability training used a pressure biofeedback unit (PBU), and it was based on CCF\ntraining for activating the deep muscles such as the longus colli and longus capitis. In\ndynamic stability training, the subjects maintained cervical flexion, and active assistive\nand active methods were conducted. After they had maintained cervical stability, the\nsubjects performed dynamic training through extremity movement. The subjects were asked to\npay attention to the cervical stability during training9). To measure the cervical proprioception of the patients with chronic neck pain, the cervical\nreposition test was conducted using an electro-goniometer (Mobee, Bitburg, 2013, Germany).\nThe study subjects were asked to sit in an upright position comfortably in a chair. The\ntarget position was randomly chosen from among 30%, 60%, and 90% of the maximal ROM. The\nsubjects kept the target position for 3 seconds, repeated it 5 times10). For measurement, the reposition test was conducted at the\nset angle 3 times. The rest time between measurements was 15 seconds. Measurement directions\nwere set to flexion, extension, right and left side-bending. The subjects were asked to sit\nupright and wear black sunglasses to inhibit their vision, and to move actively toward the\ntarget position in a random order. The difference between the target angle and the actual\nangle was used in the analysis11). All\nsubjects were asked to mark on a VAS scale ranging from 0 to 10 for the subjective\nassessment of pain. VAS is a simple way for the subjects to express their level of pain and\nhas high reproducibility. It is also an evaluation method with high validity (r=0.77) and\nreliability (r=0.99)12) (Table 1Table 1.Comparison of proprioception and pain within groups and between groups\n(N=30)Manipulation group (n=15)Control group (n=15)Flexion (angle)Pre6.07 (2.02)5.67 (2.06)Post2.47 (1.55)†4.27 (1.44)†,‡ExtensionPre4.87 (1.81)4.87 (2.48)Post3.27 (0.96)†3.53 (1.81)†Rt sidebendPre6.20 (1.79)6.73 (2.55)Post1.87 (1.30)†5.00 (2.14)†,‡Lt sidebendPre6.60 (1.55)6.53 (1.89)Post1.00 (1.20)†4.67 (1.88)†,‡VASPre7.13 (0.83)6.93 (1.44)Post1.93 (0.70)†3.40 (0.74)†,‡Values are expressed as mean (SD). p<0.05, p<0.01, †Within group\ncomparison, ‡Between group comparison). For data analysis, SPSS version 18.0 (SPSS, Inc., Chicago, USA) was used. Frequency\nanalysis and descriptive statistics were employed to compare the general characteristics of\nthe subjects. The independent t-test was conducted to compare the thoracic manipulation\ngroup and the CST group. The paired t-test was performed to compare the pre- and post\nintervention results of the UTM and the CST. The level of statistical significance was\nchosen as 0.05.\n\nBODY.RESULTS:\nThere were 8 male and 7 female in the manipulation group, and 7 male and 8 female in the\ncontrol group. The mean age of the subjects was 30.80 years in the manipulation group and\n28.07 years in the control group. The average weight, height and BMI were 63.23 kg,\n164.87 cm and 23.20 kg/m2, respectively in the manipulation group, and 62.89 kg,\n168.13 cm and 21.93 kg/m2, respectively in the control group. The UTM showed\nsignificantly smaller repositioning error in flexion and right and left side-bending and\ngreater reduction in pain than the CST group (p<0.01). Both the UTM and CST groups showed\nsignificant differences in proprioception and pain after the intervention (p<0.01).\n\nBODY.DISCUSSION:\nIn this study, CST was conducted for the patients with chronic neck pain, followed by UTM\nfor six weeks. After that, the changes in proprioception and pain were analyzed. After the\ninterventions, the UTM group showed significant reductions in error angles which were less\nthan those in the CST group, and the pain level of the UTM group was also significantly\nreduced. Proprioception receptors, such as mechanoreceptors and free nerve endings, are found in the\nskin, facial, muscles, tendons, joint capsules, and ligaments. When active or passive\nmovement occurs, receptors transmit the movement information to the central nervous system\n(CNS)13). High velocity low amplitude\nmanipulation stimulates mechanoreceptors located in the muscles, ligaments, and joint\ncapsules improving their responses in transmitting to the CNS; thus, helping the recovery of\nproprioception. It is known that manipulation mechanically stimulates joint capsules and\nthus leading to increased mobility of the spinal segments and increases ROM, which lessens\nthe fear of movement by smoothly transmitting movement information to the CNS, thereby\nreducing pain1, 14). According to many previous studies, the combined approach of a therapeutic exercise program\nand manipulation is more effective at recovering the proprioception of patients with neck\npain and their functions through pain reduction than any other kind of intervention15). Cassidy et al.16) independently conducted\nboth manipulation and joint mobilization for patients with mechanical neck pain, and\nreported the two groups showed significant improvements in pain and ROM after the\ninterventions. Joint mobilization conducted for the patients with chronic RA helped to increase their pain\nthreshold17). Another hypothesis\nregarding pain reduction after manipulation is that beta-endorphins are expressed and that\nthis alleviates pain18). According to\nVernon et al.19), after manipulation,\nbeta-endorphins increased for five minutes, but 15 minutes later, their level had returned\nto its original state. According to the results of the present study, proprioception and\npain were significantly reduced after UTM, a result that is consistent with the empirical\nevidence of previous studies. Another proposal is that spine manipulation activates type I (static movement) and type II\n(dynamic movement) mechanoreceptors, which are distributed in passive and active structures,\nsending signals through the CNS to the periaqueductal grey area, the pain control system\naround the cerebral aqueduct of mid-brain, which increases the pain threshold to control\npain20). The results of this study show that the thoracic manipulation group displayed more\nsignificant differences in pain reduction than the cervical stability group, and that CST\nalso improved proprioception and pain. According to the study of Panjabi21), cervical stability is maintained by the\nstability passive and active tissues and the capability of neuromuscular control. The\npurpose of the passive system is to use the elasticity of passive tissues including\nligaments, joint capsules, and tendons to stabilize the neutral position. The purpose of the\nactive system is to use the force generated by active tissues like muscles to maintain the\nneutral position. In addition, the neuromuscular control system controls and amplitude of\nthe overall range and mobility. The CST result was consistent with the theory that training\nimproves the stability the neutral position and its maintenance through the activation of\nthe active tissues of muscles. Despite these results, this study had several limitations. For example, the number of study\nsubjects small, and there was no long-term intervention of manipulation or CST. Therefore,\nwe consider that it will be necessary to increase the number of study subjects and lengthen\nthe intervention period to prove the effects of manipulation. In the present study, the\nrepositioning test was conducted to measure the propriocetive deficit. However, this is an\nindirect method, not a direct one, of measuring proprioception. For that reason, it is\nimpossible to generalize the results. Therefore, we think that a more objective tool and\nmeasurement method will be needed to investigate proprioception. In summary, the UTM group showed significant improvements in cervical proprioception, and\nsignificant reduction in pain, which were larger than those of the CST group. The findings\nof this study indicate that combine stability training and thoracic manipulation for\npatients with neck pain improves proprioception and reduces pain level.\n\nQuestion:* Compared to cervical stability training (CST) what was the result of upper thoracic manipulation (UTM) on repositioning error in flexion and right and left side-bending and reduction in pain?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1089	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: A single consumption of curry improved postprandial endothelial function in healthy male subjects: a randomized, controlled crossover trial\n\n ABSTRACT.BACKGROUND:\nCurry, one of the most popular foods in Japan, contains spices that are rich in potentially antioxidative compounds, such as curcumin and eugenol. Oxidative stress is thought to impair endothelial function associated with atherosclerosis, a leading cause of cardiovascular events. The aim of this study was to determine whether a single consumption of curry meal would improve endothelial function in healthy men.\n\nABSTRACT.METHODS:\nFourteen healthy male subjects (BMI 23.7 ± 2.7 kg/m2; age 45 ± 9 years) were given a single serving of curry meal or spice-free control meal (180 g of curry or control and 200 g of cooked rice; approximately 500 kcal in total) in a randomized, controlled crossover design. Before and 1 hr after the consumption, fasting and postprandial flow-mediated vasodilation (FMD) responses and other parameters were measured.\n\nABSTRACT.RESULTS:\nThe consumption of the control meal decreased FMD from 5.8 ± 2.4% to 5.1 ± 2.3% (P = 0.039). On the other hand, the consumption of the curry meal increased FMD from 5.2 ± 2.5% to 6.6 ± 2.0% (P = 0.001), and the postprandial FMD after the curry meal was higher than that after the control meal (P = 0.002). Presence of spices in the curry did not alter significantly the systemic and forearm hemodynamics, or any biochemical parameters including oxidative stress markers measured.\n\nABSTRACT.CONCLUSIONS:\nThese findings suggest that the consumption of curry ameliorates postprandial endothelial function in healthy male subjects and may be beneficial for improving cardiovascular health.\n\nABSTRACT.TRIAL REGISTRATION:\nUMIN Clinical Trials Registry\n000012012.\n\nBODY.BACKGROUND:\nCurry originated in Indian traditional diet, and has become widely eaten throughout the world, especially in Asia\n[1]. In fact, curry is one of the most popular foods in Japan\n[1]. Japanese curry is often milder in flavor and thicker in consistency than the traditional Indian curry, and usually is served with cooked rice\n[1]. With a good amount of meat and vegetables in it, Japanese curry can make a convenient and nutritious meal for people of all ages\n[1]. While being mild in flavor, Japanese curry still contains an abundant amount of spices, some of which are high in antioxidants. For example, turmeric contains antioxidant yellow pigment, curcumin, which is known to have many health benefits such as vasoprotective, antiinflammatory, anticarcinogenic, and neuroprotective effects\n[2,3]. Clove contains antioxidant aromatic oil, eugenol, which is also known to have some health benefits such as vasoprotective and pulmonary protective effects\n[4,5]. Epidemiologic studies have shown that curry improves pulmonary function in Asian elderly adults\n[6] and curry consumption improved cognitive performance of nondemented elderly Asians\n[7]. However, few intervention studies about curry have been reported. It is well known that postprandial hyperglycemia is a contributing factor to the development of atherosclerosis and is a risk factor for cardiovascular events. A meta-regression analysis showed that the progressive relationship between glucose levels and cardiovascular risk extends even in subjects with normal glucose tolerance below the diabetic threshold\n[8]. Although mechanism by which postprandial hyperglycemia induces vascular dysfunction is not fully understood, a review by Mar and Bruno points out that oxidative stress-mediated disruptions in nitric oxide homeostasis have been implicated as key events leading to vascular dysfunction\n[9]. Glucose loading produced a decrease in endothelial function and an increase in a marker of oxidative stress in normal and diabetic subjects\n[10,11]. Hyperglycemia in response to oral glucose loading rapidly suppressed endothelium-dependent vasodilation, probably through increased production of oxygen free radicals\n[11-13]. Accumulating evidence suggests that endothelial dysfunction plays a crucial role in the development and progression of atherosclerosis. The endothelium is suggested to be a target of damage in the postprandial state\n[14-16]. The aim of this study was to determine whether a single consumption of a dish of Japanese curry and rice would improve postprandial endothelial function in healthy men.\n\nBODY.METHODS.SUBJECTS:\nIn December 2012, 18 healthy males aged 33 to 64 years were recruited for the study. We selected healthy male subjects who do not have any history of hypertension, diabetes mellitus, and dyslipidemia, to avoid the possibility of any influence on the endothelial function by these factors as well as by menstrual cycle. The study protocol was approved by Tana Orthopedic Surgery Institutional Review Board. Informed consent for participation in the study was obtained from all subjects.\n\nBODY.METHODS.STUDY DESIGN:\nThe study was performed at House Foods Corporation during the period from January 2013 to February 2013. Subjects were randomized into a control-first group and a curry-first group. Each subject was given a single serving of test meal (control meal or curry meal) in a crossover manner with more than one week in between the two test meals. Fasting and postprandial measurements were taken by the primary investigator under blinded condition as follows. Subjects were asked not to take any nutritional supplements on the day before the test and were fasted for at least 12 hours overnight prior to the fasting measurements. No other instructions were given to the subjects. After the fasting measurements, subjects were given 180 g of either control (198 kcal) or curry (187 kcal) and 200 g of cooked rice (294 kcal) by a support staff, and one hour afterwards, postprandial measurements were taken. A preliminary test which we had made before this study showed that a measurement one hour after the intake of the control meal showed low endothelial function in healthy subjects but this effect was not observed two hours after the intake of the control meal. For this reason, we thought that the single point measurement one hour after meal was appropriate for studying curry effects on postprandial endothelial dysfunction in healthy subjects. The curry consisted of ground beef, tomato, tomato puree, some seasonings, and a blend of spices (Table \n1). The control was prepared as the curry except that all the spices were removed from the formula; it tasted like a meat sauce for spaghetti. The nutritional compositions of the control meal and curry meal both with 200 g of cooked rice were essentially the same as shown in Table \n2. Table 1 Composition of the spice blend used in a single serving portion of the curry meal Spice Amount Clove (g) 0.9 Coriander (g) 1.8 Cumin (g) 0.9 Garlic (g) 3.6 Ginger (g) 2.7 Onion (sautéed) (g) 9 Red pepper (g) 0.09 Turmeric (g) 4.5 Table 2 Composition of a single serving portion of the test meal with 200 g of rice Component Control Curry Energy (kcal) \n a \n 492 481 Protein (g) \n b \n 15 16 Fat (g) \n c \n 11 10 Carbohydrate (g) \n d \n 82 82 Dietary fiber (g) \n e \n 3 3 Sodium (g) \n f \n 1 1 \n a \n Modified Atwater methods. \n b \n Kjeldahl nitrogen determination method (conversion factor: 6.25). \n c \n Ether extraction method. \n d \n Carbohydrate was calculated from protein, fat, ash (direct ashing), and moisture (oven drying at 105°C for 16 hours). \n e \n Modified Prosky method. \n f \n Inductively coupled plasma emission spectrometry. Single serving portions (180 g) of both the curry and the control were packed and sterilized in retort pouches and were stored at room temperature until use. They were heated in boiling water for five minutes just before serving with 200 g of cooked rice.\n\nBODY.METHODS.FMD AND HEMODYNAMIC MEASUREMENTS:\nAll measurements were taken in the morning, in a quiet, air-conditioned room maintained at 24°C and 50% relative humidity. The subjects rested quietly in the supine position for 20 min before and during each FMD measurement. Just before the cuff inflation, systolic and diastolic blood pressure was measured on the left arm. FMD was measured on the right arm as described previously\n[17] with a UNEXEF18G ultrasound imaging system programmed specifically for FMD measurements with the autocuff (UP310), the semi-automatic vessel tracking (X-link), and the flow mode (uFFLOW) options (UNEX Co., Nagoya, Japan). After the brachial artery diameter was determined for the baseline arterial diameter from a longitudinal image of the artery acquired 5 to 10 cm above elbow, reactive hyperemia was induced by 5 min of distal lower arm occlusion by a blood pressure cuff inflated to 50 mm Hg above systolic pressure. Subsequently, the longitudinal image of the artery was recorded continuously until 2 min after the cuff deflation for the maximal brachial artery diameter determination. Pulsed Doppler velocity signals were acquired for 20 seconds before cuff inflation and for 10 seconds after cuff deflation for the hyperemic flow (% increase in blood flow) determination. We have already estimated the reproducibility and accuracy of the measurement by a preliminary test using 10 subjects. The same person, who performed the FMD measurement of this study, had measured FMD of each subject twice at one hour interval. The interclass correlation coefficient was 0.98 and systematic error across these two measurements was 0.1%.\n\nBODY.METHODS.SERUM MEASUREMENTS:\nWhole blood samples were collected from the left arm, just after the FMD and hemodynamic measurements. They were separated immediately by centrifugation (1,200 g, 10 min) and were stored at -80°C until use. Glucose, triglycerides, and total cholesterol were measured by enzymatic procedures (Mitsubishi Chemical Medience Corporation, Tokyo, Japan). High-density lipoprotein cholesterol (HDL-C) and low-density lipoprotein cholesterol (LDL-C) were measured by enzymatic procedures (Kyowa Medex Co., Ltd., Tokyo, Japan). Insulin was measured by Chemiluminescent immunoassay (ABBOTT JAPAN Co., Ltd, Tokyo, Japan). High-sensitivity C-reactive protein (hs-CRP) was measured by nephelometry using N-latex CRP-2 (Siemens Healthcare Japan, Tokyo, Japan). Malondialdehyde-modified LDL (MDA-LDL) was measured by two step ELISA (SEKISUI MEDICAL Co., Ltd., Tokyo, Japan) which uses monoclonal antibody recognizing MDA residues (ML25) and monoclonal antibody against apoB (AB16) to make the assay specific to MDA-LDL as described previously\n[18].\n\nBODY.METHODS.URINE MEASUREMENT:\nFor the urine 8-isoprostane determinations, a single voided urine sample was collected from each subject just after the blood sampling and was stored at -80°C until use. To 1000 μl (Creatinine < 50 mg/dl) or 500 μl (Creatinine ≥ 50 mg/dl) urine sample, 3H-8epi PGF2α (20 dpm/μL) 50 μL and 4% acetic acid 3 ml were added. After being stirred for 30 min, the sample was applied on an OASIS HLB solid phase extraction column (Nihon Waters K.K., Tokyo, Japan) preconditioned with 2 ml each of Ethylacetate and Acetonitryl and 3 ml of 4% acetic acid). After being washed with 15% acetonitry in Ehylacetate: hexane: 1-butanol = 15: 85: 1, the column was eluted with 2 ml ethylacetate:hexane = 85: 1. The eluted sample was dried under nitrogen, dissolved in 1 ml EIA buffer, and stirred for 30 min before being subjected to EIA assay (Cayman Chemical, Michigan, United States) as described previously\n[19]. The urine creatinine for normalization of 8-isoprostane concentration was measured by enzymatic procedures (Mitsubishi Chemical Medience Corporation, Tokyo, Japan).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA power analysis for two-way within subjects ANOVA was performed as described\n[20] and showed that a total sample size of 12 subjects was required to detect an interaction between meals and prandial status with an α error of 0.05 and a power of 0.80. Data are presented as means ± standard deviations. Baseline characteristics were compared between the curry-first and the control-first group by unpaired t-test. Statistical analyses about the effects of curry on FMD and other parameters were performed by using two-way within subjects ANOVA (control/curry and fasting/postprandial). If the interaction was significant, post hoc Student's paired t-test was performed. Statistical significance was assumed if a null hypothesis could be rejected at P = 0.05. All analyses were performed with SPSS (version 22; IBM Japan, Ltd., Tokyo, Japan).\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nOf the 18 subjects enrolled in the study, 4 subjects were excluded from the analysis for the follwoing reasons. One subject canceled after the first participation. The ultrasound images of another subject were technically unsuitable for the analysis, Another subjects had a sleeping problem on the night before the test day, and the other subject showed very low postprandial glucose level (<50 mg/dL). Table \n3 summarizes the baseline characteristics of the remaining 14 subjects. All baseline characteristics did not differ significantly between the control-first and the curry-first group. Table 3 Baseline characteristics Parameters Total (n = 14) Control-first (n = 7) Curry-first (n = 7) Age (years) 45 ± 9 42 ± 7 48 ± 10 Body mass index (kg/m 2 ) 23.7 ± 2.7 23.0 ± 1.9 24.4 ± 3.3 Systolic blood pressure (mm Hg) 112 ± 8 112 ± 5 112 ± 11 Diastolic blood pressure (mm Hg) 75 ± 7 76 ± 5 74 ± 9 Heart rate (beats/min) 60 ± 10 59 ± 7 61 ± 13 Total cholesterol (mg/dL) 196 ± 34 194 ± 34 199 ± 37 Triglycerides (mg/dL) 97 ± 44 99 ± 53 96 ± 38 HDL-cholesterol (mg/dL) 58 ± 15 58 ± 14 57 ± 17 LDL-cholesterol (mg/dL) 118 ± 28 114 ± 29 121 ± 28 Glucose (mg/dL) 90 ± 7 88 ± 6 91 ± 8 Insulin (μU/mL) 4.1 ± 1.9 3.9 ± 1.5 4.3 ± 2.4 hs-CRP (mg/dL) 0.122 ± 0.179 0.094 ± 0.176 0.149 ± 0.192 MDA-LDL (U/L) 88 ± 20 83 ± 20 93 ± 21 8-isoprostane (pg/mg Cr) 285 ± 81 276 ± 95 294 ± 70 Values are means ± SD. Abbreviations : HDL high-density lipoprotein, LDL low-density lipoprotein, hs-CRP high-sensitivity C-reactive protein, MDA malondialdehyde-modified, Cr creatinine. \n\nBODY.RESULTS.EFFECTS OF CURRY CONSUMPTION ON FMD AND OTHER HEMODYNAMIC PARAMETERS:\nTable \n4 summarizes the brachial and hemodynamic parameters with significance probability values (P values) from the ANOVA results. Table 4 Vascular function and Systemic Hemodynamics Control Curry \n P \n values \n \n a \n \n Parameters Fasting Postprandial Fasting Postprandial Meal effects Interaction Prandial effects FMD (%) 5.8 ± 2.4 5.1 ± 2.3 5.2 ± 2.5 6.6 ± 2.0 0.20 < 0.001 0.25 Systolic blood pressure (mm Hg) 110 ± 7 110 ± 10 111 ± 8 113 ± 7 0.07 0.57 0.33 Diastolic blood pressure (mm Hg) 73 ± 8 67 ± 7 75 ± 7 70 ± 7 0.07 0.32 < 0.001 Heart rate (beats/min) 60 ± 10 66 ± 11 59 ± 9 66 ± 10 0.56 0.55 < 0.001 Baseline arterial diameter (mm) 4.00 ± 0.47 4.12 ± 0.49 3.96 ± 0.47 4.02 ± 0.46 0.12 0.07 < 0.001 Peak hyperemic flow (%) 595 ± 259 536 ± 157 609 ± 217 571 ± 170 0.60 0.76 0.22 Values are means ± SD. Abbreviations : FMD flow-mediated vasodilation. \n a \n P values were calculated by using two-way within subjects ANOVA (control/curry and fasting/postprandial). Only on FMD, the interaction effect between meals (control/curry) and prandial status (fasting/postprandial) was significant (P < 0.001). Post hoc Student's paired t-tests revealed that the consumption of the control significantly decreased the FMD from 5.8 ± 2.4% to 5.1 ± 2.3% (Figure \n1, P = 0.039). On the other hand, the consumption of the curry increased FMD from 5.2 ± 2.5% to 6.6 ± 2.0% (P = 0.001), and the postprandial FMD after the curry meal was higher than that after the control meal (5.1 ± 2.3% vs. 6.6 ± 2.0%, P = 0.002). Figure 1Effects of a single consumption of curry on flow-mediated vasodilation (FMD), n = 14. Because the interaction between meals (control/curry) and prandial status (fasting/postprandial) was found significant (P = 0.002) by using two-way within subjects ANOVA, P values were calculated by post hoc Student's paired t-test. Abbreviations: FMD flow-mediated vasodilation. After consumption of the test meals, heart rate and baseline arterial diameter increased significantly, and diastolic blood pressure decreased significantly. Other than these, no main effects of the meals, the prandial status, or no interaction effects on systemic and forearm hemodynamics were significant.\n\nBODY.RESULTS.EFFECTS OF CURRY CONSUMPTION ON BIOCHEMICAL PARAMETERS:\nTable \n5 summarizes the biochemical parameters with P values from the ANOVA results. Table 5 Biochemical parameters Control Curry \n P \n values \n \n a \n \n Parameters Fasting Postprandial Fasting Postprandial Meal effects Interaction Prandial effects Total cholesterol (mg/dL) 203 ± 36 195 ± 34 197 ± 32 191 ± 28 0.40 0.36 0.001 Triglycerides (mg/dL) 107 ± 59 114 ± 59 97 ± 44 103 ± 43 0.23 0.96 0.025 HDL-cholesterol (mg/dL) 58 ± 16 56 ± 16 59 ± 15 56 ± 15 0.55 0.53 < 0.001 LDL-cholesterol (mg/dL) 122 ± 30 118 ± 28 118 ± 27 112 ± 23 0.36 0.42 0.001 Glucose (mg/dL) 89 ± 7 113 ± 24 90 ± 7 117 ± 29 0.25 0.44 0.001 Insulin (μU/mL) 3.9 ± 2.0 26.0 ± 11.7 4.3 ± 1.9 25.5 ± 9.9 0.98 0.68 < 0.001 hs-CRP (mg/dL) 0.107 ± 0.159 0.104 ± 0.158 0.089 ± 0.145 0.087 ± 0.143 0.66 0.87 0.038 MDA-LDL (U/L) 94 ± 24 85 ± 24 95 ± 26 85 ± 21 0.93 0.91 0.027 8-isoprostane (pg/mg Cr) 273 ± 76 283 ± 89 277 ± 69 324 ± 67 0.23 0.17 0.047 Values are means ± SD. Abbreviations : HDL high-density lipoprotein, LDL low-density lipoprotein, hs-CRP high-sensitivity C-reactive protein, MDA malondialdehyde-modified, Cr creatinine. \n a \n P values were calculated by using two-way within subjects ANOVA (control/curry and fasting/postprandial). While the main effects of meals and the interaction effects between meals (control/curry) and prandial status (fasting/postprandial) were not significant, the main effects of prandial status were significant for all parameters measured.\n\nBODY.DISCUSSION:\nIn the present study, we demonstrated that a single consumption of a dish of curry and rice improved the postprandial FMD in healthy men. We believe the significant interaction effect on FMD between meals and prandial status was due to the antioxidant components in the curry, although consumption of the curry meal did not change the two oxidative stress parameters (MDA-LDL and urine 8-isoprostane) measured in our study. Many researchers reported that FMD was improved by some antioxidant consumption (long term and short term) without 8-isoprostane decrease\n[21-23]. Few intervention studies using antioxidants report serum MDA-LDL levels. Pfeuffer et al. reported that consumption of 150 mg/d quercetin for 8 weeks affected neither oxidized LDL nor 8-isoprostane\n[24]. These reports suggest that no change in MDA-LDL and urine 8-isoprostane does not necessarily mean that improvement in FMD is not attributable to decrease in oxidative stress. On the other hand, it has been reported that administration of glucose in oral glucose tolerance test (OGTT) impaired endothelial function with concomitant increase in postprandial oxidative stress\n[11]. It is also reported that the postprandial serum glucose after rice is lower than that after the equivalent amount of glucose consumption\n[25]. In our study, we found that the test meals containing 82 g carbohydrate, which is nearly equivalent to the amount of glucose administered in 75-g OGTT, increased postprandial serum glucose and a consumption of the control meal resulted in decrease in FMD suggesting impairment of endothelial function. We speculate that the presence of spice antioxidants in the curry would have prevented the increase in the oxidative stress induced by postprandial serum glucose increase, but the change in the oxidative stress parameters after our test meal was too small to be detected, because the postprandial serum glucose level after our test meals (113 mg/dL after control or 117 mg/dL after curry) was much lower than that normally encountered after 75-g oral glucose loading\n[26]. Curcumin, eugenol and quercetin in curry could have contributed to our results suggesting that spices improved postprandial endothelial function. It was reported that curcumin alleviates an endothelium-dependent vasodilator dysfunction induced by high glucose in rat aortic rings and increased heme oxygenase-1 activity, and that stimulation of guanylyl cyclase may be involved in the protective effects of curcumin\n[27]. Eugenol was reported to produce smooth muscle relaxation resulting from the blockade of both voltage-sensitive and receptor-operated channels that are modulated by endothelial-generated nitric oxide\n[4]. It has been also suggested that qurcetin, which is a main polyphenol of onion and is also contained in curry, is known as a selective modulator of cyclic GMP-dependent relaxations\n[28]. Future studies are needed for elucidating the mechanism of our findings. After consumption of the test meals, baseline arterial diameter increased significantly. Similar increase in baseline arterial diameter after a fatty meal consumption has been reported\n[29,30]. Although many researchers reported that increase in baseline diameter would decrease FMD\n[31,32], the increase did not appear to have diminished the effect of spices on FMD, because significant interaction effect between meals and prandial status on baseline diameter was not found, and because the postprandial FMD after curry even increased despite that the increase of baseline diameter should decrease FMD. It is reported that a single consumption of a high antioxidant spice blend attenuated postprandial insulin and triglyceride responses and increased some plasma measures of antioxidant activities\n[33]. The results of the present study, however, showed that no interaction effects (i.e., the effects due to spices) on biochemical data between meals (control/curry) and prandial status (fasting/postprandial) were significant. In the previous study, the subjects were given a test meal with different composition, and with different kind of spices. Moreover, they collected blood samples at 30-min intervals for 3.5 h. These differences in experimental conditions may have affected the results. We found that postprandial diastolic blood pressure decreased and postprandial heart rate increased significantly, but postprandial systolic blood pressure did not change significantly. Berry et al. reported that glucose solution with ground beef (i.e., solid food), when fed to human subjects, caused higher postprandial systolic blood pressure than glucose solution alone (i.e., liquid food)\n[34]. They also reported that diastolic blood pressure fell and heart rates increased, without significant (observable) effects from the ground beef\n[34]. Although the mechanisms were not fully understood, the results of our study in which participants consumed solid meal, agree with their findings. There are some limitations in the current study. The first limitation is our small sample size (n = 14). Follow-up work using a larger sample size may be needed. The second limitation is that because of the unique flavor and color of spices used in the curry, the curry meals were readily distinguishable from the control meals by the subjects. Although we cannot exclude the possibility entirely that this feature of our study had some influence on our results, it is more likely that the presence of spices in the curry reduced the impact of the postprandial state on the endothelium after the meal.\n\nBODY.CONCLUSION:\nCurry consumption ameliorates postprandial endothelial dysfunction and may be beneficial for preventing cardiovascular events. Lifestyle-related diseases such as atherosclerosis and diabetes mellitus have become serious health problems in the modern world. Curry may be helpful in the fight against those lifestyle-related diseases.\n\nBODY.ABBREVIATIONS:\nFMD: Flow-mediated vasodilation; HDL-C: High-density lipoprotein-cholesterol; LDL-C: Low-density lipoprotein-cholesterol; hs-CRP: High-sensitivity C-reactive protein; MDA-LDL: Malondialdehyde-modified LDL; OGTT: Oral glucose tolerance test; Cr: Creatinine.\n\nBODY.COMPETING INTERESTS:\nThis study was supported by House Foods Corporation. HN, SY and SS are employees of House Foods Corporation. NT, HS, and NM are employees of House Foods Group Inc. YH has no competing interest.\n\nBODY.AUTHORS’ CONTRIBUTION:\nHN designed the research, performed measurements and statistical analysis, and wrote the manuscript. NT conducted the research. HS provided statistical consultation and critically revised the manuscript. NM provided much consultation about the study design and conducted the research. SY designed and prepared test meals. SS provided much consultation about the study design. YH provided much consultation about the study design, conducted the research, provided consultation about the discussion of the test results, and critically revised the manuscript. All authors read and approved the final manuscript.\n\nQuestion: Compared to spice-free control meal what was the result of single serving of curry meal on postprandial FMD?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1111	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of low-dose ketamine on succinylcholine-induced postoperative myalgia in outpatient surgeries: a randomized, double-blind study\n\n ABSTRACT.OBJECTIVE:\nDespite the many complications of succinylcholine, it is still widely used as a superior muscle relaxant for rapid sequence induction. One of these complications is postoperative myalgia (POM). The aim of this study was to investigate the prophylactic effect of low-dose ketamine on the incidence and severity of POM.\n\nABSTRACT.MATERIALS AND METHODS:\nIn this double-blind clinical study, a total of 148 patients scheduled for general anesthesia were randomly divided into two equal groups. Initially, in Group K, 0.5 mg/kg of ketamine was injected intravenously, whereas in Group N, the same volume (5 mL) of normal saline was injected. Thereafter, anesthesia was induced in all patients, by injecting 1.5 mg/kg of fentanyl and 2 mg/kg of propofol intravenously. Following the loss of eyelid reflex, 1.5 mg/kg of succinylcholine was injected intravenously as a muscle relaxant and then the patients were intubated. POM was defined as a pain with no surgical interferences, and its intensity was graded based on a four-point scale. The incidence and severity of myalgia were assessed by a blinded observer 24 hours after surgery.\n\nABSTRACT.RESULTS:\nIn terms of demographic data, the results of this study showed that there is no significant difference between patients in both groups (P>0.05). Overall, the incidence of POM in Group K was significantly less, when compared with Group N (P<0.05), but both groups were comparable based on the grade 2 of POM. After the induction of anesthesia, the systolic and diastolic blood pressure values were found to reduce in both groups (P<0.05). However, the changes were somehow similar, and repeated measures of variance analysis showed no significant difference in the two study groups (P>0.05).\n\nABSTRACT.CONCLUSION:\nThe addition of 0.5 mg/kg of ketamine to propofol for the induction of anesthesia can be effective in reducing the incidence of low-grade POM.\n\nBODY.INTRODUCTION:\nFor >60 years, succinylcholine is still being administered as a selective relaxant for rapid sequence intubation by anesthesiologists in many countries.1 It has been shown to possess unique features such as low cost, fast-acting, short half-life, safe metabolites, and causing excellent muscle relaxation for intubation;2 however, it has many side effects as well. Postoperative myalgia (POM), with an incidence rate of ~41%–92%, is one of the most common side effects of this drug and can take several days to cause significant discomfort in patients.3 However, its effect is felt more in the throat, neck, shoulder, and abdominal muscles and is common among patients with outpatient surgery.4 Due to its unknown real context of pathogenesis and in an effort to reduce the incidence and severity of succinylcholine-induced myalgia, various medications including nondepolarizing muscle relaxants, benzodiazepines, magnesium sulfate, opioids, gabapentin, and nonsteroidal anti-inflammatory drugs have been tested, with varying degrees of success.5,6 Ketamine is an N-methyl-d-aspartate (NMDA) receptor antagonist with excellent analgesic activity, and at subanesthetic doses it is capable of preventing central sensitization, hyperalgesia, drug resistance creation, and reduction of postoperative pain.7 Although, ketamine administration could produce unpleasant psychogenic complications, no disagreeable effects have been recorded in patients who received a low dose of ketamine. The effects of ketamine on postelectroconvulsive therapy (ECT) myalgia have been studied earlier, and the results showed that ketamine could not prevent this type of myalgia.8 To the best of our knowledge, the effect of ketamine on the prevention of POM is yet to be determined. Therefore, in this randomized, double-blind study, the prophylactic effect of low-dose ketamine on the incidence and severity of myalgia caused by succinylcholine injection in patients undergoing outpatient surgery was investigated.\n\nBODY.MATERIALS AND METHODS:\nThis study was approved by the Ethics Committee of Kurdistan University of Medical Sciences and was registered in the Iranian Registry of Clinical Trials (IRCT2014062412789N5). A complete description of the study was also presented to each participant, and written informed consent was obtained. The sample size was calculated based on the assumption that the incidence of POM in outpatient cases is ~70%, and intervention that can cause 25% reduction in incidence of POM will be interesting. To consider this difference and type I error equal to 5% and 90% power of the study, 72 patients were required to be in each group (α=0.05 and β=90%), but in order to avoid possible loss of samples during the study, the number of patients in each group was increased to 74. Thus, 148 patients, who were scheduled for outpatient surgery under general anesthesia, belonging to the American Society of Anesthesiologists physical status I and II within the age of 18–70 years, were included in this double-blind randomized clinical trial. Patients with a history of allergy to medications; substance abuse; malignant hyperthermia; myopathy; cardiovascular, liver, and advanced kidney diseases; and the risk of difficult intubation based on physical examination were excluded from the study. Before surgery, patients were evaluated by the anesthesiologists. The study protocol and evaluation of myalgia based on Kararmaz's criteria were described to the patients.4 Based on a computer-generated random sequence, the 148 patients were enrolled into one of the two groups (ketamine or saline). The patients did not receive premedication. In the operating room, standard monitoring of the noninvasive blood pressure, electrocardiogram, heart rate, and pulse oximetry was done, and the preliminary values were recorded. Thereafter, a venous cannula (G=18) was placed on the dorsum of a patient's hand. Before the induction of anesthesia in patients of Group K, 0.5 mg/kg of ketamine (a 5 mL volume was reached by adding distilled water) was injected intravenously and 5 mL of normal saline was injected intravenously slowly into patients in Group N. Drugs were prepared in 5 mL syringes by an anesthesia nurse who was unaware of the grouping. After injecting the study drugs, 1.5 mg/kg of fentanyl was injected intravenously within 60 seconds and subsequently 2 mg/kg of propofol was administered intravenously within 30 seconds for the induction of anesthesia. Following the loss of eyelid reflex, 1.5 mg/kg of succinylcholine was injected intravenously and patients were ventilated using bag and mask and with 100% oxygen. After fasciculation, the values of heart rate and blood pressure were measured and recorded, and tracheal intubation was performed. The maintenance of anesthesia continued using a mixture of oxygen, N2O (40/60), and isoflurane 1 MAC. After 5 minutes of tracheal intubation, the values of heart rate and blood pressure were obtained and recorded again. For maintenance of muscle relaxation, 0.2 mg/kg of atracurium was used as suggested by the surgeon. At the end of the surgery, muscle relaxation was reversed using neostigmine and atropine. After the desired spontaneous ventilation, the patients were extubated. The patients were transferred to the recovery room and complications, if any, were recorded during recovery. After meeting the discharge criteria, the patients were discharged to be taken home and cared for by a responsible adult. The incidence and severity of myalgia in the patients were determined 24 hours after surgery by a medical student who was unaware of the grouping. Myalgia is defined as \"a pain with no surgical interference\" and is graded based on Kararmaz et al's4 four-point scale as follows: 0= no muscle pain, 1= muscle stiffness limited to one area of the body, 2= muscle pain or stiffness noticed spontaneously by a patient who requires analgesics, and 3= incapacitating generalized, severe muscle stiffness or pain. Statistical analysis was conducted using SPSS Version 12.0 software (IBM Corporation, Armonk, NY). The comparison profile of the patients was performed using the analysis of variance test. The incidence and severity of myalgia were compared using the chi-square and independent t-tests. The value of P<0.05 was considered statistically significant.\n\nBODY.RESULTS:\nIn this study, a total of 207 patients were scheduled for outpatient surgery from July 2013 to August 2014. Of them, 29 patients could not meet the entry criteria. Twenty-seven patients had no willingness to participate in the study, and the surgery of three patients was canceled. The remaining 148 patients were randomly assigned into two groups. Two patients in Group N due to nausea, vomiting, and pain and one patient in Group K due to arrhythmia were turned from outpatient to inpatient. Two persons from Group K did not cooperate with the evaluation of POM. The data associated with the 72 patients in Group N and 71 patients in Group K were analyzed (Figure 1). There were no significant differences in terms of age, sex, and duration of surgery between both groups (Table 1). In Group K, 13 (18.1%) out of the 71 patients had myalgia, whereas 36 (50%) out of the 72 patients had myalgia in Group N (P=0.001). Grade 1 POM was lower in Group K when compared with Group N (nine in Group K versus 33 in Group N; P<0.001), whereas the incidence of grade 2 POM was comparable among patients of the two groups (Table 2). The baseline values of systolic and diastolic blood pressure and heart rate in both groups were similar. After the induction of anesthesia, the values of systolic and diastolic blood pressure decreased in both groups (P<0.05). However, these changes were somehow similar in the two groups, and repeated measures of variance analysis showed no significant difference in both groups (P>0.05). Changes in heart rate after induction and intubation between the two groups were compared and repeated measures of variance analysis showed no significant difference in the two groups (P>0.05; Table 3).\n\nBODY.DISCUSSION:\nThe results of this study showed that ketamine significantly reduced the incidence of succinylcholine-induced myalgia. Succinylcholine is a muscle relaxant that is commonly used due to deep neuromuscular blocks for intubation in patients undergoing ambulatory anesthesia, but associated myalgia has been shown to occur in 41%–92% of patients.9,10 Since ambulation increases the possibility of myalgia and its intensity, ambulatory patients are suitable for investigating this complication. Therefore, this group of patients was chosen for the study. Myalgia is most prevalent following the use of succinylcholine in the first day of surgery.11 As shown in a study, 92% of patients reported myalgia in the first 24 hours of study and the incidence of myalgia did not differ at 24 hours and 48 hours after surgery.8 In this study, myalgia was evaluated only in the first 24 hours after surgery. It seems that the intrafusal contraction of muscle fibers caused damage to spindles and subsequently myalgia.12 In vitro studies have shown that active, excessive, and continuous muscle contractions increase the uptake of calcium, activation of phospholipase A2, arachidonic acid, and prostaglandins production, thereby increasing the risk of muscle damage and pain.13 The results of this study showed that 50% of the patients in Group N experienced myalgia after anesthesia was induced with propofol. In a meta-analysis, the average incidence of myalgia in the first 24 hours with thiopental was 49.2% and with propofol was 65.4%.14 The incidence of myalgia in the present study was slightly lower when compared with the aforementioned meta-analysis. It appears that participants in this study belonged to low-level POM in general. Ketamine creates a complex combination of both antinociceptive and pronociceptive actions. In fact, based on the mechanisms of analgesia with a direct receptor, the analgesic effect of ketamine is associated with the plasma levels of drugs and pain reduces with subanesthetic doses of ketamine.15,16 In general, it seems that the NMDA receptor plays an important role in the pathophysiology of pain, and the Supra spinal block of the NR2B NMDA subunit by ketamine has an important antinociceptive effect.17 Recent studies have shown the role of NMDA receptors in facilitating the process of pain in the central nervous system, this receptor is also responsible for central sensitization and windup phenomenon. The administration of NMDA receptor antagonists prevents the development of sensitization, hyperalgesia, and drug resistance.18 Ketamine is an antagonist of this receptor and has excellent analgesic activity at doses under anesthesia.19 It strengthens the performance of mu and kappa opioid receptors and also has direct effects on the delta opioid receptor. As such, ketamine certainly modulates the response of opioid receptors and reduces tolerance to opioids.20 It also strengthens the endogenesis of antinociceptive systems, in part, by its aminergic (serotonergic and noradrenergic) activation and inhibition of reuptake.21 It inhibits the synthesis of nitric oxide, which probably contributed to the analgesic effect.22 Also, there is evidence suggesting that ketamine interferes with nicotinic, muscarinic, and monoaminergic receptors. As a result of the undesirable and unwanted side effects, ketamine usage is controversial in nonanesthetized patients, but when surgery is done under general anesthesia, these side effects are barely seen.19 In this study, surgery was performed under general anesthesia and none of the patients experienced delirium and nightmare. In our previous study,8 the effect of prophylactic ketamine on myalgia after ECT in 50 patients with major depression was demonstrated, in which 1 mg/kg of propofol and 0.3 mg/kg of ketamine were used for the induction of anesthesia, and muscle relaxation was induced using 0.5 mg/kg of succinylcholine. The results showed that the addition of ketamine to propofol had no effect on the incidence of myalgia after ECT, and only 12% of the patients had myalgia within 24 hours after ECT. However, our previous study8 is different in some aspects from the present study. In our previous study, ECT patients were investigated and the cause of myalgia was found to be different in surgical patients. Second, unlike the surgery, myalgia intensity in ECT is not related to fasciculation and motor activities.23 Third, the dose of anesthetic drugs for the induction of anesthesia and muscle relaxation was less than that of the present study. The result of our previous study, which was carried out on patients undergoing ECT, is not in line with the present study. Cardiovascular changes were similar after the induction of anesthesia in both groups. In theory, hemodynamic stability can be predicted based on the induction of anesthesia with propofol and ketamine, when compared with propofol alone. This is because ketamine increases blood pressure and heart rate; therefore, the addition of this drug to propofol during anesthesia induction can inhibit the reduction of these parameters before the stimulation of laryngoscopy and tracheal intubation. Also, following laryngoscopy and tracheal intubation, the synergistic effect of these two drugs can increase the depth of anesthesia and result in smoother cardiovascular response to airway stimulation. It appears that 0.5 mg/kg of ketamine could not produce such an impact on the hemodynamic system, thereby resulting in a significant effect.\n\nBODY.STUDY LIMITATIONS:\nOne of the limitations of this study is the insufficient time for myalgia evaluation (24 hours). Failure to assess the incidence and severity of fasciculation is another limitation of this study. In this study, ketamine was diluted with sterile water, although this is not a wrong practice, but further addition of water, as carried out in this study, could produce ketamine with concentration below the physiological osmotic pressure, which may interfere with the effects of ketamine.\n\nBODY.CONCLUSION:\nThe addition of 0.5 mg/kg of ketamine to propofol for the induction of anesthesia can be effective in reducing the incidence of POM, without any change in hemodynamic indices.\n\nQuestion: Compared to Group N, the same volume (5 mL) of normal saline was injected what was the result of Group K, 0.5 mg/kg of ketamine was injected intravenously, on grade 2 of POM?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1122	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Comparative utility of disability progression measures in PPMS\n\n ABSTRACT.OBJECTIVE:\nTo assess the comparative utility of disability progression measures in primary progressive MS (PPMS) using the PROMiSe trial data set.\n\nABSTRACT.METHODS:\nData for patients randomized to placebo (n = 316) in the PROMiSe trial were included in this analysis. Disability was assessed using change in single (Expanded Disability Status Scale [EDSS], timed 25-foot walk [T25FW], and 9-hole peg test [9HPT]) and composite disability measures (EDSS/T25FW, EDSS/9HPT, and EDSS/T25FW/9HPT). Cumulative and cross-sectional unconfirmed disability progression (UDP) and confirmed disability progression (CDP; sustained for 3 months) rates were assessed at 12 and 24 months.\n\nABSTRACT.RESULTS:\nCDP rates defined by a ≥20% increase in T25FW were higher than those defined by EDSS score at 12 and 24 months. CDP rates defined by T25FW or EDSS score were higher than those defined by 9HPT score. The 3-part composite measure was associated with more CDP events (41.4% and 63.9% of patients at 12 and 24 months, respectively) than the 2-part measure (EDSS/T25FW [38.5% and 59.5%, respectively]) and any single measure. Cumulative UDP and CDP rates were higher than cross-sectional rates.\n\nABSTRACT.CONCLUSIONS:\nThe T25FW or composite measures of disability may be more sensitive to disability progression in patients with PPMS and should be considered as the primary endpoint for future studies of new therapies. CDP may be the preferred measure in classic randomized controlled trials in which cumulative disability progression rates are evaluated; UDP may be feasible for cross-sectional studies.\n\nBODY:\nPatients with primary progressive MS (PPMS) represent 10%–15% of patients with MS and suffer the highest neurodegeneration-related disability.1–4 There are currently no approved treatments to ameliorate disease progression in PPMS, and there are several barriers to developing therapeutics in progressive MS.2,5 Specifically, individual disability measures may lack the sensitivity required to reveal all cases of disease progression within the defined time frame of a clinical trial.6 The Expanded Disability Status Scale (EDSS) remains the typical outcome measure in PPMS trials. However, it has been widely recognized as inadequate7 and is associated with several important weaknesses.3 Other widely used measures of disability in MS include the timed 25-foot walk (T25FW) and the 9-hole peg test (9HPT).8,9 Recent studies have suggested that a combined disability measure that incorporates scoring from multiple instruments—for example, using T25FW, 9HPT, and EDSS—may be associated with more progression events among patients with PPMS, and thus higher reported event rates than achieved with any single instrument alone.9,10 The PROMiSe study represents one of the best and largest (N = 943) data sources on patients with PPMS and offers a unique opportunity to assess the value of different functional measures of disability progression in a clinical trial setting.11 We report here the results of an analysis of the PROMiSe data set undertaken to better understand the utility of the different measures of disability progression—EDSS, T25FW, and 9HPT alone and in combinations—and to inform the design of future trials in PPMS.\n\nBODY.METHODS.STANDARD PROTOCOL APPROVALS, REGISTRATIONS, AND PATIENT CONSENTS.:\nParticipating study sites in each individual country locally ensured all necessary regulatory approvals (e.g., institutional review boards/institutional ethics committees) in accordance with local regulations, including local data protection regulations used in the original collection of the data for this secondary data analysis.\n\nBODY.METHODS.STUDY DESIGN.:\nThe data set for this analysis was derived from the PROMiSe study, a randomized, double-blind, placebo-controlled clinical trial with a planned duration of 3 years.11 The design of the PROMiSe study has been reported previously.11 In summary, patients who took part in the PROMiSe study (N = 943) were randomized in a 2:1 ratio to receive glatiramer acetate (GA) 20 mg once daily (n = 627) or identical-appearing placebo (n = 316) by daily subcutaneous injection.11 The primary endpoint was time to confirmed disability progression (CDP), with CDP being defined as a change of ≥1 point on the EDSS sustained for 3 months in patients with a baseline EDSS score of 3.0–5.0, or a change of ≥0.5 points for 3 months in those with a baseline score of 5.5–6.5.11 Patients also completed the MS Functional Composite (MSFC) evaluation, a 3-part test including the T25FW and 9HPT and the Paced Auditory Serial Addition Test (PASAT).11\n\nBODY.METHODS.PATIENTS.:\nPatients eligible to participate in the PROMiSe study were aged between 30 and 65 years, with an EDSS score of 3.0–6.5, investigator-confirmed PPMS, and progressive symptoms including myelopathy for ≥6 months before screening. Additional eligibility criteria included evidence of pyramidal damage on neurologic examination, including a pyramidal functional system score ≥2, and evidence of multilevel CNS disease.11 Patients with any history of MS relapse, those with lymphopenia <3,000 cells/mL, and those who had used an interferon-β drug, immunosuppressant, immunomodulating agent, corticosteroid, or investigational drug within 3 months of study initiation were not eligible to take part.11 Only data for patients randomized to placebo in the PROMiSe trial were included in this analysis in order to compare clinical measures in patients with PPMS for whom the natural course of the disease was not potentially affected by exposure to GA treatment.\n\nBODY.METHODS.OUTCOME EVALUATIONS.:\nDisability was assessed using change in single (EDSS, T25FW, and 9HPT) and composite disability measures. Combination endpoints were defined as progression by EDSS or T25FW, 9HPT or T25FW, or by EDSS or T25FW or 9HPT. The PASAT was not included in this analysis of the PROMiSe database because of the potential for practice effects occurring from repeated administration. Moreover, the test may have limited measurement reliability, is sometimes difficult to administer, has been used less frequently in recent MS trials, and is not anticipated to be featured in future trials. As per the PROMiSe study protocol, worsening of the EDSS was defined as a change from baseline of ≥1 point (for baseline EDSS 3.0–5.0) or ≥0.5 points (for baseline EDSS 5.5–6.5).11 Worsening of the T25FW was defined as an increase of ≥20% compared with baseline or as the inability to complete the T25FW after baseline due to worsening disability (increase of EDSS to 7.0 or higher).12 Worsening of the 9HPT was defined as an increase of ≥20% compared with baseline (calculated as the average across 4 trials: 2 in the dominant hand and 2 in the nondominant hand) or as the inability to complete the 9HPT after baseline due to worsening disability.12 For each measure, rates of unconfirmed disability progression (UDP) and of 3-month CDP were determined. Two trial methodologies were evaluated: cumulative and cross-sectional. The cumulative approach describes the design of the PROMiSe trial and similar large-scale randomized clinical trials, with outcome measurement every 3 months and disability progression at any time point during follow-up contributing to an overall CDP proportion. The cross-sectional approach describes the design for simple, straightforward investigator-initiated trials such as futility trials13 and observational studies on PPMS disability progression.10 In this case, the measurement at one follow-up time point (e.g., 12 months) is compared with the baseline measurement. This analysis is restricted to patients in the PROMiSe trial receiving placebo in order to compare clinical measures in patients with PPMS for whom the natural course of the disease was not affected by exposure to GA treatment.\n\nBODY.METHODS.STATISTICAL ANALYSES.:\nCumulative progression rates were estimated using the Kaplan-Meier methodology. For summaries by month, 1 month was defined as 28 days. For confirmed disability events, patients who experienced a worsening event in the measure of interest that could not be confirmed due to the patient's discontinuation from the trial prior to the confirmation visit were censored at the time of the worsening. Other patients who did not experience the progression event were censored at their last day in the study. Cross-sectional progression rates were determined by comparing baseline and follow-up disability measures. Patients missing any of the 3 disability measures at baseline, the time point of interest, or the corresponding confirmation assessment were excluded from the analysis. The relative percentage contribution of each disability measure to disease progression rates observed for the combined EDSS or T25FW or 9HPT measure was derived by determining the number of individual patients progressing on 1, 2, or all 3 outcomes measures.\n\nBODY.RESULTS:\nA total of 316 patients were assigned to receive placebo in the PROMiSe study; 314 of these patients had a postbaseline EDSS assessment, and these patients constituted the population for the cumulative analyses presented here. Of these, 272 patients were included in the 12-month cross-sectional analysis, and 214 patients constitute the population for the 24-month cross-sectional analysis. Baseline demographic and clinical characteristics for the 314 patients who received placebo are shown in table 1.11 The baseline characteristics of the subgroup of patients assigned to receive placebo were consistent with those of the entire PROMiSe patient population.11 Table 1 Baseline demographic and clinical characteristics of patients who took part in the PROMiSe trial and were randomized to receive placebo Table 2 shows cumulative and cross-sectional UDP and CDP rates at 12 and 24 months. Among single measures, a ≥20% worsening in T25FW (T25FW 20%) was associated with the highest cumulative progression rates, followed by EDSS and then a ≥20% worsening in 9HPT (9HPT 20%) at both the 12- and 24-month time points. Among combined measures, the composite of all 3 individual measures (i.e., EDSS or T25FW 20% or 9HPT 20%) had the highest cumulative 3-month CDP rate at both 12 and 24 months (41.4% and 63.9%, respectively). Cross-sectional 3-month CDP rates were also highest for the composite of all 3 scores than for any single or dual combination of scores at both 12 and 24 months (37.5% and 57.5%, respectively). UDP proportions were consistently higher than CDP proportions for all measures, with a considerably greater difference between UDP and CDP in the cumulative incidence of the composite of all 3 individual measures (1 year: 63.8% and 41.4%, respectively; 2 years: 82.1% and 63.9%, respectively) compared with the cross-sectional proportions (1 year: 47.8% and 37.5%, respectively; 2 years: 57.5% and 52.8%, respectively). Table 2 Cumulative and cross-sectional PROMiSe disease progression rates at 12 and 24 months The proportion of patients with UDP and 3-month CDP for each of the disability metrics over the course of the study is shown in figure 1 for each study paradigm (cumulative and cross sectional). The T25FW 20%-alone values were closely aligned with those from the combined EDSS-or-T25FW 20% values at all time points over the course of the study (table 3). Figure 1Comparison of cumulative and cross-sectional UDP and CDP rates for EDSS, T25FW 20%, and 9HPT 20%(A) EDSS rates. (B) T25FW 20% rates. (C) 9HPT 20% rates. 3M CDP = 3-month confirmed disability progression; 9HPT = 9-hole peg test; EDSS = Expanded Disability Status Scale; T25FW = timed 25-foot walk; UDP = unconfirmed disability progression. Table 3 Disease progression rates over the course of the PROMiSe study The relative contribution of each of the individual component measures—together and in different combinations—of a 3-part composite measure (EDSS or T25FW 20% or 9HPT 20%) is shown in figure 2 and figure e-1 at Neurology.org/nn. T25FW 20% had the greatest contribution to the overall measure, followed by EDSS, and then 9HPT 20%. These figures support the notion that CDP as defined by T25FW identifies individuals as progressors that the other measures would not have been identified. In other words, a greater proportion of patients identified as progressors by T25FW were not identified as progressors by EDSS or 9HPT, as compared with the proportion of patients identified as progressors by EDSS who were not identified as progressors by T25FW or 9HPT (figure e-2). Figure 2Contribution of individual clinical measures evaluating patient worsening at 24 months (cross-sectional 3-month CDP) within a 3-part combined measure (EDSS or T25FW 20% or 9HPT 20%)(A) Cumulative UDP. (B) Cumulative 3-month CDP. (C) Cross-sectional UDP. (D) Cross-sectional 3-month CDP. 3M CDP = 3-month confirmed disability progression; 9HPT = 9-hole peg test; EDSS = Expanded Disability Status Scale; T25FW = timed 25-foot walk; UDP = unconfirmed disability progression.\n\nBODY.DISCUSSION:\nThe data presented here show that among patients with PPMS randomized to receive placebo in the PROMiSe study, T25FW 20% at 12 and 24 months was associated with higher rates of disability progression than EDSS, and both T25FW 20% and EDSS were associated with higher disability rates than 9HPT 20%. The 3-part combination measure (EDSS or T25FW 20% or 9HPT 20%) was associated with more 3-month CDP events (41.4% and 63.9% of patients as 12 and 24 months, respectively) than the 2-part measure (EDSS or T25FW 20% [38.5% and 59.5%, respectively]), and more progression events than any single measure (EDSS, 14.9% and 32.4%, respectively; T25FW, 33.5% and 52.0%, respectively; 9HPT, 8.4% and 18.0%, respectively). Minimal changes in the 9HPT 20% outcome were noted over the course of the PROMiSe trial. As such, this measure may be less suitable than EDSS and T25FW 20% when used alone; however, 9HPT may still have utility as part of a composite measure. Moreover, future studies should explore thresholds other than 20% worsening on performance measures such as 9HPT. A marked difference was noted between cumulative and cross-sectional progression rates, which may inform the design of PPMS trials. Cumulative progression rates were generally higher than cross-sectional rates, but more strikingly, there was a greater difference between unconfirmed and CDP using the cumulative approach. Based on our results, the normative approach to use CDP in classic randomized controlled trials is supported. Failure to confirm disability progression may have a neurobiological basis or may be due to measurement unreliability; it would be preferable to exclude these from pivotal trial analyses in both cases. For trials using the cross-sectional approach, measures of UDP may still be feasible. Such studies would be resource-sparing and less burdensome for participants, but would have acknowledged data sparsity and methodological limitations. The observations presented here add to a growing body of evidence that suggests that combining specific disability measurements may be more useful in the clinical trial setting for assessing progression in patients with PPMS than single measures.9,10,14–16 In a retrospective database study of 181 patients with progressive MS (primary 47% of patients and secondary 53% of patients), combining change in T25FW with EDSS was significantly more predictive of patient prognosis than EDSS alone.15 An earlier retrospective database study of 161 patients with PPMS found that when comparing single measures or 2-instrument combinations involving EDSS, T25FW, and 9HPT, T25FW/9HPT predicted the greatest number of progression events after 1 year (46% of patients progressed compared with 17%, 34%, and 20% for the individual measures, respectively), and the combination of T25FW/EDSS predicted the greatest number of progression events after the second year (57% of patients progressed compared with 32%, 46%, and 24% for the individual measures, respectively).11 An evaluation of data from the 96-week Olympus (rituximab) trial17 in the 147 patients with PPMS randomized to placebo found that a combined measure consisting of EDSS/T25FW/9HPT was associated with more CDP events than did any single or dual combination measure.11 Progression rates at 96 weeks were 61.9% and 54.8% for those patients with an initial confirmed progression event at 12 and 24 weeks, respectively.9 Confirmed progression rates for EDSS alone were 38.5% and 30.4%; for T25FW alone the rates were 51.0% and 44.5%; and for the 9HPT alone the rates were 21.1% and 17.4%, respectively.9 Most recently, the large, prospective INFORMS (fingolimod) study, comprising patients with PPMS treated for at least 3 years, reported that a composite of EDSS, T25FW, or 9HPT predicted more progression events (80.3% cumulative probability of CDP) than any of the individual components alone (EDSS 58.7%, T25FW 70.0%, and 9HPT 41.3% of patients) among those randomized to placebo.14 Although those previous published studies offer similar conclusions to this study regarding the relative utility of outcome measures, they differ in several important ways that distinguish them from our analysis of the PROMiSe data set. The retrospective database study included both primary and secondary progressive patients with MS, was primarily focused on outcomes of early vs late changes on clinical scales, included patients who were exposed to disease-modifying therapies (DMTs) during the course of the study, did not set a minimum disability criterion as per EDSS for study entry, and included less-frequent patient assessment.15 Similarly, the earlier study likely included patients exposed to DMTs, while its entry criteria included an EDSS threshold score of 2.0–6.5, representing a less-disabled patient population than that of the PROMiSe study.10 The same EDSS criteria applied to the Olympus study, whereas none of these 3 studies, nor the INFORMS study, compared confirmed with unconfirmed progression or offered a cross-sectional analysis of disease progression data.9,14 Two other recently published studies address similar themes and arrive at compatible conclusions to those of this study.18,19 In one of these studies, however, the patient population consisted entirely of those with secondary progressive MS,18 whereas the other had a lower EDSS inclusion threshold (1–7), allowed inclusion of patients who had been treated with DMTs as recently as 3 months prior to study entry, and was intended as a validation study of a novel disability score (CombiWISE); that scoring measure, in addition to EDSS, T25FW, and 9HPT, also includes the Scripps Neurological Rating Scale.19 And, as with the previously noted studies, neither unconfirmed disease nor a cross-sectional analysis was included in the design of these studies.18,19 Thus, this study offers several unique features that make it a potentially valuable contribution to the literature, such as reflecting the untreated natural history of PPMS by including only patients receiving placebo, including patients with more severe disability, comparing confirmed and unconfirmed disease progression, and including a cross-sectional analysis. There is an unmet need for controlling disease progression in patients with PPMS. For these patients, individual measures of disease progression may limit the potential to assess the benefit of new agents to the extent that the composite measures have higher event rates. Based on the observations presented here and those from previous studies, future studies of agents for the treatment of PPMS may benefit from either using T25FW 20% as a single outcome measure or using T25FW 20% in combination with the EDSS as a primary efficacy endpoint rather than EDSS alone, particularly if higher event rates over shorter exposure periods are sought. It is largely unknown whether specific disability outcomes would differentially detect treatment effects or whether this would differ according to the mechanism of the treatment under study.\n\nBODY.SUPPLEMENTARY MATERIAL:\n\n\nData Supplement\n\nQuestion: Compared to 9-hole peg test [9HPT] what was the result of timed 25-foot walk [T25FW], on confirmed disability progression?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1126	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Clinical efficacy of \n\n ABSTRACT:\nAging has become one of the distinctive demographic phenomena in the 21st century and its social, economic and health implications are the most challenging issues. Senile Memory Impairment is a common condition characterized by mild symptoms of cognitive decline and occurs as a part of the normal aging process. It can be correlated to \"Jarajanya Smrtibhramsha\" according to Ayurveda. The present study deals with the efficacy of Guduchyadi Medhya Rasayana on Senile Memory Impairment. A total of 138 patients aged in between 55–75 years were registered and randomly divided into two groups as the trial and control groups. The drugs were administered for 3. The trial drug showed memory enhancement, anti-stress, anti-depressant and anxiolytic properties. The trial group showed better results in the management compared to the control group.\n\nBODY.INTRODUCTION:\nAging has become a great issue for many countries due to a worldwide life prolongation. Number of people over 60 years has grown rapidly to 10% of the world population.[1] In India too, in the last decade, increasing population aged has been projected significantly.[2] So, it is associated with physiological, functional, and pathological changes affecting physical, psychological, emotional and social well-being.[3] The major consequences of the increasing number of individuals in advanced age group is the increase in number of patients suffering from age-related disorders. Conservative estimation revealed that 25% of the elderly persons have significant psychiatric symptoms[4] and the number of psychologicaly ill elderly persons was estimated to be 9 million in the year 2005.[5] Though psychological disorders are common among the aged, it frequently remains undetected and untreated. It induces functional disability, disturbs rehabilitation, burdens the health system and impairs the quality of life of elderly individuals.[6] Research based on the psychological health revealed that age-associated cognitive like memory disorders are found in high prevalence among the aged.[7] Subjective complaints from individuals with age-associated memory impairment often include difficulties in remembering names and words, etc. So, this condition is the result of physiological changes in the aging brain and not a specific neurological disorder.[8] In Ayurveda literature, impairment of memory is mentioned as Smritibhramsha which occurs due to vitiation of Rajas and Tamas Doshas in the mind.[9] The appearance of Jara (aging) at the appropriate age is termed as \"Kalaja Jara\",[10] and memory impairment appears as a clinical Rupa (feature) of Jara,[11] hence Senile Memory Impairment can be correlated as Jarajanya Smritibhramsha according to Ayurveda. In Sarangadhara Samhita, it is clearly emphasized that Medha (intellect) and Buddhi (wisdom) deteriorate in the fourth and ninth decades of life accordingly.[12] Both are closely associated with the mind and help for the normal function of the mind. If these components decrease in the mind, then it will affect the normal function of mind. Moreover, Caraka has noted that cognitive functions are thoroughly affected in old age as Grahana (power of understanding), Dharana (power of retention), Smarana (power of memorizing), Vachana (speech) and functions of sense organs qualitatively.[13]\n\nBODY.INTRODUCTION.IMPORTANCE OF :\nThe aging process occurs over all the body. It does not occur in the same way in every human being. People's lifestyles also have additional influence on aging.[14] The decline in brain weight and volume, degeneration of intracellular organelles, changes in cellular DNA and RNA, neuronal degeneration as well as significant loss of synapses are the salient features of aging in the brain.[15] Therefore, psychological and neurological manifestations often form the hallmark of senility. Hence, Ayurveda clearly emphasizes that in the fourth and ninth decades of lifespan, individuals are subjected to the loss of Medha (intellect) and Buddhi (wisdom). Hence, it seems therapeutic measures of Medhya Rasayanas are exclusively needed for elders because they are brain tonics and improve the psychological faculties. It is responsible for Dhi (intelligence), Dhrti (retention power), Smriti (memory) and also possesses anti-stress and adaptogenic effect.[16] Having considered all literary views and ideas as above mentioned, Guduchyadi Medhya Rasayana (GMR)[17] has been attempted to evaluate its efficacy on Senile Memory Impairment.\n\nBODY.MATERIALS AND METHODS.SELECTION OF THE PATIENTS:\nTotal 138 patients having symptoms of memory impairment attending O.P.D. and I.P.D. of Department of Kaya Chikitsa of I.P.G.T. and R.A., Gujarat Ayurved University, Jamnagar were selected for the present study. A purposive sampling technique was adopted irrespective of their sex, religion, occupation, educational status, etc.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF INCLUSION:\nPatients aged 55 and above up to75 years of age.Complaints of memory impairment on the basis of short term and long term.\nShort term, e.g. misplacing objects, difficulty in remembering multiple items to be purchased, difficulty in recalling information quickly, problems in remembering names and telephone numbers.Long term, e.g. difficulty in recall of special events of personal life, difficulty in recall of previous histories of life and recognition.Patients suffering from dementia.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF EXCLUSION:\nPatients below 55 years and above 75 years of age.Patients with evidence of delirium, confusion or other disturbances of consciousness, Parkinson's disease, stroke, intracranial hemorrhage, brain tumors, history of alcoholism or drug dependence, use of any psychotropic drug, Alzheimer's disease, diabetes mellitus, etc.\n\nBODY.MATERIALS AND METHODS.INVESTIGATIONS:\nRoutine hematological and biochemical tests were carried out before and after the treatment. Among the biochemical tests, serum Acetylcholine Esterase (AChE) estimation, as a biomarker of Senile Memory Impairment, was carried out.\n\nBODY.MATERIALS AND METHODS.PLAN OF THE STUDY:\nPatients fulfilling the inclusion criterion were grouped in to two after obtaining written consent.\n\nBODY.MATERIALS AND METHODS.GROUP A (TRIAL GROUP):\nPatients of this group were administered with the Granules of Guduchyadi Medhya Rasayana (GMR), which contains Guduchi (Tinospora cordifolia Wild.), Apamarga (Achyranthes aspera Linn.), Vidanga (Embelia ribes Burm. f.), Shankhapushpi (Convolvulus pluricaulis Chois.), Vaca (Acorus calamus Linn.), Haritaki (Terminalia chebula Zetz.), Kushtha (Saussurea lappa C.B. Clarke), Shatavari (Asparagus racemosus Wild.), Cow's ghee and sugar. Dosage: 5 g, 3 times per day, after meal Anupana: Water in sufficient quantity Duration: 3 months Total, 73 patients were registered.\n\nBODY.MATERIALS AND METHODS.GROUP B (CONTROL GROUP):\nPatients of this group were administered Sarkaradi Granules (SG). Dosage: 3 g, 3 times per day, after meal Anupana: Water in sufficient quantity Duration: 3 months Total 65 patients were registered.. Both the drugs were prepared at Pharmacy, Gujarat Ayurved University, Jamnagar.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT:\nEffects of Medhya Rasayana on memory impairment were assessed in two ways, i.e. as subjective and objective, before and after the treatment. After completion of the treatment, the patients were graded into five groups based on their improvement in order to ascertain the overall therapeutic efficacy. The data so obtained were analyzed using SPSS and Sigma Stat statistical packages. Observations and results pertaining to clinical parameters were presented in tabular form along with the findings of statistical analysis. Paired \"t\" test was adopted to find out the effect of therapy for each group individually, while unpaired \"t\" test used for comparative effect.\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT.SUBJECTIVE CRITERIA:\nAssessments on improvements in signs and symptoms were carried out using appropriately designed scoring method, with the scores ranging from 0 to 4. Cognitive state was assessed by Mini Mental State Examination.[18] and psychological health of the patients was evaluated with Hamilton Rating Scales for Depression and Anxiety.[19]\n\nBODY.MATERIALS AND METHODS.CRITERIA OF ASSESSMENT.OBJECTIVE CRITERIA:\nSerum AChE estimation was carried out as a biomarker of Senile Memory Impairment.\n\nBODY.OBSERVATIONS AND RESULTS:\nTotal 138 patients of Senile Memory Impairment were registered in the study. Forty-three patients in the Group A (trial group) and 56 patients in the Group B (control group) completed the treatment, while 30 patients in Group A and 9 patients in Group B discontinued. In this study, various etiological factors were identified. Maximum number of patients reported Chinta (thoughts; 92%), followed by Krodha (anger; 83.3%), Shoka (worries; 70.2%), Chittodvega (anxiety; 64.4%), Bhaya (fear; 51.4%), Ruksha Ahara (dried food; 55.7%), Rattri Jagarana (awaking at night; 87%), etc.\n\nBODY.OBSERVATIONS AND RESULTS.EFFECT OF THERAPY:\nBoth the groups showed highly significant (P`0.001) relief from all the chief complaints [Table 1 and Table 2]. Table 1 Effect of GMR in Group A on the symptoms of Senile Memory Impairment Table 2 Effect of SG in Group B on the symptoms of Senile Memory Impairment In comparison to Group B, Group A showed highly significant relief in symptoms such as names forgotten (63.56%), numbers forgotten (61.62%), and memory impairment in recalling special events in life (59.71%) at a level of P`0.001, and forgetfulness (68.60%), losing of valuables (73.64%), difficulty in remembering multiple items to be purchased (68.21%), inability to concentrate (68.14%), impaired recognition (79.7%), memory impairment of recall of previous histories (60.66%) at a level of P`0.01, and a significant relief (P`0.05) from difficulty in recalling information quickly (71.57%), depression (89.66%), and inability to relax (82.93%) [Table 3]. Table 3 Comparison of the effects of GMR and SG on the symptoms of Senile Memory Impairment With respect to Dosha Dushti, the Group A showed significant relief from Vata Dushti (85.48%), Pitta Dushti (94.15%) and in Kapha Dushti (84.3%), while the Group B showed significant relief from Vata Dushti (68.3%), Pitta Dushti (61.78%) and in Kapha Dushti (62.75%). On Hamilton Anxiety Rating Scale, both the groups showed highly significant relief (P`0.001) from all the symptoms individually. In comparison to the results obtained from Group B, the Group A showed highly significant relief with respect to intellectual cognitive functions (79.03%), somatic (muscular) disorders (83.71%), depression (74.12%), and a significant relief from fear (81.11%). On Hamilton Depression Rating Scale, both the groups showed highly significant relief (P`0.001) from all the symptoms individually. However, the comparative results were insignificant. The results of symptoms of Mini Mental State Examination showed that both the groups provided highly significant (P`0.001) improvement individually. In comparison with SG, GMR showed highly significant improvement in registration (9.30%), attention and calculation (24.49%), and a significant improvement in language (13.51%) and in total score (14.89%) [Table 4]. The results obtained with hematological parameters reveal that Group A showed [Table 5] highly significant increase in total RBC (1.20%) count, a significant increase in Hb% (1.34%), packed cell volume (PCV) (1.30%) and a significant decrease in erythrocyte sedimentation rate (ESR) value (7.40%), while Group B showed highly significant decrease in RBC count (4.30%), PCV (3.34%), and a significant decrease in Hb% (1.55%). Table 4 Comparison of the effects of GMR and SG on the symptoms of mini mental state examination Table 5 Effect of GMR on hematological parameters in Group A (n=43) With regard to the biochemical parameters, Group A showed highly significant decrease (P`0.01) in serum cholesterol, serum triglyceride, low density lipoprotein (LDL), and very low density lipoprotein (VLDL) levels, while high density lipoprotein (HDL) increased highly significantly (P`0.01) and a significant decrease (P`0.05) was found in blood urea (13.80%) as well as serum AChE (3.67%) within normal limits [Table 6]. The Group B showed highly significant increase in blood urea (10.04%), but it was within normal limit. Other parameters were found to be statistically insignificant. Table 6 Effect of GMR on biochemical parameters in Group A (n=43) Regarding the overall effect, Group A showed marked improvement in 18.6% patients, moderate improvement in 74.4% patients and mild improvement in 7.0% patients, while Group B showed moderate improvement in 32.2% patients and mild improvement in 67.8% patients.\n\nBODY.DISCUSSION:\nIt has been mentioned in texts that GMR contributes to enhance the memory power within a short period. On the basis of Rasapanchaka, the pharmacotherapeutic properties reveal that it contains Katu, Tikta and Madhura in Rasa, and the effect of Katu and Madhura in Vipaka. Moreover, due to various properties of Tikshna, Laghu, Ruksha, Sara, Guru and Snigdha, it possesses markedly Ushna Virya and mildly Sheeta Virya. Accordingly, GMR was considered to be an effective treatment for Tridoshahara. In Ayurveda, it is clearly emphasized that Smritibhramsha (memory impairment) results due to Rajas and Tamasdoshas in the mind. These doshas are responsible for producing avarana over the mind. The relief from the symptoms has been found to be statistically highly significant. These observations reveal that the drug might have counteracted or pacified Raja and Tamo Doshas, so Avarana of mind was removed and the disease was subsided or controlled. Further pharmacological studies have proven that Vaca (Acorus calemus Linn.) and Shankhapushpi (Convolvulus pluricaulis Chois) have anxiolytic, memory enhancing, anti-stress, antidepressant, tranquilizing and sedative activities.[20, 21] Further, it was found that there was a significant improvement by 14.84% on the total score of the Mini Mental State Examination [Table 4]. So, these evidences indicate the positive role of Medhya property of GMR on Senile Memory Impairment among elderly individuals. Considering the symptoms of memory impairment along with the cognitive decline, a highly significant result was obtained both from GMR and SG [Table 1 and Table 2]. However, in comparison, GMR has given better relief for the majority of symptoms [Table 3]. The Medhya Rasayanas are special Ayurvedic neuro nutraceuticals which are specific to brain and nervous system. They are claimed to promote cognitive function of the brain.[22] Further, it was mentioned in the Caraka Samhita that Shankhapushpi, a Rasayana drug, has the property of promoting intellect.[23] Moreover, Group B also showed improvement of memory due to the Medhya effect of ghee.[24] The serum AChE value has shown an upper range in both the groups before the treatment and a significant decrease was observed after the treatment in Group A [Table 6]. The recent advances in clinical research reveal that AChE activity is increased in human cerebrospinal fluid during aging[25] and scientists believe that dementia-related memory issues stem from the increased breakdown of acetylcholine due to a preponderance of AChE which degrades acetylcholine.[26] Furthermore, a decrease in AChE activity has noted in the treated animals, leading to an increase in the cholinergic activity in the brain.[27] The significant reduction of AChE in Group A shows that GMR exerts its effect on memory enhancement by increasing the cholinergic function by preventing the breakdown of acetylcholine in the aging human brain.\n\nBODY.CONCLUSIONS:\nSenile Memory Impairment can be correlated to Jarajanya Smritibhramsha according to Ayurveda, and imbalance of Trigunas through aggravation of Rajas and Tamas Doshas in the mind leads to development of Senile Memory Impairment among elders. Modern literature reveals that Senile Memory Impairment is closely associated with cognitive decline during aging. All the patients of Senile Memory Impairment were having features of impairment of short memory and long memory in this study. Manasika Nidana (psychic factors), Aharaja (dietary) and Viharaja (behavioral) factors, which were reported by the patients, play a major role in the pathogenesis of Senile Memory Impairment by vitiating Rajas and Tamas Doshas in the mind. Those factors were Chinta (thoughts), Krodha (anger), Shoka (worries), Chittodvega (anxiety), Bhaya (fear), Moha (illusions), Ruksha Ahara (dried food), Ratri Jagarana (awaking at night), etc. GMR has shown statistically highly significant improvement on short memory impairment as well as long memory impairment in Senile Memory Impairment, at the level of P`0.001. Reduction of AChE showed enhancement of memory functions due to improvement of cholinergic actions in the human brain in the trial group (Group A). GMR has shown memory enhancing, antidepressant, anti-stress, and anxiolytic potential. Hence, Guduchyadi Medhya Rasayana therapy has proved so as to provide better improvement in comparison to the control group.\n\nQuestion: Compared to administered Sarkaradi Granules (SG). what was the result of administered with the Granules of Guduchyadi Medhya Rasayana (GMR), which contains Guduchi (Tinospora cordifolia Wild.), Apamarga (Achyranthes aspera Linn.), Vidanga (Embelia ribes Burm. f.), Shankhapushpi (Convolvulus pluricaulis Chois.), Vaca (Acorus calamus Linn.), Haritaki (Terminalia chebula Zetz.), Kushtha (Saussurea lappa C.B. Clarke), Shatavari (Asparagus racemosus Wild.), Cow's ghee and sugar. on high density lipoprotein (HDL)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1128	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Applicability Evaluation of Simplified Cognitive Behavioral Therapy\n\n ABSTRACT.BACKGROUND:\nWe have developed a structured cognitive behavioral therapy manual for anxiety disorder in China, and the present study evaluated the applicability of simplified cognitive behavioral therapy based on our previous research.\n\nABSTRACT.AIMS:\nTo evaluate the applicability of simplified cognitive behavioral therapy (SCBT) on generalized anxiety disorder (GAD) by conducting a multi-center controlled clinical trial.\n\nABSTRACT.METHODS:\nA multi-center controlled clinical trial of SCBT was conducted on patients with GAD, including institutions specializing in mental health and psychiatry units in general hospitals. The participants were divided into 3 groups: SCBT group, SCBT with medication group and medication group. The drop-out rates of these three groups, the therapy satisfaction of patients who received SCBT and the evaluation of SCBT from therapists were compared.\n\nABSTRACT.RESULTS:\n(1) There was no significant difference among the drop-out rates in the three groups. (2) Only the duration and times of therapy were significantly different between the two groups of patients who received the SCBT, and the therapy satisfaction of the SCBT group was higher than that of the SCBT with medication group. (3) Eighteen therapists who conducted the SCBT indicated that the manual was easy to comprehend and operate, and this therapy could achieve the therapy goals.\n\nABSTRACT.CONCLUSION:\nThe applicability of SCBT for patients with GAD is relatively high, and it is hopeful that SCBT can become a psychological treatment which can be applied in medical institutions of various levels.\n\nBODY.1. INTRODUCTION:\nThe core features of generalized anxiety disorder (GAD) are the chronic and persistent loss of self-control due to worries, and a cognitive evaluation bias towards threats and risks, which causes significant impairments in work, interpersonal social life, physical health, mental health and so forth.[1,2] Currently, the main treatment for GAD is medication with psychotherapy as the supplement.[3,4] The most commonly used form of psychotherapy to treat anxiety is cognitive behavioral therapy (CBT), and it has been shown to be more effective for the treatment of mild anxiety than other psychotherapies.[5-7] Brief cognitive behavioral therapy (BCBT) is a short-term psychotherapy which has gained more attention internationally in recent years, and clinical trials have shown it's effectiveness in treating anxiety disorder.[8,9] In the studies done outside of China, the manual for BCBT was gradually developed and applied in primary medical institutions. However, there are few systematic, detailed and structured manuals provided to medical workers for use in China. Previously, we developed a structured simplified cognitive behavioral therapy (SCBT) manual that could be used by medical workers providing services at district level institutions or those who had not received systematic training. We reported on the effectiveness of this treatment which, at the time, was quite early in the provision of psychological services in China.[10-12] The present study was based on this previous research[10,11] to provide further evaluation of the SCBT technique.\n\nBODY.2. METHODS.2.1 SCBT MANUAL:\nThere are four sections in the manual: (a) instructions, (b) procedure and content, (c) specific treatment content and (d) addendum.[10] Four key steps are emphasized in every treatment session: feedback on the previous homework, treatment content, relaxation technique exercises and homework assignments.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.1 SAMPLE:\nParticipants were recruited through posters, nurse registrations and outpatient doctors' recommendations. The time frame of the recruitment was from March, 2014 to December, 2015. Participants were recruited from the following locations: Shanghai Psychological Counselling and Treatment Center, Tenth People's Hospital of Tongji University, Shanghai Hongkou Mental Health Center, Shanghai Yangpu Mental Health Center and Nanjing Brain Hospital affiliated to Nanjing Medical University.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.2 INCLUSION CRITERIA:\n1 Participants who met the diagnostic criteria for GAD according to the DSM-IV; 2 participants whose HAMA-14 scores were equal to 14 or above, and equal to 29 or below; and participants whose GAD-7 scores were equal 5 to or above; and participants whose HAMD-17 scores were below 14; 3 females and males between 18 and 65; 4 participants whose education levels were equal to elementary school or above; 5 participants whose visual and audio levels were high enough to complete the assessments required; 6 participants who had not received psychological counselling or treatments in any form in the past three months; 7 participants who were willing to participate and provided written informed consent.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.3 EXCLUSION CRITERIA:\n1 Participants who had a current severe medical condition; 2 participants who had severe suicidal ideation; 3 females who were pregnant or lactating; 4 participants who had comorbid psychosis or had psychotic symptoms, psychoactive substance dependence or abuse, personality disorder, or mental retardation; 5 participants whose symptoms did not improve after receiving medication with sufficient doses and durations and psychotherapies.\n\nBODY.2. METHODS.2.3 RESEARCH TOOLS:\n1 Adapted patient satisfaction questionnaire [8] evaluating the acceptability of SCBT. There are 8 items using a scale of 1 to 5. 2 Adapted manual evaluation scale [8] evaluating the applicability of SCBT. There are 3 sub-scales, as stated below: (a) the treatment feedback scale for therapists after each treatment: therapists evaluate the content, goals, flexibility, effectiveness and other aspects of each treatment. There are 8 items using a scale of 1 to 7. (b) the treatment feedback scale for therapists after each week: therapists evaluate the effectiveness, applicability and other aspects of treatments after each week. There are 8 items using a scale of 1 to 7. (c) the feedback summary scale for therapists: the main focus is for therapists to evaluate SCBT in terms of their general practice and experience. There are 8 items using a scale of 1 to 7.\n\nBODY.2. METHODS.2.4 STUDY DESIGN:\nRandomized parallel control and blind evaluation methods were employed in the present study. The present study used a random table generated by computer, and participants were given random numbers according to the order of their enrollment. However, some participants did not cooperate with the group assignment or switched to another group during the study due to worries about the side-effects of drugs, thinking that psychotherapy was useless and being influenced by the information of group assignments, therefore the study was only partially randomized; in fact, the whole randomized design was affected. Participants were divided into three groups: the SCBT group, the SCBT with medication group and the regular medication group. Based on the previous related literature, we planned to recruit 30 participants into each group. Within the sample of 112 participants included in the analysis, 32 (28.6%) of them did not cooperate with the group assignment or switched to another group. Blind evaluation method means that the people who conducted the assessments did not know which group participants were assigned to.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.1 SIMPLIFIED COGNITIVE BEHAVIORAL THERAPY GROUP (SCBT GROUP):\nParticipants in this group only received SCBT during the treatment period, and did not receive any other treatment in any form. The treatment duration was 8 weeks with 12 structured sessions. In the first 4 weeks: twice a week; in the latter 4 weeks: once a week. Every individual therapy session lasted for an hour, and the evaluations were conducted at the baseline and the end of the eighth week.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.2 COMBINED TREATMENT GROUP (SCBT WITH MEDICATION GROUP):\nParticipants in this group received SCBT with medication during the treatment period. The categories of medications were mainly required to be SSRI, SNRI or benzodiazepines. The evaluation schedule was the same as the SCBT group's.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.3 REGULAR MEDICATION GROUP (MEDICATION GROUP):\nParticipants in this group received routine medication only, and did not receive any SCBT. The categories of medications and evaluation schedule were the same as those of the SCBT with medication group.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.4 THE APPLICABILITY EVALUATION OF SCBT:\nThe applicability of SCBT mainly includes acceptability and feasibility.[8] Acceptability is mainly referred to as patients benefitting from the treatment, whether or not they would recommend it to others, their satisfaction towards the treatment and so forth. The adapted patient satisfaction questionnaire was used to evaluate this factor. Feasibility mainly includes the drop-out rate, and the compliance and feedback of therapists to the manual; the adapted manual evaluation scale was employed to assess this factor.[8] The Likert Scale's rating system was employed to rate the patient satisfaction questionnaire and manual evaluation scale.[13]\n\nBODY.2. METHODS.2.6 STATISTICAL METHODS:\nAs the acceptability and partial feasibility were evaluated for the whole intervention, only the data of participants who completed the intervention were analyzed. There were participants who dropped out of the study, and their data were excluded from the analysis. Furthermore, missing data were not processed or included in the analysis. Therefore, the present study employed Per Protocol Set Analysis, which meant only analyzing data of participants who completed the intervention. SPSS 17.0 was used for statistical analysis. Enumeration data were described with frequencies and rates. Independent sample t tests, multiple tests and X2 tests were employed. The value of p being smaller than 0.05 indicated that the difference was statistically significant.\n\nBODY.3. RESULTS:\nWith Per Protocol Set Analysis being used, there was a total of 112 participants who were included in the final analysis (SCBT group: 34, SCBT with medication group: 45, medication group: 33). The three groups were not significantly different in age, gender, education level or marital status (F=1.88, df=2, p=0.158; X2=1.16, df=2, p=0.560; X2=3.50, df=6, p=0.744; X2=5.08, df=6, p=0.454).\n\nBODY.3. RESULTS.3.1 ACCEPTABILITY EVALUATION OF SCBT:\nThis part of the analysis only accepted data of participants who received SCBT and completed the eight-week-long intervention (i.e., 34 participants from the SCBT group and 45 participants from the SCBT with medication group). As stated in Table 1, participants in the SCBT group and SCBT with medication group were not significantly different in satisfaction factors, such as the quality of treatment, the duration and the number of session, or whether their expectations for treatment had been met.\n\nBODY.3. RESULTS.3.2 FEASIBILITY EVALUATION OF SCBT.3.2.1 DROP-OUT RATE:\nAs stated in Table 2, there was no significant difference among the drop-out rates of the three groups (X2=1.41, df=2, p=0.494) with the drop-out rate of the medication only group being the highest. The summation of drop-out rates of the SCBT group and SCBT with medication group was 24.8%.\n\nBODY.3. RESULTS.3.2 FEASIBILITY EVALUATION OF SCBT.3.2.2 EVALUATIONS OF THE SCBT MANUAL BY 18 THERAPISTS:\nTherapist evaluations of each treatment are shown in Table 3. Based on the content and experience of each treatment, therapists conducted evaluations on each item of each participant. All therapists indicated that the flexibility allowed by the manual was medium in each treatment, and the flexibility of the second treatment was the lowest as there was basically no flexibility. Table 4 shows the therapists' evaluation of each week's treatment. Similarly, therapists evaluated the item for each participant based on the content and experience of each weeks treatment. All therapists indicated that most content of the weekly treatment was useful, that each week's assignment could be used effectively and that the feasibility was good. Overall evaluation of the program by the therapists is shown in Table 5. Through feedback summary scales of therapists, every participant who completed the eight-week-long intervention was evaluated on every item based on each therapist's insights into the 12 interventions. Therapists suggested that this manual was basically suitable to use on patients.\n\nBODY.4. DISCUSSION.4.1 MAIN FINDINGS:\nSCBT follows the principle of starting simple and gradually becoming more advanced. The main focus of treatment is for patients to identify, analyze and modify maladaptive thoughts and behaviors. In this regard the core technique of CBT (i.e., cognition restructuring and exposing) is included in SCBT, which is consistent with conventional CBT and BCBT.[9,14] The manual for SCBT was edited in a structured way. The duration of treatment is relatively shorter, and the number of sessions is fewer, making it easier for novice therapists to master and conduct. Therefore SCBT can be applied in primary medical centers and is consistent with the lower requirements of therapists conducting BCBT.[8,10] The drop-out rates for the three groups were not significantly different, but drop out from the medication only group was the highest. This was mainly because that in contrast to the medication only group, participants of in the SCBT group and SCBT with medication group developed good working communities and stable treatment relationships by receiving 12 treatments. The drop-out rate of all participants who received SCBT (SCBT group and SCBT with medication group) was 24.8%, which is comparable to conventional CBT's and BCBT's rates.[8,15] Therapists considered treatments to be somewhat flexible, and this was mainly because the manual was structured and therapists had little experience. Among the 12 sessions, the flexibility of the second session was rated as the lowest. This was due to the fact that the second treatment session used narrative therapy. In that particular session participants wrote down content and therapists reflected main factors of these depictions back to them. The evaluation of sessions by the therapists reflected that treatment was rushed to achieve each week's goal. This was also found to be true in other studies of BCBT.[8,16] The reason for this is that therapists are accustomed to conducting conventional CBT and they may feel that 12 simplified treatments are not enough. This suggests that further simplifications and adjustments to SCBT may be needed, and every treatment needs to be organized more reasonably, which can enable participants to master the core technique of CBT within 12 treatments.[17]\n\nBODY.4. DISCUSSION.4.2 LIMITATIONS:\nParticipants were not assigned randomly, so it is difficult to generalize the conclusion that the applicability of SCBT is high. In addition, not analyzing the data of participants who dropped out may exaggerate the feasibility and acceptability of SCBT.\n\nBODY.4. DISCUSSION.4.3 IMPLICATIONS:\nOn the basis of previous studies, the present study tested the applicability of SCBT, and provided methodological evidence on treating anxiety disorder for Chinese primary medical workers.\n\nQuestion: Compared to the SCBT with medication group or regular medication group what was the result of simplified cognitive behavioral therapy (SCBT) on generalized anxiety disorder (GAD) on drop-out rates?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1129	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Applicability Evaluation of Simplified Cognitive Behavioral Therapy\n\n ABSTRACT.BACKGROUND:\nWe have developed a structured cognitive behavioral therapy manual for anxiety disorder in China, and the present study evaluated the applicability of simplified cognitive behavioral therapy based on our previous research.\n\nABSTRACT.AIMS:\nTo evaluate the applicability of simplified cognitive behavioral therapy (SCBT) on generalized anxiety disorder (GAD) by conducting a multi-center controlled clinical trial.\n\nABSTRACT.METHODS:\nA multi-center controlled clinical trial of SCBT was conducted on patients with GAD, including institutions specializing in mental health and psychiatry units in general hospitals. The participants were divided into 3 groups: SCBT group, SCBT with medication group and medication group. The drop-out rates of these three groups, the therapy satisfaction of patients who received SCBT and the evaluation of SCBT from therapists were compared.\n\nABSTRACT.RESULTS:\n(1) There was no significant difference among the drop-out rates in the three groups. (2) Only the duration and times of therapy were significantly different between the two groups of patients who received the SCBT, and the therapy satisfaction of the SCBT group was higher than that of the SCBT with medication group. (3) Eighteen therapists who conducted the SCBT indicated that the manual was easy to comprehend and operate, and this therapy could achieve the therapy goals.\n\nABSTRACT.CONCLUSION:\nThe applicability of SCBT for patients with GAD is relatively high, and it is hopeful that SCBT can become a psychological treatment which can be applied in medical institutions of various levels.\n\nBODY.1. INTRODUCTION:\nThe core features of generalized anxiety disorder (GAD) are the chronic and persistent loss of self-control due to worries, and a cognitive evaluation bias towards threats and risks, which causes significant impairments in work, interpersonal social life, physical health, mental health and so forth.[1,2] Currently, the main treatment for GAD is medication with psychotherapy as the supplement.[3,4] The most commonly used form of psychotherapy to treat anxiety is cognitive behavioral therapy (CBT), and it has been shown to be more effective for the treatment of mild anxiety than other psychotherapies.[5-7] Brief cognitive behavioral therapy (BCBT) is a short-term psychotherapy which has gained more attention internationally in recent years, and clinical trials have shown it's effectiveness in treating anxiety disorder.[8,9] In the studies done outside of China, the manual for BCBT was gradually developed and applied in primary medical institutions. However, there are few systematic, detailed and structured manuals provided to medical workers for use in China. Previously, we developed a structured simplified cognitive behavioral therapy (SCBT) manual that could be used by medical workers providing services at district level institutions or those who had not received systematic training. We reported on the effectiveness of this treatment which, at the time, was quite early in the provision of psychological services in China.[10-12] The present study was based on this previous research[10,11] to provide further evaluation of the SCBT technique.\n\nBODY.2. METHODS.2.1 SCBT MANUAL:\nThere are four sections in the manual: (a) instructions, (b) procedure and content, (c) specific treatment content and (d) addendum.[10] Four key steps are emphasized in every treatment session: feedback on the previous homework, treatment content, relaxation technique exercises and homework assignments.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.1 SAMPLE:\nParticipants were recruited through posters, nurse registrations and outpatient doctors' recommendations. The time frame of the recruitment was from March, 2014 to December, 2015. Participants were recruited from the following locations: Shanghai Psychological Counselling and Treatment Center, Tenth People's Hospital of Tongji University, Shanghai Hongkou Mental Health Center, Shanghai Yangpu Mental Health Center and Nanjing Brain Hospital affiliated to Nanjing Medical University.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.2 INCLUSION CRITERIA:\n1 Participants who met the diagnostic criteria for GAD according to the DSM-IV; 2 participants whose HAMA-14 scores were equal to 14 or above, and equal to 29 or below; and participants whose GAD-7 scores were equal 5 to or above; and participants whose HAMD-17 scores were below 14; 3 females and males between 18 and 65; 4 participants whose education levels were equal to elementary school or above; 5 participants whose visual and audio levels were high enough to complete the assessments required; 6 participants who had not received psychological counselling or treatments in any form in the past three months; 7 participants who were willing to participate and provided written informed consent.\n\nBODY.2. METHODS.2.2 PARTICIPANTS.2.2.3 EXCLUSION CRITERIA:\n1 Participants who had a current severe medical condition; 2 participants who had severe suicidal ideation; 3 females who were pregnant or lactating; 4 participants who had comorbid psychosis or had psychotic symptoms, psychoactive substance dependence or abuse, personality disorder, or mental retardation; 5 participants whose symptoms did not improve after receiving medication with sufficient doses and durations and psychotherapies.\n\nBODY.2. METHODS.2.3 RESEARCH TOOLS:\n1 Adapted patient satisfaction questionnaire [8] evaluating the acceptability of SCBT. There are 8 items using a scale of 1 to 5. 2 Adapted manual evaluation scale [8] evaluating the applicability of SCBT. There are 3 sub-scales, as stated below: (a) the treatment feedback scale for therapists after each treatment: therapists evaluate the content, goals, flexibility, effectiveness and other aspects of each treatment. There are 8 items using a scale of 1 to 7. (b) the treatment feedback scale for therapists after each week: therapists evaluate the effectiveness, applicability and other aspects of treatments after each week. There are 8 items using a scale of 1 to 7. (c) the feedback summary scale for therapists: the main focus is for therapists to evaluate SCBT in terms of their general practice and experience. There are 8 items using a scale of 1 to 7.\n\nBODY.2. METHODS.2.4 STUDY DESIGN:\nRandomized parallel control and blind evaluation methods were employed in the present study. The present study used a random table generated by computer, and participants were given random numbers according to the order of their enrollment. However, some participants did not cooperate with the group assignment or switched to another group during the study due to worries about the side-effects of drugs, thinking that psychotherapy was useless and being influenced by the information of group assignments, therefore the study was only partially randomized; in fact, the whole randomized design was affected. Participants were divided into three groups: the SCBT group, the SCBT with medication group and the regular medication group. Based on the previous related literature, we planned to recruit 30 participants into each group. Within the sample of 112 participants included in the analysis, 32 (28.6%) of them did not cooperate with the group assignment or switched to another group. Blind evaluation method means that the people who conducted the assessments did not know which group participants were assigned to.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.1 SIMPLIFIED COGNITIVE BEHAVIORAL THERAPY GROUP (SCBT GROUP):\nParticipants in this group only received SCBT during the treatment period, and did not receive any other treatment in any form. The treatment duration was 8 weeks with 12 structured sessions. In the first 4 weeks: twice a week; in the latter 4 weeks: once a week. Every individual therapy session lasted for an hour, and the evaluations were conducted at the baseline and the end of the eighth week.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.2 COMBINED TREATMENT GROUP (SCBT WITH MEDICATION GROUP):\nParticipants in this group received SCBT with medication during the treatment period. The categories of medications were mainly required to be SSRI, SNRI or benzodiazepines. The evaluation schedule was the same as the SCBT group's.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.3 REGULAR MEDICATION GROUP (MEDICATION GROUP):\nParticipants in this group received routine medication only, and did not receive any SCBT. The categories of medications and evaluation schedule were the same as those of the SCBT with medication group.\n\nBODY.2. METHODS.2.5 STUDY PROCEDURE.2.5.4 THE APPLICABILITY EVALUATION OF SCBT:\nThe applicability of SCBT mainly includes acceptability and feasibility.[8] Acceptability is mainly referred to as patients benefitting from the treatment, whether or not they would recommend it to others, their satisfaction towards the treatment and so forth. The adapted patient satisfaction questionnaire was used to evaluate this factor. Feasibility mainly includes the drop-out rate, and the compliance and feedback of therapists to the manual; the adapted manual evaluation scale was employed to assess this factor.[8] The Likert Scale's rating system was employed to rate the patient satisfaction questionnaire and manual evaluation scale.[13]\n\nBODY.2. METHODS.2.6 STATISTICAL METHODS:\nAs the acceptability and partial feasibility were evaluated for the whole intervention, only the data of participants who completed the intervention were analyzed. There were participants who dropped out of the study, and their data were excluded from the analysis. Furthermore, missing data were not processed or included in the analysis. Therefore, the present study employed Per Protocol Set Analysis, which meant only analyzing data of participants who completed the intervention. SPSS 17.0 was used for statistical analysis. Enumeration data were described with frequencies and rates. Independent sample t tests, multiple tests and X2 tests were employed. The value of p being smaller than 0.05 indicated that the difference was statistically significant.\n\nBODY.3. RESULTS:\nWith Per Protocol Set Analysis being used, there was a total of 112 participants who were included in the final analysis (SCBT group: 34, SCBT with medication group: 45, medication group: 33). The three groups were not significantly different in age, gender, education level or marital status (F=1.88, df=2, p=0.158; X2=1.16, df=2, p=0.560; X2=3.50, df=6, p=0.744; X2=5.08, df=6, p=0.454).\n\nBODY.3. RESULTS.3.1 ACCEPTABILITY EVALUATION OF SCBT:\nThis part of the analysis only accepted data of participants who received SCBT and completed the eight-week-long intervention (i.e., 34 participants from the SCBT group and 45 participants from the SCBT with medication group). As stated in Table 1, participants in the SCBT group and SCBT with medication group were not significantly different in satisfaction factors, such as the quality of treatment, the duration and the number of session, or whether their expectations for treatment had been met.\n\nBODY.3. RESULTS.3.2 FEASIBILITY EVALUATION OF SCBT.3.2.1 DROP-OUT RATE:\nAs stated in Table 2, there was no significant difference among the drop-out rates of the three groups (X2=1.41, df=2, p=0.494) with the drop-out rate of the medication only group being the highest. The summation of drop-out rates of the SCBT group and SCBT with medication group was 24.8%.\n\nBODY.3. RESULTS.3.2 FEASIBILITY EVALUATION OF SCBT.3.2.2 EVALUATIONS OF THE SCBT MANUAL BY 18 THERAPISTS:\nTherapist evaluations of each treatment are shown in Table 3. Based on the content and experience of each treatment, therapists conducted evaluations on each item of each participant. All therapists indicated that the flexibility allowed by the manual was medium in each treatment, and the flexibility of the second treatment was the lowest as there was basically no flexibility. Table 4 shows the therapists' evaluation of each week's treatment. Similarly, therapists evaluated the item for each participant based on the content and experience of each weeks treatment. All therapists indicated that most content of the weekly treatment was useful, that each week's assignment could be used effectively and that the feasibility was good. Overall evaluation of the program by the therapists is shown in Table 5. Through feedback summary scales of therapists, every participant who completed the eight-week-long intervention was evaluated on every item based on each therapist's insights into the 12 interventions. Therapists suggested that this manual was basically suitable to use on patients.\n\nBODY.4. DISCUSSION.4.1 MAIN FINDINGS:\nSCBT follows the principle of starting simple and gradually becoming more advanced. The main focus of treatment is for patients to identify, analyze and modify maladaptive thoughts and behaviors. In this regard the core technique of CBT (i.e., cognition restructuring and exposing) is included in SCBT, which is consistent with conventional CBT and BCBT.[9,14] The manual for SCBT was edited in a structured way. The duration of treatment is relatively shorter, and the number of sessions is fewer, making it easier for novice therapists to master and conduct. Therefore SCBT can be applied in primary medical centers and is consistent with the lower requirements of therapists conducting BCBT.[8,10] The drop-out rates for the three groups were not significantly different, but drop out from the medication only group was the highest. This was mainly because that in contrast to the medication only group, participants of in the SCBT group and SCBT with medication group developed good working communities and stable treatment relationships by receiving 12 treatments. The drop-out rate of all participants who received SCBT (SCBT group and SCBT with medication group) was 24.8%, which is comparable to conventional CBT's and BCBT's rates.[8,15] Therapists considered treatments to be somewhat flexible, and this was mainly because the manual was structured and therapists had little experience. Among the 12 sessions, the flexibility of the second session was rated as the lowest. This was due to the fact that the second treatment session used narrative therapy. In that particular session participants wrote down content and therapists reflected main factors of these depictions back to them. The evaluation of sessions by the therapists reflected that treatment was rushed to achieve each week's goal. This was also found to be true in other studies of BCBT.[8,16] The reason for this is that therapists are accustomed to conducting conventional CBT and they may feel that 12 simplified treatments are not enough. This suggests that further simplifications and adjustments to SCBT may be needed, and every treatment needs to be organized more reasonably, which can enable participants to master the core technique of CBT within 12 treatments.[17]\n\nBODY.4. DISCUSSION.4.2 LIMITATIONS:\nParticipants were not assigned randomly, so it is difficult to generalize the conclusion that the applicability of SCBT is high. In addition, not analyzing the data of participants who dropped out may exaggerate the feasibility and acceptability of SCBT.\n\nBODY.4. DISCUSSION.4.3 IMPLICATIONS:\nOn the basis of previous studies, the present study tested the applicability of SCBT, and provided methodological evidence on treating anxiety disorder for Chinese primary medical workers.\n\nQuestion: Compared to the SCBT with medication group what was the result of simplified cognitive behavioral therapy (SCBT) on generalized anxiety disorder (GAD) on quality of treatment, the duration and the number of session, or whether their expectations for treatment had been met.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1130	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: First-in-Human Evaluation of the Safety and Immunogenicity of an Intranasally Administered Replication-Competent Sendai Virus–Vectored HIV Type 1 Gag Vaccine: Induction of Potent T-Cell or Antibody Responses in Prime-Boost Regimens\n\n ABSTRACT:\nBackground. We report the first-in-human safety and immunogenicity assessment of a prototype intranasally administered, replication-competent Sendai virus (SeV)–vectored, human immunodeficiency virus type 1 (HIV-1) vaccine. Methods. Sixty-five HIV-1–uninfected adults in Kenya, Rwanda, and the United Kingdom were assigned to receive 1 of 4 prime-boost regimens (administered at 0 and 4 months, respectively; ratio of vaccine to placebo recipients, 12:4): priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Results. All vaccine regimens were well tolerated. Gag-specific IFN-γ enzyme-linked immunospot–determined response rates and geometric mean responses were higher (96% and 248 spot-forming units, respectively) in groups primed with SeV-Gag and boosted with Ad35-GRIN (SLA and SHA) than those after a single dose of Ad35-GRIN (56% and 54 spot-forming units, respectively) or SeV-Gag (55% and 59 spot-forming units, respectively); responses persisted for ≥8 months after completion of the prime-boost regimen. Functional CD8+ T-cell responses with greater breadth, magnitude, and frequency in a viral inhibition assay were also seen in the SLA and SHA groups after Ad35-GRIN boost, compared with those who received either vaccine alone. SeV-Gag did not boost T-cell counts in the ASH group. In contrast, the highest Gag-specific antibody titers were seen in the ASH group. Mucosal antibody responses were sporadic. Conclusions. SeV-Gag primed functional, durable HIV-specific T-cell responses and boosted antibody responses. The prime-boost sequence appears to determine which arm of the immune response is stimulated. Clinical Trials Registration. NCT01705990.\n\nBODY:\nDespite significant progress in prevention and treatment of human immunodeficiency virus type 1 (HIV-1) infection, development of a safe and effective preventive HIV-1 vaccine remains a global priority [1, 2]. Several vaccine regimens have been tested for efficacy, but only one conferred modest, transient protection against HIV-1 acquisition [3]. Various methods have been evaluated to enhance responses to HIV vaccines, including booster injections, cytokine administration, adjuvants, electroporation, vector delivery systems, and prime-boost approaches [4–8]. Development of a vaccine that stimulates sustained humoral and/or cellular immunity at mucosal entry points may be critical for an HIV preventive vaccine. Although mucosally administered vaccines have been tested and licensed for other diseases [9–12], mucosal administration of an HIV preventive vaccine has seldom been evaluated [13]. Sendai virus (SeV) is a nonsegmented negative-sense RNA virus in the Paramyxoviridae family that can infect the upper respiratory tract [14–17]. As a live viral vector that is not pathogenic in humans, SeV offers several properties important for a successful vaccine: it does not integrate into the host genome, it replicates only in the cytoplasm without DNA intermediates or a nuclear phase, and it does not undergo genetic recombination. SeV is genetically and antigenically related to hPIV-1 [18–21]. A live nonrecombinant SeV vaccine against human parainfluenza virus type 1 (hPIV-1) administered intranasally in adults and young children was safe and immunogenic [22, 23]. SeV antibodies cross-reactive with hPIV-1 antibodies are present in most people [24]. Intranasal delivery of a vaccine could induce a first line of defense at mucosal points of entry and induce effective systemic immune responses [12, 25, 26]. Nonhuman primate studies with SeV bearing simian immunodeficiency virus (SIV) genes demonstrated protection against SIV challenge and evidence that SeV vectors may boost responses primed by other HIV-1 vaccines [27–29]. Intranasal administration and heterologous prime-boost administration were shown to reduce effects of preexisting immunity [29, 30]. In this study, we report the first-in-human safety and immunogenicity evaluation of a replication-competent SeV-vectored HIV-1 vaccine administered intranasally; the vaccine was administered intranasally at a lower dose (SL) or higher dose (SH) of SeV vector encoding clade A HIV-1 Gag (SeV-Gag), given alone or as a heterologous prime-boost with a nonreplicating adenovirus (Ad) serotype 35 HIV-1 vaccine containing genes HIV-1 encoding Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) administered intramuscularly. The Ad35-GRIN was selected for these prime-boost regimens because it has well-known safety profile and robust immunogenicity in both US and African populations [4, 7, 8, 31].\n\nBODY.METHODS.VOLUNTEERS AND STUDY DESIGN:\nThis study was a multicenter, randomized, placebo-controlled, dose-escalation trial that was double blinded with respect to vaccine or placebo but not regimen. The doses were based on preclinical data [28, 29] and a nonrecombinant live SeV vaccine study in humans [23]; the initial group was administered a lower dose for safety. The study was conducted at Projet San Francisco (Kigali, Rwanda), the Kenya AIDS Vaccine Initiative Institute of Clinical Research (Nairobi, Kenya), and the St Stephen's AIDS Trust (London, United Kingdom). The objectives were to evaluate the safety and immunogenicity of 4 different 2-dose regimens (administered at 0 and 4 months) that comprised SeV-Gag administered at 2 × 107 (SL) or 2 × 108 (SH) cell infectious units and Ad35-GRIN vaccine administered at 1 × 1010 viral particles. Volunteers and clinical/laboratory personnel were blind to allocation between active vaccine and placebo. The participants were healthy HIV-negative adults 18–50 years of age engaging in behavior at low risk for HIV-1 infection; all women were nonpregnant and used an effective method of contraception until 4 months after the last vaccination (detailed inclusion/exclusion criteria are in Supplementary Materials). The respective local governmental ethics and regulatory bodies for each clinical research center approved the study. Written informed consent was obtained from each volunteer prior to undertaking any study procedure. The study was conducted in accordance with International Conference on Harmonization's good clinical practice and good clinical laboratory practice guidelines [32]. The study design is presented in Table 1 and in the Consolidated Standards of Reporting Trials diagram (Supplementary Figure 1). Volunteers in part I received low-dose SeV-Gag vaccine followed by Ad35-GRIN vaccine (SLA) or placebo. Following review of safety data from part I by an independent safety review board, a different set of volunteers was randomly assigned to participate in part II. Volunteers in part II received either the higher dose of SeV-Gag as a prime followed by Ad35-GRIN vaccine (SHA); an Ad35-GRIN prime given intramuscularly, followed by the higher-dose SeV-Gag boost given intranasally (ASH); prime-boost with the higher-dose SeV-Gag given intranasally (SHSH); or placebo.\nTable 1.Study Immunization Regimens and ScheduleGroupRegimenSubjects, No.Month 0Month 4Vaccine GroupPlacebo GroupVaccineRouteDoseaVaccineRouteDoseaASLA124SeV-GagIntranasal2 × 107Ad35-GRINIntramuscular1 × 1010BSHA124SeV-GagIntranasal2 × 108Ad35-GRINIntramuscular1 × 1010CASH125bAd35-GRINIntramuscular1 × 1010SeV-GagIntranasal2 × 108DSHSH124SeV-GagIntranasal2 × 108SeV-GagIntranasal2 × 108Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are 1 × 107 or 1 × 108 cell infectious units/100 μL per nostril (for SeV-Gag) or 1 × 1010 viral particles (for Ad35-GRIN).b Overenrollment was allowed per protocol; one additional volunteer, identified post unblinding as a placebo recipient, was enrolled. Each group had 16 volunteers: 12 vaccine recipients and 4 placebo recipients. Enrollment of an additional volunteer was allowed yielding a sample size of 65. Local and systemic reactogenicity were reported for days 0 through 14 following each vaccination, adverse events (AEs) were reported through month 1 following the second study vaccination, and serious adverse events (SAEs) were reported through the final study visit. Hematologic and biochemical parameters were assessed at 4 time points after vaccination (Supplementary Materials). Reactogenicity and AEs were assessed using an adapted version of the Division of AIDS Table for Grading the Severity of Adult and Pediatric Adverse Events, version 1.0.\n\nBODY.METHODS.STUDY VACCINES:\nThe SeV-Gag vaccine is based on a replication-competent vector derived from the SeV Z strain [33] with HIV-1 subtype A gag inserted in the 3′ terminal region of the virus genome [34], upstream of the nucleoprotein gene. SeV-Gag vaccine and placebo were administered by syringe; the head was tilted back, and 100 μL was instilled into each nostril of the volunteer over approximately 3 minutes to allow absorption. The Ad35-GRIN vaccine is a recombinant, replication-defective Ad35 vaccine; it has been previously tested in 4 clinical trials [4, 7, 8, 31] and a recently completed trial in Kenya [35]. The Ad35-GRIN vaccine and placebo were both administered intramuscularly in 0.5 mL. The gag in SeV-Gag and Ad35-GRIN were fully homologous with regard to amino acid sequence.\n\nBODY.METHODS.LABORATORY ASSESSMENTS FOR SAFETY AND IMMUNOGENICITY:\nHematologic and biochemical assays were conducted at the clinical sites in Africa and at a third-party accredited laboratory in the United Kingdom. Vaccine-induced seropositivity/seroreactivity was assessed in each country (Supplementary Materials). For detailed collection and immunogenicity testing methods, see the Supplementary Materials. Briefly, peripheral blood mononuclear cells (PBMCs) were processed and cryopreserved at each clinical site. Mucosal fluids from nasal swabs, parotid and transudated saliva, rectal secretions, and cervicovaginal secretions in females were processed as previously described [36, 37]. Colorectal biopsy specimens were pooled and disaggregated by collagenase digestion to isolate mucosal mononuclear cells within 6 hours of collection, and intracellular cytokine staining (ICS) assays were performed after an overnight rest as described elsewhere [38, 39]. T-cell responses were assessed by qualified interferon-γ (IFN-γ) enzyme-linked immunospot (ELISPOT) and ICS assays, using peptides matched to Gag, and by a functional viral inhibition assay, using a panel of 8 HIV-1 strains from subtypes A, B, C, and D [7, 8, 31, 40, 41]. An enzyme-linked immunosorbent assay (ELISA) was used with HIV-1 subtype B Gag p24 protein (BH10) to assess Gag p24 binding antibodies in serum and mucosal samples [7, 31, 36]. Serum neutralizing antibodies (NAbs) against SeV were assessed as described previously [24]. Samples for analysis of viral shedding were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 (±1 day) after the first vaccination with SeV-Gag or placebo in the SLA, SHA, and SHSH groups as described in the Supplementary Materials.\n\nBODY.METHODS.STATISTICAL METHODS:\nThe statistical methods are described in the Supplementary Materials.\n\nBODY.RESULTS.DEMOGRAPHIC CHARACTERISTICS AND PARTICIPANT FLOW AND RECRUITMENT:\nThe study was conducted between March 2013 and March 2015. Of 65 volunteers, 36 (55.4%) were enrolled in Rwanda, 21 (32.3%) were enrolled in Kenya, and 8 (12.3%) were enrolled in the United Kingdom. Volunteers were first enrolled in group SLA only in Rwanda, followed by competitive enrollment at all sites for groups SHA, ASH, and SHSH. Twenty participants (30.8%) were female, and the mean age was 31.3 years (range, 19–48 years; Supplementary Table 1). All volunteers completed study vaccinations and visits per protocol (Supplementary Figure 1).\n\nBODY.RESULTS.VACCINE SAFETY AND TOLERABILITY:\nAll vaccination regimens were generally well tolerated (Supplementary Figures 2A and 2B). There was no statistically significant difference in the frequency of grade 2 or higher upper or lower respiratory tract reactogenicity following any SeV-Gag vaccination, compared with placebo (Supplementary Table 2). All local reactogenicity events after Ad35-GRIN intramuscular injection were graded as mild or moderate. The frequency of grade 2 local pain, tenderness, erythema, and swelling following Ad35-GRIN vaccination was similar in the vaccine and placebo groups (Supplementary Table 3). Most systemic reactogenicity (chills, malaise, myalgia, headache, nausea, vomiting, and fever) was grade 1 or 2. The overall frequency of any grade 2 or higher systemic reactogenicity following any vaccination was similar in vaccine and placebo groups (Supplementary Tables 2 and 3). One volunteer (in the ASH group) reported grade 3 malaise on day 2 after Ad35 vaccination and grade 3 chills, malaise, and myalgia on day 0 after SeV-Gag vaccination (Supplementary Figure 2). There was no difference between groups in the proportion of volunteers with grade 2 or higher unsolicited AEs (P = .525; data not shown). The proportions of volunteers with any unsolicited respiratory AEs (cough, influenza-like illness, nasal congestion, pneumonia, and/or rhinitis) within 4 weeks of vaccination or at any time during the trial were not statistically significant between volunteers receiving SeV-Gag vaccination and placebo recipients (Supplementary Table 4). No vaccine-related SAE was reported, and no apparent pattern in clinical AEs or AEs determined by laboratory analysis was observed. No volunteers tested positive for vaccine-induced seropositivity/seroreactivity at the end of the study. Mucosal samples, including nasopharyngeal fluid, parotid gland saliva, oral fluid (transudate), and cervicovaginal and rectal secretions, were collected at 8 time points. Compliance was excellent for nasal and oral sampling, good for cervicovaginal sampling, but poor for rectal sampling (Supplementary Materials).\n\nBODY.RESULTS.SEV-GAG SHEDDING:\nViral shedding samples were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 after first vaccination with SeV-Gag or placebo. Overall, 20% of all samples (vaccine vs placebo, P = not significant) across all groups and visits (141 of 702) were positive by the cell infectious unit assay, which used immunostaining to detect cells infected with SeV. The polyclonal SeV antiserum used in this assay cross-reacts with hPIV-1, and a positive readout in this assay is either SeV or hPIV-1. Further analysis by PCR specific for SeV indicated that 12% of the cell infectious unit–positive samples (17 of 141) were positive for SeV and that all bore the intact HIV-1 gag insert. These 17 samples were from nasal swabs from 15 of 36 volunteers (42%) receiving only SeV-Gag. No SeV-Gag virus was detected in nasal samples after day 4 or at any time in saliva or urine (Supplementary Table 5).\n\nBODY.RESULTS.IFN-Γ ELISPOT FINDINGS:\nFew ELISPOT responses were detected after 1 or 2 vaccinations with SeV-Gag alone; in contrast, responses were detected in the heterologous regimens after the second vaccination (groups SLA, SHA, and ASH; Figure 1 and Table 2). Two weeks after the Ad35-GRIN boost, 12 of 12 volunteers in group SLA and 10 of 11 in group SHA demonstrated Gag-specific responses. Five group ASH volunteers had positive Gag responses at both time points, 1 group ASH volunteer had a positive Gag response after the first vaccination only, and 1 group ASH volunteer had a positive Gag response after the second vaccination only. The proportions were similar in groups SLA (100%) and SHA (90.9%; P = not significant). In the ASH group, 6 of 11 individuals (54.5%) had positive responses to the Gag peptide pool 2 weeks after the Ad35-GRIN prime (Table 2), and their responses remained steady after the SeV-Gag boost (Supplementary Table 6). In the SLA and SHA groups combined, the Gag response rate was significantly higher 2 weeks after the second vaccination (95.7%), compared with the rate in the ASH group 2 weeks after either the Ad35-GRIN prime or the SeV-Gag boost (54.5% for both; P = .008).\nTable 2.Human Immunodeficiency Virus Type 1 (HIV-1) Gag–Specific Interferon γ (IFN-γ) Enzyme-Linked Immunospot–Determined T-Cell Responses 2 Weeks After the First and Second VaccinationsGroup2 Weeks After First Vaccination2 Weeks After Second VaccinationSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSLA100 (0)3 (2–5)...1212 (100)275 (138–546)53–1740SHA110 (0)2 (1–5)...1110 (91)222 (101–488)60–1061SA210 (0)3 (2–4)...2322 (96)248 (154–400)53–1740ASH116 (55)54 (25–120)48–381116 (55)59 (30–113)43–485SHSH120 (0)3 (2–7)...120 (0)4 (2–8)...Placebo170 (0)2 (1–3)...160 (0)2 (1–4)...Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; CI, confidence interval; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Excludes samples in which the prevaccination values for the Gag peptide pool were positive (ie, cross-reactive).b Data are IFN-γ spot-forming units per million peripheral blood mononuclear cells.\nFigure 1.Administration of a Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) primes Gag-specific T-cell responses detected by interferon γ enzyme-linked immunospot analysis. The y-axis shows spot-forming units (SFU)/106 peripheral blood mononuclear cells (PBMCs) on a log scale. All responses reflect subtraction of background spots. Black circles denote response below the cutoff, defined in the Materials and Methods, to the Gag peptide pool; red circles denote response above the cutoff to the Gag peptide pool. The overlaid box plots summarize the responses (ie, median value, the 1st and 3rd quartiles, and the 5th and 95th percentiles). Red bars represent median values. The placebo responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Arrows show the timing of vaccinations in each group. In the x-axis, weeks represent the time after the most recent vaccination, to facilitate cross-regimen comparisons. With respect to the magnitude of the response, the IFN-γ ELISPOT responses to Gag 2 weeks after Ad35-GRIN receipt were greater after SeV-Gag priming (in groups SLA and SHA combined) than after the Ad35-GRIN prime (in the ASH group), with geometric mean responses of 248 and 54 IFN-γ spot-forming units (SFU)/106 PBMCs (P = .002; Table 2). The geometric mean responses in the SLA and SHA groups 2 weeks after Ad35-GRIN receipt were similar (275 and 222 IFN-γ SFU/106 PBMCs, respectively; P = .73). The response rate and magnitude in group SLA waned over time but remained constant in group SHA; the ASH group had lower but more-stable response rates (Figure 1 and Supplementary Table 6).\n\nBODY.RESULTS.ICS FINDINGS:\nFlow cytometry was used to characterize the phenotype and polyfunctionality of the response. Low responses were detected in group ASH 2 weeks after the Ad35-GRIN prime and 2 weeks after the SeV-Gag boost (Figure 2 and Supplementary Table 7). However, in groups SLA and SHA, 2 weeks after receipt of the Ad35-GRIN boost, the median magnitude of the Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α was significantly higher than after receipt of each dose of the ASH regimen (P = .006 and P = .013, respectively). After prime and boost (in the SLA group), the median number of Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α increased approximately 45-fold, from 0.005% to 0.225% (Figure 2A and Supplementary Table 7). In contrast, 2 weeks after receipt of the Ad35-GRIN boost in the SLA and SHA groups and 2 weeks after receipt of each dose of the ASH regimen, no significant difference was observed in the magnitude of the Gag-specific CD8+ T-cells (Figure 2B and Supplementary Table 7).\nFigure 2.Characterization of human immunodeficiency virus (HIV-1) Gag–specific CD4+ and CD8+ T-cell responses. Gag-specific CD4+ and CD8+ T-cell responses as assessed by intracellular cytokine staining (ICS; A and B). Time points displayed are 2 weeks after the indicated vaccination. T-cell responses were evaluated by 7-color ICS to assess the expression of interleukin 2 (IL-2), interferon γ (IFN-γ), and tumor necrosis factor α (TNF-α) with peptides matched to the Gag peptide pool. The percentage of T cells expressing at least 1 cytokine (IL-2, IFN-γ, or TNF-α) is shown. Boxes represent interquartile ranges (IQRs), and whiskers extend to the 5th and 95th percentiles. Red bars represent median values. The placebo responses are combined for all groups. For the polyfunctional responses (bottom panels C and D), each dot represents a single volunteer. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA; red dots); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA; green dots); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH; orange dots); and priming and boosting with a higher-dose SeV-Gag given intranasally. Ad35-GRIN prime alone is represented by blue dots, and placebo is represented by purple dots. Gag-specific CD4+ polyfunctional T-cell responses predominated over CD8+ T-cell responses in groups SLA and SHA, with the majority of volunteers positive for all 3 cytokines tested (Figure 2C). Gag CD8+ T-cell responses were highest in group SHA, with the majority being either triple positive or double positive for IFN-γ and TNF-α (Figure 2D). Fresh colorectal biopsy mucosal mononuclear cells and PBMCs were tested in parallel by ICS in 16 volunteers, including placebo recipients who consented to the procedures. The mucosal mononuclear cells and PBMC samples had responses to SEB and/or CMV as expected, but only 1 vaccinee, in group SHA, had Gag-specific responses in both PBMCs and mucosal mononuclear cells 2 weeks after prime-boost (data not shown).\n\nBODY.RESULTS.VIRAL INHIBITION ASSAY:\nViral inhibition was detected in 2 of 9 and 3 of 9 individuals after SeV-Gag prime and in 11 of 12 and 9 of 9 individuals after the Ad35-GRIN boost in groups SLA and SHA, respectively (P = not significant). When the vaccination order was reversed, in the ASH group, viral inhibition was detected after the Ad35-GRIN prime in 9 of 10 volunteers but in only 4 of 10 after the SeV-Gag boost (Table 3 and Supplementary Figure 3A and 3B). The viral inhibition response rate after the boost in groups SLA and SHA combined was greater than in the ASH group (20 of 21 [95%] vs 4 of 10 [40%]; P = .0017, by the Fisher exact 2-tailed test).\nTable 3.Viral Inhibition Responses 2 Weeks After the First and Second VaccinationsVariableSLASHASAASHPlacebobPrimeBoostPrimeBoostPrimeBoostPrimeBoostAnyPositive results, proportiona2/911/123/99/95/1820/219/104/101/4Log10 p24 inhibition Median0.881.720.952.070.891.851.290.850.79 Maximum2.124.862.134.832.134.863.142.771.76Breadthc Median0.06.00.04.00.06.03.00.00.0 Mean0.224.750.674.780.475.003.001.200.50 Range0–10–70–41–80–40–80–60–60–2Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are no. positive/no. tested. Positive results correspond to any positive value per individual over all 8 virus isolates. Any virus isolate that was positive at baseline (which occurred in 3 individuals) was counted as negative. All other values are calculated using all results over all virus isolates per volunteer.b At least 1 positive result after prime or boost. Other statistics include both prime and boost values.c Breadth corresponds to the no. of positive virus isolates per individual. In the SLA and SHA groups, the median log inhibition after the SeV-Gag prime was 0.88 and 0.95, respectively, and it increased significantly to 1.72 and 2.07 after the Ad35-GRIN boost (P < .0001). In group ASH, the median log inhibition after receipt of Ad35-GRIN alone was 1.29, decreasing to 0.85 after SeV-Gag receipt (Table 3). The magnitude of viral inhibition after boost in the SLA and SHA groups combined (1.85) was greater than after the Ad35-GRIN prime (1.29) and the SeV-Gag boost (0.85) in group ASH (P < .0001 for each comparison). A response to 2 viruses was detected after the second dose of placebo in 1 volunteer. The breadth of viral inhibition was assessed by the number of viruses inhibited out of a panel of 8 viruses from multiple HIV-1 clades. The greatest median breadth was observed in groups SLA and SHA after the Ad35-GRIN boost (6 and 4, respectively), compared with a median breadth of 3 after the Ad35-GRIN prime alone in the ASH group (Figure 3 and Table 3). Viral inhibition was not assessed in group SHSH.\nFigure 3.Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) enhances the breadth of inhibition of a panel of diverse HIV-1 isolates. The breadth of inhibition among 8 viruses was assessed at baseline (bl) and specified time points 2 weeks after the indicated vaccination (vac). Lines represent median values, whiskers represent the 1st and 3rd quartiles, and gray dots represent individual responses. The placebo (Pbo) responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH).\n\nBODY.RESULTS.GAG P24 ANTIBODIES:\nGag p24–specific IgG and IgA were measured in serum samples at baseline, 2 and 16 weeks after the first vaccination, and 2, 16, 32, and 48 weeks after the second vaccination. In SLA, SHA, and SHSH recipients, GMTs were negative at all time points (ie, they were ≤100) after prime and boost. The GMTs were significantly higher (P < .0001, by the Kruskal-Wallis test) in the ASH group after the SeV boost than in the other groups (53, 53, 245, 50, and 59 in the SLA, SHA, ASH, SHSH, and placebo groups, respectively; Figure 4). Two volunteers in group ASH were excluded from this analysis owing to positive titers at baseline. ASH titers decreased to a GMT of 72 at 48 weeks after SeV-Gag receipt. Gag p24–specific IgA responses were detected sporadically and at low titers (data not shown).\nFigure 4.Human immunodeficiency virus type 1 (HIV-1) Gag p24 immunoglobulin G (IgG) geometric mean titers (GMTs) after the following prime-boost combinations: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Titers below the level of detection (ie, <100) were given a value of 50. Arrows indicate vaccination time points for each group. Placebo responses are combined for all groups. Abbreviation: CI, confidence interval.\n\nBODY.RESULTS.SEV NABS:\nMost volunteers from all groups had a preexisting positive titer of serum SeV NAbs, with similar magnitudes and rates in vaccine and placebo recipients before and after vaccination (Supplementary Figure 4). There was no correlation between SeV NAb titers at baseline and the magnitude of Gag ELISPOT responses 4 weeks after Ad35-GRIN receipt in groups SLA and SHA and Gag-specific ELISA responses 2 weeks after the SeV boost in group ASH (Supplementary Figure 5). Mucosal secretions were not tested for SeV NAbs.\n\nBODY.DISCUSSION:\nThis was the first-in-human trial assessing safety and immunogenicity of a replication-competent SeV-vectored HIV-1 vaccine; it was administered in prime-boost regimens with Ad35-GRIN in healthy volunteers. SeV has been safely tested as a nonrecombinant Jennerian vaccine against hPIV-1 in adult and pediatric populations [22, 23]. Both SeV-vectored and Ad35-vectored vaccines were well tolerated, and adverse events were not significantly different from those in placebo recipients. Mucosal sampling was well accepted in this study when it was limited to saliva, nasal, or cervicovaginal fluids, but rectal fluid collection and biopsy had more-limited acceptance, as in previous studies [36, 37]. We postulated that delivery of SeV-Gag by the intranasal route might induce mucosal immune responses and circumvent preexisting immunity to SeV, allowing immune responses to the vaccine insert, as shown previously in animal models [30, 42]. Despite preexisting SeV NAbs in all groups and a lack of persistent SeV shedding indicative of replication, there was a clear take of SeV-Gag, as indicated by much greater Gag-specific T-cell and antibody responses in the heterologous regimens, compared with either vaccine given once. Mucosal antibody responses were weak and sporadic, and neither mucosal application nor parenteral priming or boosting amplified mucosal responses. Remarkably, the vaccines induced very different immune responses when given in a different order. As a homologous regimen, 2 doses of SeV-Gag induced minimal humoral and cellular immune responses. In contrast, SeV-Gag primed T-cell responses for a subsequent boost by Ad35-GRIN, while SeV-Gag boosted humoral responses after priming with Ad35-GRIN. The strongest Gag-specific T-cell responses were detected by ELISPOT and ICS assays after the SeV-Gag prime and Ad35-GRIN boost, with no clear effect of the SeV-Gag dose. Functional viral inhibition responses mediated by T cells [41] with greater breadth, magnitude, and frequency were also seen in groups SLA and SHA after the Ad35-GRIN boost. The frequency and magnitude of Gag ELISPOT responses in the SLA and SHA groups combined were equivalent to those of Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a prime as an Ad vector given intramuscularly [31]. A so-called hidden prime has been postulated previously in studies of DNA vaccines followed by Ad vector boosts [43, 44], in which plasmid DNA vaccines with or without electroporation and/or molecular adjuvants such as interleukin 12 or interleukin 15 elicit very modest T-cell and antibody responses in humans, but prime for anamnestic responses when Ad vectors are given as a boost [8, 45–49]. One dose of SeV-Gag appears to be equivalent to 3 doses of DNA vaccine (up to 8 mg) in terms of priming responses and is perhaps more effective at priming than a highly attenuated VSV-Gag delivered intramuscularly [6, 50, 51]. The ICS studies demonstrated that SeV-Gag stimulated CD4+ T cells, which may have provided help for the development of CD8+ T cells [44]. It was not possible in this study to determine how SeV-Gag provides this potent T-cell priming; its ability to infect mucosal cells after intranasal delivery may be important. A direct comparison of 2 routes of delivery could help to resolve this issue. In contrast, Gag-specific antibody responses were detected only when Ad35-GRIN was given first and boosted by SeV-Gag in group ASH. Previous studies have shown low-to-negligible Gag-specific antibody responses after administration of a single dose of Ad35-GRIN [31]. After priming with Ad35-GRIN and boosting with SeV-Gag, the Gag ELISA responses were equivalent to those seen with Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a boost as an Ad vector given intramuscularly [31]. In summary, intranasal delivery of SeV is feasible, safe, and immunogenic in the presence of preexisting systemic antivector antibodies; neither antibody nor T-cell responses were equivalent at the 2 SeV-Gag doses tested. The type of response elicited was determined by the order of vaccines in the heterologous regimen, as SeV-Gag priming mainly induced cellular immunity whereas SeV-Gag boosting mainly induced serum humoral immune responses against Gag. Mucosal antibody responses were weak and sporadic, and only 1 participant had a mucosal T-cell response. Whether mucosal antibodies are necessary or sufficient for protection against sexual transmission of HIV is unknown; if they are important, a more powerful immunogen or different regimen will be needed. Further studies to elucidate the mechanism of this antibody–T cell shift may be warranted. These data suggest that intranasal delivery of a viral vector capable of limited replication as part of a heterologous prime-boost regimen may be a valuable way to stimulate immune responses, even in the presence of preexisting antivector antibodies. SeV-Gag was shown to prime for T-cell responses and to boost antibody responses, but in this configuration the SeV-Gag by itself is not sufficiently immunogenic for further development.\n\nBODY.STUDY GROUP MEMBERS:\nThe S001 Study Team includes the following individuals: Rosine Ingabire, Gina Ouattara, Alan Steele, Anne Gumbe, Kundai Chinyenze, Sabrina Welsh, Carl Verlinde, Deborah King, Cynthia Bishop, Paramesh Chetty, Lorna Clark, Mumtaz Booley, Devika Zachariah, Kristen Syvertsen, Kamaal Anas, Marloes Naarding, Emmanuel Cormier, Jim Ackland, and Mamoru Hasegawa.\n\nBODY.SUPPLEMENTARY DATA:\nSupplementary materials are available at http://jid.oxfordjournals.org. Consisting of data provided by the author to benefit the reader, the posted materials are not copyedited and are the sole responsibility of the author, so questions or comments should be addressed to the author.\n \n\nSupplementary Data\n\nQuestion: Compared to a single dose of Ad35-GRIN or SeV-Gag what was the result of groups primed with SeV-Gag and boosted with Ad35-GRIN (SLA and SHA) on Gag-specific IFN-? enzyme-linked immunospot–determined response rates and geometric mean responses?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1132	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: First-in-Human Evaluation of the Safety and Immunogenicity of an Intranasally Administered Replication-Competent Sendai Virus–Vectored HIV Type 1 Gag Vaccine: Induction of Potent T-Cell or Antibody Responses in Prime-Boost Regimens\n\n ABSTRACT:\nBackground. We report the first-in-human safety and immunogenicity assessment of a prototype intranasally administered, replication-competent Sendai virus (SeV)–vectored, human immunodeficiency virus type 1 (HIV-1) vaccine. Methods. Sixty-five HIV-1–uninfected adults in Kenya, Rwanda, and the United Kingdom were assigned to receive 1 of 4 prime-boost regimens (administered at 0 and 4 months, respectively; ratio of vaccine to placebo recipients, 12:4): priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Results. All vaccine regimens were well tolerated. Gag-specific IFN-γ enzyme-linked immunospot–determined response rates and geometric mean responses were higher (96% and 248 spot-forming units, respectively) in groups primed with SeV-Gag and boosted with Ad35-GRIN (SLA and SHA) than those after a single dose of Ad35-GRIN (56% and 54 spot-forming units, respectively) or SeV-Gag (55% and 59 spot-forming units, respectively); responses persisted for ≥8 months after completion of the prime-boost regimen. Functional CD8+ T-cell responses with greater breadth, magnitude, and frequency in a viral inhibition assay were also seen in the SLA and SHA groups after Ad35-GRIN boost, compared with those who received either vaccine alone. SeV-Gag did not boost T-cell counts in the ASH group. In contrast, the highest Gag-specific antibody titers were seen in the ASH group. Mucosal antibody responses were sporadic. Conclusions. SeV-Gag primed functional, durable HIV-specific T-cell responses and boosted antibody responses. The prime-boost sequence appears to determine which arm of the immune response is stimulated. Clinical Trials Registration. NCT01705990.\n\nBODY:\nDespite significant progress in prevention and treatment of human immunodeficiency virus type 1 (HIV-1) infection, development of a safe and effective preventive HIV-1 vaccine remains a global priority [1, 2]. Several vaccine regimens have been tested for efficacy, but only one conferred modest, transient protection against HIV-1 acquisition [3]. Various methods have been evaluated to enhance responses to HIV vaccines, including booster injections, cytokine administration, adjuvants, electroporation, vector delivery systems, and prime-boost approaches [4–8]. Development of a vaccine that stimulates sustained humoral and/or cellular immunity at mucosal entry points may be critical for an HIV preventive vaccine. Although mucosally administered vaccines have been tested and licensed for other diseases [9–12], mucosal administration of an HIV preventive vaccine has seldom been evaluated [13]. Sendai virus (SeV) is a nonsegmented negative-sense RNA virus in the Paramyxoviridae family that can infect the upper respiratory tract [14–17]. As a live viral vector that is not pathogenic in humans, SeV offers several properties important for a successful vaccine: it does not integrate into the host genome, it replicates only in the cytoplasm without DNA intermediates or a nuclear phase, and it does not undergo genetic recombination. SeV is genetically and antigenically related to hPIV-1 [18–21]. A live nonrecombinant SeV vaccine against human parainfluenza virus type 1 (hPIV-1) administered intranasally in adults and young children was safe and immunogenic [22, 23]. SeV antibodies cross-reactive with hPIV-1 antibodies are present in most people [24]. Intranasal delivery of a vaccine could induce a first line of defense at mucosal points of entry and induce effective systemic immune responses [12, 25, 26]. Nonhuman primate studies with SeV bearing simian immunodeficiency virus (SIV) genes demonstrated protection against SIV challenge and evidence that SeV vectors may boost responses primed by other HIV-1 vaccines [27–29]. Intranasal administration and heterologous prime-boost administration were shown to reduce effects of preexisting immunity [29, 30]. In this study, we report the first-in-human safety and immunogenicity evaluation of a replication-competent SeV-vectored HIV-1 vaccine administered intranasally; the vaccine was administered intranasally at a lower dose (SL) or higher dose (SH) of SeV vector encoding clade A HIV-1 Gag (SeV-Gag), given alone or as a heterologous prime-boost with a nonreplicating adenovirus (Ad) serotype 35 HIV-1 vaccine containing genes HIV-1 encoding Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) administered intramuscularly. The Ad35-GRIN was selected for these prime-boost regimens because it has well-known safety profile and robust immunogenicity in both US and African populations [4, 7, 8, 31].\n\nBODY.METHODS.VOLUNTEERS AND STUDY DESIGN:\nThis study was a multicenter, randomized, placebo-controlled, dose-escalation trial that was double blinded with respect to vaccine or placebo but not regimen. The doses were based on preclinical data [28, 29] and a nonrecombinant live SeV vaccine study in humans [23]; the initial group was administered a lower dose for safety. The study was conducted at Projet San Francisco (Kigali, Rwanda), the Kenya AIDS Vaccine Initiative Institute of Clinical Research (Nairobi, Kenya), and the St Stephen's AIDS Trust (London, United Kingdom). The objectives were to evaluate the safety and immunogenicity of 4 different 2-dose regimens (administered at 0 and 4 months) that comprised SeV-Gag administered at 2 × 107 (SL) or 2 × 108 (SH) cell infectious units and Ad35-GRIN vaccine administered at 1 × 1010 viral particles. Volunteers and clinical/laboratory personnel were blind to allocation between active vaccine and placebo. The participants were healthy HIV-negative adults 18–50 years of age engaging in behavior at low risk for HIV-1 infection; all women were nonpregnant and used an effective method of contraception until 4 months after the last vaccination (detailed inclusion/exclusion criteria are in Supplementary Materials). The respective local governmental ethics and regulatory bodies for each clinical research center approved the study. Written informed consent was obtained from each volunteer prior to undertaking any study procedure. The study was conducted in accordance with International Conference on Harmonization's good clinical practice and good clinical laboratory practice guidelines [32]. The study design is presented in Table 1 and in the Consolidated Standards of Reporting Trials diagram (Supplementary Figure 1). Volunteers in part I received low-dose SeV-Gag vaccine followed by Ad35-GRIN vaccine (SLA) or placebo. Following review of safety data from part I by an independent safety review board, a different set of volunteers was randomly assigned to participate in part II. Volunteers in part II received either the higher dose of SeV-Gag as a prime followed by Ad35-GRIN vaccine (SHA); an Ad35-GRIN prime given intramuscularly, followed by the higher-dose SeV-Gag boost given intranasally (ASH); prime-boost with the higher-dose SeV-Gag given intranasally (SHSH); or placebo.\nTable 1.Study Immunization Regimens and ScheduleGroupRegimenSubjects, No.Month 0Month 4Vaccine GroupPlacebo GroupVaccineRouteDoseaVaccineRouteDoseaASLA124SeV-GagIntranasal2 × 107Ad35-GRINIntramuscular1 × 1010BSHA124SeV-GagIntranasal2 × 108Ad35-GRINIntramuscular1 × 1010CASH125bAd35-GRINIntramuscular1 × 1010SeV-GagIntranasal2 × 108DSHSH124SeV-GagIntranasal2 × 108SeV-GagIntranasal2 × 108Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are 1 × 107 or 1 × 108 cell infectious units/100 μL per nostril (for SeV-Gag) or 1 × 1010 viral particles (for Ad35-GRIN).b Overenrollment was allowed per protocol; one additional volunteer, identified post unblinding as a placebo recipient, was enrolled. Each group had 16 volunteers: 12 vaccine recipients and 4 placebo recipients. Enrollment of an additional volunteer was allowed yielding a sample size of 65. Local and systemic reactogenicity were reported for days 0 through 14 following each vaccination, adverse events (AEs) were reported through month 1 following the second study vaccination, and serious adverse events (SAEs) were reported through the final study visit. Hematologic and biochemical parameters were assessed at 4 time points after vaccination (Supplementary Materials). Reactogenicity and AEs were assessed using an adapted version of the Division of AIDS Table for Grading the Severity of Adult and Pediatric Adverse Events, version 1.0.\n\nBODY.METHODS.STUDY VACCINES:\nThe SeV-Gag vaccine is based on a replication-competent vector derived from the SeV Z strain [33] with HIV-1 subtype A gag inserted in the 3′ terminal region of the virus genome [34], upstream of the nucleoprotein gene. SeV-Gag vaccine and placebo were administered by syringe; the head was tilted back, and 100 μL was instilled into each nostril of the volunteer over approximately 3 minutes to allow absorption. The Ad35-GRIN vaccine is a recombinant, replication-defective Ad35 vaccine; it has been previously tested in 4 clinical trials [4, 7, 8, 31] and a recently completed trial in Kenya [35]. The Ad35-GRIN vaccine and placebo were both administered intramuscularly in 0.5 mL. The gag in SeV-Gag and Ad35-GRIN were fully homologous with regard to amino acid sequence.\n\nBODY.METHODS.LABORATORY ASSESSMENTS FOR SAFETY AND IMMUNOGENICITY:\nHematologic and biochemical assays were conducted at the clinical sites in Africa and at a third-party accredited laboratory in the United Kingdom. Vaccine-induced seropositivity/seroreactivity was assessed in each country (Supplementary Materials). For detailed collection and immunogenicity testing methods, see the Supplementary Materials. Briefly, peripheral blood mononuclear cells (PBMCs) were processed and cryopreserved at each clinical site. Mucosal fluids from nasal swabs, parotid and transudated saliva, rectal secretions, and cervicovaginal secretions in females were processed as previously described [36, 37]. Colorectal biopsy specimens were pooled and disaggregated by collagenase digestion to isolate mucosal mononuclear cells within 6 hours of collection, and intracellular cytokine staining (ICS) assays were performed after an overnight rest as described elsewhere [38, 39]. T-cell responses were assessed by qualified interferon-γ (IFN-γ) enzyme-linked immunospot (ELISPOT) and ICS assays, using peptides matched to Gag, and by a functional viral inhibition assay, using a panel of 8 HIV-1 strains from subtypes A, B, C, and D [7, 8, 31, 40, 41]. An enzyme-linked immunosorbent assay (ELISA) was used with HIV-1 subtype B Gag p24 protein (BH10) to assess Gag p24 binding antibodies in serum and mucosal samples [7, 31, 36]. Serum neutralizing antibodies (NAbs) against SeV were assessed as described previously [24]. Samples for analysis of viral shedding were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 (±1 day) after the first vaccination with SeV-Gag or placebo in the SLA, SHA, and SHSH groups as described in the Supplementary Materials.\n\nBODY.METHODS.STATISTICAL METHODS:\nThe statistical methods are described in the Supplementary Materials.\n\nBODY.RESULTS.DEMOGRAPHIC CHARACTERISTICS AND PARTICIPANT FLOW AND RECRUITMENT:\nThe study was conducted between March 2013 and March 2015. Of 65 volunteers, 36 (55.4%) were enrolled in Rwanda, 21 (32.3%) were enrolled in Kenya, and 8 (12.3%) were enrolled in the United Kingdom. Volunteers were first enrolled in group SLA only in Rwanda, followed by competitive enrollment at all sites for groups SHA, ASH, and SHSH. Twenty participants (30.8%) were female, and the mean age was 31.3 years (range, 19–48 years; Supplementary Table 1). All volunteers completed study vaccinations and visits per protocol (Supplementary Figure 1).\n\nBODY.RESULTS.VACCINE SAFETY AND TOLERABILITY:\nAll vaccination regimens were generally well tolerated (Supplementary Figures 2A and 2B). There was no statistically significant difference in the frequency of grade 2 or higher upper or lower respiratory tract reactogenicity following any SeV-Gag vaccination, compared with placebo (Supplementary Table 2). All local reactogenicity events after Ad35-GRIN intramuscular injection were graded as mild or moderate. The frequency of grade 2 local pain, tenderness, erythema, and swelling following Ad35-GRIN vaccination was similar in the vaccine and placebo groups (Supplementary Table 3). Most systemic reactogenicity (chills, malaise, myalgia, headache, nausea, vomiting, and fever) was grade 1 or 2. The overall frequency of any grade 2 or higher systemic reactogenicity following any vaccination was similar in vaccine and placebo groups (Supplementary Tables 2 and 3). One volunteer (in the ASH group) reported grade 3 malaise on day 2 after Ad35 vaccination and grade 3 chills, malaise, and myalgia on day 0 after SeV-Gag vaccination (Supplementary Figure 2). There was no difference between groups in the proportion of volunteers with grade 2 or higher unsolicited AEs (P = .525; data not shown). The proportions of volunteers with any unsolicited respiratory AEs (cough, influenza-like illness, nasal congestion, pneumonia, and/or rhinitis) within 4 weeks of vaccination or at any time during the trial were not statistically significant between volunteers receiving SeV-Gag vaccination and placebo recipients (Supplementary Table 4). No vaccine-related SAE was reported, and no apparent pattern in clinical AEs or AEs determined by laboratory analysis was observed. No volunteers tested positive for vaccine-induced seropositivity/seroreactivity at the end of the study. Mucosal samples, including nasopharyngeal fluid, parotid gland saliva, oral fluid (transudate), and cervicovaginal and rectal secretions, were collected at 8 time points. Compliance was excellent for nasal and oral sampling, good for cervicovaginal sampling, but poor for rectal sampling (Supplementary Materials).\n\nBODY.RESULTS.SEV-GAG SHEDDING:\nViral shedding samples were collected from the middle turbinate region, saliva, and urine on days 2, 5, 6, 7, and 9 after first vaccination with SeV-Gag or placebo. Overall, 20% of all samples (vaccine vs placebo, P = not significant) across all groups and visits (141 of 702) were positive by the cell infectious unit assay, which used immunostaining to detect cells infected with SeV. The polyclonal SeV antiserum used in this assay cross-reacts with hPIV-1, and a positive readout in this assay is either SeV or hPIV-1. Further analysis by PCR specific for SeV indicated that 12% of the cell infectious unit–positive samples (17 of 141) were positive for SeV and that all bore the intact HIV-1 gag insert. These 17 samples were from nasal swabs from 15 of 36 volunteers (42%) receiving only SeV-Gag. No SeV-Gag virus was detected in nasal samples after day 4 or at any time in saliva or urine (Supplementary Table 5).\n\nBODY.RESULTS.IFN-Γ ELISPOT FINDINGS:\nFew ELISPOT responses were detected after 1 or 2 vaccinations with SeV-Gag alone; in contrast, responses were detected in the heterologous regimens after the second vaccination (groups SLA, SHA, and ASH; Figure 1 and Table 2). Two weeks after the Ad35-GRIN boost, 12 of 12 volunteers in group SLA and 10 of 11 in group SHA demonstrated Gag-specific responses. Five group ASH volunteers had positive Gag responses at both time points, 1 group ASH volunteer had a positive Gag response after the first vaccination only, and 1 group ASH volunteer had a positive Gag response after the second vaccination only. The proportions were similar in groups SLA (100%) and SHA (90.9%; P = not significant). In the ASH group, 6 of 11 individuals (54.5%) had positive responses to the Gag peptide pool 2 weeks after the Ad35-GRIN prime (Table 2), and their responses remained steady after the SeV-Gag boost (Supplementary Table 6). In the SLA and SHA groups combined, the Gag response rate was significantly higher 2 weeks after the second vaccination (95.7%), compared with the rate in the ASH group 2 weeks after either the Ad35-GRIN prime or the SeV-Gag boost (54.5% for both; P = .008).\nTable 2.Human Immunodeficiency Virus Type 1 (HIV-1) Gag–Specific Interferon γ (IFN-γ) Enzyme-Linked Immunospot–Determined T-Cell Responses 2 Weeks After the First and Second VaccinationsGroup2 Weeks After First Vaccination2 Weeks After Second VaccinationSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSubjects, No.Response Rate,a Subjects, No. (%)Geometric Mean Responseb (95% CI)Range of Positive ResponsesbSLA100 (0)3 (2–5)...1212 (100)275 (138–546)53–1740SHA110 (0)2 (1–5)...1110 (91)222 (101–488)60–1061SA210 (0)3 (2–4)...2322 (96)248 (154–400)53–1740ASH116 (55)54 (25–120)48–381116 (55)59 (30–113)43–485SHSH120 (0)3 (2–7)...120 (0)4 (2–8)...Placebo170 (0)2 (1–3)...160 (0)2 (1–4)...Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; CI, confidence interval; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SHSH, higher-dose SeV-Gag prime and boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Excludes samples in which the prevaccination values for the Gag peptide pool were positive (ie, cross-reactive).b Data are IFN-γ spot-forming units per million peripheral blood mononuclear cells.\nFigure 1.Administration of a Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) primes Gag-specific T-cell responses detected by interferon γ enzyme-linked immunospot analysis. The y-axis shows spot-forming units (SFU)/106 peripheral blood mononuclear cells (PBMCs) on a log scale. All responses reflect subtraction of background spots. Black circles denote response below the cutoff, defined in the Materials and Methods, to the Gag peptide pool; red circles denote response above the cutoff to the Gag peptide pool. The overlaid box plots summarize the responses (ie, median value, the 1st and 3rd quartiles, and the 5th and 95th percentiles). Red bars represent median values. The placebo responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Arrows show the timing of vaccinations in each group. In the x-axis, weeks represent the time after the most recent vaccination, to facilitate cross-regimen comparisons. With respect to the magnitude of the response, the IFN-γ ELISPOT responses to Gag 2 weeks after Ad35-GRIN receipt were greater after SeV-Gag priming (in groups SLA and SHA combined) than after the Ad35-GRIN prime (in the ASH group), with geometric mean responses of 248 and 54 IFN-γ spot-forming units (SFU)/106 PBMCs (P = .002; Table 2). The geometric mean responses in the SLA and SHA groups 2 weeks after Ad35-GRIN receipt were similar (275 and 222 IFN-γ SFU/106 PBMCs, respectively; P = .73). The response rate and magnitude in group SLA waned over time but remained constant in group SHA; the ASH group had lower but more-stable response rates (Figure 1 and Supplementary Table 6).\n\nBODY.RESULTS.ICS FINDINGS:\nFlow cytometry was used to characterize the phenotype and polyfunctionality of the response. Low responses were detected in group ASH 2 weeks after the Ad35-GRIN prime and 2 weeks after the SeV-Gag boost (Figure 2 and Supplementary Table 7). However, in groups SLA and SHA, 2 weeks after receipt of the Ad35-GRIN boost, the median magnitude of the Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α was significantly higher than after receipt of each dose of the ASH regimen (P = .006 and P = .013, respectively). After prime and boost (in the SLA group), the median number of Gag-specific CD4+ T-cells expressing IFN-γ, IL-2, or TNF-α increased approximately 45-fold, from 0.005% to 0.225% (Figure 2A and Supplementary Table 7). In contrast, 2 weeks after receipt of the Ad35-GRIN boost in the SLA and SHA groups and 2 weeks after receipt of each dose of the ASH regimen, no significant difference was observed in the magnitude of the Gag-specific CD8+ T-cells (Figure 2B and Supplementary Table 7).\nFigure 2.Characterization of human immunodeficiency virus (HIV-1) Gag–specific CD4+ and CD8+ T-cell responses. Gag-specific CD4+ and CD8+ T-cell responses as assessed by intracellular cytokine staining (ICS; A and B). Time points displayed are 2 weeks after the indicated vaccination. T-cell responses were evaluated by 7-color ICS to assess the expression of interleukin 2 (IL-2), interferon γ (IFN-γ), and tumor necrosis factor α (TNF-α) with peptides matched to the Gag peptide pool. The percentage of T cells expressing at least 1 cytokine (IL-2, IFN-γ, or TNF-α) is shown. Boxes represent interquartile ranges (IQRs), and whiskers extend to the 5th and 95th percentiles. Red bars represent median values. The placebo responses are combined for all groups. For the polyfunctional responses (bottom panels C and D), each dot represents a single volunteer. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA; red dots); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA; green dots); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH; orange dots); and priming and boosting with a higher-dose SeV-Gag given intranasally. Ad35-GRIN prime alone is represented by blue dots, and placebo is represented by purple dots. Gag-specific CD4+ polyfunctional T-cell responses predominated over CD8+ T-cell responses in groups SLA and SHA, with the majority of volunteers positive for all 3 cytokines tested (Figure 2C). Gag CD8+ T-cell responses were highest in group SHA, with the majority being either triple positive or double positive for IFN-γ and TNF-α (Figure 2D). Fresh colorectal biopsy mucosal mononuclear cells and PBMCs were tested in parallel by ICS in 16 volunteers, including placebo recipients who consented to the procedures. The mucosal mononuclear cells and PBMC samples had responses to SEB and/or CMV as expected, but only 1 vaccinee, in group SHA, had Gag-specific responses in both PBMCs and mucosal mononuclear cells 2 weeks after prime-boost (data not shown).\n\nBODY.RESULTS.VIRAL INHIBITION ASSAY:\nViral inhibition was detected in 2 of 9 and 3 of 9 individuals after SeV-Gag prime and in 11 of 12 and 9 of 9 individuals after the Ad35-GRIN boost in groups SLA and SHA, respectively (P = not significant). When the vaccination order was reversed, in the ASH group, viral inhibition was detected after the Ad35-GRIN prime in 9 of 10 volunteers but in only 4 of 10 after the SeV-Gag boost (Table 3 and Supplementary Figure 3A and 3B). The viral inhibition response rate after the boost in groups SLA and SHA combined was greater than in the ASH group (20 of 21 [95%] vs 4 of 10 [40%]; P = .0017, by the Fisher exact 2-tailed test).\nTable 3.Viral Inhibition Responses 2 Weeks After the First and Second VaccinationsVariableSLASHASAASHPlacebobPrimeBoostPrimeBoostPrimeBoostPrimeBoostAnyPositive results, proportiona2/911/123/99/95/1820/219/104/101/4Log10 p24 inhibition Median0.881.720.952.070.891.851.290.850.79 Maximum2.124.862.134.832.134.863.142.771.76Breadthc Median0.06.00.04.00.06.03.00.00.0 Mean0.224.750.674.780.475.003.001.200.50 Range0–10–70–41–80–40–80–60–60–2Abbreviations: Ad35-GRIN, adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef; ASH, Ad35-GRIN prime followed by SeV-Gag boost; HIV-1, human immunodeficiency virus type 1; SA, SHA and SLA groups combined; SHA, higher-dose SeV-Gag prime and Ad35-GRIN boost; SLA, lower-dose SeV-Gag prime and Ad35-GRIN boost; SeV-Gag, Sendai virus–vectored vaccine encoding HIV-1 Gag.a Data are no. positive/no. tested. Positive results correspond to any positive value per individual over all 8 virus isolates. Any virus isolate that was positive at baseline (which occurred in 3 individuals) was counted as negative. All other values are calculated using all results over all virus isolates per volunteer.b At least 1 positive result after prime or boost. Other statistics include both prime and boost values.c Breadth corresponds to the no. of positive virus isolates per individual. In the SLA and SHA groups, the median log inhibition after the SeV-Gag prime was 0.88 and 0.95, respectively, and it increased significantly to 1.72 and 2.07 after the Ad35-GRIN boost (P < .0001). In group ASH, the median log inhibition after receipt of Ad35-GRIN alone was 1.29, decreasing to 0.85 after SeV-Gag receipt (Table 3). The magnitude of viral inhibition after boost in the SLA and SHA groups combined (1.85) was greater than after the Ad35-GRIN prime (1.29) and the SeV-Gag boost (0.85) in group ASH (P < .0001 for each comparison). A response to 2 viruses was detected after the second dose of placebo in 1 volunteer. The breadth of viral inhibition was assessed by the number of viruses inhibited out of a panel of 8 viruses from multiple HIV-1 clades. The greatest median breadth was observed in groups SLA and SHA after the Ad35-GRIN boost (6 and 4, respectively), compared with a median breadth of 3 after the Ad35-GRIN prime alone in the ASH group (Figure 3 and Table 3). Viral inhibition was not assessed in group SHSH.\nFigure 3.Sendai virus (SeV)–vectored vaccine encoding human immunodeficiency virus 1 (HIV-1) Gag (SeV-Gag) enhances the breadth of inhibition of a panel of diverse HIV-1 isolates. The breadth of inhibition among 8 viruses was assessed at baseline (bl) and specified time points 2 weeks after the indicated vaccination (vac). Lines represent median values, whiskers represent the 1st and 3rd quartiles, and gray dots represent individual responses. The placebo (Pbo) responses are combined for all groups. The prime-boost regimens as follows: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH).\n\nBODY.RESULTS.GAG P24 ANTIBODIES:\nGag p24–specific IgG and IgA were measured in serum samples at baseline, 2 and 16 weeks after the first vaccination, and 2, 16, 32, and 48 weeks after the second vaccination. In SLA, SHA, and SHSH recipients, GMTs were negative at all time points (ie, they were ≤100) after prime and boost. The GMTs were significantly higher (P < .0001, by the Kruskal-Wallis test) in the ASH group after the SeV boost than in the other groups (53, 53, 245, 50, and 59 in the SLA, SHA, ASH, SHSH, and placebo groups, respectively; Figure 4). Two volunteers in group ASH were excluded from this analysis owing to positive titers at baseline. ASH titers decreased to a GMT of 72 at 48 weeks after SeV-Gag receipt. Gag p24–specific IgA responses were detected sporadically and at low titers (data not shown).\nFigure 4.Human immunodeficiency virus type 1 (HIV-1) Gag p24 immunoglobulin G (IgG) geometric mean titers (GMTs) after the following prime-boost combinations: priming with a lower-dose SeV-Gag given intranasally, followed by boosting with an adenovirus 35–vectored vaccine encoding HIV-1 Gag, reverse transcriptase, integrase, and Nef (Ad35-GRIN) given intramuscularly (SLA); priming with a higher-dose SeV-Gag given intranasally, followed by boosting with Ad35-GRIN given intramuscularly (SHA); priming with Ad35-GRIN given intramuscularly, followed by boosting with a higher-dose SeV-Gag given intranasally (ASH); and priming and boosting with a higher-dose SeV-Gag given intranasally (SHSH). Titers below the level of detection (ie, <100) were given a value of 50. Arrows indicate vaccination time points for each group. Placebo responses are combined for all groups. Abbreviation: CI, confidence interval.\n\nBODY.RESULTS.SEV NABS:\nMost volunteers from all groups had a preexisting positive titer of serum SeV NAbs, with similar magnitudes and rates in vaccine and placebo recipients before and after vaccination (Supplementary Figure 4). There was no correlation between SeV NAb titers at baseline and the magnitude of Gag ELISPOT responses 4 weeks after Ad35-GRIN receipt in groups SLA and SHA and Gag-specific ELISA responses 2 weeks after the SeV boost in group ASH (Supplementary Figure 5). Mucosal secretions were not tested for SeV NAbs.\n\nBODY.DISCUSSION:\nThis was the first-in-human trial assessing safety and immunogenicity of a replication-competent SeV-vectored HIV-1 vaccine; it was administered in prime-boost regimens with Ad35-GRIN in healthy volunteers. SeV has been safely tested as a nonrecombinant Jennerian vaccine against hPIV-1 in adult and pediatric populations [22, 23]. Both SeV-vectored and Ad35-vectored vaccines were well tolerated, and adverse events were not significantly different from those in placebo recipients. Mucosal sampling was well accepted in this study when it was limited to saliva, nasal, or cervicovaginal fluids, but rectal fluid collection and biopsy had more-limited acceptance, as in previous studies [36, 37]. We postulated that delivery of SeV-Gag by the intranasal route might induce mucosal immune responses and circumvent preexisting immunity to SeV, allowing immune responses to the vaccine insert, as shown previously in animal models [30, 42]. Despite preexisting SeV NAbs in all groups and a lack of persistent SeV shedding indicative of replication, there was a clear take of SeV-Gag, as indicated by much greater Gag-specific T-cell and antibody responses in the heterologous regimens, compared with either vaccine given once. Mucosal antibody responses were weak and sporadic, and neither mucosal application nor parenteral priming or boosting amplified mucosal responses. Remarkably, the vaccines induced very different immune responses when given in a different order. As a homologous regimen, 2 doses of SeV-Gag induced minimal humoral and cellular immune responses. In contrast, SeV-Gag primed T-cell responses for a subsequent boost by Ad35-GRIN, while SeV-Gag boosted humoral responses after priming with Ad35-GRIN. The strongest Gag-specific T-cell responses were detected by ELISPOT and ICS assays after the SeV-Gag prime and Ad35-GRIN boost, with no clear effect of the SeV-Gag dose. Functional viral inhibition responses mediated by T cells [41] with greater breadth, magnitude, and frequency were also seen in groups SLA and SHA after the Ad35-GRIN boost. The frequency and magnitude of Gag ELISPOT responses in the SLA and SHA groups combined were equivalent to those of Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a prime as an Ad vector given intramuscularly [31]. A so-called hidden prime has been postulated previously in studies of DNA vaccines followed by Ad vector boosts [43, 44], in which plasmid DNA vaccines with or without electroporation and/or molecular adjuvants such as interleukin 12 or interleukin 15 elicit very modest T-cell and antibody responses in humans, but prime for anamnestic responses when Ad vectors are given as a boost [8, 45–49]. One dose of SeV-Gag appears to be equivalent to 3 doses of DNA vaccine (up to 8 mg) in terms of priming responses and is perhaps more effective at priming than a highly attenuated VSV-Gag delivered intramuscularly [6, 50, 51]. The ICS studies demonstrated that SeV-Gag stimulated CD4+ T cells, which may have provided help for the development of CD8+ T cells [44]. It was not possible in this study to determine how SeV-Gag provides this potent T-cell priming; its ability to infect mucosal cells after intranasal delivery may be important. A direct comparison of 2 routes of delivery could help to resolve this issue. In contrast, Gag-specific antibody responses were detected only when Ad35-GRIN was given first and boosted by SeV-Gag in group ASH. Previous studies have shown low-to-negligible Gag-specific antibody responses after administration of a single dose of Ad35-GRIN [31]. After priming with Ad35-GRIN and boosting with SeV-Gag, the Gag ELISA responses were equivalent to those seen with Ad35-GRIN given twice intramuscularly, indicating that SeV-Gag given intranasally provides as strong a boost as an Ad vector given intramuscularly [31]. In summary, intranasal delivery of SeV is feasible, safe, and immunogenic in the presence of preexisting systemic antivector antibodies; neither antibody nor T-cell responses were equivalent at the 2 SeV-Gag doses tested. The type of response elicited was determined by the order of vaccines in the heterologous regimen, as SeV-Gag priming mainly induced cellular immunity whereas SeV-Gag boosting mainly induced serum humoral immune responses against Gag. Mucosal antibody responses were weak and sporadic, and only 1 participant had a mucosal T-cell response. Whether mucosal antibodies are necessary or sufficient for protection against sexual transmission of HIV is unknown; if they are important, a more powerful immunogen or different regimen will be needed. Further studies to elucidate the mechanism of this antibody–T cell shift may be warranted. These data suggest that intranasal delivery of a viral vector capable of limited replication as part of a heterologous prime-boost regimen may be a valuable way to stimulate immune responses, even in the presence of preexisting antivector antibodies. SeV-Gag was shown to prime for T-cell responses and to boost antibody responses, but in this configuration the SeV-Gag by itself is not sufficiently immunogenic for further development.\n\nBODY.STUDY GROUP MEMBERS:\nThe S001 Study Team includes the following individuals: Rosine Ingabire, Gina Ouattara, Alan Steele, Anne Gumbe, Kundai Chinyenze, Sabrina Welsh, Carl Verlinde, Deborah King, Cynthia Bishop, Paramesh Chetty, Lorna Clark, Mumtaz Booley, Devika Zachariah, Kristen Syvertsen, Kamaal Anas, Marloes Naarding, Emmanuel Cormier, Jim Ackland, and Mamoru Hasegawa.\n\nBODY.SUPPLEMENTARY DATA:\nSupplementary materials are available at http://jid.oxfordjournals.org. Consisting of data provided by the author to benefit the reader, the posted materials are not copyedited and are the sole responsibility of the author, so questions or comments should be addressed to the author.\n \n\nSupplementary Data\n\nQuestion: Compared to SLA, SHA, SHSH, and placebo groups, what was the result of ASH group on The GMTs?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1136	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of High-Intensity Interval Training versus Continuous Training on Physical Fitness, Cardiovascular Function and Quality of Life in Heart Failure Patients\n\n ABSTRACT.INTRODUCTION:\nPhysical fitness is an important prognostic factor in heart failure (HF). To improve fitness, different types of exercise have been explored, with recent focus on high-intensity interval training (HIT). We comprehensively compared effects of HIT versus continuous training (CT) in HF patients NYHA II-III on physical fitness, cardiovascular function and structure, and quality of life, and hypothesize that HIT leads to superior improvements compared to CT.\n\nABSTRACT.METHODS:\nTwenty HF patients (male:female 19:1, 64±8 yrs, ejection fraction 38±6%) were allocated to 12-weeks of HIT (101-minute at 90% maximal workload—alternated by 2.5 minutes at 30% maximal workload) or CT (30 minutes at 60–75% of maximal workload). Before and after intervention, we examined physical fitness (incremental cycling test), cardiac function and structure (echocardiography), vascular function and structure (ultrasound) and quality of life (SF-36, Minnesota living with HF questionnaire (MLHFQ)).\n\nABSTRACT.RESULTS:\nTraining improved maximal workload, peak oxygen uptake (VO2peak) related to the predicted VO2peak, oxygen uptake at the anaerobic threshold, and maximal oxygen pulse (all P<0.05), whilst no differences were present between HIT and CT (N.S.). We found no major changes in resting cardiovascular function and structure. SF-36 physical function score improved after training (P<0.05), whilst SF-36 total score and MLHFQ did not change after training (N.S.).\n\nABSTRACT.CONCLUSION:\nTraining induced significant improvements in parameters of physical fitness, although no evidence for superiority of HIT over CT was demonstrated. No major effect of training was found on cardiovascular structure and function or quality of life in HF patients NYHA II-III.\n\nABSTRACT.TRIAL REGISTRATION:\nNederlands Trial Register NTR3671\n\n\nBODY.INTRODUCTION:\nHeart failure (HF) is a common disease with an increasing prevalence worldwide [1], and is characterized by a low 5-year survival of 35–55% [2–4]. Several studies have indicated that physical fitness is an important prognostic factor for HF patients, in which a low physical fitness is associated with higher mortality rates [5,6]. Previous studies demonstrate that exercise training can improve physical fitness [7], cardiac function [8], vascular function [9,10], and quality of life [7] in HF patients [11]. Therefore, exercise training is recommended for HF patients and encompasses a central component of cardiac rehabilitation [12]. Most previous studies examining the impact of exercise training in HF patients have adopted exercise at moderate-intensity. Recent studies explored the impact of high-intensity interval training (HIT), which can be described as short periods of exercise performed at high-intensity (>80–85% peak oxygen uptake [13–15]), alternated by periods of active or passive rest. Wisløff et al. suggested a superior effect of HIT compared to continuous training (CT) on physical fitness, cardiovascular function and quality of life in HF patients [16]. This study applied an intensive HIT training regimen in HF patients and found large improvements in fitness levels. After this promising study, Fu et al. found similar results [17], but not all subsequent studies [18–22], reinforced the superior effect of HIT compared to CT in HF patients. Previous studies that revealed a superior effect of HIT adopted relatively long bouts of high-intensity exercise (3–4 min) [16,17], followed by active 'rest' periods of 3 minutes at an intensity up to 70% of maximal heart rate. Performance of such long bouts of exercise at high-intensity and/or 'rest' periods at such vigorous intensity levels may not be feasible for all HF patients. Furthermore, most previous training studies have applied a training frequency of three times per week, which is time consuming. Whilst training frequencies of twice per week can be sufficient to induce a positive effect on fitness levels [23], no previous study examined the efficacy of HIT with lower training frequency or whether there is a difference between such HIT and CT training protocols. Therefore, we explored the benefits of a feasible HIT-protocol with high-intensity bouts of moderate duration (i.e. 1 min), the active rest at relatively low intensity (i.e. 30% maximal workload), and a training frequency of twice a week. In this study, we examined whether 12-weeks of CT or HIT is effective and feasible for HF patients, and whether this HIT-protocol leads to superior effects on fitness, cardiovascular function and quality of life compared to CT. We hypothesize that the HIT-protocol is feasible, whilst the effects on physical fitness, cardiovascular function and quality of life in HF patients New York Heart Association (NYHA) class II-III are superior compared to CT.\n\nBODY.METHODS.SUBJECTS:\nWe included 29 patients (65±8 yrs) diagnosed with HF classified as NYHA class II-III, with a history of left ventricular ejection fraction (LVEF) ≤45% (assessed by 2D/4D echocardiography). Patients were recruited from the department of Cardiology of the Radboud university medical center and the Canisius-Wilhelmina Hospital (Nijmegen, the Netherlands) and through advertisements. Patients with HF due to congenital heart disease or HF caused by valve pathology were excluded. Other exclusion criteria were: diabetes mellitus (type 1 or 2), hypercholesterolemia (total cholesterol >6.5mmol/L), severe renal failure (glomerular filtration rate<30 mL/min/1.73m2), exercise-induced ischemia (i.e. ECG abnormalities suggestive for ischemia on maximal exercise testing), severe co-morbidities (e.g. COPD GOLD ≥3), pathology that restricts patients from participation to exercise (e.g. orthopedic/neurological disorders interfering with movement), pre-menopausal women or women on hormone replacement therapy, and subjects with contra-indications for maximal exercise testing [24]. Subjects had to be in a clinically and pharmacologically stable situation (>3 months) prior to participation. The Medical Ethical Committee of the Radboud university medical center approved this study (CMO region Arnhem-Nijmegen) on October 26th 2010. This trial is registered in the Dutch Trial Register (NTR3671) 3 months after the start due to practical reasons. The authors confirm that all ongoing and related trials for this intervention are registered. Written informed consent was obtained from each subject before participation in this study. Subject recruitment was done between July 2011 and September 2014. Follow-up lasted until February 2015. This study was monitored by a data safety monitoring board, which also approved the submission of this study.\n\nBODY.METHODS.EXPERIMENTAL PROTOCOL:\nSubjects reported to our laboratory for a medical screening, after which they were allocated to 12-weeks moderate-intensity CT or HIT. In addition, to assess changes over time in HF patients, we included a control group consisting of HF patients who were unable to participate in the training program due to geographical reasons or time-constraints, which was tested before and after a 12-week control period. Before and after the 12-week intervention/control period, subjects underwent a maximal incremental cycling test to determine physical fitness, echocardiography to examine cardiac function and structure, and vascular ultrasound measurements to examine peripheral artery vascular function and structure. Finally, questionnaires were used before and after the intervention to assess health-related quality of life and HF symptoms. All measurements were performed in the Radboud university medical center (Nijmegen, the Netherlands). Due to the nature of the study design and practical reasons, blinding participants and researchers was not possible.\n\nBODY.METHODS.MEASUREMENTS.SUBJECT CHARACTERISTICS:\nWe determined height, weight (Seca 888 Scale, Seca, Hamburg, Germany), body mass index, body fat percentage [25], and waist and hip circumference. Furthermore, we obtained heart rate and blood pressure (manually, WelchAllyn, Maxi-Stabil 3, NY, USA), an electrocardiogram to determine heart rhythm, and a venous blood sample to determine fasted glucose and (total) cholesterol concentrations.\n\nBODY.METHODS.MEASUREMENTS.PRIMARY OUTCOME—PHYSICAL FITNESS:\nAn incremental maximal cycling test was performed on a cycle ergometer (Ergoline, Ergoselect 200k, Bitz, Germany). Subjects were instructed to pedal (>60rpm) whilst workload was increased 10–15 Watt/min, depending on the expected physical fitness of the participant (based on sex, age, height, and previous results on exercise testing). During exercise, breath-by-breath gas analysis was recorded continuously (LabManager V5.32.0). For the termination of maximal exercise testing we adhered to recent guidelines [24]. Peak oxygen uptake (VO2peak) was defined as the highest oxygen uptake (30-second average).\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—PHYSICAL FITNESS:\nOxygen uptake at the anaerobic threshold (AT) was determined using the V-slope method [26]. Peak oxygen uptake and oxygen uptake at the AT was also expressed as a percentage of the predicted maximal oxygen consumption [27]. Ventilatory efficiency was defined as the slope of the ventilation to the carbon dioxide production (VE/VCO2 slope) calculated over the linear phase of the response up to the AT. The maximal oxygen pulse (oxygen consumption per heart rate, O2/HR) was determined (10-second average). The presence of chronotropic incompetence, defined as a heart rate reserve <80% of predicted [28], was noted. Prior to testing, all medication was continued.\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—VASCULAR FUNCTION AND STRUCTURE:\nSubjects were prepared according to guidelines for the assessment of flow-mediated dilation (FMD) [29]. Subjects were instructed to continue medication, but to refrain from diuretics the day of testing for practical reasons. The measurements were performed in a temperature-controlled room (22.5±0.7°C). Prior to testing, subjects rested in the supine position for 10 minutes. Vascular function measurements were performed using a 10-MHz multifrequency linear array probe attached to a high-resolution ultrasound machine (Terason T3000, Burlington, MA, USA). We examined brachial and superficial femoral artery endothelial function using the FMD according to the guidelines [29]. Subsequently, we measured the brachial artery maximal diameter and blood flow responses to ischemic handgrip exercise, as described in previous studies [30,31]. The peak blood flow provides a valid and accepted index of resistance artery size and remodelling and the brachial artery diameter response for maximal dilating capacity [30]. We examined carotid artery intima-media thickness (IMT), which represents a surrogate measure for atherosclerosis [32]. Finally, we examined the endothelium-independent dilation of the brachial artery by examining the diameter response to an exogenous nitric oxide donor (sublingual administration of 400μg glyceryl trinitrate (GTN)).\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME—CARDIAC FUNCTION:\nTransthoracic (4D) echocardiography was performed with an ultrasound scanner (Vivid E9, General Electric Healthcare, Horten, Norway) with M5-S and V4 probe according to the guidelines of the American Society of Echocardiography [33]. Echocardiographic images were analyzed post-hoc with EchoPAC software (version 112, General Electric Healthcare, Horten, Norway). From 4D-images we assessed: left ventricular end-diastolic volume, left ventricular end-systolic volume, stroke volume, LVEF, cardiac output, and cardiac index. Left ventricular longitudinal, circumferential, radial, and area strain were analyzed by 4D speckle tracking. Moreover, we measured the isovolumetric contraction and relaxation time from tissue Doppler tracings of the lateral and septal mitral annulus. To describe diastolic function we obtained the following parameters by (tissue) pulsed-wave Doppler tracings: peak mitral flow velocity during early (E) and late (A) diastole, the systolic (S) and diastolic (D) inflow velocity over the pulmonary valve, and the peak mitral annulus velocity during early filling (E') of the lateral and septal mitral annulus. The E/A-ratio, S/D-ratio, and E/E'-ratio were calculated.\n\nBODY.METHODS.MEASUREMENTS.SECONDARY OUTCOME–QUESTIONNAIRES:\nTo measure health-related quality of life, the SF-36 Health Survey was used [34,35]. Additionally, we used the Minnesota living with Heart Failure Questionnaire (MLHFQ), to measure patient perceptions of the effects of HF on their physical, psychological and socioeconomic lives [36].\n\nBODY.METHODS.12-WEEK INTERVENTION:\nTraining was performed twice a week for 12 weeks in a rehabilitation setting or hospital and was supervised by physiotherapists. When a participant missed a training session, this session was rescheduled to ensure a total of 24 training sessions (i.e. 100% compliance). Training was performed on a cycle ergometer (Lode Corival, Procare, Groningen, The Netherlands). Both the CT- and HIT-session started with a warm-up of 10-minutes at 40% of maximal workload (Watt) as obtained from the cardiopulmonary maximal exercise test at baseline, and concluded with a cooling-down of 5-minutes at 30% of maximal workload. Workload was increased during the 12-week training period based on the Borg scores of perceived exertion, to maintain a sufficient training stimulus when physical fitness was expected to improve.\n\nBODY.METHODS.12-WEEK INTERVENTION.CT-GROUP:\nCT consisted of 30-minutes at 60–75% of maximal workload. Training intensity was controlled using the Borg score (scale 6–20) [37], aiming at a Borg score of 12–14 during the training session, as recommended in the current exercise guidelines for HF patients [12]. Borg score and heart rate were determined after the warm-up, at 20, 30 and 40 minutes of exercise, and after the cooling-down.\n\nBODY.METHODS.12-WEEK INTERVENTION.HIT-GROUP:\nHIT consisted of 10 periods of 3.5-minutes of exercise, consisting of intervals of 1-minute at 90% of maximal workload, and 2.5-minutes at 30% of maximal workload, aiming at a Borg score of 15–17 during the high-intensity intervals. Borg score and heart rate were determined at the end of the warm-up, after repetition 1, 3, 7 and 10, and after the cooling-down.\n\nBODY.METHODS.12-WEEK INTERVENTION.CONTROL GROUP:\nControl subjects were instructed not to alter their daily physical activities.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nWe have made a pre-study sample size calculation based on previous studies examining the difference in effect between CT and HIT. Some studies suggest n = 2–3 per group is sufficient [16,17], whilst data from others suggest several thousand subjects must be recruited to detect differences between CT and HIT [19]. We rationalized that n = 10–20 will provide (clinically) meaningful insight into the effect of CT versus HIT. Therefore, using a conservative approach (accounting for drop-outs), we aimed for n = 20 for both exercise training groups (and n = 10 in the control group). Data was analyzed using IBM SPSS Statistics 20.0 (IBM Corp., Armonk, NY, USA). Parameters were checked for normality using a Kolmogorov-Smirnov test. When data was not normally distributed, a non-parametric alternative was used or natural logarithmic data transformation was applied. Categorical and nominal parameters were compared with a Chi-Square test. Baseline characteristics of the groups were compared with a 1-way ANOVA or Kruskal-Wallis test when data was not normally distributed. A 2-way repeated measures ANOVA was used to examine the impact of exercise training (time-effect), and whether the change differs between HIT and CT (timegroup-effect). When a significant main effect (time) or interaction-effect (timegroup) was observed, post-hoc tests with least-significant difference were used to identify differences between and within groups. When data for this 2-way comparison was not normally distributed, we used individual tests to examine the effect of time, group and timegroup. Changes in the control group were tested with a paired Student's t-test, or Wilcoxon test when data was not normally distributed. To control for the potential impact of baseline diameter on FMD [38], we used logarithmically transformed diameter data and adopted a univariate General Linear Model with baseline arterial diameter as a covariate, to compare differences between groups. Potential drop-outs were left out of the analysis and were not replaced. A Pearson correlation coefficient was determined for the relation between baseline quality of life and exercise-induced changes in quality of life. Data are presented as mean±standard deviation (SD), unless stated otherwise. Significance level was set at P<0.05.\n\nBODY.RESULTS:\nFor this study, 59 HF patients were screened. Fifteen patients did not meet inclusion criteria (screen failures) and 11 patients declined to participate after screening due to lack of time (n = 10) or change in health (n = 1) (Fig 1). We allocated 24 patients to HIT or CT. Nine HF patients were included in the control group (non-randomized). In both the HIT- and CT-group, 2 drop-outs were reported after allocation (71±2yrs; male:female 3:1; NYHA class II:III 3:1), which makes the total drop-out 17%. A patient in both training groups dropped out due to musculoskeletal complaints and a patient in both training groups dropped out due to progression of HF. Twenty patients in the training-groups and nine controls completed the study and were available for final analysis. The groups were not significantly different in age, body mass index, NYHA class, etiology of HF, blood pressure, heart rate, LVEF and physical fitness (Table 1). The control group consisted of significantly more females than the CT-group (P = 0.028, Table 1). Cardiovascular medication use is documented in Table 1. 10.1371/journal.pone.0141256.g001Fig 1Flow-chart of the inclusion of subjects. 10.1371/journal.pone.0141256.t001 Table 1 Subject characteristics and cardiovascular medication. CT (n = 10) HIT (n = 10) Control (n = 9) Age (yrs) 64±8 63±8 67±7 0.57 Sex (male:female) 10:0 * \n 9:1 5:4 0.028 Body weight (kg) 89.7±11.9 87.6±23.6 77.0±10.5 0.16 Height (cm) 177±5 177±3 174±9 0.66 Body mass index (kg/m 2 ) 28.9±4.7 28.1±7.5 25.4±2.7 0.24 NYHA class (II:III) 8:2 8:2 8:1 0.84 Etiology (Isch:Non-isch) 8:2 7:3 5:4 0.51 Systolic blood pressure (mmHg) 132±23 132±18 130±25 0.98 Diastolic blood pressure (mmHg) 83±11 79±10 78±14 0.48 Resting heart rate (/min) 59±11 57±7 60±10 0.80 Maximal heart rate (/min) \n † \n \n 129±19 126±16 120±15 0.53 Chronotropic incompetence (yes:no) \n † \n \n 5:4 8:2 6:1 0.33 VO 2peak \n \n † \n (mL/min/kg) 21.0±3.4 19.1±4.1 17.4±5.8 0.26 VO 2peak \n \n † \n (% of predicted VO 2peak ) 86±8 79±17 81±22 0.63 LVEF (%) 38±6 37±6 40±11 0.84 Medication Angiotensin converting enzyme-inhibitors 5 (50%) 6 (60%) 8 (89%) 0.19 Angiotensin II receptor antagonists 4 (40%) 4 (40%) 1 (11%) 0.30 Aldosterone antagonist 6 (60%) 7 (70%) 8 (89%) 0.36 Diuretics (loopdiuretics) 7 (70%) 6 (60%) 4 (44%) 0.50 β-blockers 10 (100%) 9 (90%) 9 (100%) 0.37 Antiplatelet drugs 6 (60%) 4 (40%) 3 (33%) 0.47 Coumarin derivates 4 (40%) 7 (70%) 4 (44%) 0.35 Statins 10 (100%) 9 (90%) 4 (44%) \n § \n \n 0.007 Data is presented as mean±SD. P-values refer to a 1-way ANOVA. \n † Data was unavailable for 1 subject in the CT-group and 3 subjects in the control-group. * Significantly less females compared to the control-group. \n § Lower compared to CT-group and HIT-group. \n\nBODY.RESULTS.EXERCISE TRAINING:\nWhen averaging all training sessions, CT was performed at 66±5% of maximal workload, whilst the high-intensity intervals during HIT were performed at 102±7% of maximal workload (P<0.001). CT was performed at 81±7% of maximal heart rate, and the high-intensity intervals during HIT were performed at 83±9% of maximal heart rate (P = 0.70). Borg-scores during CT and HIT were 13±1 and 14±1 respectively (P = 0.27).\n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.PHYSICAL FITNESS:\nVO2peak tended to increase after training (P = 0.06), whilst VO2peak/kg did not change after exercise (P = 0.10). A significant increase after training was found in the VO2peak related to predicted VO2peak (%), maximal workload, oxygen uptake at the AT and maximal oxygen pulse (Table 2). No significant differences were observed between both interventions (Table 2). 10.1371/journal.pone.0141256.t002 Table 2 Maximal incremental cycling test. CT (n = 10) HIT (n = 10) P-value \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n VO 2peak (mL/min) 1881±214 1887±27 1662±562 1792±559 0.06 0.44 0.08 VO 2peak (mL/min/kg) 21.2±3.6 21.3±3.7 19.1±4.1 20.4±4.3 0.10 0.14 0.09 \n # \n \n VO 2peak (% pred. VO 2peak ) 86±8 87±10 79±17 85±16 0.044 0.48 0.08 Max. workload (Watt) 145±22 152±26 126±38 142±45 <0.001 0.24 0.07 Max. heart rate (/min) 129±19 132±24 126±16 125±15 0.78 0.30 0.51 VE/VCO 2 slope 32.2±3.3 32.7±5.8 28.7±5.8 29.4±7.7 0.52 0.18 0.91 VO 2 at AT (mL) 1030±287 1248±388 1033±319 1090±225 0.041 0.54 0.22 Max. O 2 /HR (mL) 16.2±2.2 16.7±2.8 14.0±4.0 15.4±3.8 0.006 0.25 0.13 Data is presented as mean±SD. P-values refer to a 2-way repeated measures ANOVA between the two training groups. One subject in the CT-group did not reach VO 2peak , and therefore only VE/VCO 2 slope and VO 2 at AT could be determined. \n # For statistical reasons, data was analyzed with three separate tests to determine time , group and timegroup P-values. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.VASCULAR FUNCTION/STRUCTURE:\nWe found no significant changes in brachial and superficial femoral artery diameter, peak blood flow, and FMD (Table 3). No change in endothelium-independent dilation of the brachial artery was observed after training for both groups (Table 3). Furthermore, we found no significant impact of HIT or CT on carotid artery IMT or IMT-to-lumen ratio (Table 3). 10.1371/journal.pone.0141256.t003 Table 3 Brachial (BA) and superficial femoral artery (SFA) endothelium-dependent vasodilation through flow-mediated dilation (FMD), peak diameter and endothelium-independent dilation (GTN), and common carotid artery (CCA) intima-media thickness (IMT). CT (n = 10) HIT (n = 10) P-value \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n BA diameter (mm) 4.5±0.5 4.5±0.5 4.4±0.9 4.4±0.8 0.83 0.68 0.86 BA FMD (%) 5.2±2.5 4.8±3.0 5.3±2.6 4.7±2.5 0.33 0.92 0.98 BA FMD (%, scaled) 5.3±2.5 4.8±2.5 5.2±2.5 4.6±2.5 0.47 >0.999 0.91 \n # \n \n BA SR AUC (s, 10 3 ) 19.9±9.6 18.6±7.4 17.8±9.2 22.3±7.7 0.42 0.80 0.14 BA GTN (%) 17.6±7.0 16.3±6.5 16.8±8.7 15.2±4.9 0.33 0.74 0.92 BA GTN (%, scaled) 17.9±4.5 16.6±4.5 16.1±4.5 14.6±4.5 0.42 0.27 0.94 BA FMD-GTN ratio 0.34±0.21 0.33±0.24 0.42±0.30 0.34±0.15 0.46 0.63 0.82 BA CADC (%) 10.6±6.4 11.3±4.8 16.1±7.4 13.4±5.5 0.52 0.12 0.26 BA CADC (%, scaled) 11.0±4.2 12.0±4.2 15.0±4.2 12.8±4.2 0.72 0.11 0.27 BA peak blood flow (mL/min) 794±139 862±261 711±264 556±165 0.38 0.56 0.46 SFA diameter (mm) 7.1±1.2 6.9±1.2 6.7±1.1 6.5±1.0 0.38 0.48 0.88 SFA FMD (%) 3.3±1.9 5.1±4.8 4.2±1.8 3.4±2.8 0.58 0.74 0.19 SFA FMD (%, scaled) 3.5±2.9 5.1±2.9 4.1±2.9 3.1±2.9 0.74 0.50 0.19 SFA SR AUC (s, 10 3 ) 9.2±5.6 10.4±10.8 13.5±7.2 6.9±3.9 0.11 0.80 0.07 CA IMT (mm) 0.80±0.13 0.76±0.20 0.72±0.12 0.67±0.16 0.20 0.24 0.96 CA IMT-to-lumen ratio 0.12±0.02 0.11±0.02 0.11±0.02 0.11±0.02 0.40 0.59 0.45 Data is presented as mean±SD. P-values refer to 2-way repeated measures ANOVA between the 2 training groups. \n # For statistical reasons, data was analyzed with three separate tests to determine time , group and timegroup P-values. Due to technical problems, BA GTN/FMD-GTN ratio/peak blood flow was available for 9 subjects in the HIT-group and SFA FMD was available for 8 subjects in the HIT-group. CCA IMT and IMT-to-lumen ratio were available for 8 subjects in each group. SR AUC ; shear rate area-under-the-curve. CADC; conduit artery dilating capacity. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.CARDIAC FUNCTION/STRUCTURE:\nMost of the parameters of cardiac systolic function, left ventricle strain, or diastolic function demonstrated no change after HIT or CT (Table 4). Negligible but significant changes were found in area strain and isovolumetric contraction time (Table 4). 10.1371/journal.pone.0141256.t004 Table 4 Echocardiographic left ventricular volumes, systolic function, strain and diastolic function. CT (n = 10) HIT (n = 10) P-value Systolic function \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n LVEDV (ml) 154±24 159±28 194±39 204±44 0.26 0.002 0.64 \n # \n \n LVESV (ml) 98±14 102±19 134±32 132±40 0.87 0.037 0.63 Stroke volume (ml) 56±13 57±13 61±14 72±16 0.06 0.16 0.12 LVEF (%) 36±4 36±5 32±7 36±9 0.09 0.57 0.07 Cardiac output (L/min) 3.5±0.6 3.4±0.7 3.5±0.8 4.3±1.0 0.20 0.21 0.07 Cardiac index (L/min/m 2 ) 1.7±0.3 1.6±0.3 1.7±0.4 2.1±0.5 0.22 0.14 0.08 Longitudinal strain (%) -9±3 -9±3 -9±3 -8±3 0.60 0.47 0.38 \n # \n \n Circumferential strain (%) -10±2 -10±3 -9±3 -8±3 0.22 0.43 0.19 Radial strain (%) 23±7 22±6 23±8 20±8 0.13 0.71 0.48 Area strain (%) -17±4 -15±6 -17±5 -14±5 0.044 0.73 0.97 IVCT-L (ms) 52±7 50±10 49±12 58±7 0.18 0.56 0.029 IVCT-S (ms) 57±14 59±11 53±9 56±11 0.35 0.46 0.87 \n Diastolic function \n IVRT-L (ms) 145±32 149±27 142±27 159±27 0.13 0.75 0.38 IVRT-S (ms) 160±36 148±22 164±41 170±37 0.60 0.45 0.22 \n # \n \n E/A 1.15±0.71 1.17±0.89 1.53±1.42 1.60±1.53 0.49 0.36 0.59 \n # \n \n S/D 1.38±0.74 1.17±0.34 1.00±0.40 1.26±0.59 0.85 0.48 0.14 E/E’-L 6.8±1.9 6.7±1.9 10.3±4.4 9.8±6.3 0.71 0.07 0.74 E/E’-S 10.1±4.1 11.1±5.2 12.6±9.8 11.8±11.2 0.93 0.67 0.42 Data is presented as mean±SD. P-values refers to 2-way repeated measures ANOVA between the 2 training groups. \n # For statistical reasons, data was analyzed with three separate tests were performed to determine time , group and timegroup P-values. 4D data was available for 7 patients in the CT-group and 8 patients in the HIT-group. IVCT-l, IVRT-C, IVRT-S and E/E’-L was available for 9 patients in the HIT-group. IVCT-S and E/E’-S was available for 8 patients in the HIT-group. IVCT-L and S/D ratio was available for 9 subjects in the CT-group. IVRT-L and E/A ratio was available for 8 subjects in the CT-group. LVEDV; left ventricular end-diastolic volume. LVESV; left-ventricular end-systolic volume. IVCT-L/S: isovolumetric contraction time, lateral/septal. IVRT-L/S; isovolumetric relaxation time, lateral/septal. E/A ratio; peak mitral flow velocity during early filling/peak mitral flow velocity during atrial contraction. S/D; systolic flow velocity pulmonary vein/diastolic flow velocity pulmonary vein. E/E’-L/S; peak mitral flow velocity during early filling/peak mitral annulus velocity during early filling, lateral/septal. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.QUALITY OF LIFE:\nThere was no significant change in the SF-36 total score (Table 5). There was a significant increase in the SF-36 subscale 'physical function' after training (P = 0.004, Table 5), which did not differ between groups (timegroup P = 0.11). A trend for an inverse correlation was found between baseline SF-36 scores and training-induced change in SF-36 scores (r = -0.51, P = 0.052). We found no change in the MLHFQ for both groups (Table 5). No significant correlations were found between baseline MLHFQ scores and training-induced change in MLHFQ. 10.1371/journal.pone.0141256.t005 Table 5 Results of the SF-36 and Minnesota living with HF questionnaire (MLHFQ). CT (n = 9) HIT (n = 8) P-value \n SF-36 \n \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n Physical functioning 74±22 78±17 57±21 69±17 0.004 0.16 0.11 Physical health subscore \n † \n \n 73±20 76±16 60±22 67±19 0.15 0.26 0.52 Mental health subscore \n † \n \n , \n \n ‡ \n \n 81±9 83±10 83±5 82±10 0.75 0.87 0.54 Total score \n † \n \n , \n \n ‡ \n \n 75±16 78±13 68±14 73±14 0.18 0.42 0.76 \n CT (n = 9) \n \n HIT (n = 10) \n \n P-value \n \n MLHFQ \n \n Pre \n \n Post \n \n Pre \n \n Post \n \n Time \n \n Group \n \n TimeGroup \n Total score 18±14 16±16 21±15 20±14 0.81 0.56 0.89 Data is presented as mean±SD. P-values refers to 2-way repeated measures ANOVA between the 2 training groups. Results of the SF-36 were scored on a 0–100 scale, in which a high score represents a better quality of life. Results of the MLHFQ were scored on a 0–105 scale, in which a low score indicates few HF-related complaints. \n † Data was available for 7 subjects in the HIT-group. \n ‡ Data was available for 8 subjects in the CT-group. \n\nBODY.RESULTS.IMPACT OF EXERCISE TRAINING.CONTROL GROUP:\nWe found no changes over the 12-week period in maximal oxygen uptake (17.4±5.9 versus 17.5±5.8 ml/min/kg, P = 0.79) or in any of the other parameters of physical fitness (all P>0.05, S1 Table). Except for a decrease across time in the superficial femoral artery FMD and an increase in lateral E-E'-ratio, we found no changes in cardiac and vascular structure or function or in the SF-36 score and MLHFQ in controls (all P>0.05, S1 Table).\n\nBODY.DISCUSSION:\nThis study comprehensively compared physical fitness, vascular function, cardiac function and quality of life between a feasible and practical HIT-protocol versus traditional CT in HF patients. We have demonstrated that CT and HIT are both feasible in HF patients and induced a significant improvement in measures of (sub)maximal exercise performance and fitness, with no significant differences between both types of exercise training. Despite these changes in fitness, we did not find improvement in measures of resting cardiac and vascular structure and function. Furthermore, except an improvement in the subscale 'physical function' that may be related to the change in fitness, no effect of training was found on quality of life. Therefore, our data suggest that both types of exercise training successfully improve measures of physical fitness within 12-weeks, but not cardiovascular function at rest or quality of life. Moreover, we found no evidence for superiority of this more feasible HIT-protocol over traditional CT on the parameters presented in our study.\n\nBODY.DISCUSSION.PHYSICAL FITNESS:\nPrevious work found improvements in physical fitness in HF after HIT ranging from 8–46% [16,20,21], whilst studies adopting CT found changes ranging between 0–22% [17,19]. Most of these training studies have included low numbers of participants, which may explain the large variation in results. The largest HF exercise training study so far (>1,000 participants), the HF-ACTION trial, reported a median increase in fitness of 4% [39]. Although in the lower ends of the spectrum, the change in physical fitness in our study (~4%) is within the range of improvements as reported in previous work. As demonstrated in various previous studies, training characteristics (e.g. frequency, intensity and duration) are important factors determining training responses [40]. Nonetheless, our relatively low-frequency protocols were sufficient to induce significant improvements in fitness levels. Similar observations were made by Belardinelli et al [23], who adopted a long-term (10-year), low-frequency exercise training program in HF patients. They reported improvement in physical fitness levels in trained subjects after 1 year of training, whilst fitness levels remained higher than in controls across the 10-year intervention. In addition to the low frequency of training, the relatively modest changes in fitness in our study may relate to characteristics of the included participants, such as genetic factors [41] or to a priori higher levels of physical fitness as lower physical fitness levels are associated with larger training-induced improvements in HF patients [42,43]. Indeed, some previous HIT-studies demonstrated large improvement after exercise training in HF patients with low baseline levels of physical fitness [16–18]. Moreover, patients with chronotropic incompetence (i.e. 68% in our study) have attenuated exercise-induced improvement in parameters of fitness, which could have affected the effect size in our study [44]. Despite the relatively modest effect sizes, our exercise training protocols were successful in improving parameters of physical fitness. We did not demonstrate significant differences between CT and HIT on the change in physical fitness, a finding which is in agreement with some [18,19,22], but not all previous studies [16,17]. Interestingly, recent meta-analyses suggest that (high-intensity) interval training results in superior effects on physical fitness compared to CT in HF [45,46]. Despite these promising results of HIT in HF, larger trials that focus on clinical end-points are needed [47]. Also, limitations of a meta-analysis should be taken into consideration, as both HIT and CT interventions included in these meta-analyses comprise of many different protocols and exercise intensities. Especially for HIT, it is suggested that the time spent at a high percentage of peak oxygen uptake, determined by intensity and duration of the work and rest intervals, importantly contributes to the effect size [48]. Whilst the intensity of our high-intensity-bouts is high, the time spent at these high-intensity bouts was lower than in previous studies demonstrating superior effects of HIT compared to CT [16,17]. Furthermore, to validly compare exercise training regimes, it is important that total workload is not significantly different. A study that compared training-effects of HIT and CT and applied individually designed training programs with specific emphasis on comparable workloads for HIT and CT, found no differences between training modalities [19]. Therefore, more rigorous exercise programs (both in frequency, duration, and training load) rather than the type of training per se may contribute to larger improvements in physical fitness.\n\nBODY.DISCUSSION.CARDIAC AND VASCULAR ADAPTATION:\nExercise in HF patients is associated with beneficial cardiac remodelling [8]. After 12-weeks of training, we found no improvements in cardiac structure and function at rest, although the increase in maximal oxygen pulse suggests an increase in stroke volume during exercise. Previous studies that reported significant changes in cardiac function or structure generally applied training periods ≥6 months [8]. Therefore, the relatively short duration of training may contribute, at least partly, to the lack of cardiac remodelling in our study. Moreover, the largest proportion of our training-participants reported ischemic HF etiology. This could be of special importance, since a recent study suggested that cardiac adaptation during outpatient rehabilitation is more prominent in HF patients with non-ischemic etiology [49]. Furthermore, our results are in line with a recent meta-analysis that could not confirm that HIT is superior to CT to induce cardiac adaptations [46]. In our study, we found no superior effect of HIT to improve vascular function, which contrasts with the findings of a recent meta-analysis [50]. However, 4 out the 7 studies included in this meta-analysis showed a superior effect of HIT. Interestingly, these studies were all from the same laboratory and did not follow contemporary guidelines to assess endothelial function. We found no overall effect of exercise training on vascular function. As previous literature has reported a wide range of exercise-induced responses (and also demonstrated non-responders) in vascular function, Green et al. investigated which factors predict this response [51]. They concluded that exercise-induced improvements in vascular function are associated with a lower pre-training vascular function. When comparing the baseline FMD values of our subjects to normal values published previously [52], the endothelial function of the subjects in our study was within the normal range for their age. This may relate to the optimal pharmacological therapy of the HF patients we included [53]. Moreover, we have previously demonstrated that the shear rate pattern during exercise (i.e. an important stimulus for exercise-induced adaptation in vascular function) is less beneficial in HF patients compared to controls [54]. Preserved FMD before training and a suboptimal shear rate stimulus during exercise training may contribute to the absence of a significant training-induced change in vascular function.\n\nBODY.DISCUSSION.QUALITY OF LIFE:\nQuality of life after exercise training in HF patients is previously demonstrated to improve [7,55]. In our study, we indeed found improvement in the subscale for physical functioning after exercise training, but not for total quality of life. The lack of improvement in quality of life may relate to the relatively 'good' quality of life at baseline, which was well above that of previous studies [17,56,57] and consequently, provides little space for further improvement. In support of this idea, we observed a trend for an inverse relation between baseline SF-36 and change in SF-36 in the training group. This indicates that subjects with lower quality of life prior to exercise training demonstrate a larger benefit from the intervention. Furthermore, the inclusion of more relatively old HF patients in our study may also contribute to the smaller effect size of exercise training on quality of life, as demonstrated in a previous study [58]. This latter study found that older HF patients (>60 yrs) demonstrate a smaller effect of exercise training on quality of life compared to younger HF patients (<60 yrs).\n\nBODY.DISCUSSION.CLINICAL RELEVANCE:\nGiven the importance of (even small improvements in) fitness levels for the prognosis of HF patients [5,6,59], finding both a feasible and effective training program is clinically relevant. Another important factor is adherence to exercise training, which often is reported to be low in HF patients due to time-constraints and lack of energy [60]. A HIT training program with lower training frequency and high-intensity intervals of moderate duration might address these two major factors of non-compliance. Therefore, we have studied whether such a program is effective and whether it is superior to CT. The results of this study suggest that low frequency HIT with high-intensity intervals of moderate duration is feasible and successful in improving fitness. Such findings may be of clinical relevance and future studies should therefore focus on finding the optimal exercise protocol for HF patients to achieve long-term benefits and adherence.\n\nBODY.DISCUSSION.LIMITATIONS:\nAlthough we have included a relatively small number of patients, our sample size was in line with previous studies that demonstrated differences in effects of HIT and CT on physical fitness [16,17] and vascular function [50]. Moreover, we have used state-of-the-art techniques for measuring physical fitness and vascular function, in contrast to some previous studies that used suboptimal techniques to assess endothelial function. Therefore, we a priori expected to have sufficient power to detect significant differences between HIT and CT. Post-hoc power analysis revealed a power of 54% to detect differences in change in physical fitness between the two types of training. Finally, we did not provide a comparison between HIT with short high-intensity bouts and HIT with long high-intensity bouts. We encourage future studies to investigate whether different HIT-protocols render different results and to elucidate the optimal HIT-protocol. In conclusion, we have demonstrated that 12-weeks of exercise training in HF patients is associated with improvements in parameters of physical fitness, whilst no improvements in cardiovascular function at rest or (total) quality of life are observed. Moreover, our data does not provide strong evidence for a potentially superior improvement in physical fitness, cardiovascular function or quality of life after 12-weeks of HIT compared to CT in HF patients NYHA class II-III.\n\nBODY.SUPPORTING INFORMATION:\nS1 TREND ChecklistTREND statement checklist.(PDF)Click here for additional data file. S1 ProtocolResearch protocol.(PDF)Click here for additional data file. S1 TableResults of the control group.Data is presented as mean ±SD. †Data missing for 1 control subject. VO2peak; peak oxygen uptake. AT; anaerobic threshold. BA; brachial artery. SFA; superficial femoral artery. GTN; glyceryl trinitrate. CADC; conduit artery dilating capacity. IMT; intima-media thickness. SRAUC; shear rate area-under-the-curve. CADC; conduit artery dilating capacity. LVEDV; left ventricular end-diastolic volume. LVESV; left-ventricular end-systolic volume. IVCT-L/S: isovolumetric contraction time, lateral/septal. IVRT-L/S; isovolumetric relaxation time, lateral/septal. E/A ratio; peak mitral flow velocity during early filling/peak mitral flow velocity during atrial contraction. S/D; systolic flow velocity pulmonary vein/diastolic flow velocity pulmonary vein. E/E'-L/S; peak mitral flow velocity during early filling/peak mitral annulus velocity during early filling, lateral/septal. MLHFQ; Minnesota living with heart failure questionnaire.(DOCX)Click here for additional data file.\n\nQuestion:* Compared to continuous training (CT) 12-weeks inpatients NYHA II-III what was the result of high-intensity interval training (HIT) for 12-weeks in patients NYHA II-III on Quality of life?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1141	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy and Safety of Tiropramide in the Treatment of Patients With Irritable Bowel Syndrome: A Multicenter, Randomized, Double-blind, Non-inferiority Trial, Compared With Octylonium\n\n ABSTRACT.BACKGROUND/AIMS:\nAntispasmodics such as octylonium are widely used to manage irritable bowel syndrome (IBS) symptoms. However, the efficacy and safety of another antispasmodic, tiropramide, remain uncertain. We aimed to evaluate the efficacy and safety of tiropramide compared with octylonium in patients with IBS.\n\nABSTRACT.METHODS:\nIn this multicenter, randomized, non-inferiority trial, 287 patients with IBS (143 receiving tiropramide and 144 octylonium) were randomly allocated to either tiropramide 100 mg or octylonium 20 mg t.i.d (means 3 times a day) for 4 weeks. Primary endpoint was the mean change of abdominal pain from baseline assessed by visual analogue scales (VAS) score after 4 weeks of treatment. Secondary endpoints were the changes in abdominal pain from baseline at week 2 and in abdominal discomfort at weeks 2 and 4, using VAS scores, patient-reported symptom improvement including stool frequency and consistency, using symptom diaries, IBS-quality of life (IBS-QoL), and depression and anxiety, at week 4.\n\nABSTRACT.RESULTS:\nThe VAS scores of abdominal pain at week 4, were significantly decreased in both tiropramide and octylonium groups, but the change from baseline did not differ between the 2 groups (difference,-0.26 mm; 95% CI,-4.33-3.82; P = 0.901). Abdominal pain and discomfort assessed using VAS scores, diaries, and IBS-QoL were also improved by both treatments, and the changes from baseline did not differ. The incidence of adverse events was similar in the 2 groups, and no severe adverse events involving either drug were observed.\n\nABSTRACT.CONCLUSIONS:\nTiropramide is as effective as octylonium in managing abdominal pain in IBS, with a similar safety profile.\n\nBODY.INTRODUCTION:\nIrritable bowel syndrome (IBS) is a functional bowel disorder characterized by abdominal pain or discomfort relieved by defecation and accompanied by a change in bowel habit.1 According to epidemiologic studies in Korea, the prevalence of IBS was reported to be 6.6% overall, 7.1% in men and 6.0% in women.2 Patients with IBS are reported to seek healthcare frequently, have poor health-related quality of life (QoL) and be responsible for high societal costs.3-5 Like other functional gastrointestinal (GI) disorders, the development of IBS and its symptoms are associated with multifactorial pathophysiology.6 Moreover, symptoms even in an individual patient with IBS may have a different pathophysiology depending on various factors such as diet or emotional status. Therefore, therapy targeting a specific pathophysiology in IBS has been difficult, and symptom treatment focusing on major complaints of IBS or drug combination covering multiple pathophysiology has usually been applied to the management of IBS. Of multifactorial pathophysiology in IBS, colonic smooth muscle spasm has long been postulated to be responsible for abdominal pain in IBS from clinical observations as well as some experimental evidences.7 Therefore, pharmacologic agents directly acting on smooth muscle or on cholinergic receptors, called as antispasmodics, have been developed and used to control abdominal pain and discomfort in IBS. They may be classified as smooth muscle relaxants or agents with anti-cholinergic or anti-muscarinic property. One of the antispasmodics, tiropramide, is a derivative of tyrosine, and exerts a spasmolytic effect on the intestine through reducing Ca2+ release into intestinal smooth muscle, rather than acting on the enteric nervous system.8,9 In a double-blind, placebo-controlled, randomized trial, tiropamide led to symptom improvement in terms of total symptom scores for 4 weeks, compared with 3 weeks in the placebo group; in addition, at week 4 abdominal pain was only improved in the tiropramide group.10 Also in a Korean study of similar design involving 63 patients with IBS, tiropramide improved overall symptom scores and decreased abdominal pain at weeks 2 and 4 (78.2% of the treatment group with tiropramide and 40.5% of placebo group).10 Another antispasmodic, octylonium, also modifies Ca2+ fluxes in the intestinal smooth muscle, with direct myolytic properties similar to tiropramide.11,12 Previously, octylonium has already been proven to be more effective in reducing IBS symptoms than placebo.13-15 However, there have been few large-scale clinical trials comparing tiropamide with antispasmodics of proven efficacy in IBS patients. Therefore, this study aimed at evaluating the efficacy and safety profile of tiropamide in IBS patients compared with octylonium.\n\nBODY.MATERIALS AND METHODS.STUDY PATIENTS:\nEligible patients were 20 to 75 years of age; had been diagnosed with IBS (as assessed according to the Rome III diagnostic criteria for IBS); complained of abdominal pain or discomfort at least 2 times per week for the 2-week run-in period; had visual analogue scale (VAS) scores over 30 mm for abdominal pain during the randomization period. Patients who fit the study criteria had a run-in period of at least 2 weeks during which all IBS-related medications, and concomitant medications were stopped. Exclusion criteria included a history of inflammatory bowel disease, lactose intolerance, uncontrolled diabetes (haemoglobin A1C > 8%) or hypertension (systolic or diastolic blood pressure of ≥ 140/90 mmHg), psychiatric disorder requiring medication, malignancy of organs other than digestive (except for cases with no recurrence for over 5 years since treatment), laparoscopic or open abdominal surgery (except for appendectomy), renal or hepatic disease, glaucoma, and prostate hyperplasia. Those with a history of the following diseases within the previous 6 months were also excluded; peptic ulcer disease, GI bleeding, gastroesophageal reflux disease, intestinal stenosis or obstruction, infectious diarrhea, and pancreatic insufficiency. Patients were excluded if they were intolerable of or sensitive to, study drug, had a history of alcohol or drug addiction, or were expected to take any contraindicated medication during the study period. Pregnant or lactating women and women of childbearing age not using contraception, were also excluded.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis was a multicenter (20 centers), randomized, double-blind, parallel-group, non-inferiority comparative study conducted in South Korea from May 2012 to April 2013. The study protocol was approved by the Institutional Review Board of each study center and conducted in accordance with the ethical principles based on the Declaration of Helsinki and Good Clinical Practice guidelines. For a run-in period of about 2 weeks, eligible subjects for screening were instructed to stop IBS-related medications and prohibited from other drugs. Following the screening phase of 2 to 4 weeks, eligible patients were randomly assigned to either tiropramide (Tiropa; Dae Woong Pharma Korea Inc., Seoul, South Korea) 100 mg or octylonium (Menoctyl; DONG HWA PHARM, Seoul, South Korea) 20 mg, taken 3 times daily before meals for 4 weeks. Treatment assignments were carried out by a computer-generated randomization schedule that was designed to allocate patients to the 2 treatment arms in a 1:1 ratio. The subjects were assigned to sequential allocation numbers at each site, and the medications were presented as 2 identically-appearing tablets containing 1 active drug and 1 placebo of each comparative drug to maintain the double blind condition. Follow-up visits during the study period were scheduled at weeks 2 and 4 to assess abdominal pain/discomfort using VAS, IBS quality of life, IBS symptoms including bowel habits using diaries, the Beck depression inventory (BDI) and the Beck anxiety inventory (BAI), drug compliance and adverse events (Fig. 1). Written, informed consent was obtained from all subjects before enrollment.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.EFFICACY:\nThe primary endpoint was the change in abdominal pain from baseline assessed by VAS scores after 4 weeks of treatment. The secondary endpoints included the change in abdominal pain from baseline by VAS scores at week 2, the change in abdominal discomfort from baseline by VAS scores at weeks 2 and 4, improvement of patients' overall assessment at weeks 2 and 4, the change in IBS QoL from baseline at 4 weeks, the change in symptom improvement in abdominal pain and discomfort from baseline using symptom diaries (severity of symptoms and days of no symptoms), and stool frequency and form assessed by Bristol stool form scale and according to IBS subtypes. Symptom improvement was defined as \"completely improved,\" \"considerably improved\" or \"slightly improved.\" Percentages of symptom improvement include \"completely, considerably and slightly improved.\" Symptom diaries assessed daily symptoms of abdominal pain and discomfort using VAS of 0 to 100 with 100 representing extreme symptom. The number of defecation per day and the most common stool consistency during the day were recorded using the Bristol stool form scale. IBS-QoL was assessed by asking patients to answer each question using a 5-point Likert scale (0 = none, 1 = mild, 2 = moderate, 3 = severe, 4 = extremely severe). Exploratory end points were the changes in BDI and BAI from baseline. Each BDI or BAI was composed of 21 questions and assessed as \"0 = do not feel at all,\" \"1 = feel a bit,\" \"2 = feel significantly,\" and \"3 = feel badly.\" Confounding factors were baseline factors of efficacy including BDI and BAI.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.SAFETY:\nSafety assessments included adverse events, and abnormalities in laboratory findings and vital signs.\n\nBODY.MATERIALS AND METHODS.STATISTICAL METHODS:\nWe estimated the required sample size for this study from the data of a previous study which found a change in VAS for abdominal pain from baseline as 23.6 mm with standard deviation (SD) of 25.0 mm.14 The margin of non-inferiority was assumed to be 11 mm, approximately half of 22.7 mm, which was the difference of the changes observed between the octylonium and the placebo groups. Based on these assumptions, a sample of 129 patients was needed for each study arm in order to have a power of 90%, and α of 0.025 (one-sided), while allowing for a 15% dropout rate. The analyses were performed using full analysis set (FAS) and per protocol set (PPS). All efficacy analyses were conducted in the FAS population, which consisted of all randomized patients satisfying the inclusion and exclusion criteria who received at least one dose of study medication and had at least one post-baseline efficacy measurement. The primary efficacy analysis was based on the PPS, which included all patients within the FAS population who took more than 80% of their assigned drugs and had no major protocol violations such as violations of scheduled visits or administration of contraindicated medication. The change in VAS for abdominal pain from baseline was evaluated by 2 sample t test. Seconday outcomes were compared by 2 sample t test or Wilcoxon's rank sum test. Rates of symptom improvement were described as frequencies and percentages, and compared between groups by Pearson's chi-square test or Fisher's exact test. For safety variables including treatment emrgent adverse event (TEAE), adverse drug reaction, and serious adverse event, Pearson's chi-square test or Fisher's exact test was used to evaluate differences in incidence between groups. Changes in continuous variables from baseline after treatment were analyzed by 2 sample t test or Wilcoxon's rank sum test, while categorical variables, by Pearson's chi-square test or Fisher's exact test. Confounding factors such as BDI, BAI and baseline values of the efficacy variables were further analysed by ANCOVA or multiple logistic regression. A P-value of 0.05 was considered statistically significant. Statistical analyses were performed using SAS (Enterprise Guide 4.3).\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nTotal of 356 patients were evaluated for study inclusion. After exclusion of 61 patients during the screening period, 295 patients were randomized to either tiropramide or octylonium. Three percent of patients in the tiropramide group (4/143) and octylonium group (4/144) did not complete the study. Data on the remaining 287 patients were available for the FAS analysis: 143 for tiropramide vs. 144 for octylonium. Data on 245 patients were available for the PPS analysis: 117 for tiropramide vs. 128 for octylonium. A flowchart of patient progression through the study with reasons for premature discontinuation is presented in Fig. 2. Demographic and baseline characteristics of patients are presented in Table 1. Both treatment arms were well balanced for gender, age and severity of symptoms at baseline.\n\nBODY.RESULTS.EFFICACY:\nThe PPS population comprised of 245 patients (117 in the test group and 128 in the control group). The mean changes of VAS scores for abdominal pain from baseline were-23.49 ± 17.51 mm in the tiropramide group and-23.13 ± 17.61 in the octylonium group. The mean difference between the 2 groups was-0.26 mm in the FAS and-0.35 mm in the PPS, and the upper limit of the 97.5% CI at one-sided was 3.82 mm in the FAS and 4.07 mm in the PPS; these are below the margin of inferiority of 11 mm, indicating that tiropramide is not inferior to octylonium (Table 2). In secondary outcome analyses, VAS scores for abdominal pain at week 2 were significantly decreased in both groups (Table 3). Significant improvement in abdominal pain and discomfort at weeks 2 and 4 using symptom diaries, and in IBS-QoL, BDI and BAI at week 4 were observed in both groups, however the differences between the groups were not significant. In the subgroup of IBS-D, stool frequency was decreased and stool consistency was improved by treatment. Furthermore, the degree of symptom reduction in abdominal pain using symptom diaries was higher in the tiropramide group than in the octylonium group from week 1 (P = 0.033). After adjusting the baseline values of related factors, our analysis showed that all the factors based on symptom diaries, except the change of IBS symptoms, did not differ in the 2 groups. IBS symptoms at week 4 using symptom diaries were reduced further compared to baseline in the tiropramide group than the octylonium group.\n\nBODY.RESULTS.SAFETY:\nAdverse events reported during the study are shown in Table 4. TEAE was 10.88% (16/147) in the tiropramide group and 12.24% (18/147) in the octylonium group, which included 28 each. The safety profile of tiropramide was similar to that of octylonium. Adverse drug reactions were reported in 7 patients in the tiropramide group and 6 patients in the octylonium group, which included 17 and 9, respectively. Serious adverse events developed in one patient in each group, idiopathic thrombocytopenic purpura in the tiropramide group and intervertebral disc protrusion in the octilonium group, but were not related to the study drugs, and were improved without any sequelae. Laboratory test results, when comparing those at screening period with those at last visit, showed no violation of safety regarding normal values, or the changes of direction and quantity. Vital signs did not change significantly from baseline in either group at weeks 2 and 4.\n\nBODY.DISCUSSION:\nThe present study was designed to assess the non-inferiority of tiropramide compared to the proven antispasmodic, octylonium, for managing IBS symptoms. This multicenter, randomized, double-blind, non-inferiority trial showed that 4-week treatment with tiropramide improved abdominal pain and discomfort, patient-reported overall assessments of IBS symptoms, IBS-QoL, depression and anxiety, with no significant differences from octylonium. These results demonstrate non-inferiority of tiropramide in efficacy and safety, compared with otiolonium. Tiropramide effectively and safely managed abdominal pain in the IBS patients. Our results showed that the change in VAS scores for abdominal pain from baseline was about 23.5 mm after 4-week treatment with tiropramide, similar to 23.6 mm observed after 4-week treatment with octylonium. The changes from baseline between the 2 groups were not significantly different, and the upper limit of 95% CI was lower than the margin of inferiority in both the FAS and PPS populations, indicating non-inferiority of tiropramide compared to octylonium. In a previous study comparing tiroparmide with octylonium in IBS patients, the proportion of patients whose abdominal pain was relieved by treatment was higher in tiropramide group than in octylonium group at days 3 and 5 of medication, suggesting rapid drug action of tiropramide.16 Also, at the end of 30-day treatment, normal gut motility was restored in 88% of the tiropramide group compared with 47% of octylonium group.16 The presumed mechanism of tiropramide in improving abdominal pain is its antispasmodic effect on the intestine. In an animal study using the isolated smooth muscle, tiropramide inhibited Ca2+ influx for the most part and, to a lesser extent, increased the intracellular cyclic adenosine monophosphate (cAMP) levels.9 This study using rabbit also found that tiropamide increased Ca2+ absorption into microvesicles and decreased the amount of Ca2+ released to stimulate the contraction of the smooth muscle by increasing cAMP; as a consequence the smooth muscle relaxed.9 In terms of the distribution of tiropramide, a study showed that the radioactivity of tiropramide lasted longer in the colon than in other organs after intravenous or oral administration,17 indicating relative colonic selectivity. Furthermore, the effect of tiropramide were more evident in the smooth muscle of the digestive, urinary and female genital tract than in those of the vessel, and in stimulated contractions rather than in spontaneous ones.17 In the present study, other advantages of tiropramide were observed compared with octylonium: tiropramide was effective earlier than octylonium; in the assessment using symptom diaries, the severity and degree of abdominal discomfort tended to be reduced further in the tiropramide group than in the octylonium group. Since this study was designed to evaluate the non-inferiority of tiropramide over octylonium, we could not conclude that tiropramide is more effective than octylonium, but we may at least speculate about this possibility, considering that assessment using symptom diaries is less biased than that using VAS, which is based on patients' rememberance of symptoms from the previous week. Taken together, there may be some advantage of tiroparmide over octylonium for managing IBS symptoms; this could be due to its colonic selectivity. Regarding the safety of tiropramide, percentages of patients reporting adverse events were similar in both groups. Vital signs and labortory test results did not significantly change after a 4-week treatment with either drug. It has been known that it does not affect neurotransmitters such as histamine, acetylcholine, and adrenaline, thus leading to a lower incidence of side effects than other antispasmodic agents. It was also found that tiropramide did not affect esophageal motility, including the pressure of the low esophageal sphincter, and the coordinated movements of the esophagus.18 Actually, both tiropramide and octylonium have been safely prescribed over the past ten years. Similarly, the present study raised no safety concern. In the subgroup of patients with diarrhea predominant IBS (IBS-D), tiropramide improved bowel habits. Its spasmolytic effect of the drug may be related to the improvement of bowel habits in terms of stool frequency and consistency. These improvements may also be explained by the fact that tiropramide can restore normal intestinal transit in patients with IBS-D having rapid intestinal transit, and are consistent with observations in a study on octylonium demonstrating improvements of bowel habit and abdominal pain and discomfort.14 Moreover, as previously mentioned, gut motility was normalized in 88% of the tiropramide group after 30-day treatment with tiropramide, against 47% of the octylonium group.16 Considering the effect on bowel habit improvement in the subgroup of patients with IBS-D, there may be an additional benefit of tiropramide in patients with IBS-D, although the small number of patients with constipation predominant IBS (IBS-C) in our study might preclude us from concluding that the study drug is effective in patients with IBS-C. In this study, levels of depression and anxiety in the IBS patients were also improved by tiropramide. This may be interpreted in terms of the brain-gut axis.19 Relief of abdominal pain may affect positively the emotional status of study patients. IBS-QoL was also improved. However, theses secondary outcomes should be cautiously interpreted because there may be a variety of confounding factors. Placebo effects are known to be relatively high in IBS, ranging from 20% to 70%. This is believed to be partly due to a variety of physical and psychological factors affecting the brain-gut axis, which is thought to be involved in IBS pathophysiology. Therefore, studies of the treatment of IBS should be designed as randomized, double-blind, and placebo-controlled trials.20 The present study lacks a placebo control therefore could be limited in directly showing the superiority of tiropramide to placebo. However, this limitation in our study may be sufficiently compensated by previous evidence to demonstrate the superiority of octylonium to placebo.13,14,21 Other limitations of our study include the relatively short period of treatment (only 4 weeks) and the lower dose of octylonium than that used in the reference study (20 mg vs. 40 mg, t.i.d). However, the efficacy of both tiropramide and octylonium in improving symptoms of IBS was clearly demonstrated by our study results with statistical differences between pre-and post-treatments. In conclusion, our study demonstrates that treatment with tiropramide is effective and safe for managing IBS symptoms such as abdominal pain and discomfort, stool frequency and consistency, IBS-QoL, depression and anxiety. Considering not enough data fully show the efficacy and safety of tiropramide in IBS patients, the present study should be a useful reference in IBS research and clinical practice for managing IBS patients. Further studies are required to elucidate the mechanism of action of tiropramide on intestine, particularly its pharmacodynamic and pharmacokinetic properties.\n\nQuestion: Compared to octylonium 20 mg what was the result of tiropramide 100 on The incidence of adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1142	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Efficacy and Safety of Tiropramide in the Treatment of Patients With Irritable Bowel Syndrome: A Multicenter, Randomized, Double-blind, Non-inferiority Trial, Compared With Octylonium\n\n ABSTRACT.BACKGROUND/AIMS:\nAntispasmodics such as octylonium are widely used to manage irritable bowel syndrome (IBS) symptoms. However, the efficacy and safety of another antispasmodic, tiropramide, remain uncertain. We aimed to evaluate the efficacy and safety of tiropramide compared with octylonium in patients with IBS.\n\nABSTRACT.METHODS:\nIn this multicenter, randomized, non-inferiority trial, 287 patients with IBS (143 receiving tiropramide and 144 octylonium) were randomly allocated to either tiropramide 100 mg or octylonium 20 mg t.i.d (means 3 times a day) for 4 weeks. Primary endpoint was the mean change of abdominal pain from baseline assessed by visual analogue scales (VAS) score after 4 weeks of treatment. Secondary endpoints were the changes in abdominal pain from baseline at week 2 and in abdominal discomfort at weeks 2 and 4, using VAS scores, patient-reported symptom improvement including stool frequency and consistency, using symptom diaries, IBS-quality of life (IBS-QoL), and depression and anxiety, at week 4.\n\nABSTRACT.RESULTS:\nThe VAS scores of abdominal pain at week 4, were significantly decreased in both tiropramide and octylonium groups, but the change from baseline did not differ between the 2 groups (difference,-0.26 mm; 95% CI,-4.33-3.82; P = 0.901). Abdominal pain and discomfort assessed using VAS scores, diaries, and IBS-QoL were also improved by both treatments, and the changes from baseline did not differ. The incidence of adverse events was similar in the 2 groups, and no severe adverse events involving either drug were observed.\n\nABSTRACT.CONCLUSIONS:\nTiropramide is as effective as octylonium in managing abdominal pain in IBS, with a similar safety profile.\n\nBODY.INTRODUCTION:\nIrritable bowel syndrome (IBS) is a functional bowel disorder characterized by abdominal pain or discomfort relieved by defecation and accompanied by a change in bowel habit.1 According to epidemiologic studies in Korea, the prevalence of IBS was reported to be 6.6% overall, 7.1% in men and 6.0% in women.2 Patients with IBS are reported to seek healthcare frequently, have poor health-related quality of life (QoL) and be responsible for high societal costs.3-5 Like other functional gastrointestinal (GI) disorders, the development of IBS and its symptoms are associated with multifactorial pathophysiology.6 Moreover, symptoms even in an individual patient with IBS may have a different pathophysiology depending on various factors such as diet or emotional status. Therefore, therapy targeting a specific pathophysiology in IBS has been difficult, and symptom treatment focusing on major complaints of IBS or drug combination covering multiple pathophysiology has usually been applied to the management of IBS. Of multifactorial pathophysiology in IBS, colonic smooth muscle spasm has long been postulated to be responsible for abdominal pain in IBS from clinical observations as well as some experimental evidences.7 Therefore, pharmacologic agents directly acting on smooth muscle or on cholinergic receptors, called as antispasmodics, have been developed and used to control abdominal pain and discomfort in IBS. They may be classified as smooth muscle relaxants or agents with anti-cholinergic or anti-muscarinic property. One of the antispasmodics, tiropramide, is a derivative of tyrosine, and exerts a spasmolytic effect on the intestine through reducing Ca2+ release into intestinal smooth muscle, rather than acting on the enteric nervous system.8,9 In a double-blind, placebo-controlled, randomized trial, tiropamide led to symptom improvement in terms of total symptom scores for 4 weeks, compared with 3 weeks in the placebo group; in addition, at week 4 abdominal pain was only improved in the tiropramide group.10 Also in a Korean study of similar design involving 63 patients with IBS, tiropramide improved overall symptom scores and decreased abdominal pain at weeks 2 and 4 (78.2% of the treatment group with tiropramide and 40.5% of placebo group).10 Another antispasmodic, octylonium, also modifies Ca2+ fluxes in the intestinal smooth muscle, with direct myolytic properties similar to tiropramide.11,12 Previously, octylonium has already been proven to be more effective in reducing IBS symptoms than placebo.13-15 However, there have been few large-scale clinical trials comparing tiropamide with antispasmodics of proven efficacy in IBS patients. Therefore, this study aimed at evaluating the efficacy and safety profile of tiropamide in IBS patients compared with octylonium.\n\nBODY.MATERIALS AND METHODS.STUDY PATIENTS:\nEligible patients were 20 to 75 years of age; had been diagnosed with IBS (as assessed according to the Rome III diagnostic criteria for IBS); complained of abdominal pain or discomfort at least 2 times per week for the 2-week run-in period; had visual analogue scale (VAS) scores over 30 mm for abdominal pain during the randomization period. Patients who fit the study criteria had a run-in period of at least 2 weeks during which all IBS-related medications, and concomitant medications were stopped. Exclusion criteria included a history of inflammatory bowel disease, lactose intolerance, uncontrolled diabetes (haemoglobin A1C > 8%) or hypertension (systolic or diastolic blood pressure of ≥ 140/90 mmHg), psychiatric disorder requiring medication, malignancy of organs other than digestive (except for cases with no recurrence for over 5 years since treatment), laparoscopic or open abdominal surgery (except for appendectomy), renal or hepatic disease, glaucoma, and prostate hyperplasia. Those with a history of the following diseases within the previous 6 months were also excluded; peptic ulcer disease, GI bleeding, gastroesophageal reflux disease, intestinal stenosis or obstruction, infectious diarrhea, and pancreatic insufficiency. Patients were excluded if they were intolerable of or sensitive to, study drug, had a history of alcohol or drug addiction, or were expected to take any contraindicated medication during the study period. Pregnant or lactating women and women of childbearing age not using contraception, were also excluded.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis was a multicenter (20 centers), randomized, double-blind, parallel-group, non-inferiority comparative study conducted in South Korea from May 2012 to April 2013. The study protocol was approved by the Institutional Review Board of each study center and conducted in accordance with the ethical principles based on the Declaration of Helsinki and Good Clinical Practice guidelines. For a run-in period of about 2 weeks, eligible subjects for screening were instructed to stop IBS-related medications and prohibited from other drugs. Following the screening phase of 2 to 4 weeks, eligible patients were randomly assigned to either tiropramide (Tiropa; Dae Woong Pharma Korea Inc., Seoul, South Korea) 100 mg or octylonium (Menoctyl; DONG HWA PHARM, Seoul, South Korea) 20 mg, taken 3 times daily before meals for 4 weeks. Treatment assignments were carried out by a computer-generated randomization schedule that was designed to allocate patients to the 2 treatment arms in a 1:1 ratio. The subjects were assigned to sequential allocation numbers at each site, and the medications were presented as 2 identically-appearing tablets containing 1 active drug and 1 placebo of each comparative drug to maintain the double blind condition. Follow-up visits during the study period were scheduled at weeks 2 and 4 to assess abdominal pain/discomfort using VAS, IBS quality of life, IBS symptoms including bowel habits using diaries, the Beck depression inventory (BDI) and the Beck anxiety inventory (BAI), drug compliance and adverse events (Fig. 1). Written, informed consent was obtained from all subjects before enrollment.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.EFFICACY:\nThe primary endpoint was the change in abdominal pain from baseline assessed by VAS scores after 4 weeks of treatment. The secondary endpoints included the change in abdominal pain from baseline by VAS scores at week 2, the change in abdominal discomfort from baseline by VAS scores at weeks 2 and 4, improvement of patients' overall assessment at weeks 2 and 4, the change in IBS QoL from baseline at 4 weeks, the change in symptom improvement in abdominal pain and discomfort from baseline using symptom diaries (severity of symptoms and days of no symptoms), and stool frequency and form assessed by Bristol stool form scale and according to IBS subtypes. Symptom improvement was defined as \"completely improved,\" \"considerably improved\" or \"slightly improved.\" Percentages of symptom improvement include \"completely, considerably and slightly improved.\" Symptom diaries assessed daily symptoms of abdominal pain and discomfort using VAS of 0 to 100 with 100 representing extreme symptom. The number of defecation per day and the most common stool consistency during the day were recorded using the Bristol stool form scale. IBS-QoL was assessed by asking patients to answer each question using a 5-point Likert scale (0 = none, 1 = mild, 2 = moderate, 3 = severe, 4 = extremely severe). Exploratory end points were the changes in BDI and BAI from baseline. Each BDI or BAI was composed of 21 questions and assessed as \"0 = do not feel at all,\" \"1 = feel a bit,\" \"2 = feel significantly,\" and \"3 = feel badly.\" Confounding factors were baseline factors of efficacy including BDI and BAI.\n\nBODY.MATERIALS AND METHODS.STUDY ASSESSMENTS.SAFETY:\nSafety assessments included adverse events, and abnormalities in laboratory findings and vital signs.\n\nBODY.MATERIALS AND METHODS.STATISTICAL METHODS:\nWe estimated the required sample size for this study from the data of a previous study which found a change in VAS for abdominal pain from baseline as 23.6 mm with standard deviation (SD) of 25.0 mm.14 The margin of non-inferiority was assumed to be 11 mm, approximately half of 22.7 mm, which was the difference of the changes observed between the octylonium and the placebo groups. Based on these assumptions, a sample of 129 patients was needed for each study arm in order to have a power of 90%, and α of 0.025 (one-sided), while allowing for a 15% dropout rate. The analyses were performed using full analysis set (FAS) and per protocol set (PPS). All efficacy analyses were conducted in the FAS population, which consisted of all randomized patients satisfying the inclusion and exclusion criteria who received at least one dose of study medication and had at least one post-baseline efficacy measurement. The primary efficacy analysis was based on the PPS, which included all patients within the FAS population who took more than 80% of their assigned drugs and had no major protocol violations such as violations of scheduled visits or administration of contraindicated medication. The change in VAS for abdominal pain from baseline was evaluated by 2 sample t test. Seconday outcomes were compared by 2 sample t test or Wilcoxon's rank sum test. Rates of symptom improvement were described as frequencies and percentages, and compared between groups by Pearson's chi-square test or Fisher's exact test. For safety variables including treatment emrgent adverse event (TEAE), adverse drug reaction, and serious adverse event, Pearson's chi-square test or Fisher's exact test was used to evaluate differences in incidence between groups. Changes in continuous variables from baseline after treatment were analyzed by 2 sample t test or Wilcoxon's rank sum test, while categorical variables, by Pearson's chi-square test or Fisher's exact test. Confounding factors such as BDI, BAI and baseline values of the efficacy variables were further analysed by ANCOVA or multiple logistic regression. A P-value of 0.05 was considered statistically significant. Statistical analyses were performed using SAS (Enterprise Guide 4.3).\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nTotal of 356 patients were evaluated for study inclusion. After exclusion of 61 patients during the screening period, 295 patients were randomized to either tiropramide or octylonium. Three percent of patients in the tiropramide group (4/143) and octylonium group (4/144) did not complete the study. Data on the remaining 287 patients were available for the FAS analysis: 143 for tiropramide vs. 144 for octylonium. Data on 245 patients were available for the PPS analysis: 117 for tiropramide vs. 128 for octylonium. A flowchart of patient progression through the study with reasons for premature discontinuation is presented in Fig. 2. Demographic and baseline characteristics of patients are presented in Table 1. Both treatment arms were well balanced for gender, age and severity of symptoms at baseline.\n\nBODY.RESULTS.EFFICACY:\nThe PPS population comprised of 245 patients (117 in the test group and 128 in the control group). The mean changes of VAS scores for abdominal pain from baseline were-23.49 ± 17.51 mm in the tiropramide group and-23.13 ± 17.61 in the octylonium group. The mean difference between the 2 groups was-0.26 mm in the FAS and-0.35 mm in the PPS, and the upper limit of the 97.5% CI at one-sided was 3.82 mm in the FAS and 4.07 mm in the PPS; these are below the margin of inferiority of 11 mm, indicating that tiropramide is not inferior to octylonium (Table 2). In secondary outcome analyses, VAS scores for abdominal pain at week 2 were significantly decreased in both groups (Table 3). Significant improvement in abdominal pain and discomfort at weeks 2 and 4 using symptom diaries, and in IBS-QoL, BDI and BAI at week 4 were observed in both groups, however the differences between the groups were not significant. In the subgroup of IBS-D, stool frequency was decreased and stool consistency was improved by treatment. Furthermore, the degree of symptom reduction in abdominal pain using symptom diaries was higher in the tiropramide group than in the octylonium group from week 1 (P = 0.033). After adjusting the baseline values of related factors, our analysis showed that all the factors based on symptom diaries, except the change of IBS symptoms, did not differ in the 2 groups. IBS symptoms at week 4 using symptom diaries were reduced further compared to baseline in the tiropramide group than the octylonium group.\n\nBODY.RESULTS.SAFETY:\nAdverse events reported during the study are shown in Table 4. TEAE was 10.88% (16/147) in the tiropramide group and 12.24% (18/147) in the octylonium group, which included 28 each. The safety profile of tiropramide was similar to that of octylonium. Adverse drug reactions were reported in 7 patients in the tiropramide group and 6 patients in the octylonium group, which included 17 and 9, respectively. Serious adverse events developed in one patient in each group, idiopathic thrombocytopenic purpura in the tiropramide group and intervertebral disc protrusion in the octilonium group, but were not related to the study drugs, and were improved without any sequelae. Laboratory test results, when comparing those at screening period with those at last visit, showed no violation of safety regarding normal values, or the changes of direction and quantity. Vital signs did not change significantly from baseline in either group at weeks 2 and 4.\n\nBODY.DISCUSSION:\nThe present study was designed to assess the non-inferiority of tiropramide compared to the proven antispasmodic, octylonium, for managing IBS symptoms. This multicenter, randomized, double-blind, non-inferiority trial showed that 4-week treatment with tiropramide improved abdominal pain and discomfort, patient-reported overall assessments of IBS symptoms, IBS-QoL, depression and anxiety, with no significant differences from octylonium. These results demonstrate non-inferiority of tiropramide in efficacy and safety, compared with otiolonium. Tiropramide effectively and safely managed abdominal pain in the IBS patients. Our results showed that the change in VAS scores for abdominal pain from baseline was about 23.5 mm after 4-week treatment with tiropramide, similar to 23.6 mm observed after 4-week treatment with octylonium. The changes from baseline between the 2 groups were not significantly different, and the upper limit of 95% CI was lower than the margin of inferiority in both the FAS and PPS populations, indicating non-inferiority of tiropramide compared to octylonium. In a previous study comparing tiroparmide with octylonium in IBS patients, the proportion of patients whose abdominal pain was relieved by treatment was higher in tiropramide group than in octylonium group at days 3 and 5 of medication, suggesting rapid drug action of tiropramide.16 Also, at the end of 30-day treatment, normal gut motility was restored in 88% of the tiropramide group compared with 47% of octylonium group.16 The presumed mechanism of tiropramide in improving abdominal pain is its antispasmodic effect on the intestine. In an animal study using the isolated smooth muscle, tiropramide inhibited Ca2+ influx for the most part and, to a lesser extent, increased the intracellular cyclic adenosine monophosphate (cAMP) levels.9 This study using rabbit also found that tiropamide increased Ca2+ absorption into microvesicles and decreased the amount of Ca2+ released to stimulate the contraction of the smooth muscle by increasing cAMP; as a consequence the smooth muscle relaxed.9 In terms of the distribution of tiropramide, a study showed that the radioactivity of tiropramide lasted longer in the colon than in other organs after intravenous or oral administration,17 indicating relative colonic selectivity. Furthermore, the effect of tiropramide were more evident in the smooth muscle of the digestive, urinary and female genital tract than in those of the vessel, and in stimulated contractions rather than in spontaneous ones.17 In the present study, other advantages of tiropramide were observed compared with octylonium: tiropramide was effective earlier than octylonium; in the assessment using symptom diaries, the severity and degree of abdominal discomfort tended to be reduced further in the tiropramide group than in the octylonium group. Since this study was designed to evaluate the non-inferiority of tiropramide over octylonium, we could not conclude that tiropramide is more effective than octylonium, but we may at least speculate about this possibility, considering that assessment using symptom diaries is less biased than that using VAS, which is based on patients' rememberance of symptoms from the previous week. Taken together, there may be some advantage of tiroparmide over octylonium for managing IBS symptoms; this could be due to its colonic selectivity. Regarding the safety of tiropramide, percentages of patients reporting adverse events were similar in both groups. Vital signs and labortory test results did not significantly change after a 4-week treatment with either drug. It has been known that it does not affect neurotransmitters such as histamine, acetylcholine, and adrenaline, thus leading to a lower incidence of side effects than other antispasmodic agents. It was also found that tiropramide did not affect esophageal motility, including the pressure of the low esophageal sphincter, and the coordinated movements of the esophagus.18 Actually, both tiropramide and octylonium have been safely prescribed over the past ten years. Similarly, the present study raised no safety concern. In the subgroup of patients with diarrhea predominant IBS (IBS-D), tiropramide improved bowel habits. Its spasmolytic effect of the drug may be related to the improvement of bowel habits in terms of stool frequency and consistency. These improvements may also be explained by the fact that tiropramide can restore normal intestinal transit in patients with IBS-D having rapid intestinal transit, and are consistent with observations in a study on octylonium demonstrating improvements of bowel habit and abdominal pain and discomfort.14 Moreover, as previously mentioned, gut motility was normalized in 88% of the tiropramide group after 30-day treatment with tiropramide, against 47% of the octylonium group.16 Considering the effect on bowel habit improvement in the subgroup of patients with IBS-D, there may be an additional benefit of tiropramide in patients with IBS-D, although the small number of patients with constipation predominant IBS (IBS-C) in our study might preclude us from concluding that the study drug is effective in patients with IBS-C. In this study, levels of depression and anxiety in the IBS patients were also improved by tiropramide. This may be interpreted in terms of the brain-gut axis.19 Relief of abdominal pain may affect positively the emotional status of study patients. IBS-QoL was also improved. However, theses secondary outcomes should be cautiously interpreted because there may be a variety of confounding factors. Placebo effects are known to be relatively high in IBS, ranging from 20% to 70%. This is believed to be partly due to a variety of physical and psychological factors affecting the brain-gut axis, which is thought to be involved in IBS pathophysiology. Therefore, studies of the treatment of IBS should be designed as randomized, double-blind, and placebo-controlled trials.20 The present study lacks a placebo control therefore could be limited in directly showing the superiority of tiropramide to placebo. However, this limitation in our study may be sufficiently compensated by previous evidence to demonstrate the superiority of octylonium to placebo.13,14,21 Other limitations of our study include the relatively short period of treatment (only 4 weeks) and the lower dose of octylonium than that used in the reference study (20 mg vs. 40 mg, t.i.d). However, the efficacy of both tiropramide and octylonium in improving symptoms of IBS was clearly demonstrated by our study results with statistical differences between pre-and post-treatments. In conclusion, our study demonstrates that treatment with tiropramide is effective and safe for managing IBS symptoms such as abdominal pain and discomfort, stool frequency and consistency, IBS-QoL, depression and anxiety. Considering not enough data fully show the efficacy and safety of tiropramide in IBS patients, the present study should be a useful reference in IBS research and clinical practice for managing IBS patients. Further studies are required to elucidate the mechanism of action of tiropramide on intestine, particularly its pharmacodynamic and pharmacokinetic properties.\n\nQuestion: Compared to octylonium 20 mg what was the result of tiropramide 100 on the degree of symptom reduction in abdominal pain using symptom diaries from week 1 ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1144	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Co-morbidities, complications and causes of death among people with femoral neck fracture – a three-year follow-up study\n\n ABSTRACT.BACKGROUND:\nThe poor outcome after a hip fracture is not fully understood. The aim of the study was to describe the prevalence of co-morbidities, complications and causes of death and to investigate factors that are able to predict mortality in old people with femoral neck fracture.\n\nABSTRACT.METHODS:\nData was obtained from a randomized, controlled trial with a 3-year follow-up at Umeå University Hospital, Sweden, which included 199 consecutive patients with femoral neck fracture, aged ≥70 years. The participants were assessed during hospitalization and in their homes 4, 12 and 36 months after surgery. Medical records and death certificates were analysed.\n\nABSTRACT.RESULTS:\nMultivariate analysis revealed that cancer, dependence in P-ADL (Personal Activities of Daily Living), cardiovascular disease, dementia at baseline or pulmonary emboli or cardiac failure during hospitalization were all independent predictors of 3-year mortality. Seventy-nine out of 199 participants (40 %) died within 3 years. Cardiovascular events (24 %), dementia (23 %), hip-fracture (19 %) and cancer (13 %) were the most common primary causes of death. In total, 136 participants suffered at least one urinary tract infection; 114 suffered 542 falls and 37 sustained 56 new fractures, including 13 hip fractures, during follow-up.\n\nABSTRACT.CONCLUSION:\nOld people with femoral neck fracture have multiple co-morbidities and suffer numerous complications. Thus randomized intervention studies should focus on prevention of complications that might be avoidable such as infections, heart diseases, falls and fractures.\n\nBODY.BACKGROUND:\nHip fractures are a common and major health problem among older people [1]. The annual number of such fractures in Sweden is expected to almost double during the first half of this century [2]. There is a well-established increased risk of death after hip fracture [3, 4]. It has been shown that older people have a 5- to 8-fold increased risk of dying during the first 3 months after a hip fracture [4]. Studies have been performed to optimize care of hip fracture patients and the consensus concerning preoperative management, time to surgery, operative management, surgical technique and postoperative care has led to recommendations concerning clinical care pathways and a multidisciplinary approach [5–8]. Despite research into care improvements for hip fracture patients, for example in the fields of medical and surgical care or the use of multidisciplinary teams, it has been shown that fewer than half regain their previous level of function [9] and the mortality rate has remained stable over the past 40 years [10]. A variety of postoperative complications and times to follow-up are described. One study found that 33 % of the participants had at least one complication after an operation for hip-fracture which led to prolonged hospitalization. The most common postoperative complications were delirium and infection [11]. Another study found heart failure and chest infections to be the most common postoperative complications [12], while a more recent study showed that falls, fractures and pneumonia were the most common [13]. A range of interventions to reduce the rate of in-hospital postoperative complications and mortality have been reported in the literature. One such study found that postoperative complications and 12-month mortality among community dwellers were reduced when a comprehensive multidisciplinary fast-track treatment and care program were put in place [14]. We have shown earlier that a multidisciplinary, multi-factorial rehabilitation program reduced in-hospital complications [15], including significant fewer in hospital falls but there was no difference in the number of falls during 1 year after discharge [16, 17]. Death following hip fracture has been associated with several risk factors; older age and male sex, severe systemic disease, pre-fracture functional impairment, cognitive decline, coronary heart disease and the number of co-morbidities [18–23]. The causes of excess death have been a subject of debate. One study suggests that the increased mortality is associated with postoperative complications [24], others ascribe it to pre-fracture co-morbidities together with postoperative complications [12, 19], or suggest that the co-morbidities are the underlying cause [25]. Only a few studies describe the causes of death [24, 26–29]. The most common causes of death in one autopsy study were chest infection, cardiac failure, myocardial infarction and pulmonary embolism [29]. Among nursing-home residents with hip fracture the most common causes of death were infection, dementia and cardiac events [26] and, in more recent studies, cardiac and infectious diseases [27, 28]. In spite of earlier research, the poor outcome for people with hip fracture has not improved and mortality has not been reduced. Since neither the events leading to death, nor the causes of death or the patient's outcome after discharge have been fully investigated, we decided to explore these factors in order to discover factors that might be adjusted in order to improve outcome. Thus, the aim of this study was to describe the prevalence of co-morbidities, complications and causes of death and to investigate factors that could predict mortality in old people with femoral neck fracture.\n\nBODY.METHODS.STUDY DESIGN:\nThe article is based on data from a randomized controlled trial, evaluating a multidisciplinary intervention program for persons with a femoral neck fracture compared to conventional care. The intervention resulted in fewer complications during hospitalization, but there were no differences in the incidence of complications and mortality between the intervention and control groups after discharge (data not shown). The participants are analysed as one group in the present study, they were followed from admission to hospital until death, relocation or the end of 36 months of follow-up. The description of the recruitment and randomization as well as the content of the intervention has been presented in detail in earlier articles [15, 16]. All participants received oral and written information and in those cases where they were not able to answer themselves their next of kin was also asked. A written informed consent for participation in the study was required.\n\nBODY.METHODS.SAMPLE:\nThe study included 199 participants with femoral neck fractures (index hip fracture) aged 70 years or older, consecutively admitted to the Orthopaedic Department at the University Hospital in Umeå, Sweden, over 32 months. Flow chart of the results of all 353 patients with femoral-neck fractures during the study period is shown in Fig. 1.Fig. 1Flow chart of the results of all 353 patients with femoral-neck fractures during the study period Exclusion criteria were: the presence of rheumatoid arthritis, severe hip osteoarthritis, and pathological fracture, due to the planned operation methods to be used in the study. Patients with severe renal failure, those who were bedridden prior to the fracture and patients already admitted to hospital for other reasons, who then fell and suffered a hip fracture were also excluded. The surgeon decided whether or not an operation planned according to the study protocol was appropriate for the patient.\n\nBODY.METHODS.DATA COLLECTION:\nTrained research nurses, not involved in the patients' medical care or nursing, assessed the patients during hospitalization and at 4, 12 and 36 months subsequently. At the follow-ups the nurse was accompanied by a physiotherapist or an occupational therapist who also made assessments. The patients' general health was assessed before surgery, according to the American Society of Anaesthesiologists (ASA) classification [30], by the attending anaesthesiologist. ASA 1 indicates a healthy person; ASA 2, a person with a mild systemic disease; ASA 3, a person with severe systemic disease; ASA 4, a person with an incapacitating disease that is a constant threat to life; ASA 5, a moribund person who is not expected to live 24 h with or without surgery. In the analysis the ASA results were categorized as ASA 1–2 and ASA 3–4. No person classified as ASA 5 was included. All medical and social data were collected from interviews with participants, relatives and staff, and included morbidity and complications. Data were also collected from the medical and nursing records. A broad definition of complications was chosen to describe the wide spectrum of complications. The complications were classified dichotomously (present/absent) and the total number of times a complication occurred was counted. The participants with cardiac failure at baseline were judged to have cardiac failure as a complication during follow-up if they had been treated by a medical doctor due to exacerbation of the disease. Cardiac failure and myocardial infarction are referred to in the text as cardiovascular events. Infections were divided into 5 groups; chest infections, urinary tract infections, superficial and deep wound infections and other infections. A fall was defined as an incident when the participant unintentionally came to rest on the floor or ground and also included syncopal falls [31]. For those participants who died during the study, medical records were reviewed and all complications and the \"history of death\" were noted. If a participant died between follow-ups, complications that occurred between last follow-up and death were forwarded, which means they were registered at the next follow-up. The primary and secondary causes of death were also obtained from the death certificates. In Sweden every citizen has a unique 10-digit personal identification number which makes it possible to obtain cause and date of death from the Centre for Epidemiology (EpC), National Board of Health and Welfare, Sweden. The diagnoses are coded according to the International Classification of Diseases (ICD), which is validated and used as an international standard by the WHO (World Health Organization). In Sweden 99 % of deceased receive a diagnosis [32]. If a person died within 30 days after a fracture the primary cause of death was coded, according to international standards, as related to the trauma irrespective of the actual cause of death. For example, a myocardial infarction complicating a hip fracture would be coded as a secondary cause of death. In our analyses the causes of death were determined through assessment of the notes concerning the person's death and the information obtained from death certificates. Fifteen of the causes of death stated in the death certificates were changed after examination of the patients' medical records. Two of these fifteen were changed in accordance with autopsy reports, another three after more information was retrieved and a further ten were changed to secondary cause on the death certificate. For example, a participant with advanced dementia who suffered terminal pneumonia was judged to have died due to dementia rather than pneumonia. A geriatrician, unaware of study-group allocation, analysed all assessments and documentation once the study was ended, to determine whether the participants fulfilled the DSM-IV (Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition) criteria [33] for dementia, delirium and depression. The Ethics Committee of the Faculty of Medicine at Umea University approved the study (§ 00–137).\n\nBODY.METHODS.STATISTICS:\nPearson's chi-square test, Fisher's exact test and Mann–Whitney U test were used to analyse differences between the deceased and the survivors regarding complications. Univariate and multivariate Cox proportional hazard regression was used to analyse associations between baseline variables and complications during hospitalization and all-cause mortality during the 3-year follow-up. All baseline variables and complications during hospitalization associated with time to death (p < 0.05) in univariate analyses were included in two separate multivariate models (Model A and B in Table 1). Correlations between baseline variables and among complications during hospitalization were tested using Pearson's and Spearman's coefficients; the covariate Living in residential care facilities before fracture was removed due to its strong correlation with Dependence in personal activities of daily living (P-ADL) (r > 0.6). Stepwise backward deletion was performed manually until only significant variables remained in the models.Table 1Baseline characteristics and complications among participants and differences among deceased and survivors. Univariate and multivariate cox regression analysesAll casesDeceased within 3 yearsSurvivorsUnivariateMultivariate\nn = 199 (%)\nn = 79\nn = 120Pa\nPb\nHRCIBaseline characteristics:Model A.Age, mean ± SD82.2 ± 6.282.9 ± 5.881.7 ± 6.50.2330.4351.0160.977–1.056Female148 (74 %)53950.0290.0520.6040.363–1.005Living in residential care facilities73 (37 %)37360.028Living alone146 (74 %)59870.696Current smoker (n = 169)6 (4 %)240.955Dependence in walking (n = 195)25 (13 %)15100.004Dependence in P-ADL115 (58 %)5956<0.0010.0052.3791.300–4.354Cancer (n = 194)29 (15 %)218<0.001<0.0013.4492.020–5.890Cardiovascular disease (n = 194)110 (57 %)5555<0.0010.0042.1771.287–3.682Dementia64 (32 %)37270.0010.0161.9211.131–3.262Depression (n = 197)78 (40 %)39390.040Diabetes (n = 197)40 (20 %)22180.059Kidney disease (n = 194)21 (11 %)10110.321Pulmonary disease (n = 194)33 (17 %)17160.049Stroke (n = 195)49 (25 %)23260.184ASA grade 3–4 (n = 197)109 (55 %)51580.007Internal fixation69 (35 %)33360.420Hemiarthroplasty111 (56 %)37740.228Dynamic hip screw17 (9 %)7100.998Other1 (0.5 %)100.345No of. comorbidities:031 (16 %)328<0.001137 (19 %)7300.260252 (26 %)25270.005≥379 (40 %)44 (56 %)35 (29 %)0.001Complications during hospitalization:Model B.Pneumonia/chest infection8620.0010.0212.9161.175–7.237Urinary tract infection8238440.241Other infection3415190.528Wound infection000Deep wound infection1100.054Cardiac failure171250.0010.0102.4571.242–4.858Myocardial infarction6600.052Deep vein thrombosis1100.050Pulmonary embolism1100.0020.00133.2193.961–278.570Stroke3210.072Cancer3210.120Gastric ulcer7340.538Delirium12963700.0050.0182.0061.127–3.570Fallers3819190.267Number of falls7841370.262Fracture4220.609Luxation6330.416Reoperation8350.926Decubital ulcers3016140.044Combining baseline and complication factors:Model C.Age0.7051.0080.968–1.049Female0.1180.6550.386–1.113Dependence in P-ADL0.0072.3621.271–4.387Cancer<0.0013.3931.959–5.877Cardiovascular disease0.0132.0261.160–3.539Dementia0.0231.8831.091–3.250Pneumonia/chest infectionCardiac failure0.0182.2211.148–4.294Pulmonary embolism<0.00169.3967.107–677.632Delirium\nSD Standard deviation\nP-ADL Personal Activities of Daily Living\nASA American Society of Anaesthesiologists classification\nHR Hazard ratio\nCI 95 % Confidence interval\na p according to univariate cox regression model\nb p according to multivariate cox regression model The proportionality of hazards was tested using Schoenfeld residuals and time-dependent variables in extended Cox regression models [34]. A final multivariate model adjusted for age, sex and remaining significant variables from the two separate multivariate analyses was performed (Model C in Table 1). All calculations were carried out using SPSS v 23. All statistical tests were 2-tailed and a p-value <0.05 was considered statistically significant.\n\nBODY.RESULTS.PREDICTORS OF MORTALITY:\nA history of cardiovascular disease, cancer, dependence in P-ADL, dementia, having three or more co-morbidities, dependence in walking, having an ASA score of 3 or higher, living in residential care facilities, male gender, depression and pulmonary disease were all independently associated with time to death in univariate Cox regression analyses (Table 1). The results from multivariate Cox regression analyses are also displayed in the columns to the right of Table 1. The hazard ratios (HR) and 95 % confidence intervals (CI) are presented for the significant variables remaining in the multivariate models. When analysing associations between baseline variables and time to death we found that cancer, cardiovascular disease, dependence in P-ADL and dementia were associated with time to death in a Cox proportional hazard regression model adjusted for age and sex (Model A). In a second model (Model B.) complications during hospitalization were analysed; pulmonary emboli, pneumonia, cardiac failure and delirium were all associated with time to death. In the final model (Model C.) all significant variables in the two multivariate models above were combined; pulmonary emboli (HR 69.396, CI: 7.107–677.632), cancer (HR 3.393, CI: 1.959–5.877), cardiac failure (HR 2.221, CI: 1.148–4.294), cardiovascular disease (HR 2.026, CI: 1.160–3.539), dementia (HR 1.883, CI: 1.091–3.250) and dependence in P-ADL (HR 2.362, CI: 1.271–4.387) remained independently associated with all-cause mortality adjusted for age and gender.\n\nBODY.RESULTS.CO-MORBIDITIES AND BASELINE CHARACTERISTICS:\nThe majority of the participants were women, living alone and independently; they walked independently indoors but only four out of ten were independent in P-ADL before the index hip fracture. Fifty-seven percent had a history of cardiovascular disease and 55 % had an ASA score of 3 or higher at baseline. The deceased had three or more co-morbidities in 56 % of the cases at baseline compared to 29 % among the survivors (Table 1).\n\nBODY.RESULTS.DEATHS:\nSeventy-nine out of 199 participants (40 %) died. Mortality was 13/199 (6 %) at 30 days and 34/199 (17 %) at 1 year after the index hip fracture. Twenty-six out of 51 (51 %) men died compared to 53/148 (36 %) women. After discharge, a total of 65 participants died during the 3 years of follow-up (Table 2).Table 2Primary causes of deathCause of deathDuring hospitalizationBetween discharge and 4 monthsBetween 4 and 12 monthsBetween 12 and 36 monthsTotalCardiovascular0121619Dementia0041418Hip fracture1130115Cancer023510Cerebrovascular00134Infection10012Deep infection00022Renal failure10102Fracture01102Gastrointestinal bleeding10001Ruptured aortic aneurysm00011Parkinson's disease00011Pancreatitis00011Gangrene01001Sum148124579Autopsy721415\n\nBODY.RESULTS.CAUSES OF DEATH:\nIn this study 13 participants died within 30 days of sustaining the index hip fracture. Ten of these 13 died during hospitalization: one before the operation, due to myocardial infarction; two on the day of operation, due to cardiovascular events; two the day after the operation (one due to gastrointestinal bleeding and one to myocardial infarction); one suffered a cerebrovascular event during the operation and never regained consciousness; one suffered a myocardial infarction after a week; two died of pneumonia and one died due to an intestinal infarction. The participants who died during hospitalization due to a cardiovascular event all had a history of cardiovascular disease. The three participants who died after discharge but within 30 days of the index hip fracture did so due to a cerebrovascular event, a myocardial infarction and a pulmonary emboli, respectively. The secondary cause of death within 30 days of the index fracture was due to a cardiovascular event in 6/13 (46 %) cases. In addition four participants died within 30 days after sustaining a new fracture. One of these participants fell and suffered a new hip fracture while still in hospital and then died due to an infection. After discharge one participant suffered a hip fracture and died due to pneumonia, one sustained a head trauma with a face fracture and died due to intracerebral bleeding and one had a knee fracture and died due to rupture of the aorta. Cardiovascular events (19/65), Dementia (18/65), cancer (10/65), fractures (6/65) and cerebrovascular events (4/65) were the most common primary causes of death after discharge (Table 2).\n\nBODY.RESULTS.COMPLICATIONS:\nIn total 166 participants suffered from 583 infections, including 136 participants who suffered 363 urinary tract infections. Seventy-four participants suffered 111 cardiovascular events during the 3 years following the hip fracture. One-hundred and fourteen participants suffered 542 falls. Thirty-seven participants suffered 56 new fractures, including 13 new hip fractures, seven wrist fractures and seven rib fractures. Forty-nine participants suffered 60 decubital ulcers. During follow-up 96 participants had 234 hospital admissions with a total of 3984 days spent in hospital. Infections and cardiovascular events were more common after discharge among those who died (Table 3).Table 3Complications after femoral neck fracture occurring between discharge and until three year follow-up, differences between deceased and survivorsComplicationsBetween discharge and 4 months (n = 176)Between 4 and 12 months (n = 172)Between 12 and 36 months (n = 149)Pneumonia/chest infection5821Urinary tract infection515978Other infection344156Wound infection300Deep wound infection202Cardiac failure181730Myocardial infarction5612Deep vein thrombosis101Pulmonary embolism112Stroke2810Cancer044Gastric ulcer227Fallers536166Number of falls126130208Number of fractures61729Luxation324Reoperation327Decubital ulcers91011Number of participants hospitalized254864Number of hospitalizations2966139Number of days in hospital41311342437Median days in hospital, IQR9.0 (5.0–18.0)15.0 (4.0–31.2)23.5 (9.2–48.8)* = p < 0,05 according to Pearson's chi-square, Fisher's exact test or Mann–Whitney U test as appropriate, when comparing deceased and survivors\nIQR Inter Quartile Rate\n\nBODY.DISCUSSION:\nThis study shows that both co-morbidities at baseline and complications during hospitalization are associated with mortality. Cancer, dependence in P-ADL, cardiovascular disease and dementia at baseline, and pulmonary emboli and cardiac failure during hospitalization were all independent predictors of mortality. Forty percent had died after 3 years despite the exclusion of those who were bedridden, had severe renal failure or pathological fractures. The most common primary causes of death were cardiovascular events, dementia, fractures, cancer and cerebrovascular events. The participants had several co-morbidities and suffered numerous complications such as infections, falls and fractures, cardiovascular events, delirium, and pressure ulcers. When analysing factors associated with death we found that both comorbidities and post-operative complications were of significance, a finding which is also verified in a recent review using data from a National Trauma Data Bank [35]. A study by Roche et al. [12] found that age, male sex, cancer, chest infection, cardiac failure and stroke could predict mortality but they did not include dementia or functional measurements in their model. Dementia, however, is common among hip fracture patients and was thus included in the present study. Dementia is also found to be a risk factor for death and in another large cohort study by Petersen et al. [19] age, cardiac complications and dementia were associated with mortality at 12 months but malignancies, cardiovascular disease and measurements of function were not included. In a large cohort study by Castronuovo et al. [36] heart disease was a risk factor for 30-days mortality but not during follow-up though no complications were included in the study. A reduced mental and medical status, and a poor physical ability at baseline were found among the deceased in the current study, similar to the results of a Norwegian study [23], although those living in nursing homes and patients who did not pass a mental status test had been excluded. Such patients were not excluded in the present study. Among those who died, 56 % had three or more co-morbidities at baseline and 65 % had an ASA score of 3 or higher. The number of co-morbidities and poor pre-fracture status might be indicators of frailty. It has been shown that the (ASA) classification of medical co-morbidities is strongly associated with medical problems in the perioperative period [37] and an earlier Swedish study shows that a high ASA score is a factor associated with mortality [21]. A cardiovascular disease is a strong predictor of post-operative cardiac failure, according to Roche et al. [12]. All participants in the present study who died during hospitalization due to a cardiovascular events had a pre-fracture cardiovascular disease. Early death within 30 days after admission to hospital due to a hip fracture has recently been described in a study that examines post-mortem reports, where respiratory infections and cardiovascular disease were the main causes of death [28]. These results are in line with earlier studies [24, 29] and our study shows a similar result as 46 % of early deaths were due to a cardiovascular event. During follow-up cardiovascular events, dementia and cancer were the most common causes of death in the present study, which is partly consistent with earlier studies [26, 27, 38]. The difference in the prevalence of infection as a cause might be due to the manner in which assessment of the causes of death was determined in the present study, as described above in the method section. There might also be an under diagnosis of dementia among many old people [39]. The participants in the present study were cognitively tested during hospitalization and at 4, 12 and 36 months. Our study confirms that complications among people suffering from a hip fracture are numerous, both early post-operatively and during follow-up. In-hospital complications among hip fracture patients, such as urinary tract infections, delirium, decubital ulcers and falls, can be successfully prevented and treated [14, 15] but as far as we know few intervention studies have succeeded in preventing cardiac complications [40–42]. Since we can now identify the most vulnerable patients, the focus in further research should be on prevention of infections and heart diseases in early postoperative care since they might be avoidable. These findings are in line with Petersen et al. [19] who concluded that cardiac complications constituted an important risk factor that might be modified and with Roche et al. [12] who emphasized the need for medical assessment among those with heart failure and chest infection. In addition, prevention should also focus on the numerous complications that occur after discharge from hospital. General complications were associated with loss of function in a recent study by Hansson et al. [13] Improved rehabilitation after stroke, including treatment of underlying comorbidities as well as secondary prevention, has increased the survival rate after stroke over the last few decades [43] while mortality after femoral neck fracture has remained constant. Treatment of risk factors for stroke and myocardial infarction as well as secondary prevention are currently well established in routine care. The 56 new fractures that occurred in the present sample indicate that fracture prevention also needs to become a part of routine care aimed at reducing fracture rates and mortality. Since hip fracture is, in many cases, an event that signals a systemic decline in the person's health, it is crucial to preserve and improve the clinical care pathways to ensure optimal recovery and survival for these patients. The present study will, hopefully, contribute to the knowledge available concerning the causes of death and highlight the potentially modifiable/preventable complications that we need to focus on in the future. The strength of our study is that we have systematically analysed all complications and the secondary causes of death among people with hip fracture, which no other study has reported to our knowledge. Differences in the present results compared to other studies might be due to the definitions applied to complications and co-morbidities and to the choice of exclusion criteria. In the future a more standardized description of the samples would facilitate comparison. In the present study we tried to obtain information about all events that the participants experienced and that led to death. An underlying cause of death is defined as \"the disease or injury which initiated the train of morbid events leading directly to death, or the circumstances of the accident or violence which produced the fatal injury\", in accordance with the rules of the ICD. Although the intention of the ICD is to provide a standard means of recording underlying causes of death, comparison of cause-of-death data over time and across countries should be undertaken with caution. The rules for selecting the underlying cause of death have been re-evaluated and sometimes changed. Incorrect or incomplete death certificates, misinterpretation of ICD rules for selection of the underlying cause, and variations in the use of coding categories for unknown and ill-defined causes might all occur, according to the WHO. There are some limitations to the present study. The sample was relatively small and the participants were only assessed three times over 3 years after discharge and there are certainly complications that were missed, despite the thorough reviews of the participants' medical records. As people with vertebral fractures and rib fractures do not always seek medical care such fractures are poorly documented. The number of vertebral and rib fractures has probably been underestimated in our study since x-rays were not routinely taken during follow-up. Suffering pulmonary emboli is a serious condition and the HR for pulmonary emboli in the multivariate analyse should be interpreted with precaution as only one person in this sample had an emboli and died soon after the fracture.\n\nBODY.CONCLUSION:\nOld people with femoral neck fracture have multiple co-morbidities and suffer numerous complications which might lead to death, both during hospitalization and after discharge. Thus randomized intervention studies should focus on prevention of complications that might be avoidable such as infections, heart diseases, falls and fractures.\n\nBODY.ABBREVIATIONS:\nASA, American Society of Anaesthesiologists classification; CI, 95 % confidence intervals; DSM-IV, diagnostic and statistical manual of mental disorders, fourth edition; EpC, centre for epidemiology; HR, hazard ratios; ICD, International Classification of Diseases; P-ADL, personal activities of daily living; WHO, World Health Organization.\n\nQuestion: Compared to no comorbidities what was the result of pulmonary emboli or cancer or cardiac failure or cardiovascular disease or dementia or dependence in P-ADL on mortality in old people with femoral neck fracture.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1145	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Acute effect of Ethanol and Taurine on frontal cortex absolute beta power before and after exercise\n\n ABSTRACT:\nEthanol (ET) is a substance that modulates the Central Nervous System (CNS). Frequently, ET intake occurs combined with energy drinks, which contain taurine (TA), an important amino acid found in the body (i.e brain and muscles). Although TA administration has been used in the improvement of physical performance, the impact of TA, ET and exercise remains unknown. This study aimed to analyze the acute effect of 6g of Taurine (TA), 0.6 mL∙kg-1 of Ethanol (ET), and Taurine combined with Ethanol (TA+ET) ingestion on the electrocortical activity before and after a moderate intensity exercise in 9 subjects, 5 women (counterbalanced experimental design). In each of the 4 treatments (Placebo—PL, TA, ET and TA+ET), electroencephalography (EEG) tests were conducted in order to analyze changes in absolute beta power (ABP) in the frontal lobe in 3 moments: baseline (before ingestion), peak (before exercise) and post-exercise. In the PL treatment, the frontal areas showed decrease in ABP after exercise. However, in the ET+TA treatment, ABP values were greater after exercise, except for Fp1. The ET treatment had no effect on the Superior Frontal Gyrus area (F3, Fz and F4) and ABP decreased after exercise in Fp1 and Fp2. In the TA treatment, ABP increased after exercise, while it decreased at the peak moment in most of the frontal regions, except for Fp1, F3 and Fz. We concluded that after a moderate intensity exercise, a decrease in cortical activity occurs in placebo treatment. Moreover, we found a inhibitory effect of TA on cortical activity before exercise and a increased in cortical activity after exercise. A small ET dose is not enough to alter ABP in all regions of the frontal cortex and, in combination with TA, it showed an increase in the frontal cortex activity at the post-exercise moment.\n\nBODY.INTRODUCTION:\nEthanol (ET), or Ethyl Alcohol, is a substance widely consumed by population; however, its effects on the Central Nervous System (CNS) are not completely known yet. ET is able to alter the CNS excitatory and inhibitory neurotransmitter balance, most times favoring the inhibitory influence [1]. The acute effect of ET contributes to a decrease in cortical activity [2]. Given the importance of such substance, its influence in some regions of the cortex (i.e. the frontal cortex) has been widely studied. This area takes part in functions such as learning, planning, decision making, motivation, attention, working memory and sensory and motor information integration [3]. The frontal region is meant to monitor performance and to implement necessary adjustments in cognitive control [4]. According to reports from the literature, ethanol may cause changes in some functions, such as for example executive control, decision making and risk management [5]. In addition to changes in the CNS, ET acute effect may also harm other organism functions, such as the metabolic and cardiovascular ones, and it may therefore negatively affect physical performance [2]. Ethanol intake commonly occurs together with energy drinks, which contain an amino acid called taurine (TA), which objective is to reduce the symptons of depression [6]. Due to the different components contained in energy drinks, it is difficult to affirm the effects of each substance interacting with ethanol. While caffeine is considered to be an excitatory substance, TA may act as a CNS inhibitor, just like alcohol, through the stimulation of inhibitory receptor agonists [7]. TA has been used in the treatment of alcoholism and to improve physical performance. In animals, the quantity of extra-cellular TA in the CNS was found to increase immediately after alcohol ingestion, thus suggesting a protecting effect of cerebral activity deriving from alcohol intake [8]. Whereas the CNS has multiple and complex functions, the combination of these two related substances and the exercise could clarify physiological mechanisms in response to neural stimulus. Although TA has been used as an alternative therapy [9] and as a performance enhancer during exercise [10], no studies have been conducted with human beings about the acute effects of such amino acid on electrocortical activity in the frontal cortex, when ingested alone or together with alcohol, before and after exercise. Quantitative electroencephalography (qEEG) is a non-invasive tool of electrocortical activity analysis, and it has been widely used to assess the influence of physical exercise and of different substances in the central nervous system. After exercise, cortical activity may increase or decrease, depending on the physical exercise protocol and on the analyzed cortical region [11]. Beta frequency band has been used to evaluate the post-exercise effects, mainly in the brain frontal regions [11–13]. Nevertheless, the impact of the TA, ET and exercise on EEG activity remains unknown. Our objective was to apply the qEEG in order to investigate the acute effect of ET, TA and both of these substances together in the frontal cortex before and after exercise. In particular, beta absolute power (13–30 Hz) was analyzed; this is a fast frequency and it is associated with the alertness/attention state and with motor activity. We hypothesize that the cortical activity (ABP) may be affected by these substances in the frontal cortex areas before and after exercise. Furthermore, TA may modulate ET effect when ingested together.\n\nBODY.MATERIALS AND METHODS.SUBJECTS:\nAll participants, five healthy women (22 ± 3 years) and four healthy men (26 ± 5 years), were right-handed, regular drinkers of alcoholic beverages, amateur practitioners of physical exercise and non-smokers. The participants were asked to avoid physical activities with more than 5 metabolic equivalents (METs) and any food containing caffeine, alcohol and taurine for 48 hours before the test. Individuals with liver disorders(as determined by the activity of the enzymes aspartate amino-transferase, alanine aminotransferase, direct and indirect bilirubin, alkaline phosphatase, gamma-glutamyl transferase and lactatedehydrogenase) or who were taking medications, as well as alcohol users with a weekly intake greater than fifteen or less than two alcohol servings were excluded from this study. Volunteers read and signed an informed consent form. All experimental procedures were approved by the local ethics committee of University Hospital Clementino Fraga Filho (HUCFF) at Federal University of Rio de Janeiro (03899312.5.0000.5257). All of research protocols described here were carried out in accordance to the declaration of Helsinki\".\n\nBODY.MATERIALS AND METHODS.EXPERIMENTAL DESIGN:\nThis study lasted approximately five weeks for each participant. The experiment began with an anthropometric and an effort test. During the following visits (once a week), a particular intervention was applied in randomized order (PL, TA, ET or TA+ET). The experimental design of these tests was in agreement with a specific treatment, using a protocol described previously [14]. Six grams of microcrystalline cellulose were diluted in 150 ml of an artificial orange juice (Clight®, 21 g.L-1) and used as the placebo (PL) solution, while six grams of powdered taurine (TA) were used for the experimental solution. Ethanol (Orloff® vodka, Resende, RJ, Brazil—38% alcohol content) was administered in doses of 0.6 ml. kg-1, combined with the ingestion of artificial orange juice in a proportion of 2:1 (juice: vodka). The TA and PL solutions were ingested two hours before the exercise, while the ET alcoholic beverage was ingested thirty minutes before the exercise. Such ingestion time was determined according to the peak plasma levels of each substance after intake [15]. In the TA+ET treatment, ethanol was ingested one hour and thirty minutes after the administration of taurine; Taurine administration followed a simple double-blind procedure. The EEG was recorded at the peak and post-exercise. Since the frontal region is related to executive functions, our aim was to observe the frontal regions dynamics in order to evaluate cognitive alterations when subjects were under drug influence.\n\nBODY.MATERIALS AND METHODS.ERGOMETRIC PROTOCOL:\nA continuous and maximal load ramp testing on a cycle ergometer with an electromagnetic brake (Imbrasport®, Porto Alegre, RS, Brazil) was used to determine maximal power output (Wmax), maximal aerobic power (V ̇O2max) and anaerobic threshold (Vista Mini-CPX®, Vacumed®, Ventura, CA, USA). The test started with the subject seated on a cycle ergometer for six minutes, followed by a four-minute warm-up pedaling without any load. After the warm-up, the maximum test was performed according to the procedures described by Nogueira and Pompeu [16]. The effort perceived exertion was determined at the end of each minute. A constant-load protocol (SWT), with an intensity 10% lower than the load of the anaerobic threshold set for the maximum effort test was adopted for 10 minutes at a rate of 60 revolutions per minute (RPM) as a physical tool for the ergometric test, causing a stress on the body, in order to help in the analysis of ABP under the influence of PL, TA, ET and TA+ET.\n\nBODY.MATERIALS AND METHODS.BLOOD COLLECTION—BIOCHEMICAL ANALYSIS:\nSerum and plasma were obtained from peripheral blood samples at three moments (at the beginning, thirty minutes after ethanol ingestion and immediately after exercise) for each treatment (ET and TA+ET). Serum levels of liver enzymes were determined using the VITROS® Chemical System and plasma Ethanol levels by Siemens Dimension® Series.\n\nBODY.MATERIALS AND METHODS.ACQUISITION OF ELECTROENCEPHALOGRAPHIC SIGNAL:\nThe EEG signal capture was performed using the BrainNet-BNT device 36 (EMSA, Medical Instruments, Brazil). Twenty monopolar electrodes were arranged following the 10/20 International System Protocol. The impedance of the electrodes was maintained between 5 and 10 kΩ. Recorded data had a total range of less than 70 μV. The data signal was amplified with a gain of 22,000, analogically filtered between 0.01 Hz (high-pass) and 80 Hz (low-pass), and sampled at 200 Hz. The Data Acquisition software (Delphi 5,0TM, USA) from the Brain Mapping and Sensory Motor Integration Lab was employed with the digital notch filter (60 Hz).\n\nBODY.MATERIALS AND METHODS.DATA PROCESSING AND ANALYSIS:\nVisual inspection and independent component analysis (ICA) were applied to remove possible sources of artifacts produced during data collection. The data were collected using a bi-auricular reference, and they were transformed using the average reference after ICA was applied and artifact elimination was concluded. Through ICA and visual inspection, all the ranges which clearly showed artifacts such as blinking and muscle-related movements were removed. A classic estimator was applied for the power spectral density (PSD) performed by MATLAB 5.3 (Matworks, Inc.).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nStatistical analysis was performed using the Statistical Package for the Social Sciences® (SPSS® Inc., Chicago, IL, USA), SigmaPlot® (Systat® Software Inc., Chicago IL, USA) and Microsoft Excel® for Windows® (Microsoft®, Redmond, WA, USA). In order to analyze the absolute power, two-way ANOVA was used (treatment vs. moment) in order to assess the interaction of absolute beta power (ABP) between treatment and moment for all frontal electrodes. When an interaction between factors was found, a one-way ANOVA (Bonferroni post-hoc) was applied to each treatment for all frontal electrodes. A ANOVA one-way was conducted to compare ethanol concentration in the plasma between moments (baseline, peak and post-exercise) to each treatment (ET and TA+ET). A Student t-test was used to compare ethanol concentration in the plasma moments in different treatments (ET Baseline vs. TA+ET Baseline; ET peak vs. TA+ET peak; ET post-exercise vs. TA+ET post-exercise). Descriptive statistics were used with the mean ± standard error (se) (p ≤ 0.05). The p-value was adjusted through the bonferroni correction for multiple comparisons. The effect size was estimated using the Cohen's d method.\n\nBODY.RESULTS:\nWhen investigating the ethanol concentration in the plasma in ET and TA+ET treatments, a significant increase was seen for both treatments, compared to the Baseline values (0 mmol.L-1). However, there was no significant difference between baseline, peak and post-exercise to each treatment. Also, there was no significant difference between treatments when comparing the specific moments (ET Baseline vs. TA+ET Baseline; ET peak vs. TA+ET peak; ET post-exercise vs. TA+ET post-exercise) (Table 1). 10.1371/journal.pone.0194264.t001 Table 1 Plasma ethanol concentrations. Treatment Plasma ethanol concentration (mmol . L -1 ) 30 min after the ingestion P value Post-exercise P- value TA+ET 13.7 ± 2.9 0.001 10.9 ± 1.4 0.001 ET 12.3 ± 4.3 0.001 9.7 ± 2.0 0.001 Values are expressed as means and SDs. Baseline values equal to 0 mmol . L -1 . ** Significant difference compared to the baseline for each treatment. A two-way ANOVA (moment vs. treatment) demonstrated interaction between the two factors for all investigated electrodes [Fp1- F(11;13795) = 7.156, η2p = 0,003, p<0.001; Fp2—F(11;13795) = 17.794, η2p = 0,008, p<0.001; F7—F(11;13795) = 26.174, η2p = 0,011; F8—F(11,13795) = 29.548., η2p = 0,013, p<0.001; F3—F(11,13795) = 22.903, η2p = 0,010, p<0.001; Fz—F(11,13795) = 18.800, η2p = 0,008, p<0.001; F4—F(11,13795) = 26.289, η2p = 0,011, p<0.001]. With the aim to analyze in detail all interactions found between moment and treatment, a one-way ANOVA was conducted separately for each treatment (PL, TA, ET and TA+ET). Interaction analyses are reported below. The effect sizes for all variables were summarized in S1 Table.\n\nBODY.RESULTS.ANTERIOR PREFRONTAL CORTEX (FP1 AND FP2):\nDifference was found at Fp1 between the baseline and post-exercise moments (p<0.05) and between peak and post-exercise (p<0.05) for the PL, ET and TA treatments. On the other hand, at Fp2, difference was found among moments for all treatments. For the PL, ET and TA treatments, difference was observed among all moments (p<0.05). For ET+TA, significant difference occurred between the baseline and post-exercise (p<0.001) and between the peak and post-exercise (p = 0.009) moments (Fig 1). 10.1371/journal.pone.0194264.g001Fig 1Absolute beta power of anterior prefrontal.Values are expressed as means and standard error. * Significant difference (p ≤ 0.05). This figure shows the absolute beta power of anterior prefrontal area (Fp1 e Fp2), in each treatment (Placebo, Taurine, Ethanol and Taurine + Ethanol) before (baseline and peak) and after (post-exercise) exercise.\n\nBODY.RESULTS.INFERIOR PREFRONTAL GYRUS (F7 AND F8):\nFor the F7 electrode, difference was found between the baseline and peak (p<0.05), and between peak and post-exercise (p<0.05) moments for the ET and TA treatments. For the TA+ET treatment, difference occurred between the baseline and peak moments (p<0.001), and between baseline and post-exercise (p = 0.021). On the other hand, in the PL treatment, difference was observed between the baseline and post-exercise moments (p<0.001), and between peak and post-exercise (p<0.001). At F8, significant difference was found between the baseline and post-exercise moments (p<0.05) and between peak and post-exercise (p<0.05) for the ET and ET+TA treatments. For the PL treatment, significant difference was identified between the baseline and peak moments (p<0.001) and between baseline and post-exercise (p<0.001). And for the TA treatment, difference was found at all moments (p<0.05) (Fig 2). 10.1371/journal.pone.0194264.g002Fig 2Absolute beta power of inferior prefrontal gyrus.Values are expressed as means and standard error. * Significant difference (p ≤ 0.05). This figure shows the absolute beta power of inferior prefrontal gyrus (F7 e F8), in each treatment (Placebo, Taurine, Ethanol and Taurine + Ethanol) before (baseline and peak) and after (post-exercise) exercise.\n\nBODY.RESULTS.SUPERIOR FRONTAL GYRUS (F3, FZ AND F4):\nFor the F3 electrode, significant difference was only found for PL and ET+TA. In the PL treatment, significant difference was observed between all moments (p<0.05); in the ET+TA treatment, difference occurred between the baseline and peak moments (p<0.001) and baseline and post-exercise (p<0.001). For the F4 electrode, significant difference was found among all moments in the TA treatment (p<0.05). In the ET+TA treatment, significant difference was found between the baseline and post-exercise moments (p<0.001), and between baseline and peak (p<0.001). On the contrary, for the PL treatment, difference was observed between the baseline and post-exercise moments (p<0.001) and between peak and post-exercise (p<0.001). At Fz, just like at F4, significant difference occurred among all moments (p<0.05) for the TA treatment. Significant difference was found between the baseline and post-exercise moments (p<0.001) and between baseline and peak (p<0.001) for the ET+TA treatment. In the PL treatment, significant difference was observed between the baseline and post-exercise moments (p<0.001), and between peak and post-exercise (p<0.001) (Fig 3). 10.1371/journal.pone.0194264.g003Fig 3Absolute beta power of superior frontal gyrus.Values are expressed as means and standard error. * Significant difference (p ≤ 0.05). This figure shows the absolute beta power of superior prefrontal gyrus (F3, F4 e Fz), in each treatment (Placebo, Taurine, Ethanol and Taurine + Ethanol), before (baseline and peak) and after (post-exercise) exercise.\n\nBODY.DISCUSSION:\nThe present study aimed to analyze the effect of TA, ET and these two substances administered together on the electrocortical activity, before and after moderate intensity exercise. An overwiew of these results was available as a cartoon (Fig 4). Specifically, changes in the absolute beta power in the frontal cortex were assessed. We hypothesize that the cortical activity (ABP) may be affected by these substances in the frontal cortex areas before and after exercise. Furthermore, TA may modulate ET effect when ingested together. Despite acknowledging the complexity of cerebral activity and of its multiple networks at various frequencies, due to methodological reasons, the discussion of electrophysiological data has been divided into three different subtopics, related to the areas associated with the investigated electrodes, as follows: Superior Frontal Gyrus—SFG (F3, Fz and F4); Anterior Pre-Frontal Cortex—PFC (Fp1 and Fp2); Inferior Frontal Gyrus–IFG (F7 and F8). 10.1371/journal.pone.0194264.g004Fig 4A cartoon representation demonstrates an overview of the absolute beta power results in different areas of frontal cortex.The arrow \"↑\" means an increase of absolute beta power. The arrow \"↓\" means a decrease of absolute beta power and the double arrow \"↔\" means no modification in absolute beta power.\n\nBODY.DISCUSSION.SUPERIOR FRONTAL GYRUS—SFG (F3, FZ AND F4) AREA—8 AND 8L:\nBrodmann area 8 is considered to be an important area for motor learning. Studies from the literature have demonstrated this area to be responsible for starting, keeping, coordinating and planning complex movement sequences [17]. The transformation of such sensory signals into motor responses occurs through the visual and auditory systems [18]. In addition, this area also acts in working memory [19] and it may be involved in a cognitive control process, which is able to modulate the current emotional state [20]. As expected, no difference was found between the baseline and peak moments in the PL treatment for most of the electrodes relate to this region (i.e., Fz and F4), except in F3. However, a decrease in beta power was observed at the post-exercise moment, when compared to the others. Kubitz and Pothakos [21] have also observed a decrease in beta values after exercise. Nevertheless, Moraes et al. [12] and Bailey et al. [22] verified an increase in absolute beta power for F3 and F4 immediately after exercise. Kubitz and Mott [23] have not found any difference in absolute beta power before or after exercise. The different exercise intensity and duration and the time of cortical activity measurement may be involved with the different results. Such difference in the methods leads to different physiological responses (i.e. temperature, cerebral blood flow and hypoxia), which may influence the brain, therefore generating different results Lardon and Polich [24]. Bailey et al. [22] state that exercise intensity may affect cerebral activity: the greater the intensity, the greater the cerebral activity and, therefore, the beta values. The time of cortical activity measurement after exercise may also influence on beta values; in this same study, such values were found to be greater immediately after exercise, when compared to the pre-exercise moment, showing no difference between the pre- and post- moments when measured 10 minutes after exercise. Results by Petruzzello and Landers [25] also show a decrease in cortical activity along time for F4, when a comparison was done between the 10th and 30th minute after exercise. In the TA treatment, difference was found for the Fz and F4 electrodes, with TA causing beta increase at Fz and beta decrease at F4. With regards to the post-exercise moment, an increase in beta power was found for both electrodes, when comparing this moment to the others. Taurine is used to improve exercise performance. Reports from the literature highlight some metabolic benefits for the membrane, fat oxidation, insulin sensitivity and cardiac muscle; however, its acute and chronic effects on the CNS need to be better investigated during exercise [10, 15] (Balshaw et al., 2013; Galloway et al., 2008). Taurine ingestion may benefit the cardiac and skeletal muscles, by modulating the Calcium channels, therefore favoring cardiac contraction and helping with blood distribution [7]. Such greater cerebral blood flow, deriving from the response to TA ingestion, may influence greater cerebral activation (greater ABP values) at FZ and F4, after exercise [24]. It is important to highlight that no significant difference was found in the ET treatment for this region. Such findings are in agreement with the results in the studies by Ehlers et al. [26] and Cohen et al. [27], where no significant difference in ABP was found for the F3 and F4 electrodes (left and right side of this area, respectively), when comparing the moments before and after substance intake. Such responses may have occurred due to the similar ET quantity ingested in both studies mentioned in this research, with a consumption level between 0.6 and 0.8 ml/kg. In spite of such result, Zheng et al. [28] found ET to have an effect on the superior frontal gyrus, pointing out possible alterations in the CNS, such as: memory, motor control, cognitive ability and spatial function. The aforementioned authors observed changes in the alpha band values (lower frequencies) in this region, thus justifying the ET depressive effect in this area. On the other hand, in the ET+TA treatment, similar results were found for the whole superior frontal gyrus region (F3, F4 and Fz), with an increase in ABP at the peak and exercise moments, when compared to the baseline moment. Since no changes in ABP were found in this region for the ET treatment, and since similar results were found for the TA treatment after exercise, TA is suggested to stand out, with similar physiological adaptations to the TA treatment during exercise, thus influencing beta values increase after exercise. No reports about the effect of both TA and TA+ET on this region are present in the literature. Network changes in this region may cause impairment in motor and executive functions, working memory and high-demand cognitive functions [29]. Li et al. [30] observed a decrease in the grey matter volume in the SFG in patients with Parkinson's disease, when compared to healthy individuals, suggesting a relation with the motor impairment typical of the disease. The greater ABP values found after exercise, in both TA and TA+ET treatments, when compared to baseline indicate greater cerebral activity after exercise in this region, with possible function improvement.\n\nBODY.DISCUSSION.ANTERIOR PRE-FRONTAL CORTEX (FP1 AND FP2):\nThe pre-frontal cortex (Brodmann area 10) has been associated with complex executive functions (executive control of behavior, decision making and inferential reasoning) and it plays an important role in memory control and manipulation, in addition to being also related to emotional and cognitive tasks [31]. On the other hand, beta is a fast frequency associated with attention processes, arousal and movement execution [32]. Our results highlighted an interaction between moment and treatment factors, that is, changes in the beta cortical activity in this region will occur according to the ingested substance and to the treatment moment (i.e., baseline, peak or post-exercise). Specifically, when investigating the left anterior pre-frontal cortex (Fp1) and the right pre-frontal cortex (Fp2), the TA and ET conditions were found to have an effect on the right pre-frontal cortex during the performance peak, with no difference between the baseline and peak moments in the left pre-frontal cortex for all conditions. In particular, all substances caused a decrease in beta power during its performance peak. As observed for ABP, changes in the right hemisphere may be related to the substance effects on some specific functions of this area. The anterior pre-frontal cortex is directly related to visuospatial prospective memory. In addition, the ABP oscillations are associated with motor activity, thus we hypothesized this frequency band to be involved in keeping the current sensory/cognitive state [32]. This region is strictly related to risk decision making; according to Kwon et al. [31], risk decisions are more related to the right side of this region, suggesting these decisions to be dependent on the level of activation of this side. On the other hand, Aron et al. [33] state the right side to be responsible for suppressing memories and for responding to visual and auditory distractions. According to Arnsten [34], the PFC is crucial to centralize attention onto a specific task and to regulate behavior and emotions, especially to inhibit inappropriate emotions, impulses and habits. This region is also necessary for goal planning as well as behavior and thought organization. Mainly the right hemisphere is important to regulate distractions, inappropriate behavior and emotional response. As with regards to specific treatments, decrease in ABP was found in the PL treatment for the post-exercise moment, when compared to the baseline moment. The different intensities and duration of exercise have an influence in the acute physiological adaptations, which could interfere in the electrocortical activity. For example, catecholamines and temperature regulation, also modulated by the hypothalamic nucleus, may influence beta activity [35]. However, more studies are needed to better understand the mechanisms inherent to the relation between different exercise protocols and beta activity in this specific region. When analyzing the ET+TA combination, a significant effect was found only in the right anterior pre-frontal cortex, with ABP increase at the post- moment, when compared to the others. Our results suggest the intake of the ET+TA combination alone do not provoke any changes in the anterior pre-frontal cortex; however, exercise potentializes the combination of these two substances, thus causing significant beta power increase in the right anterior pre-frontal cortex. As previously said, this area is directly related to executive control, specifically motor and behavioral executive control, attention, and inhibitory control. In particular, the right hemisphere features characteristics related to spatiality and development of direction sense. Therefore, this study hypothesized beta power increase at Fp2 to be associated with an increase in attention and executive motor control, required for the performance of physical exercise. Despite a beta decrease at the peak moment, TA provokes an increase in beta power during the exercise moment in both hemispheres of the anterior pre-frontal cortex, when ingested alone. Therefore, depending on the region, taurine may decrease electrocortical activity; this finding is in agreement with other studies demonstrating the inhibitory effect of this amino-acid on the central nervous system [36]. However, the acute effect of taurine seems to be related to the effect of exercise, with an increase in beta activity after exercise. Some studies found taurine to also increase glutamate receptor activity, through the regulation of cytoplasmic and intramitochondrial calcium regulation [37]. Even when taurine is ingested with alcohol, ABP increased after exercise for Fp2. Since beta plays an initial role in the selective inhibition of some actions and in cognitive control [38], it is possible to suggest that TA may have two important effects: first, it may diminish beta activity and negatively alter the two aforementioned tasks; secondly, it may increase cortical activity and, consequently, beta values, thus improving the performance of such tasks. In the ET treatment, this substance was found to also play an important role in the right anterior pre-frontal cortex; however, in addition to the ET intake alone decreasing ABP, the combination of ET and exercise also provokes decrease in beta power. Such results are in agreement with the literature about ethanol effects before and after intake, with lower cortical activity caused by the acute effect of the substance [39] mainly at Fp2 [40]. Such electrocortical activity decrease in this region may negatively influence some processes, such as working memory and decision making [5]. This may happen due to the ethanol effects on the CNS, directly facilitating GABA neurotransmitter transmission and inhibiting the glutamate neurotransmitter functions [1]. Few studies have related beta band to this region (PFC). Researches in the literature performed with animals (monkeys) affirm that beta neuronal synchronization involves execution tasks, such as rule selection. A given rule is represented by a group of PFC neurons, oscillating in synchrony at this frequency [41]. Buschman et al. [42] also demonstrate beta band synchrony in the PFC of monkeys to select the most relevant group of rules. Studies with humans highlight beta oscillations to start the cognitive control and selective inhibition process in the PFC [38]. In other words, specifically in this region, the alcohol effects are found and suggested to significantly influence inhibition decrease. Empirically, it is possible to observe people who consume alcohol in bars and restaurants becoming more extroverted and disinhibited and acting in a certain way, only because they were under the influence of such substance.\n\nBODY.DISCUSSION.INFERIOR FRONTAL GYRUS–IFG (F7 AND F8):\nTraditionally, the IFG has been widely associated with aspects related to language and semantics [43]. In addition to this, the activation of such area may be related to selection tasks and working memory (spatial and non-spatial) [19]. Activities in this area may also reflect the inhibition of a motor act associated with a reactive emotional response [20]. Increase in beta activity may be associated with increased cortical activity, and according to Gilbertson et al. [44], beta increase may be related to worse movement performance, demonstrating triggered voluntary movements to be smaller when beta activity is greater. However, the ability to perform a Go/NoGo task was associated with the increase in beta band activity in the IFG [45]. In this region, interaction between the moment and treatment factors was also found for the two analyzed electrodes. In the PL treatment, decrease in ABP occurred at the baseline moment, compared to the post-exercise moment in this area. Schneider et al. [13] have also observed similar results after moderately intense running, that is, exercise causes decrease in absolute beta power. A study by Li et al. [11] is in agreement with such results; they identified a decrease in the left IFG cortical activity after exercise. On the other hand, in the ET+TA treatment, increase in ABP was found for the peak moment, when compared to baseline only at F7, demonstrating this treatment to influence beta power only in the left IFG. However, beta increase was verified at the post-exercise moment for both left and right IFG, showing an influence of exercise on absolute beta power in both hemispheres. Despite acamprosate (a substance containing TA) being used in the treatment of alcoholics in order to reduce ethanol-abstinence symptoms Plosker [46], there are no studies in the literature about the acute effect of TA+ET on the electrocortical activity in humans. Taurine seems to maximize the effects of alcohol in the left hemisphere of the IGF, considering that beta activity stayed high after exercise in the TA+ET treatment. On the other hand, in the right hemisphere, the TA effect together with ET did not modify beta activity, considering that the TA+ET results were similar to the ET ones. In great part of the frontal cortex, TA seems to increase beta activity after exercise, even with ET intake. We hypothesized the increase in cortical activity after exercise to be related to the TA effects on the modulation of the glutamate receptor activation, through the cytoplasmic and intramitochondrial calcium regulation [47]. In a study with animals, the acute administration of TA+ET, TA was proved to exert a neuroprotecting action on the apoptosis induced by the acute effect of ethanol on the cerebellum [48]. The pioneer present study allows verifying the cortical activity of the TA+ET acute administration in humans, but the mechanisms inherent to the effects of such substances on the CNS need to be furtherly studied. In the ET treatment, a substance influence on the left hemisphere of this area (F7) was found, provoking an increase in beta power. However, when ET is combined with exercise, an increase in beta power is found in the right hemisphere (F8), while decrease in beta power is found in the left hemisphere (F7) of this region. The area correspondent to the right hemisphere (F8) is activated when cognitive tasks require inhibition [49]. In addition to the function related to language, the IFG activation may occur during the execution of distal movements, such as grabbing, and is also directly related to mirror neurons for expressive movements [50]. We suggest that some of these specific functions related to the IGF may have been influenced by alcohol intake and exercise, seen through changes in beta activity. Therefore, it is possible to observe this small dose of ET to alter the left IFG activity, thus possibly affecting some specific functions of this region, such as attention [19]. In terms of TA treatment, TA was seen to provoke a decrease in beta power in both hemispheres. Furthermore, in TA treatment, absolute beta power increased in the right side of this region after exercise, thus showing interaction between such amino acid and exercise. Such effect may interfere in some tasks associated with this region, since the right inferior frontal gyrus is directly related to some specific brain functions, such as inhibitory and attention control [51]. The absolute beta power decrease at the peak moment may be explained by its already proven inhibitory effects [47]. Studies involving the effect of TA have been increasing in recent years due to their potential physiological influence. In addition, the simultaneous use of TA and ET justifies a better understanding of the acute effects of these substances. The complexity of CNS and the multiple, distinct, and important functions that each of its regions play, generate innumerable interpretations of brain functions. Thus, the combination of two substances that appear to be metabolically associated, and exercise as a physiological stressor, provide a more comprehensive understanding of the relationship of those compounds and the operation of CNS. Although our work has shown attractive results, some limitations could be highlighted: the amount of ET administered in comparison to some studies was small. It would be applicable to evaluate these effects in higher ET concentration. The taurine peak levels were defined from literature data. The analysis of taurine serum levels could avoid possible problems involving individual variability of this measure and also improve the explanation of the results. It is a fact that counterbalanced design favors the number of cell cases for each condition and, consequently, the sample size. However, evaluating a larger number of subjects and the gender effect would be interesting due to the great interindividual variability of neural measures. In summary, due to many different results, we can highlight that the acute effect of placebo ingestion decreased the electrocortical activity after exercise. The TA acute effect seems to inhibit the superior frontal region at the plasma peak; however, in such region, the TA effect increases ABP after exercise. A small ET dose was not enough to alter beta activity in the superior frontal area and it was sufficient to diminish it on the left side of the brain (Fp1 and F7) after exercise. We could observe that the ingestion of taurine in combination with ethanol showed different results of the ingestion of ethanol separately. TA when ingested together with ET had an similar effect in the right side (Fp2, F8, F4) of the frontal cortex that TA treatment after exercise. More research is thus needed to better understand the mechanisms involved in the CNS response, such as electrocortical activities and frontal cortex functions, to such substances (TA and ET) with different dosage, exercise type and intensity.\n\nBODY.SUPPORTING INFORMATION:\nS1 TableThe effect sizes for variables of frontal cortex, moments and treatments.(DOCX)Click here for additional data file.\n\nQuestion: Compared to Placebo—PL what was the result of Taurine combined with Ethanol (TA+ET) on absolute beta power (ABP) after exercise?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1156	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Pioglitazone Decreases Hepatitis C Viral Load in Overweight, Treatment Naïve, Genotype 4 Infected-Patients: A Pilot Study\n\n ABSTRACT.BACKGROUND:\nInsulin resistance (IR) is induced by chronic hepatitis C virus (HCV) genotypes 1 and 4 infections. It is not known whether drugs that affect IR such as Pioglitazone and Prednisone also affect serum HCV RNA titers independently of PEG-Interferon-α2/ribavirin treatment. The primary aim was to assess whether Pioglitazone by improving IR and/or inflammation decreases HCV viral load independently of standard of care HCV treatment. A secondary aim was to assess whether Prednisone, a drug that induces insulin resistance and stimulates HCV viral entry and replication in replicon culture systems, increases HCV viral load in this population.\n\nABSTRACT.METHODOLOGY/PRINCIPAL FINDINGS:\nWe designed a two-arm, parallel Pilot Study of overweight, treatment naïve genotype 4 HCV-infected patients at a public referral Liver Clinic in Giza, Egypt. The subjects received Pioglitazone (30 mg/day for 14 days) or Prednisone (40 mg/day for 4 days) in a randomized fashion, but the two arms can be considered independent pilot studies. Only changes from baseline within each arm were assessed and no contrasts of the interventions were made, as this was not an aim of the study. Among 105 consecutive HCV genotype 4 patients, 39 were enrolled based on the optimal sample size and power analysis according to the CONSORT statement; 20 to the Pioglitazone group and 19 to the Prednisone group. Pioglitazone was effective in decreasing serum HCV RNA at day-14 (n = 10; difference of means = 205,618 IU/ml; 95% CI 26,600 to 384,600; P<0.001). Although Prednisone did increase serum HCV RNA at day-4 (n = 10; change from baseline = −42,786 IU/ml; 95% CI −85,500 to −15,700; P = 0.049), the log10 HCV RNA titers were statistically not different from baseline day-0.\n\nABSTRACT.CONCLUSION/SIGNIFICANCE:\nThis is the first documentation that Pioglitazone decreases the serum HCV RNA titers independently of PEG-Interferon-α2/ribavirin treatment. The novel findings of our Study provide the foundation for basic and clinical investigations on the molecular mechanisms responsible for the Pioglitazone-induced decrease in HCV genotype 4 RNA titers.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov NCT01157975\n\n\nBODY.INTRODUCTION:\nChronic hepatitis C viral (HCV) infection markedly increased the risk for type 2 diabetes in cohorts with recognized diabetes risk factors [1]. A meta-analysis also found that HCV infection is associated with excess type 2 diabetes risk [2]. Moreover, IR is a specific feature of chronic HCV genotypes 1 and 4 infections since its prevalence is ∼7-fold higher among these patients compared to chronic Hepatitis B-infected patients [3], and changes in IR occur among patients with chronic HCV infection during and after treatment of HCV with PEG-interferon-α and ribavirin [4]. In patients with genotypes 1, 2 and 3 increased IR was associated with decreased sustained virological response (SVR) [5]. Among patients infected with genotype 1, decreases in Homeostasis Model Assessment (HOMA)-IR correlated with obtaining an SVR and increases in HOMA-IR were observed in patients who relapsed [6]. Similarly, IR may correlate with the virological response to standard of care treatment of HCV genotype 4 patients in Egypt [7]. Because Pioglitazone, a peroxisome proliferator-activated receptor (PPAR)-γ agonist, improves insulin sensitivity [8] and it is also effective in controlling liver inflammation in subjects with non-alcoholic steatohepatitis (NASH) [9], it has been used as triple therapy in addition to PEG-interferon-α and ribavirin to treat HCV-infected patients. The study in HCV genotype 1 non-responders was terminated when none of the five patients responded to the triple therapy at week 12 [10]. In contrast, Pioglitazone improved virological response to PEG-interferon α-2b/ribavirin combination therapy in hepatitis C genotype 4 treatment naïve patients with insulin resistance [11]. However, the mechanisms by which Pioglitazone influenced SVR in treatment naïve patients with HCV genotype 4 infection remain unknown. It is unknown whether Pioglitazone modifies the bioavailability of PEG-interferon α-2b/ribavirin or directly or indirectly affects HCV infection and replication. Therefore, we designed a Pilot Study to assess whether Pioglitazone decreases HCV viral load in overweight HCV genotype 4, treatment naïve patients independently of standard of care PEG-interferon α-2b/ribavirin treatment. A secondary end-point was to analyze whether Prednisone, a drug that induces insulin resistance in susceptible patients [12] and stimulates HCV viral entry and replication in replicon culture systems [13], increases HCV viral load in this population. There were no data available on the effect of Pioglitazone or Prednisone on HCV RNA viral load in patients. Here, we provide the first documentation that Pioglitazone decreases the serum HCV genotype 4 RNA titers independently of treatment with PEG-Interferon-α2/ribavirin. Prednisone did increase serum HCV RNA viral load at day-4 in this cohort.\n\nBODY.METHODS:\nThe protocol for this trial and supporting CONSORT checklist are available as supporting information; see Checklist S1 and Protocol S1.\n\nBODY.METHODS.PARTICIPANTS:\nEligible participants were all overweight (BMI>25 kg/m2), given their susceptibility for IR, adults age 25 to 65 years, with active HCV genotype 4 chronic infection (>10,000 IU/ml viral load) who had a liver biopsy within two years of recruitment (added to the protocol), were treatment naïve (never treated for HCV infection) and met the eligibility criteria for the Study. Exclusion criteria included cirrhosis, the presence of other liver diseases, diabetes, pregnancy, significant clinical co-morbidities, and the inability to provide informed consent. Participants were recruited from July 2010 to February 2011 at the primary care referral of subjects of a disadvantaged social-economical group at the Agouza Hospital in Giza, Egypt. The estimated prevalence of Hepatitis C in Egypt is 12% in adults.\n\nBODY.METHODS.ETHICS:\nWritten informed consent was obtained by the medical staff before entry into the Study. The study was registered at the clinicaltrials.gov website (NCT-01157975) and received Human Subjects' Research approval at the University of California, San Diego (UCSD Human Research protections Program) and at the Agouza Hospital, Giza, Egypt (Director's Research Board) before starting the study. The study protocol conforms to the ethical guidelines of the 1975 Declaration of Helsinki.\n\nBODY.METHODS.OBJECTIVES:\nBecause the objective of the Study was to determine whether Pioglitazone and Prednisone treatment would affect the HCV RNA viral load (decrease and increase it, respectively), and these were not a treatment of the HCV infection in this situation, we decided not to use a placebo since we utilized de-identified samples to blinding the investigators analyzing the outcomes.\n\nBODY.METHODS.INTERVENTIONS:\nEligible subjects were randomly assigned to receive orally Pioglitazone 30 mg/day for 14 days or Prednisone 40 mg/day for 4 days. These medications were taken in the morning. Visits were at screening (up to 30 days before randomization); randomization (day -2); baseline visit (day 0); and follow-up visits for the Pioglitazone group (on days 2, 4, 7 and 14) and the Prednisone group (on days 2 and 4). For safety issues subjects were continued to be seen off protocol at day-7 post-treatment. Blood samples were obtained at each visit for HCV RNA viral load and for inflammatory, adipogenic, and insulin resistance markers. In addition, a 2-hr oral 75 g glucose tolerance test (OGTT) was performed after a 10-hr fast at day-0 before administration of the medication and at the last day of treatment (day-14 for Pioglitazone and day-4 for Prednisone). On all other visits, patients were also fasting. Patients received the first dose of the study drug (oral Pioglitazone 30 mg or Prednisone 40 mg) after blood samples were obtained on day 0. Compliance with the medication was >90% as assessed at each visit.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome with respect to the effect of Pioglitazone in HCV genotype 4 infections was the decrease in HCV RNA viral load at day 14. The secondary outcome with respect to the effect of Prednisone in HCV genotype 4 infections was the increase in HCV RNA viral load at day 4 instead of at day 14 for safety reasons given the potential adverse events associated with longer corticosteroid treatment. Additional secondary outcome measures were insulin resistance (oral glucose tolerance test; serum insulin, C-peptide; HOMA-IR; insulin sensitivity check index (QUICKI); HOMA-B; sex hormone BG (SHBG); resistin; adiponectin) and liver injury (alanine aminotransferase (ALT); aspartate aminotransferase (AST)) and inflammation (serum interleukin (IL)-8, IL-28B, tumor necrosis factor (TNF), IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, monocyte chemokine protein (MCP) and hepatocyte growth factor (HGF)). De-identified blood samples from all the enrolled subjects that received the treatments were analyzed for the standard clinical laboratory tests and for HCV RNA viral load using PCR amplification (COBAS, TACKMAN) (lowest detectable limit: 50 IU/ml). A multiplex peptide detection system (Quansys Biosciences, Logan, UT) was utilized according to the manufacturer's protocol to determine inflammatory, adipogenic, and insulin resistance markers. Values calculated from individual pixels using the Q-View Imager system. An enzyme-linked immunosorbent assay kit was used to determine human adiponectin according to the manufacturer's protocol (BioVision, Mountain View, CA). Surrogate indicators of insulin resistance and β-cell function were analyzed as described previously [14]. The indicators of insulin resistance HOMA1-IR and QUICKI were determined. HOMA1-IR = (FSI×FSG)/22.5 where FSI is fasting serum insulin concentration (μU/l) and FSG is fasting serum glucose (mmol/l). QUICKI = 1/[log (fasting insulin-μU/ml)+log (fasting glucose- mg/dl)]. β-Cell function was assessed by the HOMA –B 20.I0/(G0 -3.5); I0 = fasting insulin in μU/ml and G0 = fasting glucose in mmol/l [14].\n\nBODY.METHODS.SAMPLE SIZE:\nThere were no data available on the effect of Pioglitazone or Prednisone on HCV RNA viral load. However, we considered a reduction of 25% in HCV RNA viral load in 14 days to be relevant as proof of principle of the effects of Pioglitazone on HCV RNA titers. To detect a reduction of 25% in HCV RNA in the Pioglitazone group at day-14 assuming a standard deviation of 20% with a two-sided 5% significance level and a power of 90%, a sample size of 9 patients per group completing the study was necessary, and it was decided to enroll at least 19 subjects per group given an anticipated dropout rate of 50% mainly prior to dosing. Because the cultural environment (unwillingness to tell the research staff that they cannot participate in the study) and the social conditions (such as severe problems with transportation and employer's authorization) were expected to prevent a significant proportion of patients to attend the Clinic for follow-up visits after randomization, a larger number of eligible subjects were randomized to achieve the desirable number of subjects completing the Study. To recruit this number of patients a 12-month inclusion period was anticipated. No interim analysis was performed during the trial. An intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication (10 patients in each group was optimal based on sample size and power analysis).\n\nBODY.METHODS.RANDOMIZATION—SEQUENCE GENERATION:\nParticipants were randomly assigned following simple randomization procedures (computerized random numbers) to one of two treatment groups. Independent pharmacists dispensed either Pioglitazone or Prednisone according to a computer generated randomization list.\n\nBODY.METHODS.RANDOMIZATION—ALLOCATION CONCEALMENT:\nThe decision to accept or reject a participant was made, and informed consent was obtained from the participant, in ignorance of the next assignment in the sequence.\n\nBODY.METHODS.RANDOMIZATION—IMPLEMENTATION:\nBlock randomization was by a computer generated random number list prepared by a pharmacist with no clinical involvement in the trial. After the research nurse had obtained the subject's consent, she contacted the pharmacist who was independent of the recruitment process for allocation consignment.\n\nBODY.METHODS.BLINDING:\nWhereas patients and physicians allocated to the intervention groups were aware of the allocated arm, outcome assessors and data analysts of primary and secondary end-points were kept blinded to the allocation.\n\nBODY.METHODS.STATISTICAL METHODS:\nAn intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication. The primary and secondary endpoints were assessed with a paired-sample t-test. We also explored correlations between IL8 and TNFα using Pearson's correlation coefficient with 95% confidence intervals. The significance level was fixed at α = 5% for all tests. All analyses were carried using R version 2.12.2 (2011 Vienna, Austria; http://www.R-project.org).\n\nBODY.RESULTS.PARTICIPANT FLOW:\nThe optimal subjects' recruitment number was pre-determined by sample size and power analysis as described above. One hundredth and five consecutive patients with chronic Hepatitis C genotype 4 referred to the Hepatology Clinic were assessed for eligibility (\nFig. 1\n). Among these 105 patients, 66 were excluded because they did not meet the eligibility criteria (42 subjects), they refused to participate (8 subjects), or for other reasons (16 subjects). Therefore, 39 patients were randomized; 20 to the Pioglitazone group and 19 to the Prednisone group. Ten patients in each group received the allocated intervention, while 10 patients in the Pioglitazone group and 9 patients in the Prednisone group were unable to participate because of their inability to attend the Clinic visits. These patients did not receive the allocated intervention (\nFig. 1\n). The randomized groups that received the allocated intervention were balanced in regards to age, gender, HCV genotype and titers and the severity of their liver disease (\nTable 1\n). 10.1371/journal.pone.0031516.g001Figure 1Participant Flow.Patients with chronic Hepatitis C genotype 4 referred to the Hepatology Clinic were assessed for eligibility as described in Methods. 10.1371/journal.pone.0031516.t001 Table 1 Baseline demographic and clinical characteristics of treated subjects. Pioglitazone (N = 10) Prednisone (N = 10) \n P value \n \n Age (years) 44 (9.3) 42(10.4) 0.592 \n Sex (male) 7 (70%) 8 (80%) 0.429 \n Ethnic origin: Arab \n 10 (100%) 10 (100%) 1.000 \n Height (cm) 173 (5.8) 175(8.7) 0.458 \n Weight (kg) 88.3 (9.2) 85.7(9.9) 0.550 \n BMI (kg/m 2 ) 29.5(1.5) 27.9(1.6) 0.027 \n HCV Genotype 4 \n 10 (100%) 10 (100%) 1.000 \n HCV RNA (log 10 ) 5.41(0.80) 5.10(0.92) 0.432 \n Albumin (g/dl) 3.8(0.3) 3.8(0.3) 0.939 \n Total bilirubin (mg/dl) 0.97(0.15) 0.90 (0.16) 0.319 \n ALT (IU/ml) 63 (23) 53 (14) 0.283 \n AST (IU/ml) 54 (17) 52 (11) 0.795 \n Metavir score: \n \n A (inflammation) A1(n:5) A2(n:5) A1(n:5) A2(n:5) 1.000 \n F (fibrosis) F1(n:7); F2(n:3) F1(n:6); F2(n:4) 0.639 Data are means (SD) or numbers (%). The patients that did receive the allocated intervention were similar in demographics, ethnicity and degree of liver disease to those that did not receive the allocated intervention (\nTable 2\n). By chance allocation, the serum ALT was lower in the group that received Prednisone than in the group that did not received the allocated Prednisone (53 vs 69 IU/ml; P = 0.012) (\nTables 1\n\nand\n\n2\n). 10.1371/journal.pone.0031516.t002 Table 2 Baseline demographic and clinical characteristics of non-treated subjects. Pioglitazone (N = 10) \n P value \n Prednisone (N = 9) \n P value \n \n Age (years) 39 (4.2) 0.139 43(11.2) 0.842 \n Sex (male) 6 (60%) 0.660 5 (55%) 0.277 \n Ethnic origin: Arab \n 10 (100%) 1.000 9 (100%) 1.000 \n Height (cm) 172 (5.9) 0.706 177(8.1) 0.612 \n Weight (kg) 85.7 (7.6) 0.499 84.8(8.8) 0.837 \n BMI (kg/m 2 ) 28.8(2.1) 0.402 28.2(3.7) 0.818 \n HCV Genotype 4 \n 10 (100%) 1.000 9 (100%) 1.000 \n ALT (IU/ml) 68 (10) 0.536 69 (10) 0.012 \n AST (IU/ml) 63 (12) 0.188 57 (8) 0.278 \n Metavir score: \n \n A (inflammation) A1(n:4); A2(n:6) 0.673 A1(n:4); A2(n:5) 0.821 \n F (fibrosis) F1(n:5); F2(n:5) 0.388 F1(n:5); F2(n:4) 0.855 Data are means (SD) or numbers (%). P values are for comparisons between treated and untreated subjects within the same arm. No participant was excluded after randomization because they were found not to meet eligibility criteria. All the patients allocated to the interventions (10 in each arm) completed the study (\nFig. 1\n).\n\nBODY.RESULTS.BASELINE DEMOGRAPHIC AND CLINICAL CHARACTERISTICS:\nAn intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication; all of these patients had a subsequent efficacy observation (10 patients in each group). As outlined in \nTable 1\n, all patients were middle age Egyptian Arabs, predominantly males that had HCV genotype 4 with mild or moderate inflammation (A1 and A2, respectively) and mild or moderate fibrosis (F1 and F2, respectively) on their liver biopsy. They had normal albumin and total bilirubin and mild increase in ALT/AST. All subjects were overweight and five were obese (body mass index, BMI; the weight in kg divided by the square of the height in meters was >29 kg/m2: 3 in the Pioglitazone group and 2 in the Prednisone group). By chance allocation, the BMI was higher in the group receiving Pioglitazone than in the group receiving Prednisone (29.5 vs 27.9 kg/m2; P = 0.027) (\nTable 1\n). There was no indication that significant chance imbalances had occurred between the two groups. Further, no direct analysis between the two groups was intended for the primary or secondary end points. Rather, a comparison between baseline and post-treatment results within each group was the Pilot Study's intent.\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON SERUM HCV RNA TITERS:\nPioglitazone decreased serum HCV RNA titers in overweight HCV genotype 4, treatment naïve patients. In the Pioglitazone-treated group, the log10 transformed HCV RNA titers were statistically different from baseline day-0 (5.41+/−0.80) on day-14 (5.24+/−0.79; P<0.001) and day-7 (5.30+/−0.78; P = 0.009) (\nTable 3\n), providing evidence that Pioglitazone was effective in decreasing HCV RNA in this cohort of patients. Pioglitazone treatment decreased the HCV RNA from baseline in 9 out of 10 subjects at day-7. The log10 HCV RNA values were also decreased by day-4 but they were statistically not different from baseline (5.38+/−0.78; P = 0.059). The log10 HCV RNA values were not affected at day-2 by Pioglitazone treatment. Further, the decrease in the log10 HCV RNA between day-7 and day-14 was highly significant (mean change = 0.063; 95% CI, 0.045; P<0.001) (\nTable 3\n). 10.1371/journal.pone.0031516.t003 Table 3 Effects of Pioglitazone on serum HCV RNA titers. Day HCV (IU/ml ×10 −3 ) \n P value \n \n 95% CI \n HCV log 10 \n \n P value \n \n 95% CI \n \n 0 \n 608.2(696.4) 5.41(0.80) \n 2 \n 586.9(663.9) 0.178 −11.5, 53.9 5.41(0.78) 0.854 −0.029 \n 4 \n 531.5(553.6) 0.151 −33.6, 186.9 5.38(0.78) 0.077 −0.002 \n 7 \n 455.3(504.4) 0.044 4.8, 300.7 5.30(0.78) 0.001 −0.156 \n 14 \n 402.5(452.4) 0.029 26.6, 384.6 5.24(0.79) <0.001 −0.215 Values are mean (SD) of HCV RNA titers determined as described in Methods . In spite of the variable baseline HCV RNA viral load, Pioglitazone also decreased significantly the absolute HCV RNA levels at day-14 (mean change = 205,618 IU/ml; P = 0.028) and at day-7 (mean change = 152,772 IU/ml; P = 0.044) (\nTable 3\n).\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON INDICES OF INSULIN RESISTANCE:\nPioglitazone treatment decreased by day-14 fasting serum glucose (Glucose-0) (mean change = 8.2 mg/dL; P = 0.024) as well as the 2-hr glucose (Glucose-120 min) after an OGTT (mean change = 18.8 mg/dL; P = 0.001) (\nTable 4\n). 10.1371/journal.pone.0031516.t004 Table 4 Effects of Pioglitazone on glucose homeostasis, insulin resistance and secretion. Test Day-0 Day-14 \n P value \n \n 95% CI \n \n Glucose-0 (mg/dL) 105 (11.4) 96.8 (6.8) 0.024 1.3, 15.1 \n Glucose-120 (mg/dL) 120.6 (11.9) 101.8 (7.4) 0.0004 10.9, 26.7 \n HOMA-IR \n 2.71 (1.61) 2.38 (1.60) 0.326 −0.95 \n QUICK-I \n 0.339 (0.031) 0.348 (0.036) 0.587 \n …… \n \n HOMA-B \n 92.65 (57.5) 115.26 (90.85) 0.52 −99.6, 54.4 \n Insulin (µIU/ml) 10.4 (6.2) 10.1 (7.0) 0.914 −6.2, 6.8 \n C-peptide (nmol/L) 6.4 (9.4) 9.6 (8.5) 0.278 \n − 9.5, 3.1 \n SHBG (µg/ml) 3.8 (2.4) 1.7 (2.1) 0.062 −140 \n Adiponectin (µg/ml) 3.19 (1.32) 3.64 (1.71) 0.512 \n ……‥ \n \n Resistin (ng/ml) 2,0 (0.2) 1,7 (0.6) 0.116 −2.0 Values are mean (+/− SD). Tests were performed as described in Methods . However, Pioglitazone treatment did not affect by day-14 the following surrogate indicators of insulin resistance and secretion: HOMA-IR; QUICK-I; and HOMA-B. In addition, other surrogate indicators of insulin resistance were not affected by Pioglitazone treatment on day-14, including fasting serum insulin; C-peptide; SHBG; resistin; and adiponectin (\nTable 4\n).\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON INDICATORS OF LIVER INJURY AND INFLAMMATION:\nElevated serum ALT and AST values are surrogate indicators of liver injury used in patient care and clinical research [9]. Pioglitazone treatment decreased at day-14 serum ALT levels (mean change = 7.5 IU/ml; 95% CI: 2.1 to 12.9; P = 0.012) and to a smaller degree serum AST levels (mean change = 2.6 IU/ml; 95% CI: −0.6 to 5.8; P = 0.096) (\nTable 5\n). 10.1371/journal.pone.0031516.t005 Table 5 Effects of Pioglitazone on liver injury indicators. Day ALT (IU/L) \n P value \n \n 95% CI \n AST (IU/L) \n P value \n \n 95% CI \n \n 0 \n 62.7 (23.1) 53.6 (15.6) \n 14 \n 55.2(18.7) 0.0118 2.1, 12.9 51.0 (14.0) 0.0963 −0.6, 5.8 Values are mean (+/− SD). ALT and AST were determined as described in Methods . It has been suggested that serum IL-8 values are elevated in HCV infection and that these values may reflect the effects of the HCV on il-8 gene transcription [15]. Pioglitazone increased serum IL-8 levels at day-14 when compared to baseline day-0 values (mean change = −166.8 IU/ml; 95% CI: −300.1 to −33.5; P = 0.019) (\nTable 6\n). Given the possible induction of IL-8 expression by TNF-α [15], we analyzed post-hoc their correlation by a Pearson's correlation coefficient. We found that there was a relatively strong correlation between serum IL-8 and serum TNF-α levels for day-0 and day-14 (n = 20; r = 0.64; 95% CI = 0.28 to 0.85; P = 0.002). 10.1371/journal.pone.0031516.t006 Table 6 Effects of Pioglitazine on serum cytokines. Serum Cytokine Day-0 Day-14 \n P value \n \n 95% CI \n \n IL-8 (pg/ml) 181.0 (182.8) 347.8 (123.9) 0.020 −300, −33.5 \n IL-28B (pg/ml) 837.2 (1,068) 1,597 (955.5) 0.060 −1,564, 47 \n TNF-α (pg/ml) 92.9 (139.6) 275.5 (268.5) 0.056 −371.7, 6.6 \n IL-1α (pg/ml) 136.6 (324.4) 223.6 (452.1) 0.415 −317, 143 \n IL-1β (pg/ml) 627.4 (1,046) 724.0 (1,098) 0.748 −760, 566 \n IL-2 (pg/ml) 13.9 (11.1) 16.1 (10.1) 0.632 −12.3, 7.9 \n IL-4 (pg/ml) 10.9 (4.9) 10.4 (4.3) 0.817 −4.8, 5.9 \n IL-6 (pg/ml) 337.9 (454.8) 560.5 (482.1) 0.280 −661, 216 \n IL-10 (pg/ml) 32.4 (58.2) 27.6 (44.6) 0.831 −44.7, 54.3 \n IFN-γ (pg/ml) 5.7(4.2) 7.4 (4.6) 0.403 −5.9, 2.6 \n MCP-1 (pg/ml) 338.4(151.4) 330.6(157.9) 0.915 155, 170 \n HGF (pg/ml) 1008 (736) 975 (603) 0.914 −665, 732 Values are mean (+/− SD). Serum cytokines were determined as described in Methods . We found no statistically significant differences between day-0 and day-14 in serum IL-28B, TNF-α, IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, MCP-1 and HGF (\nTable 6\n).\n\nBODY.RESULTS.EFFECT OF PREDNISONE ON SERUM HCV RNA:\nPrednisone increased the absolute HCV RNA level at day-2 (mean change = −35,636 IU/ml; 95% CI −64,665 to −6,607; P = 0.021) and at day-4 (mean change = −42,786 IU/ml; 95% CI −85,556 to −15.7; P = 0.049) (\nTable 7\n), providing some evidence that Prednisone may be effective in increasing HCV RNA in this cohort of patients for that short period of time. When compared to their baseline day-0 values, eight of 10 subjects had an increase in HCV RNA at day-4. Prednisone treatment also increased HCV RNA from baseline day-0 in 9 of 10 subjects at day-2 (\nTable 7\n). However, in the Prednisone-treated group, the HCV RNA titers expressed as log10 values on day-2 and day-4 were not statistically different from baseline day-0 (\nTable 7\n). 10.1371/journal.pone.0031516.t007 Table 7 Effects of Prednisone on serum HCV RNA titers. Day HCV (IU/ml ×10 −3 ) \n P value \n \n 95% CI \n HCV log 10 \n \n P value \n \n 95% CI \n \n 0 \n 498.0(805.3) 5.10(0.92) \n 2 \n 533.7(834.4) 0.0215 −64.6,−6.6 5.14(0.94) 0.059 0.08 \n 4 \n 540.8(855.2) 0.0499 −85.5,−15.7 5.13(0.92) 0.18 0.03 Values are mean (SD). HCV RNA titers were determined as described in Methods . \n\nBODY.RESULTS.EFFECT OF PREDNISONE ON INDICES OF INSULIN RESISTANCE:\nPrednisone treatment increased by day-4, when compared to baseline day-0 values, fasting serum glucose (Glucose-0) (mean change = 9.0 mg/dL; 95% CI: 20.4 to −2.4; P = 0.108) as well as the 2-hr (Glucose-120 min) after an OGTT (mean change = 11.0 mg/dL; 95% CI: 17.9 to 4.1; P = 0.006). Collectively, the CI and t-tests suggest that Prednisone increased serum glucose levels at day-4 (\nTable 8\n). However, Prednisone treatment did not affect by day-4 other surrogate indicators of insulin resistance and secretion (\nTable 8\n). 10.1371/journal.pone.0031516.t008 Table 8 Effects of Prednisone on glucose homeostasis, insulin resistance and secretion. Test Day-0 Day-4 \n P value \n \n 95% CI \n \n Glucose-0 (mg/dL) 88.0 (14.7) 97.0 (12.9) 0.107 −20.4, 2.4 \n Glucose-120 (mg/dL) 96.4 (10.5) 107.4 (12.3) 0.0055 −17.9, −4.1 \n HOMA-IR \n 1.73 (1.06) 2.55(1.96) 0.162 −1.06 \n QUICK-I \n 0.358(0.022) 0.345 (0.032) 0.275 \n HOMA-B \n 95.48 (49.35) 115.86 (95.96) 0.623 −20.38 \n Insulin (µIU/ml) 7.5(3.9) 10.5 (8.2) 0.374 −10.2, 4.4 \n C-peptide (nmol/L) 11.3 (8.9) 4.1 (1.3) 0.061 −0.5, 14.9 \n SHBG (µg/ml) 3.4(2.5) 2.7 (2.2) 0.591 −2.4 \n Adiponectin (µg/ml) 5.9 (8.2) 2.6 (2.1) 0.306 −4.5 \n Resistin (ng/ml) 3.4 (2.5) 2.7 (2.2) 0.591 −2.4 Values are mean (+/− SD). Tests were performed as described in Methods . \n\nBODY.RESULTS.EFFECT OF PREDNISONE ON INDICATORS OF LIVER INJURY AND INFLAMMATION:\nPrednisone treatment did not affect at day-4 either serum ALT, AST, IL-8 or other inflammatory mediators (\nTables 9\n\n and \n\n10\n). 10.1371/journal.pone.0031516.t009 Table 9 Effects of Prednisone on liver injury indicators. Day ALT (IU/L) \n P value \n \n 95% CI \n AST (IU/L) \n P value \n \n 95% CI \n \n 0 \n 53.2 (14.4) 52.0(11.3) \n 4 \n 55.7 (15.7) 0.080 5.4, −0.4 52.2 (12.8) 0.896 3.6, −3.2 Values are mean (+/− SD). ALT and AST were determined as described in Methods . 10.1371/journal.pone.0031516.t010 Table 10 Effects of Prednisone on serum cytokines. Serum Cytokine Day-0 Day-4 \n P value \n \n 95% CI \n \n IL-8 (pg/ml) 123.1 (163.5) 159.5 (185.1) 0.353 −123, 50 \n IL-28B (pg/ml) 485.9(876.4) 610.8 (857.7) 0.120 −292, 42 \n TNF-α (pg/ml) 146.6 (268.8) 146.1 (284.4) 0.996 −275, 276 \n IL-1α (pg/ml) 80.1 (208.3) 19.2(38.3) 0.450 −119, 240 \n IL-1β (pg/ml) 92.7 (120.3) 144.8 (293.0) 0.682 −348, 244 \n IL-2 (pg/ml) 11.8 (9.8) 11.3 (9.6) 0.742 −3.1, 4.2 \n IL-4 (pg/ml) 19.3 (19.1) 10.9 (7.2) 0.329 −10.5, 27.3 \n IL-6 (pg/ml) 292.8 (445.7) 359.9 (501.4) 0.492 −282, 149 \n IL-10 (pg/ml) 67.4 (106.8) 30.8 (51.2) 0.144 −16.1, 89.4 \n IFNγ (pg/ml) 13.9 (24.9) 4.9 (4.3) 0.342 −11.9, 29.9 \n MCP-1 (pg/ml) 232.7 (126.1) 266.8 (112.8) 0.469 −139, 71 \n HGF (pg/ml) 1345 (800) 1022 (681) 0.483 −711, 1357 Values are mean (+/− SD). Serum cytokines were determined as described in Methods . \n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events in either treatment group. Mild or moderate adverse events unrelated to the allocated treatment occurred in 20% of subjects in the Prednisone group and in 30% of the subjects in the Pioglitazone group. There were no significant changes from baseline during treatment in safety laboratory tests in either treatment group.\n\nBODY.DISCUSSION:\nIt was not known whether Pioglitazone and Prednisone affect serum HCV genotype 4 RNA titers independently of PEG-Interferon-α2/ribavirin treatment. This Study documented for the first time that Pioglitazone (30 mg daily) decreases the serum HCV RNA titers after a 14-day treatment in overweight subjects with treatment naïve, chronic HCV genotype 4 infections. The statistical differences between the mean at day-0 (baseline) and day-14 were highly significant whether the serum HCV RNA was analyzed as IU/ml or log10 values (\nTable 3\n). Pioglitazone treatment also decreased the HCV genotype 4 titers on day-4 and day-7, suggesting a rapid effect on HCV RNA titers. The comparable mean decrease in HCV RNA for the first week and for the second week indicates a continuing effect during the 14-day treatment. It remains to be studied whether the rate of decrease of serum HCV RNA titers continues after day-14 in the Pioglitazone group. If the effects of Pioglitazone on in HCV genotype 4 RNA titers would continue at the same rate as for the first 2 weeks, it would achieve a clinically significant decrease of ∼1 log10 in HCV RNA titers by week-12, an important predictive timeline for a sustained virological response in HCV treatments [16]. Given the relative safety of Pioglitazone administration [9],[17], it could be, as a co-adjuvant, a valuable therapeutic effect for difficult to treat HCV genotype 4-infected patients. This Study also documented for the first time that Prednisone (40 mg daily) increases the serum HCV RNA titers after a 4-day treatment of HCV genotype 4 overweighed patients (\nTable 7\n). Our results with Prednisone treatment are congruent with the recently reported increased HCV replication by corticosteroids in the Huh-7 replicon system [13], but whether in HCV genotype 4-infected patients, this reflects a direct corticosteroid effect on HCV replication, an indirect effect mediated by insulin resistance, or another mechanism is unknown. Because the Huh-7 replicon system uses de-differentiated, tumoral liver cells that have higher expression of glucose metabolism enzymes (glucose-6-phosphate 1-dehydrogenase and isocitrate dehydrogenase) and of the mitochondrial dicarboxylate carrier [18], it may not be suitable for the evaluation of interaction between glucose homeostasis and HCV replication. To minimize potential adverse events associated with the administration of Prednisone, its use was limited to 40 mg/day for a 4-day treatment, a relatively safe and frequent standard of care practice for some clinical conditions [19]. It remains to be determined whether a more prolonged corticosteroid treatment in HCV-infected patients has detrimental effects on RNA titers of different HCV genotypes. The subjects' recruitment number was pre-determined by the sample size and power analysis. An appropriate sample size was utilized in this study, which achieved the primary and secondary end-points with a relatively small cohort of patients. If the sample size of the study were unnecessarily large, then the risks to the subjects would have been excessive according to the CONSORT statement [20]. An intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication; all of these subjects completed the study and had a subsequent efficacy observation. Because these randomized arms were not treatments of the HCV infection in this Study, and because during chronic infection, the level of serum HCV RNA is in a steady state with only minor fluctuations in untreated patients [21], instead of using demanding placebo arms, we utilized randomization as well as de-identified samples to blinding the investigators analyzing the outcomes. These approaches minimize biases in executing the study and in analyzing the outcomes according to the CONSORT statement [20]. Triple combination therapy of Pioglitazone/PEG-Interferon-α2/ribavirin has been used for previously treated HCV genotype 1 infection unsuccessfully in Switzerland [10] and in the USA [22], [23] or for treatment naive HCV genotype 4 infection successfully in Egypt [11]. It is unknown whether the beneficial effects of Pioglitazone together with PEG-Interferon-α2/ribavirin are circumscribed to HCV genotype 4 or to treatment naïve HCV of various genotypes. Although, the relatively low 15 mg Pioglitazone dose used in the INSPIRED-HCV trial in Switzerland [10] could have been insufficient to achieve efficacy, higher Pioglitazone doses (30 mg or 45 mg per day) have been utilized in HCV genotype 1 infection trials together with PEG-Interferon-α2/ribavirin without improving the sustained virological response [22], [23]. These higher Pioglitazone doses (30 mg or 45 mg per day) have been successfully utilized to prevent the development of type 2 diabetes in patients with impaired glucose tolerance in the USA [8], in the treatment of HCV genotype 4 treatment naive patients together with PEG-Interferon-α2/ribavirin in Egypt [11] and in our Study. Further, the known effects of Pioglitazone and related PPARγ agonists on glucose homeostasis [8],[12] and as documented in our Study, and their effects on serum HCV RNA titers (\nTable 3\n) suggest, but does not prove, that improving insulin sensitivity lowers HCV RNA titers. This has been proposed by Harrison on the basis that patients with QUICK-I values <0.35 (equivalent to HOMA-IR>1.8) have significantly higher HCV titers than patients with QUICK-I values >0.35 [24]. Further, treating patients with hepatitis C genotype 1 and insulin resistance using metformin improves insulin sensitivity and increases SVR rate in patients who reached HOMA lower than 2 at week 24 of therapy and in women, in whom the therapy doubled the SVR rate [25]. The findings of our Study support the notion that sequential treatment with Pioglitazone and PEG-Interferon-α2/ribavirin rather than concomitant administration should be considered in the treatment of chronic HCV genotype 4 infections, as suggested by Serfaty and coworkers [26]. The beneficial effects of Pioglitazone treatment on glucose homeostasis have been well documented in patients with impaired glucose tolerance [8], and it was also reported in triple combination therapy of Pioglitazone/PEG-Interferon-α2/ribavirin in patients with HCV genotype 1 or 4 [10],[11]. In our Study, Pioglitazone treatment decreased by day-14 and Prednisone increased by day-4 fasting serum glucose as well as the 2-hr glucose after an OGTT (\nTable 4\n\n and \n\n8\n\n). However, when compared to baseline day-0 values, neither Pioglitazone treatment at day-14 nor Prednisone treatment at day-4 affected HOMA-IR; QUICK-I; and HOMA-B, surrogate indicators of insulin resistance and secretion (\nTables 4\n\n and \n\n8\n). It would probably require a more prolonged treatment with Pioglitazone and Prednisone to induce changes in these surrogate indicators of insulin resistance and secretion [26]. Elevated serum ALT and AST values are surrogate indicators of liver injury used in patient care and clinical research [9]. Pioglitazone treatment decreased at day-14 serum ALT levels and to a smaller degree serum AST levels (\nTable 5\n). Additional insights into the mechanisms of Pioglitazone on liver injury in chronic HCV infection would require assessment of liver biopsies before and after prolonged treatment since the effects on serum ALT were clinically modest at day-14. Prednisone treatment did not affect at day-4 serum ALT or AST levels (\nTable 9\n). Many experimental and clinical studies have shown that PPARγ signaling has anti-inflammatory properties in the liver [27]. Interestingly, HCV infection in Huh-7 cells and in humans inhibits PPARγ expression and function [27]. Two studies suggested therapeutic effects of bezafibrate, a non-selective agonist of PPAR α/δ/γ, during chronic HCV infection. Patients with HCV genotype 1 and 2 unresponsive to interferon therapy were treated for 8 weeks or 6 months with bezafibrate [28], [29]. At endpoint, HCV viral load (−0.5 log10) and ALT were statistically significantly decreased, suggesting anti-inflammatory and antiviral activities of the PPAR α/δ/γ signaling pathways in patients with chronic HCV infection. Given the non-selective nature of the PPAR α/δ/γ agonist, it is difficult to determine whether induction of PPARγ pathways occurred and played a role in the decreased HCV RNA. Pioglitazone also has shown improvement in liver injury and inflammation in patients with non-alcoholic steatohepatitis [9] and this has been attributed to the beneficial effects of Pioglitazone on insulin signaling [8]. An alternative explanation is a possible direct effect of Pioglitazone either as a PPARγ agonist or through other mechanisms on liver injury, independently of its insulin sensitizing actions [8]. Indeed, PPARγ agonists induce alternative, anti-inflammatory M2 macrophage activation [30], possibly linking insulin sensitivity with decreased liver injury in patients with HCV infection. At the molecular level, insulin resistance is promoted by a transition from an anti-inflammatory macrophage M2 state maintained by STAT6 and PPARγ to a pro-inflammatory macrophage M1 state driven by C/EBPβ and NF-κB activation and other transcription factors that play important roles in innate immunity [30]. Relevant to the management of HCV infected patients, liver fibrogenesis is expected to be ameliorated by PPARγ signaling [31] as well as by decreased inflammatory pathways arising from M2 macrophages [32] and resulting in decreased activation of hepatic stellate cells [33]. Pioglitazone increased serum IL-8 levels at day-14 when compared to baseline day-0 values (\nTable 6\n). Serum IL-8 values are elevated in HCV infection [34] and these values may reflect the effects of the HCV on il-8 gene transcription as well as its induction by TNFα [15]. We found that there was a relatively strong correlation between serum IL-8 and serum TNF-α levels for day-0 and day-14. Although it has been suggested that elevated levels of serum IL-8 may be associated with HCV resistance to Interferon-α2 therapy, the clinical or biological significance of the elevated serum IL-8 in HCV genotype 4 patients treated with Pioglitazone remains to be determined. Prednisone did not affect serum IL-8 levels at day-4 when compared to baseline day-0 values (\nTable 10\n). We found no differences between day-0 and day-14 in the Pioglitazone group and day-4 in the Prednisone group in other inflammatory markers such as serum IL-28B, TNF-α, IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, MCP-1 and HGF (\nTables 6\n\n and \n\n10\n). The lack of changes in IL-28B (IFN-γ3) is relevant since genetic variation in IL-28B affects the spontaneous clearance of HCV in patients [35]. Our study has some limitations: i] there were, as expected, clinically modest decreases in HCV RNA at day-14 in the Pioglitazone group; ii] the relatively small cohort could introduce potential biases; and iii] the findings may not be applicable for patients with HCV genotype 4 in other ethnic groups It remains to be elucidated whether the effects of Pioglitazone also occur in HCV genotype 4 infections in previously treated patients. The novel findings of our Study provide the foundation for basic and clinical investigations on the molecular mechanisms responsible for the Pioglitazone-induced decrease in HCV genotype 4 RNA titers. Future research should characterize whether the effects of Pioglitazone on HCV genotype 4 RNA titers are mediated indirectly by insulin signaling pathways or directly by affecting HCV genotype 4 hepatocyte entry and/or replication.\n\nBODY.SUPPORTING INFORMATION:\nChecklist S1\nCONSORT Checklist. CONSORT 2010 checklist of information to include when reporting a randomised trial.(DOC)Click here for additional data file. Protocol S1\nTrial Protocol.\n(DOC)Click here for additional data file.\n\nQuestion: Compared to baseline what was the result of Pioglitazone (30 mg/day for 14 days) on HCV RNA at day-14?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1158	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Pioglitazone Decreases Hepatitis C Viral Load in Overweight, Treatment Naïve, Genotype 4 Infected-Patients: A Pilot Study\n\n ABSTRACT.BACKGROUND:\nInsulin resistance (IR) is induced by chronic hepatitis C virus (HCV) genotypes 1 and 4 infections. It is not known whether drugs that affect IR such as Pioglitazone and Prednisone also affect serum HCV RNA titers independently of PEG-Interferon-α2/ribavirin treatment. The primary aim was to assess whether Pioglitazone by improving IR and/or inflammation decreases HCV viral load independently of standard of care HCV treatment. A secondary aim was to assess whether Prednisone, a drug that induces insulin resistance and stimulates HCV viral entry and replication in replicon culture systems, increases HCV viral load in this population.\n\nABSTRACT.METHODOLOGY/PRINCIPAL FINDINGS:\nWe designed a two-arm, parallel Pilot Study of overweight, treatment naïve genotype 4 HCV-infected patients at a public referral Liver Clinic in Giza, Egypt. The subjects received Pioglitazone (30 mg/day for 14 days) or Prednisone (40 mg/day for 4 days) in a randomized fashion, but the two arms can be considered independent pilot studies. Only changes from baseline within each arm were assessed and no contrasts of the interventions were made, as this was not an aim of the study. Among 105 consecutive HCV genotype 4 patients, 39 were enrolled based on the optimal sample size and power analysis according to the CONSORT statement; 20 to the Pioglitazone group and 19 to the Prednisone group. Pioglitazone was effective in decreasing serum HCV RNA at day-14 (n = 10; difference of means = 205,618 IU/ml; 95% CI 26,600 to 384,600; P<0.001). Although Prednisone did increase serum HCV RNA at day-4 (n = 10; change from baseline = −42,786 IU/ml; 95% CI −85,500 to −15,700; P = 0.049), the log10 HCV RNA titers were statistically not different from baseline day-0.\n\nABSTRACT.CONCLUSION/SIGNIFICANCE:\nThis is the first documentation that Pioglitazone decreases the serum HCV RNA titers independently of PEG-Interferon-α2/ribavirin treatment. The novel findings of our Study provide the foundation for basic and clinical investigations on the molecular mechanisms responsible for the Pioglitazone-induced decrease in HCV genotype 4 RNA titers.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov NCT01157975\n\n\nBODY.INTRODUCTION:\nChronic hepatitis C viral (HCV) infection markedly increased the risk for type 2 diabetes in cohorts with recognized diabetes risk factors [1]. A meta-analysis also found that HCV infection is associated with excess type 2 diabetes risk [2]. Moreover, IR is a specific feature of chronic HCV genotypes 1 and 4 infections since its prevalence is ∼7-fold higher among these patients compared to chronic Hepatitis B-infected patients [3], and changes in IR occur among patients with chronic HCV infection during and after treatment of HCV with PEG-interferon-α and ribavirin [4]. In patients with genotypes 1, 2 and 3 increased IR was associated with decreased sustained virological response (SVR) [5]. Among patients infected with genotype 1, decreases in Homeostasis Model Assessment (HOMA)-IR correlated with obtaining an SVR and increases in HOMA-IR were observed in patients who relapsed [6]. Similarly, IR may correlate with the virological response to standard of care treatment of HCV genotype 4 patients in Egypt [7]. Because Pioglitazone, a peroxisome proliferator-activated receptor (PPAR)-γ agonist, improves insulin sensitivity [8] and it is also effective in controlling liver inflammation in subjects with non-alcoholic steatohepatitis (NASH) [9], it has been used as triple therapy in addition to PEG-interferon-α and ribavirin to treat HCV-infected patients. The study in HCV genotype 1 non-responders was terminated when none of the five patients responded to the triple therapy at week 12 [10]. In contrast, Pioglitazone improved virological response to PEG-interferon α-2b/ribavirin combination therapy in hepatitis C genotype 4 treatment naïve patients with insulin resistance [11]. However, the mechanisms by which Pioglitazone influenced SVR in treatment naïve patients with HCV genotype 4 infection remain unknown. It is unknown whether Pioglitazone modifies the bioavailability of PEG-interferon α-2b/ribavirin or directly or indirectly affects HCV infection and replication. Therefore, we designed a Pilot Study to assess whether Pioglitazone decreases HCV viral load in overweight HCV genotype 4, treatment naïve patients independently of standard of care PEG-interferon α-2b/ribavirin treatment. A secondary end-point was to analyze whether Prednisone, a drug that induces insulin resistance in susceptible patients [12] and stimulates HCV viral entry and replication in replicon culture systems [13], increases HCV viral load in this population. There were no data available on the effect of Pioglitazone or Prednisone on HCV RNA viral load in patients. Here, we provide the first documentation that Pioglitazone decreases the serum HCV genotype 4 RNA titers independently of treatment with PEG-Interferon-α2/ribavirin. Prednisone did increase serum HCV RNA viral load at day-4 in this cohort.\n\nBODY.METHODS:\nThe protocol for this trial and supporting CONSORT checklist are available as supporting information; see Checklist S1 and Protocol S1.\n\nBODY.METHODS.PARTICIPANTS:\nEligible participants were all overweight (BMI>25 kg/m2), given their susceptibility for IR, adults age 25 to 65 years, with active HCV genotype 4 chronic infection (>10,000 IU/ml viral load) who had a liver biopsy within two years of recruitment (added to the protocol), were treatment naïve (never treated for HCV infection) and met the eligibility criteria for the Study. Exclusion criteria included cirrhosis, the presence of other liver diseases, diabetes, pregnancy, significant clinical co-morbidities, and the inability to provide informed consent. Participants were recruited from July 2010 to February 2011 at the primary care referral of subjects of a disadvantaged social-economical group at the Agouza Hospital in Giza, Egypt. The estimated prevalence of Hepatitis C in Egypt is 12% in adults.\n\nBODY.METHODS.ETHICS:\nWritten informed consent was obtained by the medical staff before entry into the Study. The study was registered at the clinicaltrials.gov website (NCT-01157975) and received Human Subjects' Research approval at the University of California, San Diego (UCSD Human Research protections Program) and at the Agouza Hospital, Giza, Egypt (Director's Research Board) before starting the study. The study protocol conforms to the ethical guidelines of the 1975 Declaration of Helsinki.\n\nBODY.METHODS.OBJECTIVES:\nBecause the objective of the Study was to determine whether Pioglitazone and Prednisone treatment would affect the HCV RNA viral load (decrease and increase it, respectively), and these were not a treatment of the HCV infection in this situation, we decided not to use a placebo since we utilized de-identified samples to blinding the investigators analyzing the outcomes.\n\nBODY.METHODS.INTERVENTIONS:\nEligible subjects were randomly assigned to receive orally Pioglitazone 30 mg/day for 14 days or Prednisone 40 mg/day for 4 days. These medications were taken in the morning. Visits were at screening (up to 30 days before randomization); randomization (day -2); baseline visit (day 0); and follow-up visits for the Pioglitazone group (on days 2, 4, 7 and 14) and the Prednisone group (on days 2 and 4). For safety issues subjects were continued to be seen off protocol at day-7 post-treatment. Blood samples were obtained at each visit for HCV RNA viral load and for inflammatory, adipogenic, and insulin resistance markers. In addition, a 2-hr oral 75 g glucose tolerance test (OGTT) was performed after a 10-hr fast at day-0 before administration of the medication and at the last day of treatment (day-14 for Pioglitazone and day-4 for Prednisone). On all other visits, patients were also fasting. Patients received the first dose of the study drug (oral Pioglitazone 30 mg or Prednisone 40 mg) after blood samples were obtained on day 0. Compliance with the medication was >90% as assessed at each visit.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome with respect to the effect of Pioglitazone in HCV genotype 4 infections was the decrease in HCV RNA viral load at day 14. The secondary outcome with respect to the effect of Prednisone in HCV genotype 4 infections was the increase in HCV RNA viral load at day 4 instead of at day 14 for safety reasons given the potential adverse events associated with longer corticosteroid treatment. Additional secondary outcome measures were insulin resistance (oral glucose tolerance test; serum insulin, C-peptide; HOMA-IR; insulin sensitivity check index (QUICKI); HOMA-B; sex hormone BG (SHBG); resistin; adiponectin) and liver injury (alanine aminotransferase (ALT); aspartate aminotransferase (AST)) and inflammation (serum interleukin (IL)-8, IL-28B, tumor necrosis factor (TNF), IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, monocyte chemokine protein (MCP) and hepatocyte growth factor (HGF)). De-identified blood samples from all the enrolled subjects that received the treatments were analyzed for the standard clinical laboratory tests and for HCV RNA viral load using PCR amplification (COBAS, TACKMAN) (lowest detectable limit: 50 IU/ml). A multiplex peptide detection system (Quansys Biosciences, Logan, UT) was utilized according to the manufacturer's protocol to determine inflammatory, adipogenic, and insulin resistance markers. Values calculated from individual pixels using the Q-View Imager system. An enzyme-linked immunosorbent assay kit was used to determine human adiponectin according to the manufacturer's protocol (BioVision, Mountain View, CA). Surrogate indicators of insulin resistance and β-cell function were analyzed as described previously [14]. The indicators of insulin resistance HOMA1-IR and QUICKI were determined. HOMA1-IR = (FSI×FSG)/22.5 where FSI is fasting serum insulin concentration (μU/l) and FSG is fasting serum glucose (mmol/l). QUICKI = 1/[log (fasting insulin-μU/ml)+log (fasting glucose- mg/dl)]. β-Cell function was assessed by the HOMA –B 20.I0/(G0 -3.5); I0 = fasting insulin in μU/ml and G0 = fasting glucose in mmol/l [14].\n\nBODY.METHODS.SAMPLE SIZE:\nThere were no data available on the effect of Pioglitazone or Prednisone on HCV RNA viral load. However, we considered a reduction of 25% in HCV RNA viral load in 14 days to be relevant as proof of principle of the effects of Pioglitazone on HCV RNA titers. To detect a reduction of 25% in HCV RNA in the Pioglitazone group at day-14 assuming a standard deviation of 20% with a two-sided 5% significance level and a power of 90%, a sample size of 9 patients per group completing the study was necessary, and it was decided to enroll at least 19 subjects per group given an anticipated dropout rate of 50% mainly prior to dosing. Because the cultural environment (unwillingness to tell the research staff that they cannot participate in the study) and the social conditions (such as severe problems with transportation and employer's authorization) were expected to prevent a significant proportion of patients to attend the Clinic for follow-up visits after randomization, a larger number of eligible subjects were randomized to achieve the desirable number of subjects completing the Study. To recruit this number of patients a 12-month inclusion period was anticipated. No interim analysis was performed during the trial. An intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication (10 patients in each group was optimal based on sample size and power analysis).\n\nBODY.METHODS.RANDOMIZATION—SEQUENCE GENERATION:\nParticipants were randomly assigned following simple randomization procedures (computerized random numbers) to one of two treatment groups. Independent pharmacists dispensed either Pioglitazone or Prednisone according to a computer generated randomization list.\n\nBODY.METHODS.RANDOMIZATION—ALLOCATION CONCEALMENT:\nThe decision to accept or reject a participant was made, and informed consent was obtained from the participant, in ignorance of the next assignment in the sequence.\n\nBODY.METHODS.RANDOMIZATION—IMPLEMENTATION:\nBlock randomization was by a computer generated random number list prepared by a pharmacist with no clinical involvement in the trial. After the research nurse had obtained the subject's consent, she contacted the pharmacist who was independent of the recruitment process for allocation consignment.\n\nBODY.METHODS.BLINDING:\nWhereas patients and physicians allocated to the intervention groups were aware of the allocated arm, outcome assessors and data analysts of primary and secondary end-points were kept blinded to the allocation.\n\nBODY.METHODS.STATISTICAL METHODS:\nAn intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication. The primary and secondary endpoints were assessed with a paired-sample t-test. We also explored correlations between IL8 and TNFα using Pearson's correlation coefficient with 95% confidence intervals. The significance level was fixed at α = 5% for all tests. All analyses were carried using R version 2.12.2 (2011 Vienna, Austria; http://www.R-project.org).\n\nBODY.RESULTS.PARTICIPANT FLOW:\nThe optimal subjects' recruitment number was pre-determined by sample size and power analysis as described above. One hundredth and five consecutive patients with chronic Hepatitis C genotype 4 referred to the Hepatology Clinic were assessed for eligibility (\nFig. 1\n). Among these 105 patients, 66 were excluded because they did not meet the eligibility criteria (42 subjects), they refused to participate (8 subjects), or for other reasons (16 subjects). Therefore, 39 patients were randomized; 20 to the Pioglitazone group and 19 to the Prednisone group. Ten patients in each group received the allocated intervention, while 10 patients in the Pioglitazone group and 9 patients in the Prednisone group were unable to participate because of their inability to attend the Clinic visits. These patients did not receive the allocated intervention (\nFig. 1\n). The randomized groups that received the allocated intervention were balanced in regards to age, gender, HCV genotype and titers and the severity of their liver disease (\nTable 1\n). 10.1371/journal.pone.0031516.g001Figure 1Participant Flow.Patients with chronic Hepatitis C genotype 4 referred to the Hepatology Clinic were assessed for eligibility as described in Methods. 10.1371/journal.pone.0031516.t001 Table 1 Baseline demographic and clinical characteristics of treated subjects. Pioglitazone (N = 10) Prednisone (N = 10) \n P value \n \n Age (years) 44 (9.3) 42(10.4) 0.592 \n Sex (male) 7 (70%) 8 (80%) 0.429 \n Ethnic origin: Arab \n 10 (100%) 10 (100%) 1.000 \n Height (cm) 173 (5.8) 175(8.7) 0.458 \n Weight (kg) 88.3 (9.2) 85.7(9.9) 0.550 \n BMI (kg/m 2 ) 29.5(1.5) 27.9(1.6) 0.027 \n HCV Genotype 4 \n 10 (100%) 10 (100%) 1.000 \n HCV RNA (log 10 ) 5.41(0.80) 5.10(0.92) 0.432 \n Albumin (g/dl) 3.8(0.3) 3.8(0.3) 0.939 \n Total bilirubin (mg/dl) 0.97(0.15) 0.90 (0.16) 0.319 \n ALT (IU/ml) 63 (23) 53 (14) 0.283 \n AST (IU/ml) 54 (17) 52 (11) 0.795 \n Metavir score: \n \n A (inflammation) A1(n:5) A2(n:5) A1(n:5) A2(n:5) 1.000 \n F (fibrosis) F1(n:7); F2(n:3) F1(n:6); F2(n:4) 0.639 Data are means (SD) or numbers (%). The patients that did receive the allocated intervention were similar in demographics, ethnicity and degree of liver disease to those that did not receive the allocated intervention (\nTable 2\n). By chance allocation, the serum ALT was lower in the group that received Prednisone than in the group that did not received the allocated Prednisone (53 vs 69 IU/ml; P = 0.012) (\nTables 1\n\nand\n\n2\n). 10.1371/journal.pone.0031516.t002 Table 2 Baseline demographic and clinical characteristics of non-treated subjects. Pioglitazone (N = 10) \n P value \n Prednisone (N = 9) \n P value \n \n Age (years) 39 (4.2) 0.139 43(11.2) 0.842 \n Sex (male) 6 (60%) 0.660 5 (55%) 0.277 \n Ethnic origin: Arab \n 10 (100%) 1.000 9 (100%) 1.000 \n Height (cm) 172 (5.9) 0.706 177(8.1) 0.612 \n Weight (kg) 85.7 (7.6) 0.499 84.8(8.8) 0.837 \n BMI (kg/m 2 ) 28.8(2.1) 0.402 28.2(3.7) 0.818 \n HCV Genotype 4 \n 10 (100%) 1.000 9 (100%) 1.000 \n ALT (IU/ml) 68 (10) 0.536 69 (10) 0.012 \n AST (IU/ml) 63 (12) 0.188 57 (8) 0.278 \n Metavir score: \n \n A (inflammation) A1(n:4); A2(n:6) 0.673 A1(n:4); A2(n:5) 0.821 \n F (fibrosis) F1(n:5); F2(n:5) 0.388 F1(n:5); F2(n:4) 0.855 Data are means (SD) or numbers (%). P values are for comparisons between treated and untreated subjects within the same arm. No participant was excluded after randomization because they were found not to meet eligibility criteria. All the patients allocated to the interventions (10 in each arm) completed the study (\nFig. 1\n).\n\nBODY.RESULTS.BASELINE DEMOGRAPHIC AND CLINICAL CHARACTERISTICS:\nAn intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication; all of these patients had a subsequent efficacy observation (10 patients in each group). As outlined in \nTable 1\n, all patients were middle age Egyptian Arabs, predominantly males that had HCV genotype 4 with mild or moderate inflammation (A1 and A2, respectively) and mild or moderate fibrosis (F1 and F2, respectively) on their liver biopsy. They had normal albumin and total bilirubin and mild increase in ALT/AST. All subjects were overweight and five were obese (body mass index, BMI; the weight in kg divided by the square of the height in meters was >29 kg/m2: 3 in the Pioglitazone group and 2 in the Prednisone group). By chance allocation, the BMI was higher in the group receiving Pioglitazone than in the group receiving Prednisone (29.5 vs 27.9 kg/m2; P = 0.027) (\nTable 1\n). There was no indication that significant chance imbalances had occurred between the two groups. Further, no direct analysis between the two groups was intended for the primary or secondary end points. Rather, a comparison between baseline and post-treatment results within each group was the Pilot Study's intent.\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON SERUM HCV RNA TITERS:\nPioglitazone decreased serum HCV RNA titers in overweight HCV genotype 4, treatment naïve patients. In the Pioglitazone-treated group, the log10 transformed HCV RNA titers were statistically different from baseline day-0 (5.41+/−0.80) on day-14 (5.24+/−0.79; P<0.001) and day-7 (5.30+/−0.78; P = 0.009) (\nTable 3\n), providing evidence that Pioglitazone was effective in decreasing HCV RNA in this cohort of patients. Pioglitazone treatment decreased the HCV RNA from baseline in 9 out of 10 subjects at day-7. The log10 HCV RNA values were also decreased by day-4 but they were statistically not different from baseline (5.38+/−0.78; P = 0.059). The log10 HCV RNA values were not affected at day-2 by Pioglitazone treatment. Further, the decrease in the log10 HCV RNA between day-7 and day-14 was highly significant (mean change = 0.063; 95% CI, 0.045; P<0.001) (\nTable 3\n). 10.1371/journal.pone.0031516.t003 Table 3 Effects of Pioglitazone on serum HCV RNA titers. Day HCV (IU/ml ×10 −3 ) \n P value \n \n 95% CI \n HCV log 10 \n \n P value \n \n 95% CI \n \n 0 \n 608.2(696.4) 5.41(0.80) \n 2 \n 586.9(663.9) 0.178 −11.5, 53.9 5.41(0.78) 0.854 −0.029 \n 4 \n 531.5(553.6) 0.151 −33.6, 186.9 5.38(0.78) 0.077 −0.002 \n 7 \n 455.3(504.4) 0.044 4.8, 300.7 5.30(0.78) 0.001 −0.156 \n 14 \n 402.5(452.4) 0.029 26.6, 384.6 5.24(0.79) <0.001 −0.215 Values are mean (SD) of HCV RNA titers determined as described in Methods . In spite of the variable baseline HCV RNA viral load, Pioglitazone also decreased significantly the absolute HCV RNA levels at day-14 (mean change = 205,618 IU/ml; P = 0.028) and at day-7 (mean change = 152,772 IU/ml; P = 0.044) (\nTable 3\n).\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON INDICES OF INSULIN RESISTANCE:\nPioglitazone treatment decreased by day-14 fasting serum glucose (Glucose-0) (mean change = 8.2 mg/dL; P = 0.024) as well as the 2-hr glucose (Glucose-120 min) after an OGTT (mean change = 18.8 mg/dL; P = 0.001) (\nTable 4\n). 10.1371/journal.pone.0031516.t004 Table 4 Effects of Pioglitazone on glucose homeostasis, insulin resistance and secretion. Test Day-0 Day-14 \n P value \n \n 95% CI \n \n Glucose-0 (mg/dL) 105 (11.4) 96.8 (6.8) 0.024 1.3, 15.1 \n Glucose-120 (mg/dL) 120.6 (11.9) 101.8 (7.4) 0.0004 10.9, 26.7 \n HOMA-IR \n 2.71 (1.61) 2.38 (1.60) 0.326 −0.95 \n QUICK-I \n 0.339 (0.031) 0.348 (0.036) 0.587 \n …… \n \n HOMA-B \n 92.65 (57.5) 115.26 (90.85) 0.52 −99.6, 54.4 \n Insulin (µIU/ml) 10.4 (6.2) 10.1 (7.0) 0.914 −6.2, 6.8 \n C-peptide (nmol/L) 6.4 (9.4) 9.6 (8.5) 0.278 \n − 9.5, 3.1 \n SHBG (µg/ml) 3.8 (2.4) 1.7 (2.1) 0.062 −140 \n Adiponectin (µg/ml) 3.19 (1.32) 3.64 (1.71) 0.512 \n ……‥ \n \n Resistin (ng/ml) 2,0 (0.2) 1,7 (0.6) 0.116 −2.0 Values are mean (+/− SD). Tests were performed as described in Methods . However, Pioglitazone treatment did not affect by day-14 the following surrogate indicators of insulin resistance and secretion: HOMA-IR; QUICK-I; and HOMA-B. In addition, other surrogate indicators of insulin resistance were not affected by Pioglitazone treatment on day-14, including fasting serum insulin; C-peptide; SHBG; resistin; and adiponectin (\nTable 4\n).\n\nBODY.RESULTS.EFFECT OF PIOGLITAZONE ON INDICATORS OF LIVER INJURY AND INFLAMMATION:\nElevated serum ALT and AST values are surrogate indicators of liver injury used in patient care and clinical research [9]. Pioglitazone treatment decreased at day-14 serum ALT levels (mean change = 7.5 IU/ml; 95% CI: 2.1 to 12.9; P = 0.012) and to a smaller degree serum AST levels (mean change = 2.6 IU/ml; 95% CI: −0.6 to 5.8; P = 0.096) (\nTable 5\n). 10.1371/journal.pone.0031516.t005 Table 5 Effects of Pioglitazone on liver injury indicators. Day ALT (IU/L) \n P value \n \n 95% CI \n AST (IU/L) \n P value \n \n 95% CI \n \n 0 \n 62.7 (23.1) 53.6 (15.6) \n 14 \n 55.2(18.7) 0.0118 2.1, 12.9 51.0 (14.0) 0.0963 −0.6, 5.8 Values are mean (+/− SD). ALT and AST were determined as described in Methods . It has been suggested that serum IL-8 values are elevated in HCV infection and that these values may reflect the effects of the HCV on il-8 gene transcription [15]. Pioglitazone increased serum IL-8 levels at day-14 when compared to baseline day-0 values (mean change = −166.8 IU/ml; 95% CI: −300.1 to −33.5; P = 0.019) (\nTable 6\n). Given the possible induction of IL-8 expression by TNF-α [15], we analyzed post-hoc their correlation by a Pearson's correlation coefficient. We found that there was a relatively strong correlation between serum IL-8 and serum TNF-α levels for day-0 and day-14 (n = 20; r = 0.64; 95% CI = 0.28 to 0.85; P = 0.002). 10.1371/journal.pone.0031516.t006 Table 6 Effects of Pioglitazine on serum cytokines. Serum Cytokine Day-0 Day-14 \n P value \n \n 95% CI \n \n IL-8 (pg/ml) 181.0 (182.8) 347.8 (123.9) 0.020 −300, −33.5 \n IL-28B (pg/ml) 837.2 (1,068) 1,597 (955.5) 0.060 −1,564, 47 \n TNF-α (pg/ml) 92.9 (139.6) 275.5 (268.5) 0.056 −371.7, 6.6 \n IL-1α (pg/ml) 136.6 (324.4) 223.6 (452.1) 0.415 −317, 143 \n IL-1β (pg/ml) 627.4 (1,046) 724.0 (1,098) 0.748 −760, 566 \n IL-2 (pg/ml) 13.9 (11.1) 16.1 (10.1) 0.632 −12.3, 7.9 \n IL-4 (pg/ml) 10.9 (4.9) 10.4 (4.3) 0.817 −4.8, 5.9 \n IL-6 (pg/ml) 337.9 (454.8) 560.5 (482.1) 0.280 −661, 216 \n IL-10 (pg/ml) 32.4 (58.2) 27.6 (44.6) 0.831 −44.7, 54.3 \n IFN-γ (pg/ml) 5.7(4.2) 7.4 (4.6) 0.403 −5.9, 2.6 \n MCP-1 (pg/ml) 338.4(151.4) 330.6(157.9) 0.915 155, 170 \n HGF (pg/ml) 1008 (736) 975 (603) 0.914 −665, 732 Values are mean (+/− SD). Serum cytokines were determined as described in Methods . We found no statistically significant differences between day-0 and day-14 in serum IL-28B, TNF-α, IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, MCP-1 and HGF (\nTable 6\n).\n\nBODY.RESULTS.EFFECT OF PREDNISONE ON SERUM HCV RNA:\nPrednisone increased the absolute HCV RNA level at day-2 (mean change = −35,636 IU/ml; 95% CI −64,665 to −6,607; P = 0.021) and at day-4 (mean change = −42,786 IU/ml; 95% CI −85,556 to −15.7; P = 0.049) (\nTable 7\n), providing some evidence that Prednisone may be effective in increasing HCV RNA in this cohort of patients for that short period of time. When compared to their baseline day-0 values, eight of 10 subjects had an increase in HCV RNA at day-4. Prednisone treatment also increased HCV RNA from baseline day-0 in 9 of 10 subjects at day-2 (\nTable 7\n). However, in the Prednisone-treated group, the HCV RNA titers expressed as log10 values on day-2 and day-4 were not statistically different from baseline day-0 (\nTable 7\n). 10.1371/journal.pone.0031516.t007 Table 7 Effects of Prednisone on serum HCV RNA titers. Day HCV (IU/ml ×10 −3 ) \n P value \n \n 95% CI \n HCV log 10 \n \n P value \n \n 95% CI \n \n 0 \n 498.0(805.3) 5.10(0.92) \n 2 \n 533.7(834.4) 0.0215 −64.6,−6.6 5.14(0.94) 0.059 0.08 \n 4 \n 540.8(855.2) 0.0499 −85.5,−15.7 5.13(0.92) 0.18 0.03 Values are mean (SD). HCV RNA titers were determined as described in Methods . \n\nBODY.RESULTS.EFFECT OF PREDNISONE ON INDICES OF INSULIN RESISTANCE:\nPrednisone treatment increased by day-4, when compared to baseline day-0 values, fasting serum glucose (Glucose-0) (mean change = 9.0 mg/dL; 95% CI: 20.4 to −2.4; P = 0.108) as well as the 2-hr (Glucose-120 min) after an OGTT (mean change = 11.0 mg/dL; 95% CI: 17.9 to 4.1; P = 0.006). Collectively, the CI and t-tests suggest that Prednisone increased serum glucose levels at day-4 (\nTable 8\n). However, Prednisone treatment did not affect by day-4 other surrogate indicators of insulin resistance and secretion (\nTable 8\n). 10.1371/journal.pone.0031516.t008 Table 8 Effects of Prednisone on glucose homeostasis, insulin resistance and secretion. Test Day-0 Day-4 \n P value \n \n 95% CI \n \n Glucose-0 (mg/dL) 88.0 (14.7) 97.0 (12.9) 0.107 −20.4, 2.4 \n Glucose-120 (mg/dL) 96.4 (10.5) 107.4 (12.3) 0.0055 −17.9, −4.1 \n HOMA-IR \n 1.73 (1.06) 2.55(1.96) 0.162 −1.06 \n QUICK-I \n 0.358(0.022) 0.345 (0.032) 0.275 \n HOMA-B \n 95.48 (49.35) 115.86 (95.96) 0.623 −20.38 \n Insulin (µIU/ml) 7.5(3.9) 10.5 (8.2) 0.374 −10.2, 4.4 \n C-peptide (nmol/L) 11.3 (8.9) 4.1 (1.3) 0.061 −0.5, 14.9 \n SHBG (µg/ml) 3.4(2.5) 2.7 (2.2) 0.591 −2.4 \n Adiponectin (µg/ml) 5.9 (8.2) 2.6 (2.1) 0.306 −4.5 \n Resistin (ng/ml) 3.4 (2.5) 2.7 (2.2) 0.591 −2.4 Values are mean (+/− SD). Tests were performed as described in Methods . \n\nBODY.RESULTS.EFFECT OF PREDNISONE ON INDICATORS OF LIVER INJURY AND INFLAMMATION:\nPrednisone treatment did not affect at day-4 either serum ALT, AST, IL-8 or other inflammatory mediators (\nTables 9\n\n and \n\n10\n). 10.1371/journal.pone.0031516.t009 Table 9 Effects of Prednisone on liver injury indicators. Day ALT (IU/L) \n P value \n \n 95% CI \n AST (IU/L) \n P value \n \n 95% CI \n \n 0 \n 53.2 (14.4) 52.0(11.3) \n 4 \n 55.7 (15.7) 0.080 5.4, −0.4 52.2 (12.8) 0.896 3.6, −3.2 Values are mean (+/− SD). ALT and AST were determined as described in Methods . 10.1371/journal.pone.0031516.t010 Table 10 Effects of Prednisone on serum cytokines. Serum Cytokine Day-0 Day-4 \n P value \n \n 95% CI \n \n IL-8 (pg/ml) 123.1 (163.5) 159.5 (185.1) 0.353 −123, 50 \n IL-28B (pg/ml) 485.9(876.4) 610.8 (857.7) 0.120 −292, 42 \n TNF-α (pg/ml) 146.6 (268.8) 146.1 (284.4) 0.996 −275, 276 \n IL-1α (pg/ml) 80.1 (208.3) 19.2(38.3) 0.450 −119, 240 \n IL-1β (pg/ml) 92.7 (120.3) 144.8 (293.0) 0.682 −348, 244 \n IL-2 (pg/ml) 11.8 (9.8) 11.3 (9.6) 0.742 −3.1, 4.2 \n IL-4 (pg/ml) 19.3 (19.1) 10.9 (7.2) 0.329 −10.5, 27.3 \n IL-6 (pg/ml) 292.8 (445.7) 359.9 (501.4) 0.492 −282, 149 \n IL-10 (pg/ml) 67.4 (106.8) 30.8 (51.2) 0.144 −16.1, 89.4 \n IFNγ (pg/ml) 13.9 (24.9) 4.9 (4.3) 0.342 −11.9, 29.9 \n MCP-1 (pg/ml) 232.7 (126.1) 266.8 (112.8) 0.469 −139, 71 \n HGF (pg/ml) 1345 (800) 1022 (681) 0.483 −711, 1357 Values are mean (+/− SD). Serum cytokines were determined as described in Methods . \n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events in either treatment group. Mild or moderate adverse events unrelated to the allocated treatment occurred in 20% of subjects in the Prednisone group and in 30% of the subjects in the Pioglitazone group. There were no significant changes from baseline during treatment in safety laboratory tests in either treatment group.\n\nBODY.DISCUSSION:\nIt was not known whether Pioglitazone and Prednisone affect serum HCV genotype 4 RNA titers independently of PEG-Interferon-α2/ribavirin treatment. This Study documented for the first time that Pioglitazone (30 mg daily) decreases the serum HCV RNA titers after a 14-day treatment in overweight subjects with treatment naïve, chronic HCV genotype 4 infections. The statistical differences between the mean at day-0 (baseline) and day-14 were highly significant whether the serum HCV RNA was analyzed as IU/ml or log10 values (\nTable 3\n). Pioglitazone treatment also decreased the HCV genotype 4 titers on day-4 and day-7, suggesting a rapid effect on HCV RNA titers. The comparable mean decrease in HCV RNA for the first week and for the second week indicates a continuing effect during the 14-day treatment. It remains to be studied whether the rate of decrease of serum HCV RNA titers continues after day-14 in the Pioglitazone group. If the effects of Pioglitazone on in HCV genotype 4 RNA titers would continue at the same rate as for the first 2 weeks, it would achieve a clinically significant decrease of ∼1 log10 in HCV RNA titers by week-12, an important predictive timeline for a sustained virological response in HCV treatments [16]. Given the relative safety of Pioglitazone administration [9],[17], it could be, as a co-adjuvant, a valuable therapeutic effect for difficult to treat HCV genotype 4-infected patients. This Study also documented for the first time that Prednisone (40 mg daily) increases the serum HCV RNA titers after a 4-day treatment of HCV genotype 4 overweighed patients (\nTable 7\n). Our results with Prednisone treatment are congruent with the recently reported increased HCV replication by corticosteroids in the Huh-7 replicon system [13], but whether in HCV genotype 4-infected patients, this reflects a direct corticosteroid effect on HCV replication, an indirect effect mediated by insulin resistance, or another mechanism is unknown. Because the Huh-7 replicon system uses de-differentiated, tumoral liver cells that have higher expression of glucose metabolism enzymes (glucose-6-phosphate 1-dehydrogenase and isocitrate dehydrogenase) and of the mitochondrial dicarboxylate carrier [18], it may not be suitable for the evaluation of interaction between glucose homeostasis and HCV replication. To minimize potential adverse events associated with the administration of Prednisone, its use was limited to 40 mg/day for a 4-day treatment, a relatively safe and frequent standard of care practice for some clinical conditions [19]. It remains to be determined whether a more prolonged corticosteroid treatment in HCV-infected patients has detrimental effects on RNA titers of different HCV genotypes. The subjects' recruitment number was pre-determined by the sample size and power analysis. An appropriate sample size was utilized in this study, which achieved the primary and secondary end-points with a relatively small cohort of patients. If the sample size of the study were unnecessarily large, then the risks to the subjects would have been excessive according to the CONSORT statement [20]. An intention-to-treat analysis was conducted in patients who had received ≥1 dose of study medication; all of these subjects completed the study and had a subsequent efficacy observation. Because these randomized arms were not treatments of the HCV infection in this Study, and because during chronic infection, the level of serum HCV RNA is in a steady state with only minor fluctuations in untreated patients [21], instead of using demanding placebo arms, we utilized randomization as well as de-identified samples to blinding the investigators analyzing the outcomes. These approaches minimize biases in executing the study and in analyzing the outcomes according to the CONSORT statement [20]. Triple combination therapy of Pioglitazone/PEG-Interferon-α2/ribavirin has been used for previously treated HCV genotype 1 infection unsuccessfully in Switzerland [10] and in the USA [22], [23] or for treatment naive HCV genotype 4 infection successfully in Egypt [11]. It is unknown whether the beneficial effects of Pioglitazone together with PEG-Interferon-α2/ribavirin are circumscribed to HCV genotype 4 or to treatment naïve HCV of various genotypes. Although, the relatively low 15 mg Pioglitazone dose used in the INSPIRED-HCV trial in Switzerland [10] could have been insufficient to achieve efficacy, higher Pioglitazone doses (30 mg or 45 mg per day) have been utilized in HCV genotype 1 infection trials together with PEG-Interferon-α2/ribavirin without improving the sustained virological response [22], [23]. These higher Pioglitazone doses (30 mg or 45 mg per day) have been successfully utilized to prevent the development of type 2 diabetes in patients with impaired glucose tolerance in the USA [8], in the treatment of HCV genotype 4 treatment naive patients together with PEG-Interferon-α2/ribavirin in Egypt [11] and in our Study. Further, the known effects of Pioglitazone and related PPARγ agonists on glucose homeostasis [8],[12] and as documented in our Study, and their effects on serum HCV RNA titers (\nTable 3\n) suggest, but does not prove, that improving insulin sensitivity lowers HCV RNA titers. This has been proposed by Harrison on the basis that patients with QUICK-I values <0.35 (equivalent to HOMA-IR>1.8) have significantly higher HCV titers than patients with QUICK-I values >0.35 [24]. Further, treating patients with hepatitis C genotype 1 and insulin resistance using metformin improves insulin sensitivity and increases SVR rate in patients who reached HOMA lower than 2 at week 24 of therapy and in women, in whom the therapy doubled the SVR rate [25]. The findings of our Study support the notion that sequential treatment with Pioglitazone and PEG-Interferon-α2/ribavirin rather than concomitant administration should be considered in the treatment of chronic HCV genotype 4 infections, as suggested by Serfaty and coworkers [26]. The beneficial effects of Pioglitazone treatment on glucose homeostasis have been well documented in patients with impaired glucose tolerance [8], and it was also reported in triple combination therapy of Pioglitazone/PEG-Interferon-α2/ribavirin in patients with HCV genotype 1 or 4 [10],[11]. In our Study, Pioglitazone treatment decreased by day-14 and Prednisone increased by day-4 fasting serum glucose as well as the 2-hr glucose after an OGTT (\nTable 4\n\n and \n\n8\n\n). However, when compared to baseline day-0 values, neither Pioglitazone treatment at day-14 nor Prednisone treatment at day-4 affected HOMA-IR; QUICK-I; and HOMA-B, surrogate indicators of insulin resistance and secretion (\nTables 4\n\n and \n\n8\n). It would probably require a more prolonged treatment with Pioglitazone and Prednisone to induce changes in these surrogate indicators of insulin resistance and secretion [26]. Elevated serum ALT and AST values are surrogate indicators of liver injury used in patient care and clinical research [9]. Pioglitazone treatment decreased at day-14 serum ALT levels and to a smaller degree serum AST levels (\nTable 5\n). Additional insights into the mechanisms of Pioglitazone on liver injury in chronic HCV infection would require assessment of liver biopsies before and after prolonged treatment since the effects on serum ALT were clinically modest at day-14. Prednisone treatment did not affect at day-4 serum ALT or AST levels (\nTable 9\n). Many experimental and clinical studies have shown that PPARγ signaling has anti-inflammatory properties in the liver [27]. Interestingly, HCV infection in Huh-7 cells and in humans inhibits PPARγ expression and function [27]. Two studies suggested therapeutic effects of bezafibrate, a non-selective agonist of PPAR α/δ/γ, during chronic HCV infection. Patients with HCV genotype 1 and 2 unresponsive to interferon therapy were treated for 8 weeks or 6 months with bezafibrate [28], [29]. At endpoint, HCV viral load (−0.5 log10) and ALT were statistically significantly decreased, suggesting anti-inflammatory and antiviral activities of the PPAR α/δ/γ signaling pathways in patients with chronic HCV infection. Given the non-selective nature of the PPAR α/δ/γ agonist, it is difficult to determine whether induction of PPARγ pathways occurred and played a role in the decreased HCV RNA. Pioglitazone also has shown improvement in liver injury and inflammation in patients with non-alcoholic steatohepatitis [9] and this has been attributed to the beneficial effects of Pioglitazone on insulin signaling [8]. An alternative explanation is a possible direct effect of Pioglitazone either as a PPARγ agonist or through other mechanisms on liver injury, independently of its insulin sensitizing actions [8]. Indeed, PPARγ agonists induce alternative, anti-inflammatory M2 macrophage activation [30], possibly linking insulin sensitivity with decreased liver injury in patients with HCV infection. At the molecular level, insulin resistance is promoted by a transition from an anti-inflammatory macrophage M2 state maintained by STAT6 and PPARγ to a pro-inflammatory macrophage M1 state driven by C/EBPβ and NF-κB activation and other transcription factors that play important roles in innate immunity [30]. Relevant to the management of HCV infected patients, liver fibrogenesis is expected to be ameliorated by PPARγ signaling [31] as well as by decreased inflammatory pathways arising from M2 macrophages [32] and resulting in decreased activation of hepatic stellate cells [33]. Pioglitazone increased serum IL-8 levels at day-14 when compared to baseline day-0 values (\nTable 6\n). Serum IL-8 values are elevated in HCV infection [34] and these values may reflect the effects of the HCV on il-8 gene transcription as well as its induction by TNFα [15]. We found that there was a relatively strong correlation between serum IL-8 and serum TNF-α levels for day-0 and day-14. Although it has been suggested that elevated levels of serum IL-8 may be associated with HCV resistance to Interferon-α2 therapy, the clinical or biological significance of the elevated serum IL-8 in HCV genotype 4 patients treated with Pioglitazone remains to be determined. Prednisone did not affect serum IL-8 levels at day-4 when compared to baseline day-0 values (\nTable 10\n). We found no differences between day-0 and day-14 in the Pioglitazone group and day-4 in the Prednisone group in other inflammatory markers such as serum IL-28B, TNF-α, IL-1α, IL-1β, IL-6, IL-8, IL-10, IFN-γ, MCP-1 and HGF (\nTables 6\n\n and \n\n10\n). The lack of changes in IL-28B (IFN-γ3) is relevant since genetic variation in IL-28B affects the spontaneous clearance of HCV in patients [35]. Our study has some limitations: i] there were, as expected, clinically modest decreases in HCV RNA at day-14 in the Pioglitazone group; ii] the relatively small cohort could introduce potential biases; and iii] the findings may not be applicable for patients with HCV genotype 4 in other ethnic groups It remains to be elucidated whether the effects of Pioglitazone also occur in HCV genotype 4 infections in previously treated patients. The novel findings of our Study provide the foundation for basic and clinical investigations on the molecular mechanisms responsible for the Pioglitazone-induced decrease in HCV genotype 4 RNA titers. Future research should characterize whether the effects of Pioglitazone on HCV genotype 4 RNA titers are mediated indirectly by insulin signaling pathways or directly by affecting HCV genotype 4 hepatocyte entry and/or replication.\n\nBODY.SUPPORTING INFORMATION:\nChecklist S1\nCONSORT Checklist. CONSORT 2010 checklist of information to include when reporting a randomised trial.(DOC)Click here for additional data file. Protocol S1\nTrial Protocol.\n(DOC)Click here for additional data file.\n\nQuestion: Compared to baseline what was the result of Pioglitazone (30 mg/day for 14 days) on day-14 fasting serum glucose and the 2-hr glucose (Glucose-120 min) after an OGTT ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1168	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Sensitivity to scale of willingness‐to‐pay within the context of menorrhagia\n\n ABSTRACT.ABSTRACT.OBJECTIVES:\nWillingness‐to‐pay (WTP) provides a broad assessment of well‐being, capturing benefits beyond health. However, the validity of the approach has been questioned and the evidence relating to the sensitivity of WTP to changes in health status is mixed. Using menorrhagia (heavy menstrual bleeding) as a case study, this exploratory study assesses the sensitivity to scale of WTP to change in health status as measured by a condition‐specific measure, MMAS, which includes both health and non‐health benefits. The relationship between EQ‐5D and change in health status is also assessed.\n\nABSTRACT.ABSTRACT.METHODS:\nBaseline EQ‐5D and MMAS values were collected from women taking part in a randomized controlled trial for pharmaceutical treatment of menorrhagia. Following treatment, these measures were administered along with a WTP exercise. The relationship between the measures was assessed using Spearman's correlation analysis, and the sensitivity to scale of WTP was measured by identifying differences in WTP alongside differences in MMAS and EQ5D values.\n\nABSTRACT.ABSTRACT.RESULTS:\nOur exploratory findings indicated that WTP, and not EQ‐5D, was significantly positively correlated with change in MMAS, providing some evidence for convergent validity. These findings suggest that WTP is capturing the non‐health benefits within the MMAS measure. Mean WTP also increased with percentage improvements in MMAS, suggesting sensitivity to scale.\n\nABSTRACT.ABSTRACT.CONCLUSION:\nWhen compared to quality of life measured using the condition‐specific MMAS measure, the convergent validity and sensitivity to scale of WTP is indicated. The findings suggest that WTP is more sensitive to change in MMAS, than with EQ‐5D.\n\nBODY.INTRODUCTION:\nContingent valuation is a method for assigning monetary values to non‐market goods, such as health‐care interventions, for use as an outcome measure within cost–benefit analysis (CBA). Willingness‐to‐pay (WTP) is the most commonly used contingent valuation approach and provides an overall measure of strength of preference expressed in monetary terms. Using this approach, individuals are asked to consider hypothetical scenarios that describe both the process and outcome of the health‐care intervention and asked to state maximum WTP for the health care good being valued. Sample average WTP values are typically used as an indication of strength of preference and can be directly compared to assess the value of alternative health‐care interventions. In a similar way to how EQ‐5D is used to inform the outcome measure for cost–utility analysis (CUA), WTP can also be used to inform the outcome for a CBA. Used in this way, it becomes a generic measure of value for treatment or services and is thus weighed against cost to measure overall cost‐effectiveness. Depending on the ratio between the incremental difference in costs and benefits (WTP) of alternative treatment options, judgements can then be made by decision makers on whether to recommend the treatment/service based on this ratio. WTP encapsulates both health and non‐health aspects of well‐being, the advantages of such an approach are ever more recognized, particularly because the National Institute for Health and Care Excellence are now also commissioning across public health and social care.1 Despite this, there are key limitations to the WTP approach including the difficulty with contemplating the hypothetical survey scenario, and the lack of well‐defined preferences when individuals are unfamiliar with the goods they are asked to value. The literature also refers to evidence on strategic bias and questions about the validity of the approach.2\n The objective of this exploratory study was to examine the validity of the WTP approach using treatment for heavy menstrual bleeding (clinically termed menorrhagia) as a case example. Menorrhagia is a chronic condition with episodic symptoms which is known to affect both health and non‐health aspects of life. Generic quality of life measures, such as EQ‐5D and SF‐6D, that are focused on health alone are recommended for use in health care to be used to capture the impact of conditions. The advantage of these generic measures is that they enable comparison of effectiveness across different treatment conditions as the outcomes are measured using one commensurate unit. An interesting feature of menorrhagia is the condition's chronic but episodic nature as the symptoms occur for approximately 1 week every month which has implications for the timing of assessment when using generic measures with standard recall periods.3 In terms of validity, within the context of menorrhagia the condition‐specific quality of life measure, MMAS (menorrhagia multi‐attribute scale described in detail below), is considered to be the gold standard measure.4 Whilst condition‐specific measures can be more sensitive than generic measures, their use in decision making is limited due to the lack of comparability across conditions. There are several types of validity that one can assess including content validity (whether all relevant aspects of the condition are considered in the instrument), construct validity (determines whether an underlying relationship exists between questions in the instrument and an attribute that is measured), and criterion validity (whether one attribute or set of attributes predicts an outcome based on information from other attributes).5, 6 The focus of this paper is construct validity, or more specifically convergent validity which is the degree to which two theoretically equivalent measures converge, and within the context of contingent valuation, it is often referred to as sensitivity to scale or scope.7\n This question is of theoretical relevance as many studies have shown that WTP demonstrates theoretical validity with WTP increasing with income,8 and others have focused on convergent validity with other preference elicitation measures such as time trade‐off (TTO) and standard gamble (SG).9 The evidence on convergent validity within the health‐care sector and sensitivity to the size of the benefit is mixed 9, 10 and in particular, the evidence relating to the sensitivity of WTP to changes in health status 9 is far from conclusive. In theory, the respondent's perception of the value of a treatment should be sensitive to changes in the size of the benefit derived from the treatment. For example, WTP demonstrates convergent validity if the WTP increases with a perception of greater improvement in treatment benefit. This study presented a unique opportunity to assess the sensitivity of WTP longitudinally as both EQ5D and MMAS data were collected at different time points, along with WTP. The sensitivity to scale of WTP can therefore be assessed in relation to EQ5D and MMAS over time. First, we assessed the change in condition‐specific quality of life following treatment for menorrhagia, as measured by MMAS, against the WTP for this change in outcome, and second, we assessed the underlying relationship between WTP and general health‐related quality of life when measured using EQ‐5D.\n\nBODY.METHODS:\nWe carried out the exploratory study with women who were already participating in the NIHR funded ECLIPSE trial (ISRCTN86566246).11 Ethical approval was obtained from the National Research Ethics Service Committee South West‐Exeter and clinical trial authorization from the Medicines and Healthcare Regulatory Authority. Written consent was obtained from the participants.\n\nBODY.METHODS.STUDY POPULATION:\nThe ECLIPSE trial is a pragmatic, multicentre, randomized trial, comparing the clinical and cost‐effectiveness of levonorgestrel‐releasing intrauterine device (LNG‐IUS) against usual medical treatment in the primary care setting.11, 12 Women between 25 and 50 years of age that presented to their general practitioner (GP) with menorrhagia, occurring over at least three consecutive cycles, were randomized to a treatment group by telephone or web‐based central randomization service. Women were excluded if they intended to become pregnant over the next 5 years, were taking hormone replacement therapy or tamoxifen, had intermenstrual or post‐coital bleeding or examination suggestive of fibroids (abdominally palpable uterus equivalent in size to 10–12 weeks of gestation) or other pathologies, or had contraindications to, or a preference for, LNG‐IUS or usual medical treatments. The pharmaceutical treatments were either the LNG‐IUS (termed Mirena in the questionnaire) or usual medical treatment (oral treatment), which can include tranexamic acid, mefenamic acid, combined oral contraceptive or Depo‐Provera.\n\nBODY.METHODS.DATA COLLECTION:\nData were collected at baseline and once symptoms had stabilized with treatment ('post‐initial treatment effectiveness'). As the study is nested within the ECLIPSE trial, ECLIPSE trial data collection forms were used to collect baseline data. For the post‐initial treatment effectiveness data collection and for the purposes of this study, we adapted the ECLIPSE trial forms by adding an additional WTP question. Both questionnaires were sent to women in the ECLIPSE trial for completion.\n\nBODY.METHODS.DATA COLLECTION.ECLIPSE TRIAL BASELINE QUESTIONNAIRE:\nAs part of the trial, follow‐up women were asked to complete the condition‐specific measure MMAS and the generic health‐related quality of life measure EQ‐5D‐3L. The instruments had the following properties: \nMMAS. MMAS is a self‐report questionnaire that has six attributes including 'practical difficulties', 'social life', 'psychological health', 'physical health and well‐being', 'work/daily routine' and 'family life/relationships'. Each attribute has four levels ranging from unaffected to severely affected. For example, the wording for social life relating to severely affected reads 'My social life is devastated during my cycle. I am unable to make any plans'. The questions refer to 'during my cycle', and the respondent ticks the level that most accurately reflects their experience. The measure is scored on a 0–100 scale, with 0 being worst possible state for the condition and 100 being best possible state. Each attribute has been weighted according to the menorrhagia patients' preferences using 21 counters, which are considered to be importance points. The visual analogue scale (0–100) is then used to weight the relative importance of the levels within the attribute. The weighting for the levels is then multiplied by the weighting for the attribute. The overall score is then derived by summing the value of the levels ticked by the respondent to provide an overall score between 0 and 100.13\nEQ‐5D‐3L. EQ‐5D is a generic measure of health outcome that can be used across a range of conditions. Its five attributes include 'mobility', 'self‐care', 'usual activities', 'pain/discomfort' and 'Anxiety/depression' The attributes each have three levels and the questions are asked with reference to 'health today'. Responses to the instrument can be used to generate a health‐related quality of life score referred to as a 'utility' value expressed on a scale where 0 represents death, values below zero worse than death and 1 indicates full health.\n\n\nBODY.METHODS.DATA COLLECTION.POST‐INITIAL TREATMENT EFFECTIVENESS QUESTIONNAIRE:\nThe questionnaire booklets that were designed for the purpose of this study were posted in August 2012 to all eligible women in the ECLIPSE trial. This time point captured women who were either 2 or 5 years post‐initial treatment effectiveness, due to the 3‐year time period for recruitment into the trial. By post, women received (1) a patient information sheet outlining the purpose of the work and; (2) an 'ex‐post' (post‐initial treatment effectiveness) questionnaire; and (3) a prepaid stamped addressed envelope to return the completed questionnaire. The objective of the ex‐post questionnaire was to elicit a WTP value for the pharmaceutical treatment that the women were currently taking, either LNG‐IUS or oral treatment. In this context therefore, average maximum WTP values were derived after the change in outcome had occurred, from respondents who had experience of the condition and experience of the treatment. Hence, WTP was elicited from the ex‐post perspective. The WTP value therefore reflected the direction and level of change in outcome over time in response to treatment. It is a commonly practiced approach to consider use value when eliciting WTP in health care.14, 15, 16\n Maximum WTP values were elicited for both LNG‐IUS and oral treatment using the self‐complete ex‐post booklet questionnaire. The booklet was similar in design to the trial questionnaire and captured data on condition‐specific quality of life (MMAS), WTP, socio‐demographic details and health‐related quality of life using the EQ‐5D‐3L. The MMAS was first presented in the questionnaire, followed by questions to determine current and previous treatment taken as part of the ECLIPSE trial. Respondents were asked for their maximum monthly out of pocket WTP value for their current treatment. The time frame of payment of 'up until menopause' was explicitly stated to ensure WTP values were not overestimated.17 To elicit WTP, the payment scale elicitation format was used as it has a higher completion rate than other methods that can be used in a postal questionnaire.18 The scale range used was £0–£500, and an open‐ended option for values greater than £500 was offered. To assess the validity of the WTP responses and the respondents understanding of the WTP question, we then asked the respondent to outline reasons for their WTP values in an open‐ended question. This approach enabled an assessment of responses as well as providing insight into the way in which the WTP question was interpreted. To ensure the WTP values were realistic, that is within the respondent's resources, and in line with good practice, a reminder was included asking the women to consider the amount that they can actually afford to pay.19\n\n\nBODY.METHODS.ANALYSIS:\nFor the analysis, baseline data were taken from the ECLIPSE trial questionnaire and post‐initial treatment effectiveness data were from the purposely developed WTP questionnaire. Scores were calculated for the baseline MMAS, obtained from the ECLIPSE trial, and the current ('ex‐post') MMAS score. Similarly, baseline and follow‐up EQ‐5D quality of life score was calculated for every woman.20 Descriptive statistics are reported for each measure and a paired t‐test was conducted to determine the difference between follow‐up and baseline values at the 5% level. Cohen's effect size (mean change divided by standard deviation) is calculated for each of the measures where 0.2–0.5 indicates a small change, 0.5–0.8 moderate and >0.8 large.21 As the assessment of the validity of WTP is the aim of this study, and not the incremental difference between treatment arms, the WTP values for both treatments were combined. The CUA and CBA which consider the treatment effect by group are presented elsewhere.12, 22 Thus, the WTP for overall treatment (both LNG‐IUS and oral treatment) for menorrhagia is used to assess the convergent validity. The association between WTP and change in condition‐specific quality of life (MMAS), from baseline to the ex‐post values, was first assessed. Second, the association between WTP and change in general health‐related quality of life as measured by the EQ‐5D was assessed. Finally, the association of change in MMAS and change in EQ‐5D was explored. The associations between the measures were assessed by Spearman's correlation analysis. A Rho value between 0.10 and 0.29 indicates a small association, 0.30–0.49 medium association and greater than 0.5 a large association.23 The percentage improvement in MMAS from baseline to current time point was also calculated, using percentage improvements (<25, 26–50, 51–75 and >75%) to establish the extent to which WTP increased with improvement in MMAS from baseline. The Wilcoxon rank–sum test was carried out to identify whether the differences between the WTP values for each percentage change were significant at the 5% level. The qualitative reasons for the WTP values were further analysed and categories generated based on a previous published WTP study.14 The qualitative information was supplemented by exploring the influence of prominent numbers on the WTP results. Prominent numbers are those that are typically selected by respondents and include £0, 1, 2, 5, 10, 20, 50, 100, 200, 500 and so on.24 The selection of prominent numbers is thought to be related to the respondent's perception of the difficulty of the task and their knowledge of the intervention.25 Where appropriate, GBP is converted to USD using a currency conversion website www.fxexchangerate.com; (£1 = US$0.665; 2013). We carried out all data analyses in STATA (v11.0) and Microsoft Excel.\n\nBODY.RESULTS:\nAll of the two hundred and seventy‐two women who were eligible to complete the questionnaire in the trial received a copy. One hundred and sixty‐three questionnaires (60%) were received; however, 78 of these questionnaires were excluded as the women were no longer taking either of the randomized pharmaceutical treatments, and therefore, the WTP section was not applicable to these women. Our intention was to obtain the value for either treatment (LNG‐IUS or oral treatment) and the question posed in the questionnaire referred to 'current treatment'. As these women were either no longer taking any treatment due to menopause or other reasons, it would not be appropriate to use values for 'current treatment'. However, the values of those who have crossed over to the other treatment are included to ensure that the values of those who were unhappy with their original treatment were included. Of the remaining 85 women who returned the questionnaire and were currently taking one of the randomized treatments, 4 (4%) women did not provide a WTP value and MMAS score for their current treatment, and 11 (13%) protest answers were identified from the qualitative explanations offered for the WTP value. Protest responses are defined as an explicit objection to being asked to 'pay' for health care and therefore a misunderstanding of the hypothetical nature of the exercise and are therefore invalid. These 15 non‐responses and protest answers were removed from the analysis. It is generally accepted in the literature that qualitative information associated with the protest responses should be assessed to determine whether the values are genuine WTP values or whether the respondent is protesting against the exercise. There is a debate in the literature about the inclusion of protest responses.14 Where protests are identified, it has been argued that these should not be included in the analysis as they are not valid responses; however, some authors have expressed concerns about their exclusion if the characteristics of the excluded and included group are not assessed.14 There were no significant differences between the characteristics of this excluded group to the sample analysed (see online supplementary material). In total, 70 respondents gave a WTP value for either LNG‐IUS or oral treatment and the characteristics of this sample are presented in Table 1. The proportion of respondents that had a household income of less than £30 000 (US$45 113) was approximately 50%, which was lower than the national average where 65% are below approximately £27 000 (US$40 602).26\n Table 1 Sample characteristics of WTP respondents Variable Treatment ( n = 70) Expected age of menopause (yrs) [SD] 53.80 [2.50] Age [SD] 48.09 [3.93] Marital status (%) Married or living with partner 53 (76) Not 17 (24) Employment status (%) Employed (FT)/(PT) 56 (80) Not 14 (20) Household income (%) Less than £20 000 (<$30 075) 22 (32) £20 001–30 000 ($30 077–$45 113) 14 (20) £30 001–40 000 ($45 114–$60 150) 10 (14) £40 001–50 000 ($60 152–$75 188) 9 (13) More than £50 000 (>$75 189) 13 (20) Main earner (%) Yes 32 (46) No 37 (54) FT, full‐time; PT, part‐time; SD, standard deviation. (US$). John Wiley & Sons, Ltd \n\nBODY.RESULTS.TREATMENT RESPONSE:\nThe average maximum WTP for treatment for menorrhagia was approximately £27 (US$41) per month (see Table 2). The average combined MMAS score for treatment doubled from approximately 43 at pre‐treatment to 85 following treatment, generating a statistically significant improvement in health status as measured by this instrument (P = 0.000). According to the Cohen's standardized effect size, the mean effect of 1.97 observed on MMAS would indicate a large change as the effect size is greater than 0.8. Whilst average EQ‐5D values increased significantly (P = 0.0168) from 0.789 pre‐treatment to 0.880 post‐initial treatment effectiveness, the mean effect size of 0.36 indicates a small change using the same Cohen's criteria (Table 3). Whilst 0.789 pre‐treatment to 0.880 post‐initial treatment effectiveness generates a mean effect size of 0.36 which would indicate a small change using the same Cohen's criteria, it should be noted that this level of change in EQ‐5D would lead to a change in one level of one attribute; for example, using the pain attribute a change would be observed from some pain to no pain which could be deemed clinically important. Table 2 Descriptive statistics for WTP Valid responses Mean (Median) [$] Min–Max [$] SD [$] WTP 70 \n£26.99 (£10) \n[$40.59 ($15)]\n \n£0–£500 \n[$0–$752]\n \n£60.73 \n[$91.32]\n SD, standard deviation; WTP, willingness‐to‐pay. (US$). John Wiley & Sons, Ltd Table 3 Average scores for the instruments Mean MMAS [SD] EQ‐5D [SD] WTP ($) Baseline ( n = 70) 43.23[21.22] 0.789 [0.250] Post‐initial treatment effectiveness ( n = 70) 85.00 [23.15] 0.880 [0.215] £26.99 ($40.59) Change ( n = 70) 41.77 [32.03] 0.09 [0.31] MMAS, Menorrhagia multi‐attribute scale; SD, standard deviation; WTP, willingness‐to‐pay. John Wiley & Sons, Ltd \n\nBODY.RESULTS.RESPONDENT'S UNDERSTANDING OF WTP:\nAmong the 70 women who provided a WTP value, 69 provided a reason for the value. Nine categories of reasons for a WTP value were generated from the qualitative information from all of the women, which included protests and non‐response. The categories of reasons for the sample analysed are presented in Table 4. It can be seen that for both LNG‐IUS and oral treatment that 'R4: affordability' and 'R7: effects of treatment' are the most commonly cited reason for a WTP value. In addition to this finding, it can be seen from Fig. 1, which presents the WTP values for treatment against the number of observations, that the most commonly selected WTP values were prominent numbers, those are £10 and £20, which make up 31 and 16% of the sample which could indicate difficulty with the WTP exercise or a tendency to round numbers (discussed later). Table 4 Explanation given for WTP value (sample analysed, ex‐post) Category Explanation Total n (%) R2 \nSubject expressed difficulty estimating WTP owing to: \nDifficult to answer \nCannot put a price on health care\n 8 (7) R3 \nWTP based on nominal amount \nArbitrary sum/guess/out of thin air\n 1 (0.9) R4 \nWTP reflects ability to pay (affordability) \nMaximum affordable amount given current situation\n 37 (35) R5 \nWTP reflects reasonable value \nNHS should pay but this is a reasonable limit\n 8 (7) R6 \nWTP reflects cost of treatment \nAttempted to estimate cost \nUsed a comparator such as prescription costs\n 5 (5) R7 \nWTP reflects effect of treatment \nIn terms of effectiveness outcomes \nIn terms of process utility\n 30 (28) R9 \nRelated to cost of sanitary wear \nWashing clothes/wipes/painkillers\n 13 (12) R10 Misunderstood exercise but provided WTP value 5 (5) Total 107 a \n NHS; National Health Service, WTP; willingness‐to‐pay. a Some respondents gave more than one reason for their WTP value. Categories R1 and R8 were related to protest responses and are deleted from the table as they were not included in the sample analysed. John Wiley & Sons, Ltd Figure 1Frequency of WTP values.\n\nBODY.RESULTS.ASSOCIATIONS:\nAverage maximum WTP was significantly positively correlated with change in MMAS (P = 0.025) (Table 5). That is, the greater the change in health state, as measured by change in MMAS, the greater the WTP value. However, the strength of the relationship is relatively small, generating a rho value of 0.27. In contrast, the association between change in EQ‐5D and change in MMAS did not show statistical significance (P = 0.059), despite demonstrating a positive correlation (r = 0.23). An unusual, though non‐significant result is generated in the association between WTP and change in EQ‐5D, as a minor negative correlation (r = −0.02) is observed. Table 5 Associations between measures Change in MMAS (rho) WTP (rho) Change in EQ‐5D (rho) Change in MMAS 1.0000 WTP 0.2674 a \n 1.000 Change in EQ‐5D 0.2265 −0.0158 1.000 a \n P = 0.0252 (<0.05) MMAS; menorrhagia multi‐attribute scale, WTP; willingness‐to‐pay. John Wiley & Sons, Ltd When WTP for percentage change in MMAS is assessed, the mean WTP increases as the change in health status increases (from approximately £16 to £63 (US$25–US$95)). Whilst the mean values would suggest that WTP would continue to increase the greater the change in health status, the median values illustrate the skewness of the data but still demonstrate an increase in WTP as health status improves (Table 6). The significance tests show the WTP values between '<25%' and '51–75%' to be significantly increased as percentage change in MMAS increases (P = 0.033; P < 0.05). Table 6 Mean WTP against percentage improvement in MMAS % change in MMAS Mean MMAS [SD] No. obs Mean WTP [SD] ($) Median ($) Min–Max WTP ($) <25 1.27 [12.82] 21 £16.29 [£17.97] ($24.50) £10 ($15) £0–£50 ($0–75) 26–50 36.13 [8.3] 14 £20.86 [£24.65] ($31.37) £10 ($15) £6–£100 ($9–$150) 51–75 60.95 [9.04] 24 £23.38 [£20.63] ($35.16) £20 ($30) £8–£100 ($5–$150) >75 84.44 [10.00] 11 £63.09 [£145.86] ($94.87) £20 ($30) £0–£500 ($0–$752) MMAS; menorrhagia multi‐attribute scale, SD, standard deviation; WTP; willingness‐to‐pay. (US$). John Wiley & Sons, Ltd \n\nBODY.DISCUSSION:\nIn this exploratory study, we aimed to assess the convergent validity of WTP within the context of menorrhagia by comparing change in the condition‐specific measure (MMAS) to (1) change in WTP and (2) the generic health‐related quality of life measure, EQ‐5D‐3L. Overall, our findings suggest the convergent validity of WTP as it behaves as would intuitvely be expected in response to change in health status, as measured by MMAS. Specifically, following treatment, WTP increases with a greater improvement in treatment benefit, and the correlation between the change in condition‐specific MMAS and WTP suggests statistical significance. An association between MMAS and the generic measure, EQ‐5D, was not observed as the change in EQ‐5D scores before and after treatment was not significantly associated with the equivalent change in MMAS. This result suggests that WTP is more sensitive to change in the condition‐specific measure (MMAS), than the generic measure (EQ‐5D). We hypothesize that this finding is attributed to the EQ‐5D instrument being designed as a generic health‐related quality of life measure, which is not focussed specifically on menorrhagia. We suggest that WTP is more sensitive given that it has the potential to measure both health and non‐health aspects of quality of life that are important to women who suffer with menorrhagia, which are also encompassed by the MMAS measure. Qualitative reasons for the WTP responses provided a further opportunity to assess the reliability of the WTP values. The analyses of the reasons confirmed that respondents were considering the 'value' of the treatment as was theoretically expected. These values are therefore reflective of what the theory says people consider when completing WTP exercises. However, the selection of prominent numbers could be related to the perceived difficulty of the task 25 where respondents provide less precise values when they do not feel they have adequate knowledge of the good being valued.24 In this study, the WTP values were elicited from the ex‐post perspective where respondents have experience of, and are knowledgeable about, the treatments and despite this, prominent numbers were most commonly selected. This indicates that although respondents stated 'true' WTP values as confirmed by the qualitative responses, the selection of prominent numbers alludes to the WTP elicitation task being difficult to complete. Finally, as there are several possible approaches for eliciting WTP, the method used in the analysis reported here requires some justification. With respect to the WTP question, the time period 'up until menopause' seemed intuitive given that menorrhagia ceases at menopause and the scale of £0–£500 was thought most suitable, given that the questionnaire asked respondents to provide a monthly WTP value. The monthly payment time frame was used because women generally pay monthly (or every 3 months) for prescriptions for menorrhagia, for sanitary protection and they experience the benefits of treatment on a monthly basis. The out of pocket payment vehicle was deemed appropriate for this context because whilst the full price for treatment is not paid in the UK, patients do make an out of pocket payment for prescriptions for oral treatment in the UK. Although this private payment does not exist for LNG‐IUS, the existence of private payment within this context is likely to minimize the issue of hypothetical bias. To our knowledge, this is the first study to assess the convergent validity of WTP against a change in condition‐specific quality of life measure in menorrhagia. It is also the first to compare the correlation of WTP and change in EQ‐5D with a condition‐specific quality of life measure. A limitation of this exploratory study is the sample size used. Given that the significant difference was observed between the two percentage change categories with the greatest number of observations, it is likely that the remaining categories were not found to be significant due to the limited sample size for the groups '26–50%' and '>75%'. Thus, there may not have been sufficient power to detect a significant difference between these groups. The findings from this exploratory study, however, can be used to inform future sample size calculations for subsequent WTP studies in the area. Prior to this study, it was not readily possible to calculate sample size requirements as a priori data on the distribution of WTP values for the LNG‐IUS or oral treatment were not available.27 This study therefore enables researchers to identify the number and range of responses given to determine how many respondents are required to detect a certain difference in WTP across treatments, that is the WTP value that constitutes a meaningful difference in improvements from baseline or between treatments. To our knowledge, no other study has assessed the sensitivity to scale of WTP according to a longitudinal change in outcome measured by a condition‐specific measure. Other related studies have, however, assessed the relative sensitivity of WTP and time trade‐off (TTO) for changes in described dimensions of health states and have tentatively suggested that WTP is sensitive to change in different levels of health within the same dimension.9 The sensitivity of (ex ante) WTP with a condition‐specific measure at one time point has also been explored.28, 29 Radtke et al.28 assessed the relationship between WTP, EQ‐5D and a condition‐specific measure for vitiligo; and Schiffner et al.29 assessed the sensitivity of WTP and TTO with a condition‐specific measure for psoriasis. Baseline EQ‐5D (or TTO) and condition‐specific scores for current health state were identified, and hypothetical WTP values were elicited for a cure. Both studies found that WTP had a significant correlation with the condition‐specific measure, and Radtke et al.28 also showed WTP and EQ‐5D to have negative correlation. Other psychometric properties of WTP and EQ‐5D in menorrhagia have also been explored. A review of psychometric properties of measures used in menorrhagia3 identified four key studies. One study assessed the consistency of responses of WTP from women with menorrhagia and found a lack of external reliability of WTP.30 The second found EQ‐5D to be unsuitable for patients with menorrhagia.4 In the third, MMAS was statistically associated with changes in satisfaction post‐initial treatment effectiveness, whilst EQ‐5D was not.31 Finally, a lack of sensitivity of EQ‐5D to changes in quality of life associated with menorrhagia was observed.32\n Further research is required to consolidate our findings using a larger sample size, the requirements for which can now be derived based on our study. Additional research could explore the convergent validity of other methods of valuation such as SF‐6D in such a condition, assessing changes in SF‐6D in relation to WTP and MMAS to determine the extent to which SF‐6D reflects changes in MMAS. This exploratory study suggests that there is the potential, and a benefit, to the use of WTP in chronic conditions with episodic symptoms which impact on health and non‐health aspects of life.\n\nBODY.CONFLICTS OF INTEREST:\nThe authors declare that they have no conflict of interest.\n\nBODY.SOURCE OF FUNDING:\nThis study research relates to a PhD studentship which was funded by the National Institute for Health Research Health Technology Assessment programme, UK.\n\nBODY.SUPPORTING INFORMATION:\n\nTable S1. Characteristics of sample analysed and excluded respondentsClick here for additional data file.\n\nQuestion: Compared to before treatment what was the result of after treatment on willingness?to?pay.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1173	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Evaluation of different sodium bicarbonate regimens for the prevention of contrast medium-induced nephropathy\n\n ABSTRACT.INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease. The pathophysiology of contrast-induced nephropathy (CIN) is poorly understood, but it may include acute hypoxia-induced oxidative stress and free radicals generated within the acid environment of the renal medulla. Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN. The aim of this study was to determine whether a long-duration sodium bicarbonate regimen is more effective than a short-duration regimen in reducing CIN.\n\nABSTRACT.METHODS:\nOne hundred patients were assigned randomly to treatment with sodium bicarbonate solution using either the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) or the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). Patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergent coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at Nephrology Department (Theodor Bilharz Research Institute) were enrolled in the study. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nABSTRACT.RESULTS:\nThere was a significant increase in serum creatinine and a decrease in eGFR 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters group 2 (long regimen). Serum potassium clearly was decreased significantly post procedure in both groups.\n\nABSTRACT.CONCLUSIONS:\nThe results of our study indicated that the long regimen of bicarbonate supplementation was a more effective strategy to prevent CIN than the short regimen.\n\nBODY.1. INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease (CKD) or even end-stage renal disease (ESRD). Contrast-induced nephropathy (CIN) is a leading cause of new-onset renal failure in hospitalized patients, with the highest risk observed in patients with CKD (1, 2). It is associated with significantly increased in-hospital and long-term morbidity and mortality and acceleration of chronic renal disease (3). Since there is no specific therapy for CIN and the disease is iatrogenic, prevention is of paramount importance. The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction resulting in renal hypoperfusion, hypoxia-induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4, 5). Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN (6–11). Putting into consideration that the alkalization of urine can be used to prevent CIN, our aim was to evaluate whether a longer duration of sodium bicarbonate infusion is more beneficial than a shorter duration infusion in reducing the frequency of contrast nephropathy in patients after coronary angiography.\n\nBODY.2. MATERIAL AND METHODS:\nThe protocol of this study was approved by the Ethics Committee of Theodor Bilharz Research Institute, and written informed consent was obtained from all patients. The study complies with the Declaration of Helsinki. All adult patients, i.e., those over the age of 18 who were scheduled for coronary angiography, were screened for inclusion and exclusion criteria. Between November 2013 and November 2014, 200 patients were considered eligible for the trial. After 100 exclusions, 100 patients were assigned randomly to either the short-duration or the long duration treatment with sodium bicarbonate solution. The short-duration treatment consisted of intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before the injection of the radiocontrast, with subsequent treatment with the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. The long-duration treatment consisted of initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr before the injection of the radiocontrast, after which the patients received the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. Demographic data, current medication, and medical history were recorded at baseline. Serum creatinine (S. Cr), eGFR, and serum potassium were measured before initiating the pre-procedural hydration. Urine samples were obtained to analyze the pH of the urine one hour prior to the procedure. Two days after coronary angiography, serum creatinine, eGFR, and serum potassium were analyzed again. We calculated eGFR according to the MDRD formula (20). Change in creatinine, percent change in creatinine, percent change in eGFR, change in serum potassium, and urine pH were compared between the two groups. The side effects of the high-dose of sodium bicarbonate, such as congestive heart failure, respiratory disorder, and low potassium, were carefully evaluated during the study. CIN was defined as an increase of more than absolute 0.5 mg/dL and/or relative 25% in serum creatinine after 48 hr. Consecutive patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergency coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at our institution were enrolled. The eGFR was calculated using the MDRD formula. Patients were excluded for any of the following reasons: end-stage renal insufficiency (eGFR <15 mL/min), acute renal insufficiency, a history of reaction to contrast media, the use of potentially nephrotoxic medicines (48 h before and 24 h after the procedure), pulmonary edema, multiple myeloma, exposure to contrast media within 7 days before the procedure, pregnancy, patient non-compliance, and the use of either N-acetylcystein, dopamine, fenoldopam, or mannitol before coronary angiography. Patients were randomized to one of the two regimens of volume supplementation described below. Randomization with stratification for intra-arterial and intravenous radiographic contrast procedures were performed by using sealed envelopes, 1:1 to each group (12). The analysis was performed according to the intent-to-treat principle. All patients were hydrated with intravenous normal saline at 1 mL/kg/h for 12 hr before exposure to the contrast and 12 h after coronary angiography. The rate of infusion was reduced in patients who developed signs of pulmonary congestion. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nBODY.3. RESULTS AND DISCUSSION:\nBetween November 2013 and November 2014, 200 patients were screened, and, after 100 exclusions, 100 patients were randomly assigned to treatment either with short regimen (60 minutes) bicarbonate solution prior to contrast administration (50 patients) or with long regimen (6 hr prior to the intervention) (50 patients). Thus, the final study population was 100 patients. No side effects of sodium bicarbonate infusion were observed, and discontinuation of protocol dose of infusion was not necessary in any of the patients. Our findings showed that there were no significant differences between the two groups in age, gender, smoking, body mass index, diabetes mellitus, hypertension, percutaneous coronary intervention, and volume of contrast administered (Table 1). There were no statistical differences in baseline urine pH, baseline S. Cr., baseline eGFR by MDRD, or baseline serum potassium (S. K.) between the two groups (Table 2). There was a significant increase in S. Cr., and a significant decrease in eGFR by MDRD 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters in group 2 (long regimen). S. K clearly was decreased significantly post-procedure in both groups (short and long regimens). There was no correlation between S. K. and S. Cr. and eGFR by MDRD 48 hr post intervention in both groups. Also, a highly-significant negative correlation between s. Cr and eGFR by MDRD was reported in both groups (Table 3). Note that acute deterioration in renal function can be caused by radiographic contrast agents, but, generally, it is mild and transient. However, acute deterioration can result in lasting renal dysfunction and the need for renal replacement therapy (1). Contrast-induced nephropathy (CIN) is a leading cause of new onset renal failure in hospitalized patients, with the highest risk observed in patients with pre-existing impaired renal function (2). It is associated with significantly increased long-term morbidity and mortality, acceleration of chronic renal disease, and increased costs of medical care (13). The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction, resulting in renal hypoperfusion, hypoxia induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4). Thus, studies have begun to evaluate the effect of volume supplementation with sodium bicarbonate in prevention of CIN based on the hypothesis that alkalinizing renal tubular fluid with bicarbonate may reduce renal injury and increase medullary pH with subsequent slowing of the production of free radicals (14). Similarly, it was stated in (4) that the role of bicarbonate in protecting against CIN is attributed to buffering of subclinical acidosis-induced vasoconstriction, which is typical of acute settings and may amplify the vasoconstriction induced by the contrast itself. On the contrary, some studies have indicated that the effectiveness of sodium bicarbonate treatment to prevent CIN in high risk patients remains uncertain and that the magnitude of any benefit probably had ben overestimated (15, 16). However Klima et al. (16) explained these discrepant findings by the early termination of these studies, publication bias, small differences in the concentration, the overall amount of sodium bicarbonate applied, the type of the contrast procedure, and the patient selection. In our study we compared two procedures of CIN prevention in patients with renal dysfunction: group 1 (short regimen) in which the patients received sodium bicarbonate 20 minutes prior to the contrast administration and group 2 (long regimen) in which the patients received the same amount and concentration sodium bicarbonate but 7 hr prior to the intervention, taken into consideration that all patients in our study received non-ionic low osmolar contrast agents. We observed a significant increase in S. Cr. and significant decrease in eGFR calculated by MDRD formula in (group 1) when we compare their levels prior to contrast administration with their levels 48 hr after the intervention (S. Cr: 2.32 ± 0.41 vs. 2.42 ± 0.48) and (eGFR by MDRD: 30.22 ± 6.07 vs, 28.97 ± 6.57). Regarding group 2, the results of our study showed no statistical difference in S. Cr. and eGFR calculated by MDRD 48 hr post-procedure (S. Cr: 2.26 ± 0.47 vs. 2.26 ± 0.49) and (eGFR by MDRD: 30.97 ± 7.13 vs. 31.06 ± 7.41). Also, we demonstrated a significant inverse correlation between S. Cr. and eGFR calculated by MDRD for both group 1 and group 2 (group 1: r = −0.856, p < 0.001) and (group 2: r = −0.908, p < 0.001). In agreement with our study, Briguori et al. (17) found that the long-term regimen of sodium bicarbonate was superior to the short regimen. This was in agreement with with Recio-Mayoral et al. (18). On the contrary, Klima et al. (16) and Mueller (4) stated that both regimens (the long and the short regimens) have the same effectiveness with very high safety, even in patients with NYHA class I or II heart failure, and, thus, the short-term regimen may be the regimen of choice because it is very easy to apply, even to outpatient procedures (15–17). Our research also showed that S. K. has significantly decreased post procedure in both group 1 and group 2 (group1: 4.21 ± 0.43 vs. 3.88 ± 0.33) and (group 2: 4.16 ± 0.42 vs. 3.92 ± 0.34). Also, we demonstrated a non-significant negative correlation between S. Cr. and S. K. in both groups (group 1: r = −0.184) and (group 2: r = −0.235). This was in agreement with Walter et al. (19) who reported that the infusion of sodium bicarbonate can shift potassium from the extracellular to the intracellular space by increasing blood pH. However, this should be reserved for situations with severe educational environments (19). In contrast, Kim (20) stated that sodium bicarbonate is no longer recommended to lower potassium, although it may be appropriate in patients with severe metabolic acidosis (20). Regarding the pH of urine, we found that it was (5.95 ± 0.26) in group 1 and (5.97 ± 0.24) in group 2, showing no statistical difference and highlighting the fact that both regimen had almost the same alkalinizing efficacy with no proven extra benefit for patients with pH values greater than 6.\n\nBODY.4. CONCLUSIONS:\nWe should stress the importance of sodium bicarbonate infusion prior to the administration of the contrast medium to guard against CIN, especially in renally-impaired patients who could easily be susceptible to CIN. In addition, the results of our study indicated that the long regimen of bicarbonate supplementation was a better and more efficient strategy to prevent CIN than the short regimen.\n\nQuestion: Compared to sodium bicarbonate solution using the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). what was the result of sodium bicarbonate solution using the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) on the pH of urine?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1174	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Evaluation of different sodium bicarbonate regimens for the prevention of contrast medium-induced nephropathy\n\n ABSTRACT.INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease. The pathophysiology of contrast-induced nephropathy (CIN) is poorly understood, but it may include acute hypoxia-induced oxidative stress and free radicals generated within the acid environment of the renal medulla. Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN. The aim of this study was to determine whether a long-duration sodium bicarbonate regimen is more effective than a short-duration regimen in reducing CIN.\n\nABSTRACT.METHODS:\nOne hundred patients were assigned randomly to treatment with sodium bicarbonate solution using either the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) or the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). Patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergent coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at Nephrology Department (Theodor Bilharz Research Institute) were enrolled in the study. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nABSTRACT.RESULTS:\nThere was a significant increase in serum creatinine and a decrease in eGFR 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters group 2 (long regimen). Serum potassium clearly was decreased significantly post procedure in both groups.\n\nABSTRACT.CONCLUSIONS:\nThe results of our study indicated that the long regimen of bicarbonate supplementation was a more effective strategy to prevent CIN than the short regimen.\n\nBODY.1. INTRODUCTION:\nThe rapid decline in renal function caused by radiographic contrast agents usually is transient, but it can result in chronic kidney disease (CKD) or even end-stage renal disease (ESRD). Contrast-induced nephropathy (CIN) is a leading cause of new-onset renal failure in hospitalized patients, with the highest risk observed in patients with CKD (1, 2). It is associated with significantly increased in-hospital and long-term morbidity and mortality and acceleration of chronic renal disease (3). Since there is no specific therapy for CIN and the disease is iatrogenic, prevention is of paramount importance. The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction resulting in renal hypoperfusion, hypoxia-induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4, 5). Thus, the alkalization of urine by sodium bicarbonate has been regarded as resulting in the reduction of CIN (6–11). Putting into consideration that the alkalization of urine can be used to prevent CIN, our aim was to evaluate whether a longer duration of sodium bicarbonate infusion is more beneficial than a shorter duration infusion in reducing the frequency of contrast nephropathy in patients after coronary angiography.\n\nBODY.2. MATERIAL AND METHODS:\nThe protocol of this study was approved by the Ethics Committee of Theodor Bilharz Research Institute, and written informed consent was obtained from all patients. The study complies with the Declaration of Helsinki. All adult patients, i.e., those over the age of 18 who were scheduled for coronary angiography, were screened for inclusion and exclusion criteria. Between November 2013 and November 2014, 200 patients were considered eligible for the trial. After 100 exclusions, 100 patients were assigned randomly to either the short-duration or the long duration treatment with sodium bicarbonate solution. The short-duration treatment consisted of intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before the injection of the radiocontrast, with subsequent treatment with the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. The long-duration treatment consisted of initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr before the injection of the radiocontrast, after which the patients received the same fluid at a rate of 1 mL/kg/h during the contrast exposure and for 6 h after the procedure. Demographic data, current medication, and medical history were recorded at baseline. Serum creatinine (S. Cr), eGFR, and serum potassium were measured before initiating the pre-procedural hydration. Urine samples were obtained to analyze the pH of the urine one hour prior to the procedure. Two days after coronary angiography, serum creatinine, eGFR, and serum potassium were analyzed again. We calculated eGFR according to the MDRD formula (20). Change in creatinine, percent change in creatinine, percent change in eGFR, change in serum potassium, and urine pH were compared between the two groups. The side effects of the high-dose of sodium bicarbonate, such as congestive heart failure, respiratory disorder, and low potassium, were carefully evaluated during the study. CIN was defined as an increase of more than absolute 0.5 mg/dL and/or relative 25% in serum creatinine after 48 hr. Consecutive patients with renal dysfunction (estimated glomerular filtration rate [eGFR], 60 mL/min/1.73 m2 or less) who underwent elective or emergency coronary angiography (CAG) with/without percutaneous coronary intervention (PCI) at our institution were enrolled. The eGFR was calculated using the MDRD formula. Patients were excluded for any of the following reasons: end-stage renal insufficiency (eGFR <15 mL/min), acute renal insufficiency, a history of reaction to contrast media, the use of potentially nephrotoxic medicines (48 h before and 24 h after the procedure), pulmonary edema, multiple myeloma, exposure to contrast media within 7 days before the procedure, pregnancy, patient non-compliance, and the use of either N-acetylcystein, dopamine, fenoldopam, or mannitol before coronary angiography. Patients were randomized to one of the two regimens of volume supplementation described below. Randomization with stratification for intra-arterial and intravenous radiographic contrast procedures were performed by using sealed envelopes, 1:1 to each group (12). The analysis was performed according to the intent-to-treat principle. All patients were hydrated with intravenous normal saline at 1 mL/kg/h for 12 hr before exposure to the contrast and 12 h after coronary angiography. The rate of infusion was reduced in patients who developed signs of pulmonary congestion. Data were analyzed by SPSS version 12, using Kruskal Wallis, ANOVA, Chi square test and Spearman rank correlation coefficient.\n\nBODY.3. RESULTS AND DISCUSSION:\nBetween November 2013 and November 2014, 200 patients were screened, and, after 100 exclusions, 100 patients were randomly assigned to treatment either with short regimen (60 minutes) bicarbonate solution prior to contrast administration (50 patients) or with long regimen (6 hr prior to the intervention) (50 patients). Thus, the final study population was 100 patients. No side effects of sodium bicarbonate infusion were observed, and discontinuation of protocol dose of infusion was not necessary in any of the patients. Our findings showed that there were no significant differences between the two groups in age, gender, smoking, body mass index, diabetes mellitus, hypertension, percutaneous coronary intervention, and volume of contrast administered (Table 1). There were no statistical differences in baseline urine pH, baseline S. Cr., baseline eGFR by MDRD, or baseline serum potassium (S. K.) between the two groups (Table 2). There was a significant increase in S. Cr., and a significant decrease in eGFR by MDRD 48 hr post-intervention in group 1 (short regimen) with no statically difference regarding those parameters in group 2 (long regimen). S. K clearly was decreased significantly post-procedure in both groups (short and long regimens). There was no correlation between S. K. and S. Cr. and eGFR by MDRD 48 hr post intervention in both groups. Also, a highly-significant negative correlation between s. Cr and eGFR by MDRD was reported in both groups (Table 3). Note that acute deterioration in renal function can be caused by radiographic contrast agents, but, generally, it is mild and transient. However, acute deterioration can result in lasting renal dysfunction and the need for renal replacement therapy (1). Contrast-induced nephropathy (CIN) is a leading cause of new onset renal failure in hospitalized patients, with the highest risk observed in patients with pre-existing impaired renal function (2). It is associated with significantly increased long-term morbidity and mortality, acceleration of chronic renal disease, and increased costs of medical care (13). The pathophysiology of CIN is poorly understood, but it may include acute vasoconstriction, resulting in renal hypoperfusion, hypoxia induced oxidative stress, and free radicals generated within the acid environment of the renal medulla (4). Thus, studies have begun to evaluate the effect of volume supplementation with sodium bicarbonate in prevention of CIN based on the hypothesis that alkalinizing renal tubular fluid with bicarbonate may reduce renal injury and increase medullary pH with subsequent slowing of the production of free radicals (14). Similarly, it was stated in (4) that the role of bicarbonate in protecting against CIN is attributed to buffering of subclinical acidosis-induced vasoconstriction, which is typical of acute settings and may amplify the vasoconstriction induced by the contrast itself. On the contrary, some studies have indicated that the effectiveness of sodium bicarbonate treatment to prevent CIN in high risk patients remains uncertain and that the magnitude of any benefit probably had ben overestimated (15, 16). However Klima et al. (16) explained these discrepant findings by the early termination of these studies, publication bias, small differences in the concentration, the overall amount of sodium bicarbonate applied, the type of the contrast procedure, and the patient selection. In our study we compared two procedures of CIN prevention in patients with renal dysfunction: group 1 (short regimen) in which the patients received sodium bicarbonate 20 minutes prior to the contrast administration and group 2 (long regimen) in which the patients received the same amount and concentration sodium bicarbonate but 7 hr prior to the intervention, taken into consideration that all patients in our study received non-ionic low osmolar contrast agents. We observed a significant increase in S. Cr. and significant decrease in eGFR calculated by MDRD formula in (group 1) when we compare their levels prior to contrast administration with their levels 48 hr after the intervention (S. Cr: 2.32 ± 0.41 vs. 2.42 ± 0.48) and (eGFR by MDRD: 30.22 ± 6.07 vs, 28.97 ± 6.57). Regarding group 2, the results of our study showed no statistical difference in S. Cr. and eGFR calculated by MDRD 48 hr post-procedure (S. Cr: 2.26 ± 0.47 vs. 2.26 ± 0.49) and (eGFR by MDRD: 30.97 ± 7.13 vs. 31.06 ± 7.41). Also, we demonstrated a significant inverse correlation between S. Cr. and eGFR calculated by MDRD for both group 1 and group 2 (group 1: r = −0.856, p < 0.001) and (group 2: r = −0.908, p < 0.001). In agreement with our study, Briguori et al. (17) found that the long-term regimen of sodium bicarbonate was superior to the short regimen. This was in agreement with with Recio-Mayoral et al. (18). On the contrary, Klima et al. (16) and Mueller (4) stated that both regimens (the long and the short regimens) have the same effectiveness with very high safety, even in patients with NYHA class I or II heart failure, and, thus, the short-term regimen may be the regimen of choice because it is very easy to apply, even to outpatient procedures (15–17). Our research also showed that S. K. has significantly decreased post procedure in both group 1 and group 2 (group1: 4.21 ± 0.43 vs. 3.88 ± 0.33) and (group 2: 4.16 ± 0.42 vs. 3.92 ± 0.34). Also, we demonstrated a non-significant negative correlation between S. Cr. and S. K. in both groups (group 1: r = −0.184) and (group 2: r = −0.235). This was in agreement with Walter et al. (19) who reported that the infusion of sodium bicarbonate can shift potassium from the extracellular to the intracellular space by increasing blood pH. However, this should be reserved for situations with severe educational environments (19). In contrast, Kim (20) stated that sodium bicarbonate is no longer recommended to lower potassium, although it may be appropriate in patients with severe metabolic acidosis (20). Regarding the pH of urine, we found that it was (5.95 ± 0.26) in group 1 and (5.97 ± 0.24) in group 2, showing no statistical difference and highlighting the fact that both regimen had almost the same alkalinizing efficacy with no proven extra benefit for patients with pH values greater than 6.\n\nBODY.4. CONCLUSIONS:\nWe should stress the importance of sodium bicarbonate infusion prior to the administration of the contrast medium to guard against CIN, especially in renally-impaired patients who could easily be susceptible to CIN. In addition, the results of our study indicated that the long regimen of bicarbonate supplementation was a better and more efficient strategy to prevent CIN than the short regimen.\n\nQuestion: Compared to sodium bicarbonate solution using the long regimen (initial intravenous bolus of 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 6 hr). what was the result of sodium bicarbonate solution using the short regimen (intravenous bolus 3 mL/kg/h of 166 mEq/L sodium bicarbonate for 1 hour immediately before radiocontrast) on serum creatinine?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1177	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Mirabegron for the treatment of overactive bladder: a prespecified pooled efficacy analysis and pooled safety analysis of three randomised, double-blind, placebo-controlled, phase III studies\n\n ABSTRACT.INTRODUCTION:\nTo examine pooled efficacy data from three, large phase III studies comparing mirabegron (50 and 100 mg) with placebo, and pooled safety data including additional mirabegron 25 mg and tolterodine extended release (ER) 4 mg results.\n\nABSTRACT.METHODS:\nThis prespecified pooled analysis of three randomised, double-blind, placebo-controlled, 12-week studies, evaluated efficacy and safety of once-daily mirabegron 25 mg (safety analysis), 50 or 100 mg (efficacy and safety analyses) and tolterodine ER 4 mg (safety analysis) for the treatment of symptoms of overactive bladder (OAB). Co-primary efficacy measures were change from baseline to Final Visit in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h. Key secondary efficacy end-points included mean number of urgency episodes/24 h and mean volume voided/micturitions, while other end-points included patient-reported outcomes according to the Treatment Satisfaction-Visual Analogue Scale (TS-VAS) and responder analyses [dry rate (posttreatment), ≥ 50% reduction in incontinence episodes/24 h, ≤ 8 micturitions/24 h (post hoc analysis)]. The safety analysis included adverse event (AE) reporting, laboratory assessments, ECG, postvoid residual volume and vital signs (blood pressure, pulse rate).\n\nABSTRACT.RESULTS:\nMirabegron (50 and 100 mg once daily) demonstrated statistically significant improvements compared with placebo for the co-primary end-points, key secondary efficacy variables, TS-VAS and responder analyses (all comparisons p < 0.05). Mirabegron is well tolerated and demonstrates a good safety profile. The most common AEs (≥ 3%) included hypertension, nasopharyngitis and urinary tract infection (UTI); the incidence of hypertensive events and UTIs decreased with increasing dose. For mirabegron, the incidence of the bothersome antimuscarinic AE, dry mouth, was at placebo level and of a lesser magnitude than tolterodine.\n\nABSTRACT.CONCLUSION:\nThe efficacy and safety of mirabegron are demonstrated in this large pooled clinical trial dataset in patients with OAB.\n\nBODY:\nWhat's knownOveractive bladder (OAB) is a chronic condition that is increasingly prevalent with age and represents an increasing healthcare burden to society.Antimuscarinic drugs are the current mainstay of pharmacologic treatment for OAB, but are commonly associated with adherence-limiting adverse effects including dry mouth, constipation and blurred vision.Many patients discontinue antimuscarinic therapy or seek alternative approaches to control OAB as a result of adverse effects or suboptimal efficacy.What's newMirabegron is a β3-adrenoceptor agonist, the first in a new class of drugs with a mode of action that is different from antimuscarinic agents.Mirabegron stimulates the β3-adrenoceptors in the bladder leading to detrusor relaxation and increased bladder capacity.In three international, multicentre, phase III studies, comparing mirabegron, at doses of 25, 50 and 100 mg, with placebo, mirabegron was associated with significant improvements in incontinence episodes and micturition frequency, and was well tolerated.\n\nBODY.INTRODUCTION:\nOveractive bladder (OAB) is defined by the International Continence Society as urinary urgency, with or without urinary incontinence, usually with frequency and nocturia, with no proven infection or other obvious pathology 1,2. Lower urinary tract symptoms, including those associated with OAB, are prevalent in approximately half of the general population 3, are often debilitating and have a significant impact on patients' daily routines and quality of life 3–5. OAB affects 12–16% of the adult population across Europe, the USA and Japan 6–8, and its prevalence increases with age, affecting approximately 30% of individuals > 65 years of age 9, therefore representing a substantive health problem for the ageing population. Normal bladder function is regulated by the synergistic actions of the autonomic nervous system: parasympathetic nerves stimulate contraction of the detrusor muscle via muscarinic receptors while stimulation of the sympathetic nerves leads to detrusor relaxation via β-adrenoceptors. The central pathophysiology of OAB involves involuntary contractions of the detrusor muscle as a result of increased afferent activity, decreased inhibitory control from the central nervous system, and/or increased sensitivity of the detrusor muscle to parasympathetic stimulation 10,11. Because of the role of β-adrenoceptors in relaxation of the detrusor, research was aimed at identifying an effective and well-tolerated agent directed at the β-adrenoceptor. The β3-adrenoceptor was recognised as the predominant β-receptor subtype in the human urinary bladder, representing 97% of total β-adrenoceptor mRNA expression in the human bladder 12. The importance of its role in the relaxation of the detrusor has been confirmed by in vitro pharmacological studies using human bladder strips 13–15. In animal models, activation of the β-adrenoceptor in the bladder facilitates urine storage through flattening and lengthening of the bladder base 16. Furthermore, stimulation of the β3-adrenoceptor is associated with increased bladder capacity, without change in micturition pressure, residual volume or voiding contraction 17–19. As a consequence, targeting the β3-adrenoceptor increases the storage capacity of the bladder without affecting the amplitude of the voiding contraction. Mirabegron, a β3-adrenoceptor agonist approved in Japan, the USA, Canada and Europe, for the treatment of OAB symptoms, is the first of a new class of compounds with a mechanism of action that is different from antimuscarinic agents 20. The recommended starting dose of mirabegron is 25 mg in the USA, which can be increased to 50 mg based on individual efficacy and tolerability, and 50 mg in Japan and Europe; the 100 mg dose is not approved for use. Three large-scale, 12-week, phase III studies conducted in the USA/Canada (study 047; NCT00662909) 21; Europe and Australia (study 046; NCT00689104) 22; and Europe/USA/Canada (study 074; NCT00912964)23 have demonstrated the safety, tolerability and superior efficacy of mirabegron at doses of 25 mg (NCT00912964 only), 50 mg (all three studies) and 100 mg (NCT00662909 and NCT00689104) compared with placebo for the treatment of OAB symptoms. The pooled efficacy analysis was prespecified and excluded the 25 mg mirabegron dose because it was limited to a single study. The safety analysis was an aggregate of all data from the three phase III studies and included the 25, 50 and 100 mg mirabegron doses. Pooling these data allows for additional analyses of efficacy and safety in a large dataset representative of the general OAB population in terms of demographics, previous OAB history and prevalence of comorbidities. In particular, it is important to examine the efficacy, safety and tolerability profile demonstrated in the individual studies in the pooled population for overall effect size as well as safety data reporting across the treatment groups. These pooled mirabegron data evaluations inform benefit–risk assessments and support judicious dose selection.\n\nBODY.METHODS.STUDY DESIGN:\nThis was a prespecified pooled analysis of three randomised, double-blind, placebo-controlled, 12-week studies, which evaluated the efficacy of mirabegron 50 and 100 mg, and safety of mirabegron 25 mg (NCT00912964 only), 50 mg or 100 mg for the treatment of symptoms of OAB. Each study shared a similar design, although the assessed doses of mirabegron and inclusion of an active control arm with tolterodine extended release (ER) 4 mg varied across trials (Figure 1). Male and female patients aged ≥ 18 years with OAB symptoms for ≥ 3 months were enrolled. Following a 2-week, single-blind, placebo run-in period to determine baseline symptoms and patient eligibility, patients were randomised if, during a 3-day micturition diary period, they recorded ≥ 8 micturitions/24 h and ≥ 3 urgency episodes – based on urgency grade of 3 or 4 according to the Patient Perception of Intensity and Urgency Scale [PPIUS 24] – with or without urgency incontinence. Patients were excluded with stress incontinence or mixed incontinence with stress predominance at screening or had an average total daily urine volume > 3000 ml. Figure 1Overview of the individual phase III studies included in the pooled analyses. †Screening from weeks −3 to −2; Evaluation of adverse events and concomitant medication by telephone contact or visit 30 days after Final Visit in studies 046 and 047 and 2 weeks after Final Visit in Study 074. n, number of patients randomised Patients were randomised to receive once-daily oral placebo, mirabegron 25 mg (NCT00912964 only), mirabegron 50 mg (NCT00912964/NCT00689104/NCT00662909), mirabegron 100 mg (NCT00689104/NCT00662909) or tolterodine ER 4 mg (NCT00689104 only) for 12 weeks using a computer-generated randomisation scheme; after assignment to treatment, both patient and study investigator were blinded to the identity of the study drug. Efficacy data for treatment arms that were represented in only one study (i.e. mirabegron 25 mg or tolterodine ER 4 mg) were not pooled as these data were only available from one trial. In summary, the efficacy data in these pooled analyses relate to the placebo and 50 mg mirabegron groups from all three phase III studies, and the 100 mg mirabegron group from two of the studies [NCT00662909 21/NCT00689104 22]. In contrast, the pooled 12-week phase III safety analysis includes data for the placebo, 25, 50 and 100 mg mirabegron doses and the tolterodine ER 4 mg active control arm.\n\nBODY.METHODS.EFFICACY END-POINTS:\nEfficacy measures were recorded in a patient micturition diary over a 3-day period prior to clinic visits which occurred at baseline and 4, 8 and 12 weeks/Final Visit (end of treatment, i.e. last on-treatment assessment including patients who did not complete week 12 visit) after randomisation to treatment. The co-primary end-points in all three studies were change from baseline to Final Visit in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h. Key secondary efficacy end-points in all three studies were change from baseline to Final Visit in the mean volume voided/micturition, change from baseline to week 4 in the mean number of incontinence episodes/24 h, and change from baseline to week 4 in the mean number of micturitions/24 h. Study 074 (NCT00912964) had three additional key secondary end-points – mean level of urgency (based on the PPIUS), mean number of urgency episodes (PPIUS grade 3 or 4)/24 h, and the mean number of urgency incontinence episodes/24 h – which were also included as additional secondary end-points in Study 046 (NCT00689104) and Study 047 (NCT00662909) but did not undergo the hierarchical testing procedure for multiple end-points. Further secondary end-points included change from baseline to Final Visit in mean number of nocturia episodes/24 h and patients considered 'responders' to treatment, i.e. the proportion of patients with incontinence episode(s) at baseline with zero incontinence at Final Visit, the proportion of patients with a ≥ 50% decrease from baseline in mean number of incontinence episodes/24 h, and a post hoc analysis of the proportion of patients with ≤ 8 micturitions/24 h at Final Visit. Patient-reported outcomes were assessed using the Treatment Satisfaction-Visual Analogue Scale (TS-VAS), a quantitative instrument measuring subjective improvement in patients with OAB. Complete satisfaction was indicated by a score of 10, with positive change from baseline indicating improvement.\n\nBODY.METHODS.SAFETY END-POINTS:\nThe analysis of the pooled safety data included adverse event (AE) reporting, laboratory parameters (haematology and serum chemistry), vital signs (pulse rate and blood pressure), ECG data and postvoid residual (PVR) volume. AEs of interest were based on potential or theoretical risk related to the pharmacology of β3-agonists, observed findings in non-clinical or clinical data, or recommended monitoring for specific events. The most common treatment-emergent AEs (TEAEs), according to the preferred term, are reported herein as TEAEs in ≥ 3% of the total mirabegron population. Hypertension was reported as an AE if average systolic blood pressure (SBP) was ≥ 140 mmHg and/or average diastolic blood pressure (DBP) ≥ 90 mmHg at two consecutive postbaseline visits for normotensive patients at baseline; average SBP increased ≥ 20 mmHg and/or average DBP increased ≥ 10 mmHg at two consecutive postbaseline visits for patients with hypertension at baseline; initiation or increase in antihypertensive medication; or according to clinical assessment by the investigator. Tachycardia was to be reported as an AE if average AM or PM resting pulse rate measured by the patient over 3 days was > 100 bpm (unless in the investigator's opinion this did not constitute an AE of tachycardia). Urinary retention was summarised as a reported TEAE based on spontaneous reporting by the investigator, without a prespecified definition per protocol, and assessed concurrently with changes in PVR volume (change from baseline of ≥ 150 ml).\n\nBODY.METHODS.STATISTICAL ANALYSES:\nThe safety analysis set (SAF) comprised all randomised patients who took ≥ 1 dose of double-blind study drug; the full analysis set (FAS) comprised SAF patients who had ≥ 1 micturition measurement at baseline and ≥ 1 postbaseline micturition measurement; the FAS-incontinence (FAS-I) set comprised FAS patients who reported ≥ 1 incontinence episode at baseline. Efficacy analyses were performed using the FAS except for incontinence episode end-points which used the FAS-I. Safety analyses were performed using the SAF. Descriptive statistics were used for baseline demographic and clinical characteristics. For the efficacy analysis, data for the placebo and 50 mg mirabegron groups from all three studies were pooled, and data for the 100 mg mirabegron groups from two studies were pooled. Hypothesis testing on the change from baseline in incontinence episodes was performed using a separate stratified rank analysis of covariance (ANCOVA) for each pairwise treatment group difference (mirabegron 50 and 100 mg vs. placebo). For all other efficacy end-points, hypothesis testing comparing mirabegron 50 and 100 mg vs. placebo on the change from baseline values was performed using an ANCOVA model including treatment, gender and study as fixed factors, and baseline value as a covariate. Based on the ANCOVA, least squares mean estimates and two-sided 95% confidence intervals (CIs) for mean changes from baseline were derived within treatment groups and between each mirabegron treatment group and placebo on all efficacy end-points. Multiplicity between the two primary and six key secondary efficacy end-points was controlled at the α = 0.05 type I error rate using a stepwise parallel gatekeeping procedure in which the placebo-corrected difference in mean change from baseline for each mirabegron dose had to be statistically significant to allow hypothesis testing to proceed to the next end-point step. The Hochberg procedure was performed at the α = 0.05 significance level for comparisons of the 50 and 100 mg mirabegron treatment groups with placebo to adjust for multiplicity within each stage. If only one mirabegron dose group proceeded to the next stage for any efficacy end-point, the comparison with placebo was assessed at the α = 0.025 level. Responder end-points were analysed using a logistic regression model which included treatment, gender, study and baseline value. For the pooled safety analysis, data from all three studies were included: placebo, 25, 50 and 100 mg mirabegron groups, and tolterodine ER 4 mg arm. All AEs were coded using the Medical Dictionary for Regulatory Activities version 12.1. TEAEs were defined as any AE which started, or worsened, after the first dose of study drug through 30 days after the last dose of study drug. Drug-related TEAEs included those AEs reported as probably or possibly related to study drug as assessed by the investigator or if the AE had a missing relationship. Descriptive statistics were used for measurements of laboratory parameters, ECGs and PVR volume. Change from baseline values for vital sign variables was analysed using the ANCOVA model described above.\n\nBODY.RESULTS.DEMOGRAPHIC AND BASELINE CLINICAL CHARACTERISTICS:\nOverall, there were a total of 3542 patients (placebo, n = 1328; mirabegron 50 mg, n = 1324; mirabegron 100 mg, n = 890) and 2317 patients (placebo, n = 878; mirabegron 50 mg, n = 862; mirabegron 100 mg, n = 577), respectively, in the FAS and FAS-I population for the pooled efficacy analysis. The pooled safety analysis included the additional 25 mg mirabegron dose and tolterodine active control arm and consisted of 4611 patients (mirabegron 25 mg, n = 432; mirabegron 50 mg, n = 1375; mirabegron 100 mg, n = 929; placebo, n = 1380; tolterodine, n = 495) who took at least one dose of double-blind study medication. In the FAS and SAF analyses, the disposition and reasons for discontinuation of study drug were similar for all treatment groups (Figure 2). Figure 2Patient disposition in the pooled efficacy and safety analyses Demographic and baseline characteristics were similar between the FAS and FAS-I population with the exception of gender; approximately 72% and 82% of patients were female in the FAS and FAS-I population, respectively (Table 1). Of the patients who had received prior antimuscarinic OAB medication, approximately two-thirds discontinued prior OAB treatment because of insufficient efficacy, and approximately one-quarter because of poor tolerability. The proportion discontinuing prior OAB treatment for either reason was similar across treatment groups (Table 1). Table 1 Patient demographics and baseline clinical characteristics by treatment group (FAS) Placebo ( n = 1328) Mirabegron 50 mg ( n = 1324) Mirabegron 100 mg ( n = 890) Gender, n (%) Male 362 (27.3) 382 (28.9) 241 (27.1) Female 966 (72.7) 942 (71.1) 649 (72.9) Age (years) Mean (SD) 59.2 (13.2) 59.7 (12.6) 59.8 (12.9) Range 20–95 21–91 19–90 Race, n (%) White 1227 (92.4) 1235 (93.3) 838 (94.2) Black or African American 80 (6.0) 61 (4.6) 36 (4.0) Asian 13 (1.0) 17 (1.3) 8 (0.9) Other 8 (0.6) 11 (0.8) 8 (0.9) BMI (kg/m 2 ) Mean 29.1 (6.3) 29.0 (6.1) 29.1 (6.1) Range 15.9–58.1 16.3–60.5 16.2–62.6 Type of OAB, n (%) Urgency incontinence 442 (33.3) 491 (37.1) 297 (33.4) Mixed 415 (31.3) 412 (31.1) 271 (30.4) Frequency 471 (35.5) 421 (31.8) 322 (36.2) Duration of OAB (months) Mean (SD) 86.3 (99.1) 85.2 (93.1) 88.3 (101.6) Previous OAB drug, n (%) Yes 704 (53.0) 688 (52.0) 460 (51.7) Reasons for previous OAB drug discontinuation, n (%) † Insufficient effect Yes 466 (66.2) 464 (67.4) 296 (64.3) No 238 (33.8) 224 (32.6) 164 (35.7) Poor tolerability Yes 185 (26.3) 173 (25.1) 113 (24.6) No 519 (73.7) 515 (74.9) 347 (75.4) Mean number of incontinence episodes/24 h Mean (SD) 1.8 (2.5) 1.8 (2.5) 1.8 (2.4) Range 0–26 0–18 0–15 Mean number of micturitions/24 h Mean (SD) 11.6 (3.1) 11.7 (3.2) 11.6 (3.0) Range 4–40 6–37 7–35 FAS, full analysis set; SD, standard deviation; BMI, body mass index; OAB, overactive bladder. * For BMI, placebo ( n = 1327) and mirabegron 100 mg ( n = 889). † Percentages are based on patients who had taken previous OAB medication. Patients could choose more than one reason for discontinuation. \n\nBODY.RESULTS.EFFICACY OUTCOMES:\nMirabegron at doses of 50 and 100 mg once daily demonstrated statistically significant improvement from baseline to Final Visit compared with placebo in reducing the mean number of incontinence episodes/24 h and the mean number of micturitions/24 h (p < 0.05 for all comparisons; Table 2 and Figures 3 and 4, respectively). The adjusted mean (95% CI) change from baseline to Final Visit in the mean number of incontinence episodes/24 h was −1.10 (−1.23, −0.97), −1.49 (−1.63, −1.36) and −1.50 (−1.67, −1.34) in the placebo, mirabegron 50 and 100 mg groups, respectively, and −1.20 (−1.34, −1.06), −1.75 (−1.89, −1.61), −1.74 (−1.91, −1.56) for the adjusted mean change from baseline to Final Visit in the mean number of micturitions/24. Table 2 Summary of primary and secondary efficacy end-points (FAS and FAS-I) Placebo Mirabegron 50 mg Mirabegron 100 mg Co-primary end-points Change from baseline to Final Visit in the mean number of incontinence episodes/24 h (FAS-I) Baseline 2.73 (0.09) 2.71 (0.09) 2.79 (0.10) Final Visit 1.64 (0.09) 1.23 (0.08) 1.25 (0.09) Change from baseline −1.09 (0.09) −1.48 (0.08) −1.54 (0.09) Adjusted change from baseline * (95% CI) −1.10 (−1.23, −0.97) −1.49 (−1.63, −1.36) −1.50 (−1.67, −1.34) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.58, −0.21) 3 −0.41 (−0.62, −0.19) 3 Change from baseline to Final Visit in the mean number of micturitions/24 h (FAS) Baseline 11.58 (0.09) 11.70 (0.09) 11.58 (0.10) Final Visit 10.39 (0.09) 9.93 (0.09) 9.83 (0.11) Change from baseline −1.18 (0.08) −1.77 (0.08) −1.75 (0.09) Adjusted change from baseline * (95% CI) −1.20 (−1.34, −1.06) −1.75 (−1.89, −1.61) −1.74 (−1.91, −1.56) Adjusted difference vs. placebo * (95% CI) – −0.55 (−0.75, −0.36) † −0.54 (−0.77, −0.31) † Key secondary end-points Change from baseline to Final Visit in the mean volume voided/micturition (FAS) Baseline 159.2 (1.54) 159.0 (1.55) 157.9 (1.89) Final Visit 168.6 (1.90) 180.2 (2.01) 179.9 (2.39) Change from baseline 9.4 (1.31) 21.2 (1.31) 22.0 (1.52) Adjusted change from baseline * (95% CI) 9.4 (6.9, 12.0) 21.4 (18.8, 23.9) 21.7 (18.5, 24.9) Adjusted difference vs. placebo * (95% CI) – 11.9 (8.3, 15.5) † 12.3 (8.1, 16.5) † Change from baseline to week 4 in the mean number of incontinence episodes/24 h (FAS-I) Baseline 2.73 (0.09) 2.71 (0.09) 2.79 (0.10) Week 4 2.06 (0.10) 1.59 (0.08) 1.69 (0.10) Change from baseline −0.67 (0.08) −1.12 (0.08) −1.10 (0.09) Adjusted change from baseline * (95% CI) −0.67 (−0.81, −0.54) −1.12 (−1.26, −0.98) −1.09 (−1.27, −0.92) Adjusted difference vs. placebo * (95% CI) – −0.45 (−0.64, −0.26) † −0.42 (−0.65, −0.20) † Change from baseline to week 4 in the mean number of micturitions/24 h (FAS) Baseline 11.58 (0.09) 11.71 (0.09) 11.58 (0.10) Week 4 10.82 (0.09) 10.52 (0.10) 10.26 (0.11) Change from baseline −0.76 (0.07) −1.19 (0.07) −1.32 (0.09) Adjusted change from baseline * (95% CI) −0.77 (−0.90, −0.64) −1.17 (−1.30, −1.04) −1.33 (−1.50, −1.16) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.59, −0.22) † −0.56 (−0.78, −0.35) † Mean level of urgency (FAS) Baseline 2.39 (0.02) 2.42 (0.02) 2.46 (0.02) Final Visit 2.25 (0.02) 2.15 (0.02) 2.19 (0.02) Change from baseline −0.14 (0.02) −0.27 (0.02) −0.27 (0.02) Adjusted change from baseline * (95% CI) −0.15 (−0.18, −0.12) −0.26 (−0.30, −0.23) −0.26 (−0.30, −0.22) Adjusted difference vs. placebo * (95% CI) – −0.11 (−0.16, −0.07) † −0.11 (−0.16, −0.06) † Mean number of urgency incontinence episodes/24 h (FAS−I) Baseline 2.42 (0.08) 2.42 (0.08) 2.53 (0.10) Final Visit 1.46 (0.08) 1.05 (0.07) 1.11 (0.09) Change from baseline −0.96 (0.08) −1.37 (0.07) −1.42 (0.09) Adjusted change from baseline * (95% CI) −0.98 (−1.10, −0.86) −1.38 (−1.50, −1.26) −1.38 (−1.53, −1.23) Adjusted difference vs. placebo * (95% CI) – −0.40 (−0.57, −0.23) † −0.40 (−0.60, −0.20) † Mean number of urgency episodes (PPIUS grade 3 or 4)/24 h (FAS) Baseline 5.61 (0.10) 5.80 (0.10) 5.96 (0.12) Final Visit 4.38 (0.11) 3.85 (0.11) 4.02 (0.13) Change from baseline −1.23 (0.10) −1.95 (0.10) −1.94 (0.12) Adjusted change from baseline * (95% CI) −1.29 (−1.47, −1.11) −1.93 (−2.11, −1.75) −1.89 (−2.11, −1.66) Adjusted difference vs. placebo * (95% CI) – −0.64 (−0.89, −0.39) † −0.60 (−0.89, −0.31) † Additional secondary end-points Change from baseline to Final Visit in mean number of nocturia episodes/24 h (FAS) Baseline 2.18 (0.04) 2.22 (0.04) 2.25 (0.05) Final Visit 1.78 (0.04) 1.66 (0.04) 1.71 (0.05) Change from baseline −0.41 (0.04) −0.56 (0.04) −0.54 (0.04) Adjusted change from baseline * (95% CI) −0.42 (−0.48, −0.35) −0.55 (−0.62, −0.49) −0.54 (−0.62, −0.46) Adjusted difference vs. placebo * (95% CI) – −0.14 (−0.23, −0.05) ‡ −0.12 (−0.23, −0.02) ‡ Change from baseline to Final Visit in TS-VAS (FAS) Baseline 4.87 (0.11) 4.82 (0.11) 4.43 (0.13) Final Visit 6.05 (0.10) 6.79 (0.09) 6.94 (0.11) Change from baseline 1.18 (0.11) 1.96 (0.12) 2.51 (0.14) Adjusted change from baseline * (95% CI) 1.25 (1.08, 1.42) 2.01 (1.84, 2.19) 2.33 (2.11, 2.55) Adjusted difference vs. placebo * (95% CI) – 0.76 (0.52, 1.01) ‡ 1.08 (0.80, 1.37) ‡ All values mean (SE) unless otherwise stated. * Estimates are based on an analysis of covariance model, which included treatment group, gender and study as fixed factors, and baseline as a covariate. † p < 0.05 vs. placebo with multiplicity adjustment. ‡ p < 0.05 vs. placebo without multiplicity adjustment. Figure 3Adjusted mean change from baseline (±SE) by time point in the mean number of incontinence episodes/24 h for the pooled placebo, mirabegron 50 and 100 mg groups (FAS-I). #Statistically significant treatment benefit relative to placebo (p < 0.05) with multiplicity adjustment. Statistically significant treatment benefit relative to placebo (p < 0.05) without multiplicity adjustment. SE, standard error; FAS-I, full analysis set-incontinence. Figure 4Adjusted mean change from baseline (±SE) by time point in mean number of micturitions/24 h for the pooled placebo, mirabegron 50 and 100 mg groups (FAS). #Statistically significant treatment benefit relative to placebo (p < 0.05) with multiplicity adjustment. Statistically significant treatment benefit relative to placebo (p < 0.05) without multiplicity adjustment. SE, standard error; FAS, full analysis set. The key secondary end-points, change from baseline to week 4 (first time point assessed) in the mean number of incontinence episodes/24 h and mean number of micturitions/24 h, were significantly improved for both mirabegron doses compared with placebo (p < 0.05, all comparisons; Table 2 and Figures 3 and 4, respectively). The adjusted mean (95% CI) change from baseline to week 4 in the mean number of incontinence episodes/24 h was −0.67 (−0.81, −0.54), −1.12 (−1.26, −0.98) and −1.09 (−1.27, −0.92) in the placebo, mirabegron 50 and 100 mg groups, respectively. The adjusted mean (95% CI) change from baseline to week 4 in the mean number of micturitions/24 h was −0.77 (−0.90, −0.64), −1.17 (−1.30, −1.04) and −1.33 (−1.50, −1.16) in the placebo, mirabegron 50 and 100 mg groups, respectively. Both 50 and 100 mg mirabegron doses were associated with statistically significant improvements from baseline to Final Visit compared with placebo for the key secondary efficacy end-points of mean volume voided/micturition (p < 0.05 for all comparisons; Table 2), mean level of urgency, mean number of urgency episodes (grade 3 or 4)/24 h and mean number of urgency incontinence episodes/24 h (p < 0.05 for all comparisons; Table 2 and Figure 5). Figure 5Adjusted mean change from baseline to Final Visit (SE) in key secondary end-points: (A) mean level of urgency (FAS) (B) number of urgency episodes/24 h (FAS) and number of urgency incontinence episodes/24 h (FAS-I). #Statistically significant treatment benefit compared with placebo (p < 0.05) with multiplicity adjustment. SE, standard error; FAS, full analysis set; FAS-I, full analysis set-incontinence. Significant improvements were also evident in the pooled efficacy analysis with respect to the change from baseline to Final Visit (95% CI) in the mean number of nocturia episodes/24 h in the mirabegron 50 mg [−0.55 (−0.62, −0.49)] and mirabegron 100 mg groups [−0.54 (−0.62, −0.46)] vs. placebo [−0.42 (−0.48, −0.35)] (p < 0.05; Table 2). For the responder analyses, the percentage of patients with zero incontinence episodes at Final Visit ('dry rate') was significantly higher in the mirabegron 50 and 100 mg groups (44.1% and 46.4%, respectively) compared with placebo (37.8%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.32 (1.08, 1.61) and 1.58 (1.25, 2.00), respectively (p < 0.05). The percentage of patients with a ≥ 50% reduction from baseline to Final Visit in mean number of incontinence episodes/24 h was also significantly higher in the mirabegron 50 and 100 mg groups (69.5% and 70.5%, respectively) compared with placebo (59.6%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.54 (1.26, 1.89) and 1.64 (1.29, 2.07), respectively (p < 0.05). In the post hoc responder analysis, both 50 and 100 mg mirabegron doses were also associated with a significant improvement in 'micturition normalisation' (i.e. the percentage of patients with ≤ 8 micturitions/24 h) at Final Visit (31.6% and 34.0%) compared with placebo (24.6%). The corresponding odds ratios (95% CI) for the mirabegron 50 and 100 mg groups were 1.57 (1.30, 1.89) and 1.69 (1.37, 2.09), respectively (p < 0.05). In health-related quality of life outcomes, mirabegron 50 and 100 mg was associated with a statistically significant improvement in the TS-VAS score at Final Visit compared with placebo (p < 0.05; Table 2). The adjusted mean (95% CI) changes from baseline to Final Visit were 1.25 (1.08, 1.42), 2.01 (1.84, 2.19) and 2.33 (2.11, 2.55) for the placebo, mirabegron 50 and 100 mg groups, respectively.\n\nBODY.RESULTS.EFFICACY IN PATIENTS WITH PRIOR ANTIMUSCARINIC USE AND TREATMENT-NAÏVE PATIENTS:\nBoth mirabegron 50 and 100 mg doses improved the co-primary end-points in patients who had discontinued previous antimuscarinic medication and in treatment-naïve patients. The adjusted mean difference (95% CI) from baseline to Final Visit in the mean number of incontinence episodes/24 h in patients who had discontinued previous antimuscarinic medication was −0.92 (−1.09, −0.75), −1.49 (−1.66, −1.32) and −1.42 (−.64, −1.21) in the placebo, mirabegron 50 mg and mirabegron 100 mg groups, respectively, and −1.35 (−1.55, −1.14), −1.50 (−1.71, −1.29) and −1.62 (−1.87, −1.36) in treatment-naïve patients. The adjusted mean difference (95% CI) in the mean number of micturitions/24 h from baseline to Final Visit in the placebo, mirabegron 50 and 100 mg groups, respectively, was −0.93 (−1.12, −0.74), −1.67 (−1.86, −1.48) and −1.61 (−1.85, −1.37) in patients who discontinued previous antimuscarinic therapy, and −1.51 (−1.71, −1.31), −1.84 (−2.04, −1.64) and −1.87 (−2.12, −1.63) in treatment-naïve patients. The adjusted mean difference vs. placebo in patients who discontinued previous antimuscarinic therapy was of a greater magnitude than in treatment-naïve patients because of the higher placebo response in treatment-naïve patients.\n\nBODY.RESULTS.SAFETY OUTCOMES:\nThe overall incidence of TEAEs was similar across treatment groups (Table 3) and there was no evidence of a dose–response relationship across the mirabegron treatment groups for overall rates of TEAEs: placebo (47.7%), mirabegron 25 mg (48.6%), mirabegron 50 mg (47.1%), mirabegron 100 mg (43.3%), total mirabegron (46.0%) and tolterodine ER 4 mg (46.7%). The most common TEAEs reported in ≥ 3% of the total mirabegron group were hypertension, nasopharyngitis and urinary tract infection (Table 3). The incidence of hypertension and urinary tract infection decreased as the dose of mirabegron increased from 25 to 100 mg. The most common drug-related TEAEs in the mirabegron groups were hypertension and headache, which were of similar incidence with placebo and tolterodine, with the exception of dry mouth, which was at placebo level for mirabegron but of a higher magnitude in the tolterodine group (Table 3). The majority of AEs were of mild or moderate severity across treatment groups. Table 3 Overview of treatment-emergent adverse events in the pooled safety analysis (SAF) Mirabegron Number of patients (%) Placebo ( n = 1380) 25 mg ( n = 432) 50 mg ( n = 1375) 100 mg ( n = 929) Total ( n = 2736) Tolterodine ER 4 mg ( n = 495) Any TEAE 658 (47.7) 210 (48.6) 647 (47.1) 402 (43.3) 1259 (46.0) 231 (46.7) Drug-related TEAE 232 (16.8) 87 (20.1) 256 (18.6) 172 (18.5) 515 (18.8) 131 (26.5) TEAE leading to discontinuation 46 (3.3) 17 (3.9) 53 (3.9) 34 (3.7) 104 (3.8) 22 (4.4) Drug-related TEAE leading to discontinuation 27 (2.0) 11 (2.5) 35 (2.5) 25 (2.7) 71 (2.6) 20 (4.0) SAE 29 (2.1) 7 (1.6) 29 (2.1) 26 (2.8) 62 (2.3) 11 (2.2) Drug-related SAE 6 (0.4) 3 (0.7) 7 (0.5) 3 (0.3) 13 (0.5) 6 (1.2) Common TEAEs by preferred term (reported by ≥ 3% in total mirabegron group) Hypertension 105 (7.6) 49 (11.3) 103 (7.5) 48 (5.2) 200 (7.3) 40 (8.1) Nasopharyngitis 35 (2.5) 15 (3.5) 54 (3.9) 25 (2.7) 94 (3.4) 14 (2.8) Urinary tract infection 25 (1.8) 18 (4.2) 40 (2.9) 25 (2.7) 83 (3.0) 10 (2.0) Antimuscarinic AEs of interest by preferred term (reported by ≥ 2% in any group) Headache 43 (3.1) 10 (2.3) 47 (3.4) 23 (2.5) 80 (2.9) 18 (3.6) Dry mouth 29 (2.1) 8 (1.9) 23 (1.7) 23 (2.5) 54 (2.0) 50 (10.1) Constipation 20 (1.4) 7 (1.6) 22 (1.6) 15 (1.6) 44 (1.6) 10 (2.0) Drug-related * \n TEAEs by preferred term (reported by ≥ 2% in any group) Hypertension 63 (4.6) 30 (6.9) 65 (4.7) 32 (3.4) 127 (4.6) 30 (6.1) Headache 18 (1.3) 4 (0.9) 28 (2.0) 12 (1.3) 44 (1.6) 11 (2.2) Dry mouth 22 (1.6) 7 (1.6) 13 (0.9) 20 (2.2) 40 (1.5) 47 (9.5) SAF, safety analysis set; ER, extended release; TEAE, treatment-emergent adverse event; SAE, serious adverse event. * Possible or probable, as assessed by the investigator, or records where relationship was missing. The proportion of patients discontinuing study drug because of TEAEs was low and similar across each group: placebo (3.3%), mirabegron 25 mg (3.9%), mirabegron 50 mg (3.9%), mirabegron 100 mg (3.7%), total mirabegron (3.8%) and tolterodine ER 4 mg (4.4%). The incidence of serious AEs was also low and similar between placebo and mirabegron groups: placebo (2.1%), mirabegron 25 mg (1.6%), mirabegron 50 mg (2.1%), mirabegron 100 mg (2.8%), total mirabegron (2.3%) and tolterodine ER 4 mg (2.2%). Three deaths were reported in this pooled 12-week safety analysis: in the placebo group, a 76-year-old woman died as a result of cardiac arrest 56 days after the last dose of study drug; in the mirabegron 100 mg group, a 66-year-old woman died because of metastatic colon cancer 30 days after the last dose of study drug – neither case was considered to be related to study drug – and in the tolterodine ER 4 mg group, a 74-year-old man died because of a ruptured cerebral aneurysm on day 70 (treatment-emergent), 10 days after the last dose of study drug was administered, and was considered as possibly related to study drug. In terms of vital sign measurements for blood pressure and pulse rate, the adjusted mean difference vs. placebo for change from baseline to Final Visit in SBP and DBP (AM and PM measurements) was negligible and comparable across each mirabegron group and the tolterodine ER 4 mg group. The adjusted mean difference vs. placebo for change from baseline to Final Visit in pulse rate (AM and PM measurements) increased dose-dependently by 0.6–2.3 bpm in the mirabegron groups and by 1.0–2.1 bpm in the tolterodine ER 4 mg group (Table 4). The overall occurrence of tachycardia events, either based on TEAE and/or observations of pulse rate ≥ 100 bpm captured by patient diary, was less than 5% in each treatment group and comparable with placebo (Table 4). ECG findings revealed no overt trends in central tendency or categorical outliers for QTc interval assessment across treatment groups. Changes in haematology and serum chemistry, including renal parameters, were small and comparable across treatment groups. Table 4 Summary of changes from baseline to Final Visit in blood pressure and pulse rate Placebo ( n = 1380) Mirabegron 25 mg ( n = 432) Mirabegron 50 mg ( n = 1375) Mirabegron 100 mg ( n = 929) Tolterodine ER 4 mg ( n = 495) AM PM AM PM AM PM AM PM AM PM Blood pressure (mmHg) SBP N 1329 1326 410 410 1327 1327 891 890 476 476 Baseline, mean (SE) 125.9 (0.47) 125.0 (0.41) 129.2 (0.81) 129.0 (0.71) 126.4 (0.47) 125.6 (0.43) 125.0 (0.55) 123.7 (0.49) 128.2 (0.75) 127.4 (0.64) Final Visit, mean (SE) 126.2 (0.45) 125.7 (0.41) 128.8 (0.75) 128.3 (0.67) 127.2 (0.46) 126.6 (0.41) 125.6 (0.51) 125.2 (0.46) 128.4 (0.70) 127.9 (0.63) Adjusted change from baseline, mean (SE), (95% CI) † 0.2 (0.25), (−0.3, 0.7) 0.6 (0.25), (0.1, 1.1) −0.3 (0.52), (−1.3, 0.7) −0.5 (0.53), (−1.5, 0.6) 0.8 (0.25), (0.3, 1.3) 1.1 (0.25), (0.6, 1.6) 0.6 (0.32), (−0.0, 1.2) 1.4 (0.33), (0.8, 2.1) 0.1 (0.45), (−0.8, 1.0) 0.5 (0.46), (−0.4, 1.4) Difference vs. placebo, mean (SE), (95% CI) ‡ – – −0.5 (0.57), (−1.6, 0.6) −1.0 (0.58), (−2.2, 0.1) 0.6 (0.35), (−0.1, 1.3) 0.5 (0.36), (−0.2, 1.2) 0.4 (0.41), (−0.4, 1.2) 0.9 (0.42), (0.1, 1.7) −0.1 (0.52), (−1.1, 1.0) −0.0 (0.53), (−1.1, 1.0) DBP N 1329 1326 410 410 1327 1327 890 890 476 476 Baseline, mean (SE) 77.1 (0.26) 75.3 (0.23) 78.2 (0.48) 76.1 (0.46) 77.2 (0.25) 75.4 (0.24) 77.4 (0.30) 75.3 (0.28) 76.8 (0.40) 75.4 (0.38) Final Visit, mean (SE) 77.2 (0.25) 75.7 (0.24) 77.6 (0.43) 75.7 (0.42) 77.6 (0.24) 76.2 (0.24) 77.7 (0.28) 76.3 (0.28) 77.7 (0.39) 76.6 (0.36) Adjusted change from baseline, mean (SE), (95% CI) † 0.0 (0.16), (−0.3, 0.3) 0.4 (0.16), (0.1, 0.7) −0.1 (0.33), (−0.8, 0.5) 0.1 (0.34), (−0.6, 0.7) 0.4 (0.16), (0.1, 0.7) 0.7 (0.16), (0.4, 1.1) 0.2 (0.21), (−0.2, 0.6) 0.9 (0.21), (0.5, 1.3) 0.8 (0.29), (0.2, 1.3) 1.4 (0.30), (0.8, 2.0) Difference vs. placebo, mean (SE), (95% CI) ‡ – – −0.1 (0.37), (−0.9, 0.6) −0.3 (0.37), (−1.0, 0.4) 0.4 (0.22), (−0.1, 0.8) 0.4 (0.23), (−0.1, 0.8) 0.2 (0.26), (−0.3, 0.7) 0.5 (0.27), (−0.0, 1.0) 0.7 (0.33), (0.1, 1.4) 1.0 (0.34), (0.4, 1.7) Pulse rate (bpm) N 1329 1326 410 410 1327 1327 891 890 476 476 Baseline, mean (SE) 70.5 (0.28) 75.3 (0.29) 71.0 (0.50) 75.5 (0.51) 70.4 (0.28) 74.9 (0.28) 70.4 (0.34) 74.4 (0.34) 69.8 (0.44) 73.9 (0.45) Final Visit, mean (SE) 70.9 (0.29) 74.7 (0.29) 71.7 (0.52) 75.3 (0.53) 71.8 (0.29) 75.5 (0.28) 72.9 (0.34) 76.5 (0.34) 71.4 (0.44) 76.0 (0.45) Adjusted change from baseline, mean (SE), (95% CI) † 0.4 (0.17), (0.1, 0.8) −0.4 (0.18), (−0.8, −0.1) 1.3 (0.36), (0.6, 2.0) 0.2 (0.37), (−0.6, 0.9) 1.4 (0.17), (1.1, 1.8) 0.6 (0.18), (0.2, 0.9) 2.3 (0.22), (1.9, 2.8) 1.9 (0.23), (1.4, 2.3) 1.4 (0.31), (0.8, 2.0) 1.7 (0.32), (1.1, 2.3) Difference vs. placebo, mean (SE), (95% CI) ‡ – – 0.9 (0.40), (0.1, 1.6) 0.6 (0.41), (−0.2, 1.4) 1.0 (0.24), (0.5, 1.5) 1.0 (0.25), (0.5, 1.5) 1.9 (0.28), (1.3, 2.5) 2.3 (0.29), (1.7, 2.9) 1.0 (0.36), (0.3, 1.7) 2.1 (0.37), (1.4, 2.8) Incidence of tachycardia (%) * Tachycardia events, N (%) 43 (3.1) 21 (4.9) 52 (3.8) 43 (4.6) 16 (3.2) SBP, systolic blood pressure; DBP, diastolic blood pressure. * Based on TEAE and/or observations of pulse rate ≥ 100 bpm captured by patient diary. † Adjusted change from baseline is generated from the ANCOVA model with treatment group, gender and study as fixed factors, and baseline as a covariate. ‡ Differences in the adjusted means are calculated by subtracting the adjusted mean of placebo from the adjusted mean of treatment group. With respect to other events of interest, the incidence of urinary retention was infrequent in the studies and less in mirabegron-treated patients than in placebo or tolterodine-treated patients: placebo (n = 7; 0.5%), mirabegron 25 mg (n = 0), mirabegron 50 mg (n = 1; 0.1%), mirabegron 100 mg (n = 0), total mirabegron (n = 1; < 0.1%) and tolterodine (n = 3; 0.6%). The mean change from baseline to Final Visit in PVR volume was unremarkable across treatment groups: placebo (−1.6 ml), mirabegron 25 mg (−3.0 ml), mirabegron 50 mg (−0.9 ml), mirabegron 100 mg (−0.7 ml) and tolterodine ER 4 mg (+ 0.1 ml). The proportion of patients experiencing ≥ 150 ml change from baseline in PVR volume was lower in the mirabegron groups compared with placebo and tolterodine: placebo (0.7%), mirabegron 25 mg (0%), mirabegron 50 mg (0.3%), mirabegron 100 mg (0.4%) and tolterodine ER 4 mg (0.8%).\n\nBODY.DISCUSSION:\nMirabegron, a β3-adrenoceptor agonist, is approved for the treatment of OAB symptoms in Japan, the USA, Canada and Europe, and has a different mechanism of action from the antimuscarinic agents currently available. Mirabegron facilitates detrusor relaxation during the storage phase of the micturition cycle and, in contrast with antimuscarinic agents, improves the storage capacity of the bladder without impairing the amplitude of the contraction during the voiding phase of the micturition cycle 25. In this pooled analysis of three international phase III studies 21–23, a total of 3542 OAB patients were included in the efficacy analysis, and 4611 OAB patients in the safety analysis, reflective of the general OAB population. More than half of these patients were randomised to mirabegron for 12 weeks at doses of 25, 50 and 100 mg. Furthermore, this pooled dataset included approximately 50% of OAB patients who had been previously treated with antimuscarinic agents but had discontinued either because of insufficient efficacy and/or poor tolerability. In OAB patients, mirabegron 50 and 100 mg demonstrated significant and clinically meaningful efficacy in terms of improving the symptoms of OAB, including incontinence episodes, micturition frequency and urgency, which are recognised by international guidelines as important outcome measures for OAB therapies 26. The benefit of mirabegron is evident in both treatment-naïve and previous OAB-treated patients. This is a clinically relevant observation, given the poor persistence rate associated with antimuscarinic drugs – discontinuation rates above 50% and 75% have been reported at 6 months and 1 year, respectively 27,28 – and the fact that, in addition to bothersome AEs (e.g., dry mouth), inadequate response to treatment is an underlying reason for discontinuation of antimuscarinic treatment 27,29–31. Both 50 and 100 mg doses of mirabegron demonstrated significant improvements compared with placebo for all of the key secondary end-points, including measures of urgency (the core symptom of OAB), and mean volume voided/micturition. Across primary and key secondary end-points, significant improvements with both mirabegron doses were evident at the first assessment period (week 4) and were maintained throughout the 12-week treatment period – an earlier benefit cannot be ruled out but was not assessed prior to the initial 4-week evaluation. Responder analyses showed a significant improvement with mirabegron 50 and 100 mg in terms of dry rates, ≥ 50% reduction in mean number of incontinence episodes/24 h and the proportion of patients with ≤ 8 micturitions/24 h at Final Visit. Taken together, these data demonstrate a clinically meaningful benefit with mirabegron in the objective end-points of OAB. As OAB is a symptom complex, it can be difficult to determine the efficacy of treatments using objective measures alone. Hence, patient-reported outcomes are increasingly important in the assessment of treatments for symptom-based conditions such as OAB 4. The TS-VAS scores for the 50 and 100 mg mirabegron doses were significantly better and approximately one point higher than patients receiving placebo and reflect the directional parallelism of the subjective and objective improvements in OAB symptoms. The mirabegron 100 mg dose does not appear to afford a greater efficacy benefit than the 50 mg dose for reduction in incontinence episodes or micturition frequency vs. placebo. A dose–response effect was not evident with the 50 and 100 mg doses across the co-primary and secondary end-points. Although data from the 25 mg mirabegron arm 23 were not included in the pooled efficacy analysis, 25 mg is the recommended starting dose in the USA. In the NCT00912964 phase III study, mirabegron 25 mg showed clinically significant efficacy compared with placebo for the co-primary end-points; however, for the majority of the secondary end-points it did not demonstrate significance vs. placebo 23. In terms of the safety and tolerability profile of mirabegron, the pooled analysis confirms the results of the individual phase III studies 21–23. The most common AEs (> 3% of total mirabegron group) were hypertension, nasopharyngitis and urinary tract infection. The incidence of hypertension and urinary tract infection decreased as the mirabegron dose increased and both incidences in the total mirabegron group were similar to placebo or tolterodine. The incidence of the most bothersome AE for antimuscarinic drugs, dry mouth, was at placebo level with each mirabegron dose and lower than tolterodine. This finding is consistent with previous randomised, controlled trials of other antimuscarinic therapies, which have reported even higher incidences of dry mouth (9–93%); these studies have also reported high incidences of constipation (4–21%) 32–41. Given that dry mouth is the chief cause of discontinuation because of poor tolerability with antimuscarinic drugs 27,29, the pooled safety data indicate that mirabegron may be a valuable treatment option for patients with OAB. The pooled safety analysis offers more precise estimates of certain safety parameters, such as vital signs and AEs related to cardiovascular safety, than the individual phase III studies. In this pooled analysis, mirabegron was associated with approximate increases of ≤ 1 mmHg in blood pressure and ≥ 1 bpm in pulse rate vs. placebo. The incidence of hypertension was similar among the total mirabegron group, placebo and tolterodine. The incidence of urinary retention was greater in the placebo and tolterodine groups than in mirabegron-treated patients. ECG, PVR volume and laboratory data were unremarkable across each treatment group. Overall, the data support the good safety profile of mirabegron based on this pooled phase III clinical study dataset.\n\nBODY.CONCLUSIONS:\nMirabegron, a β3-adrenoceptor agonist, and the first in its class for the treatment of OAB symptoms, has a distinct mechanism of action from antimuscarinic agents, the current pharmacological mainstay in treating OAB. In these pooled analyses of efficacy and safety, mirabegron administered at daily doses of 50 and 100 mg for 12 weeks demonstrated significant and clinically meaningful improvement in treating the symptoms of OAB, including urinary incontinence, micturition frequency and urgency. Mirabegron was beneficial in both treatment-naïve patients and in patients who used prior antimuscarinic treatment. The improvement in OAB symptoms measured objectively was reflected in the improvement in the patient-reported outcome related to treatment satisfaction. Mirabegron was well tolerated with an incidence of dry mouth at placebo level and lower than tolterodine. Mirabegron represents a new therapeutic in a new class of medication for the treatment of OAB and has demonstrable efficacy and tolerability in a large clinical trial dataset in OAB patients. In clinical practice, mirabegron will provide a valuable treatment option for OAB syndrome.\n\nQuestion: Compared to placebo what was the result of mirabegron (50 and 100 mg) on mean volume voided/micturition, mean level of urgency, mean number of urgency episodesand mean number of urgency incontinence episodes/24 h?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1180	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Effects of a balance-based exergaming intervention using the Kinect sensor on posture stability in individuals with Parkinson’s disease: a single-blinded randomized controlled trial\n\n ABSTRACT.BACKGROUND:\nThe present study examined the effects of a balance-based exergaming intervention using the Kinect sensor on postural stability and balance in people with Parkinson's disease (PD).\n\nABSTRACT.METHODS:\nWe conducted a subject-blinded, randomized controlled study. Twenty people with PD (Hoehn and Yahr stages I through III) were recruited and randomly assigned to either a balance-based exergaming group (N = 10) or a balance training group (N = 10) for an 8-week balance training period. Postural stability was assessed using the limits of stability (LOS) and one-leg stance (OLS) tests. Balance was assessed using the Berg Balance Scale (BBS) and the timed up and go (TUG) test. Participants were assessed pre- and post-training.\n\nABSTRACT.RESULTS:\nAfter training, participants in the balance-based exergaming group showed significant improvements in LOS performance, and in the eyes-closed condition of the OLS test. Both training programs led to improvements in BBS and TUG performance. Furthermore, balance-based exergaming training resulted in significantly better performance in directional control in the LOS test (78.9 ± 7.65 %) compared with conventional balance training (70.6 ± 9.37 %).\n\nABSTRACT.CONCLUSIONS:\nBalance-based exergaming training resulted in a greater improvement in postural stability compared with conventional balance training. Our results support the therapeutic use of exergaming aided by the Kinect sensor in people with PD.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov.NCT02671396\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nThe online version of this article (doi:10.1186/s12984-016-0185-y) contains supplementary material, which is available to authorized users.\n\nBODY.BACKGROUND:\nPeople with idiopathic Parkinson's disease (PD) commonly exhibit postural instability during daily activities [1]. PD-related balance impairment is associated with a loss of mobility and increased likelihood of falls, and can cause marked disability [2, 3]. To ameliorate postural instability, techniques using external feedback with cueing or sensory stimuli have been investigated [4, 5]. Several studies suggest that external feedback may initiate other neural pathways and play a significant role in the volitional control of movements for people with PD [6, 7]. Virtual reality (VR) technologies such as exergaming may have therapeutic value in the treatment of postural instability [8–10]. VR is a technology that allows the user to interact directly with a computer-simulated environment [11]. Exergames are computer games that are controlled by body movements. VR and exergaming can provide augmented feedback in real time, while a person performs specific motor tasks [12]. Opportunities for repeated accurate performance can be incorporated into VR and exergaming to enhance motor learning [7, 13]. Moreover, VR games can be effective for retaining participants' interest and motivation. A recent meta-analysis suggested that exergaming may provide an appropriate training approach to improve balance and functional mobility in healthy older people [14]. These findings raise the possibility that exergaming might also provide an approach for improving postural instability for people with PD. A previous study examined the effects a 6-week home-based balance training program using the Wii Fit game for a total of 18 training sessions on balance and functional abilities in people with PD, compared with a group of paired healthy participants [15]. Another study investigated the effects of Wii-based training compared with conventional balance training for 7 weeks (a total of 14 training sessions) on activities of daily living in people with PD [16]. Both studies revealed positive effects of exergaming on balance, functional abilities and activities of daily living among people with PD. However, positive effects were found only within groups, with no between-group differences observed in a comparison with the control group. The absence of between-group differences may have resulted from an inability to capture the full-body motion involved in postural control, or the lack of a sufficiently sensitive sensor to accurately measure motion. The shortcomings of the Wii system's sensors may limit its potential as an effective intervention [17]. A new exergaming system was recently developed using the Kinect sensor. The Kinect sensor is a low-cost device that can provide measurements for most of the main human joints. Previous studies reported that a kinematic measurement method using the Kinect sensor was accurate and reliable for measuring postural control [18, 19]. These findings suggest that the Kinect sensor could provide a useful tool for therapeutic use. However, there has been little research into the therapeutic use of the Kinect sensor to date. The present study sought to test a therapeutic application of exergaming using the Kinect sensor. We examined the effects of an 8-week balance-based exergaming program developed in our lab, compared with an 8-week period of conventional balance training (16 training sessions), on postural stability and balance in people with PD. We hypothesized that participants who underwent an 8-week balance-based exergaming intervention would demonstrate superior performance on measures of postural stability and balance, compared with those who received balance training.\n\nBODY.METHODS.PARTICIPANTS:\nParticipants were recruited from Mackay Memorial Hospital in Taipei. Outpatients with PD were informed about the study by a neurologist. Eligibility required a diagnosis of idiopathic PD according to the United Kingdom Brain Bank Criteria [20] by the same neurologist. Information on age, gender, the more affected side, and disease duration were obtained through patient interviews and from medical charts. All participants met the following inclusion criteria: (1) Hoehn and Yahr stages I through III, (2) a score of ≥ 24 on the mini-mental state examination, (3) stable medication usage and (4) standing unaided to perform the measurement and training. The exclusion criteria were as follows: (1) histories of other neurological, cardiovascular, or orthopedic diseases affecting postural stability and (2) uncontrolled chronic diseases. In total, 48 individuals were identified as potential participants for this study. Of these, 22 participants gave informed consent and participated in the study.\n\nBODY.METHODS.STUDY DESIGN:\nThis study was a subject-blinded, randomized controlled trial. The study protocol was approved by the Institutional Review Board of Mackay Memorial Hospital (reference number: 13MMHIS120) and was explained to all participants before their participation. The study was performed in accordance with the Declaration of Helsinki. Block randomization was used to assign participants to either the balance-based exergaming (BE) or the conventional balance training (BT) group. Assignment was performed by an independent person who selected one of a set of sealed envelopes 30 min before the intervention began. Participants in the BE and BT groups received an 8-week balance-based exergaming intervention, and conventional balance training, respectively. Measures of postural stability and functional balance were measured pre- and post-training. The measurement and intervention were conducted with participants in the \"on\" state, when they were moving freely and easily without dystonia, excessive rigidity or tremor. The data were collected in a university laboratory.\n\nBODY.METHODS.INTERVENTION:\nParticipants in both groups underwent balance training for 50 min per session, two sessions every week, for 8 weeks. Each training session began with a 10-min warm-up and ended with a 10-min cool-down. Both the warm-up and cool-down periods focused on stretching exercises of the trunk and extremities. Participants in the BE group received a 30-min balance-based exergaming intervention using the Kinect sensor (Microsoft Corporation, Redmond, WA, USA). The Kinect sensor incorporates infrared light and a video camera, which creates a 3D map of the area in front of it. This device provides full-body 3D motion capture. Four exergaming programs were used for training (Fig. 1), designed to incorporate an appropriate level of challenge to match the ability and fitness of people with PD. The first program was called Reaching task 1. In this task, participants were asked to reach toward a stationary target at a given location. The second program was called Reaching task 2. Participants were asked to track a moving object by lengthening the arm and immersing the hand into the object as it flew in 3D space. The third program was called Obstacle avoidance. Participants were instructed to avoid upcoming obstacles that approached from varying directions at random, by moving the body right/left or up/down. The final task was called Marching. Participants were instructed to step alternately without going forward or backward while following dynamic bars that were automatically rising and falling at a predetermined speed and frequency. During the training duration, the challenge level was increased progressively by adjusting the amplitude, frequency, speed, complexity and number of hints. The details of the exergaming programs are shown in Table 1.Fig. 1Screen shots of interaction with the exergaming program. Four exergaming programs, Reaching task 1 (a), Reaching task 2 (b), Obstacle avoidance (c) and Marching (d), were designed and used for trainingTable 1Program of balance-based exergaming interventionProgramActionProgressionMotor demandReaching task 1Standing in a given area and reaching toward a stationary target at different heights, depths and in different directions• Reaching length• Number of targets• Range of distribution• Amount of repetition• Weight shifting• Challenging limits of stability• Functional transitionsReaching task 2Standing in a given area and tracking a moving object while extending arm and immersing the hand into the object as it flew in 3D space• Speed• Moving range• Pathway pattern• Remembered sequence or course of trajectory• Weight shifting• Arm coordination• Advance motor planningObstacle avoidanceStanding in a given area and preparing to avoid upcoming obstacles that randomly approached from varying directions by moving body sideways or up/down• Obstacle hitting ratio• Speed• Dual task• Hitting direction• Quick change strategy• Movement adaption• AgilityMarchingAlternating steps without going forward while following dynamic bars that automatically rose and fell at a predetermined speed and frequency• Frequency• Gap between steps• Functional stepping• Leg coordination• Single limb support Participants in the BT group underwent a 30-min conventional balance training session. The training program included reaching activities, weight-shifting activities and marching activities. The general training protocols used for the BT group were the same as those used for the BE group. The challenge level was increased progressively by changing the base of support, speed, complexity and deprivation of sensory inputs.\n\nBODY.METHODS.OUTCOME MEASURES.POSTURAL STABILITY:\nThe limits of stability (LOS) and one-leg stance (OLS) tests were used to assess postural stability in this study. Participants were harnessed into a suspension system to prevent falls when performing the tasks. LOS performance was measured using the Smart Balance Master (NeuroCom International Inc., Clackamas, OR, USA) instrument to extract quantitative data [21–24]. The LOS test provides an assessment of the ability to intentionally displace the center of gravity (COG) to the participant's stability limits without losing balance. In this task, participants were asked to quickly transfer their COG, while standing on stable force plates, toward eight targets spaced at 45° intervals around the COG, represented on a computer monitor. All participants underwent one practice trial followed by one test trial. In the LOS test, we measured reaction time (the time from the presentation of a start cue to the onset of the voluntary shifting of the participant's COG toward the target position), movement velocity (average speed of COG movement based on the middle 90 % of the distance, measured in degrees per second), end point excursion (percentage of the distance achieved toward a target on the initial movement) and directional control (100 % being a straight line from the center of pressure to the intended target). The validity and reliability of the LOS test in people with neurological disease has been well established [25–27]. The OLS test is an assessment of postural steadiness [15, 28–31]. Participants were asked to cross their arms over the chest, and to stand on either the less or more affected leg, with the other leg raised so that the raised foot was near but not touching the ankle of the stance leg. The assessor timed the OLS test until participants either: (1) uncrossed the arms, (2) moved the stance leg, (3) moved the raised leg touching the floor or the stance leg, (4) opened the eyes on eyes-closed trials or (5) reached a maximum of 30 s. Each participant performed three trials with the eyes open, and three trials with the eyes closed. Data were averaged from the three trials. A previous study found a high degree of reliability (ICC = 0.87) in the OLS test in older adults [32].\n\nBODY.METHODS.OUTCOME MEASURES.FUNCTIONAL BALANCE:\nThe Berg Balance Scale (BBS) and the timed up and go (TUG) test were used to assess functional balance. The BBS comprises a set of 14 balance-related tasks, ranging from standing up from a sitting position, to standing on one foot. The degree of success in each task is given a score from zero (unable) to four (independent), and the final measure is the sum of all scores. The highest possible score on the BBS is 56, which indicates excellent balance. The validity and reliability (ICC > 0.95) of BBS scores in people with PD has been established in several studies [33–35]. The TUG test is a mobility test requiring both static and dynamic balance. During the test, the assessors measured the time participants took to rise from a chair, walk 3 meters, turn around, walk back to the chair, and sit down. Each participant performed three trials of the TUG test. Data were averaged from the three trials. The TUG test has previously been found to have high validity and reliability (ICC > 0.87) for assessing balance in people with PD [36, 37].\n\nBODY.METHODS.SAMPLE SIZE:\nThe sample size calculation was based on a pilot study that tested eight participants at Hoehn and Yahr stages 1 and 2, indicating a difference of 0.2 s between pre- and post-training on reaction time in the LOS test. Based on this difference, a sample size calculation indicated that 20 participants would be sufficient for 85 % power (α = 0.05).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nAll analyses were performed using the SPSS 20.0 statistical package (SPSS Inc., Chicago, IL, USA). Descriptive statistics were generated for all variables, and distributions of variables were expressed as the mean ± standard deviation. Because of the relatively small number of participants included in the current study (N < 30) and since the results of a Shapiro-Wilk test did not allow us to assume that the data were normally distributed, nonparametric tests were employed. Comparison of two groups for general characteristics was made using chi-square or Mann-Whitney U test for categorical or continuous variables, respectively. The Friedman test, followed by a post hoc test, was used to determine differences in each dependent variable. The Wilcoxon signed-rank post hoc test was performed for within-group comparisons and the Mann-Whitney U post hoc test was performed for between-group comparisons. The statistical significance was set at P ≤ 0.05.\n\nBODY.RESULTS:\nA total of 48 individuals were screened and 22 enrolled between 2013 and 2014. Of these, 11 were assigned to the BT group, and 11 were assigned to the BE group. Of 22 participants, two did not complete the intervention (one in the BT group and one in the BE group). A flow diagram of the study protocol is shown in Fig. 2. The 20 participants who completed the intervention attended all intervention sessions. None of the participants reported any adverse events.Fig. 2Flowchart of the experimental design The demographic characteristics of participants in both groups are presented in Table 2. Demographic differences between the two groups were not significant. Moreover, differences in all pre-intervention-selected outcome measures in the two groups were not significant (Table 3).Table 2Baseline demographics and clinical characteristics of the subjectsBalance-based exergaming group (N = 10)Balance training group (N = 10)\nP\nAge (years)67.5 ± 9.9668.8 ± 9.670.67Sex (male/female)9/17/30.58Disease duration (years)4.03 ± 3.745.22 ± 4.850.34Hoehn and Yahr stage1.6 ± 0.841.4 ± 0.520.73Mini-Mental State Examination27.4 ± 2.5928.2 ± 1.990.40More affected side (right/left)8/25/50.35Data are presented as the mean ± standard deviation or proportionTable 3Outcome measures for each groupBalance-based exergaming group (N = 10)Balance training group (N = 10)Friedman testPre-trainingPost-trainingPre-trainingPost-training\nP\nLimits of stability Reaction time (sec)0.96 ± 0.330.74 ± 0.240.88 ± 0.240.79 ± 0.18<0.001 Movement velocity (deg/sec)3.37 ± 1.353.83 ± 0.974.19 ± 1.544.57 ± 1.410.07 Endpoint excursion (%)75.2 ± 12.4884 ± 12.0479.7 ± 13.8481.8 ± 11.370.04 Directional control (%)75.7 ± 8.7878.9 ± 7.65,†\n70.9 ± 10.8570.6 ± 9.370.02One-leg stance Less affected with eyes open (sec)17.39 ± 12.8715.16 ± 10.539.14 ± 9.6312.98 ± 11.080.47 More affected with eyes open (sec)15.06 ± 11.2315.58 ± 11.5813.72 ± 12.4314.54 ± 9.650.09 Less affected with eyes closed (sec)3.35 ± 2.856.1 ± 8.652.71 ± 2.545.31 ± 7.680.002 More affected with eyes closed (sec)3.06 ± 2.554.13 ± 2.745.88 ± 7.566.66 ± 8.410.16Berg Balance Scale50.9 ± 5.3253.2 ± 2.8650.4 ± 4.7953 ± 1.890.001Timed up and go (sec)9.5 ± 2.458.71 ± 1.810.05 ± 4.669.18 ± 3.420.007Data are presented as mean ± standard deviationand †are P ≤ 0.05 for within-group and between-group comparisons, respectively The results of the interventions are presented in Table 3. Analysis of selected outcomes using the Friedman test revealed a significant effect of intervention type on reaction time, endpoint excursion and directional control in the LOS test, and in the less affected leg in the eyes-closed condition in the OLS test, the BBS and the TUG test. Within-group post hoc analysis revealed that balance-based exergaming training significantly improved LOS performance (improving reaction time from 0.96 ± 0.33 to 0.74 ± 0.24 s, end point excursion from 75.2 ± 12.48 to 84 ± 12.04 % and directional control from 75.7 ± 8.78 to 78.9 ± 7.65 %) and OLS on the less affected leg in the eyes-closed condition (from 3.35 ± 2.85 to 6.1 ± 8.65 s). Compared with the BT group (70.6 ± 9.37 %), the BE group (78.9 ± 7.65 %) exhibited better performance in directional control of LOS post-training. Functional balance in both groups, as measured by the BBS and the TUG test, was improved significantly post-training compared with pre-training. However, no significant differences were found between groups.\n\nBODY.DISCUSSION:\nThis study produced two main findings: (1) balance-based exergaming training had a greater effect on postural stability compared with conventional balance training; and (2) both training programs improved functional balance in people with PD. The current study tested two balance training programs with similar training protocols. A recent meta-analysis examined the BBS, postural sway, TUG, and Functional Reach test as measures of postural stability, reporting that exercise therapy is an important treatment option for improving postural stability in people with PD [38]. The findings suggested that exercises containing a balance component were most beneficial in improving postural stability in people with PD [38]. In the current study, we used the LOS and OLS tests to measure postural stability, and the BBS and TUG tests to measure functional balance. The current findings were in line with the findings of Klamroth et al., who reported that balance training was beneficial for performance in the BBS and TUG tests [38]. Our findings revealed that only balance-based exergaming training produced positive effects on LOS and OLS, with particularly strong effects on directional control in LOS. These findings suggest that exergaming training using the Kinect sensor contributed to the beneficial gains we observed. As a therapeutic tool, the Kinect sensor can provide specific motor practice using full-body motion capture, which offers precise real-time information to guide performance and monitor body movement. Previous clinical trials indicated that exergaming programs using the Kinect sensor resulted in accurate capture of movement components [39, 40]. Our results revealed within-group improvements on most measures of postural stability during the exergaming intervention training period. Our exergaming programs involved various balance challenges. This may have contributed to our positive findings, involving actions focused on agility, challenging postural or locomotor-like skills, and reaching away from the base of support. All of these are involved in whole-body movements. In addition, the repetitive, real-time feedback and graded complexity in our exergaming programs may have contributed to the positive effects of training reflected in LOS performance. However, the movement velocity of LOS remained unchanged after exergaming training. Persistent bradykinesia [41] and a choice to focus on improving accuracy rather than faster motor performance among people with PD are possible reasons for our movement velocity findings [21]. The current results also revealed better OLS performance in the eyes-closed condition after exergaming training. A previous study using a Wii-based system reported similar results [15]. Because participants needed to focus on each joint position while carrying out the fine motor plan necessary for many of the tasks in the exergaming training, stimulation of proprioceptive feedback or an improvement in the internal representation of balance may have enhanced OLS performance. Little evidence is available regarding the minimal clinically important differences in postural stability and balance outcomes in people with PD. Evidence of minimal clinically important differences for LOS and OLS test in PD is lacking. Steffen and Seney reported a minimal detectable change of 5 points on the BBS for people with PD [34]. In the current study, we recorded a 2.45-point improvement after balance training for BBS. The minimally detectable change in TUG performance in people with PD has previously been reported to be 3.5 s [42], which is greater than the 0.83-second improvement observed in the present study. The small but significant changes observed in this study support the therapeutic use of exergaming interventions. However, a greater evidence base is required to support the clinical significance of these results. Several important characteristics have been identified for useful interventions in PD, suggesting that interventions should be task-specific, progressive, variable in terms of practice, and highly challenging [43, 44]. The exergaming programs designed for the current study involved each of these components. For specificity, the full-body motion capture method can be tailored for the needs of balance strategies. To create an appropriate practice resource and construct the progression and variability of program, we implemented enriched setting parameters by increasing speed, repetition and the addition of tasks. Additionally, the novel motor training gave participants more experience and an opportunity to explore or learn to negotiate the new challenges. Although only directional control in the LOS test showed a significant between-group difference, exergaming training using the Kinect system may provide additional benefits. Participants are able to practice free motions without wearing a sensor that could cause discomfort and inconvenience. Reduced staff intervention and the affordability of the device are important economic benefits of the system. Finally, considering the clinical implications of our findings, the current results suggest that the Kinect system can provide an assistive modality with therapeutic potential as a training tool under the supervision of a therapist. The current study involved several limitations. First, the sample size was small, limiting the strength to interpret our results. Second, calibration variability was observed during the preparation of each exergaming session. This issue may have influenced the effect of training because calibration was used to normalize each participant's body information. This formed the basis of the exergaming programs that were tailored for individuals with varying levels of ability. Third, most participants in this study exhibited only mild impairment, and performance at baseline was relatively high. This may have limited the benefits received from training, and the generalizability of our findings to the target population. Finally, the absence of kinematic data meant we were unable to examine spatio-temporal changes in detailed movements.\n\nBODY.CONCLUSION:\nThe current study revealed that an 8-week period of balance-based exergaming training using the Kinect sensor resulted in a greater improvement of postural stability than conventional balance training. Both exergaming and conventional balance training had positive effects on functional balance. This trial supports the potential therapeutic use of exergaming aided by the Kinect sensor for people with PD. Importantly, the significant changes in BBS and TUG performance observed after both the exergaming and conventional balance training did not reach the minimal detectable change in patients with PD. Further studies on the use of exergaming are needed to verify the clinical implications of these results.\n\nQuestion:* Compared to a balance training group for an 8-week balance training period. what was the result of a balance-based exergaming group for an 8-week balance training period. on the limits of stability (LOS) performance and one-leg stance (OLS) tests?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1189	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The evaluation of effects two different doses of hydrocortisone on the intensity of perioperative shivering in elective surgery under spinal anesthesia: A double-blind randomized controlled trial study\n\n ABSTRACT.BACKGROUND:\nPost- and intra-operative shivering is one of the most complications of spinal anesthesia so recommend a suitable drug with at least complications for prevention and control of postoperative shivering. This current study aimed to compare the preventive effect of hydrocortisone on intra- and post-operative shivering in patients undergoing surgery with spinal anesthesia.\n\nABSTRACT.MATERIALS AND METHODS:\nIn a clinical trial study, ninety patients who candidate for surgery with spinal anesthesia were selected and randomly divided into three groups. The first and second groups were received 1 mg/kg and 2 mg/kg hydrocortisone, respectively, and the third group was received normal saline, and postoperative shivering was compared between the three groups.\n\nABSTRACT.RESULTS:\nThe investigation of the incidence of inter- and post-operative shivering in patients in the three groups revealed that within the study period, 31 patients suffered from shivering among which 9, 5, and 17 cases were in 1 mg/kg hydrocortisone group, 2 mg/kg hydrocortisone group, and placebo group, respectively, and according to the Chi-square test, the difference among the three groups was significant (P = 0.004).\n\nABSTRACT.CONCLUSION:\nAccording to the obtained results, the overall conclusion of the study is that using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of intra- and post-operative shivering with spinal anesthesia.\n\nBODY.INTRODUCTION:\nThe reactions of the immune system to temperature loss include activities of skin vasomotor, thermogenesis, sweating, and shivering, which is indeed the last immune mechanism, is produced in associated with muscular activities with a frequency of 4–8 Hz, and reinforces the temperature metabolism to 600% compared to the base level.[123456] Some processes can lead to central hypothermia. General and regional anesthesia are the same and in both the distribution of heat is from the center to the initial process environment that in spinal and epidural, the process does not reach to the balance because the environmental vasoconstriction is lost and shivering and low temperature are produced by a small volume of muscles above the block level.[78] Shivering occurs in 50% of patients with the core temperature of 35.5°C and in 90% of cases with the core temperature of 34.5°C.[9] Postoperative shivering is a common complication of spinal anesthesia which has different incidence in various studies and has been expressed up to 40–56.7% depending on the type and consumed drug.[1011] To treatment and prevent postoperative shivering, different drugs can be used that among from opioid drugs, pethidine, fentanyl, and tramadol and out of nonopioid drugs, dexamethasone, ondansetron, clonidine, pentazocine, ketamine, and magnesium sulfate can be mentioned.[7] Hydrocortisone is corticosteroids similar to the natural hormone produced by the adrenal gland that causes to remove inflammation (sweating, heat, redness, and pain) and its intravenous injection controls postoperative shivering with general anesthesia. The mechanism of hydrocortisone effect is applied through anti-inflammatory mechanism, core temperature gradient, and skin.[11] Since it is tried to recommend a suitable drug with at least side complications for the prevention and control of postoperative shivering, most conducted studies emphasize on the treatment of shivering, and prophylaxis has been studied less; on the other hand, until now, such study has not been conducted on people with spinal anesthesia and given the prevalence and increase of surgeries with spinal anesthesia, the current study aimed to compare the preventive effect of hydrocortisone on the incidence and intensity of shivering in patients undergoing surgery with spinal anesthesia.\n\nBODY.MATERIALS AND METHODS:\nThis is a randomized, double-blind clinical trial study conducted in an educational hospital (Kashani Hospital) of Isfahan University of Medical Sciences in Isfahan, Iran on 2013–2014. Patients were selected from those who were referred for elective orthopedic operation. Inclusion criteria were the age range of 18–60-year-old, patients undergoing lower extremity orthopedic operation with spinal anesthesia (knee arthroplasty, hip arthroplasty, femoral fracture...) American Society of Anesthesiologists physical status I–II,[2] no having hypothyroidism, hyperthyroidism, cardiopulmonary diseases, psychological disorders, no alcohol and drugs, lack of using vasodilator or drugs affecting the body's temperature settings, and patient's consent to participate in the study. It was also decided that patients requiring blood transfusions during operation, with the base temperature more than 38°C and <36°C or change in the techniques of anesthesia were excluded from the study. We assumed the incidence of shivering in the case and control group 10% and 40%, respectively, due to previous studies[56] with respect to α =0.05 and β =0.2. We calculated 29 patients in each group as the sample size. The method was in a way that after the approval of proposal and adoption of consent of Medical Ethics Committee, ninety patients with inclusion criteria were selected and divided into three 30-case equal groups by using random allocation software. Exactly, 1 mg/kg hydrocortisone + 2 cc normal saline, 2 mg/kg hydrocortisone + 2 cc normal saline, and the same normal saline (2 cc) were injected to patients in M, P, and C (control) groups, respectively. The volume of each syringe was maximally 2 cc. The syringe was similar with respect to the shape and color. The study drugs were administered 10 min before spinal anesthesia. Fluid therapy and anesthesia method were the same in all three groups. All patients were NPO for 8 h and during this time, the fluid therapy was done according to 4-2-1 formula of serum (4 ml/kg/h for the first 10 kg of body weight, 2 ml/kg/h for the second 10 kg of body weight, and 1 ml/kg/h for the third 10 kg of body weight) and then intravenous midazolam 0.05 mg/kg was injected to all patients 5 min before the onset of anesthesia. Before the onset of anesthesia, 10 cc/kg of Ringer Lactate was injected to all patients within 30 min, and patients were routinely monitored including pulse oximetry, automatic control blood pressure, central and peripheral temperature, and 3-lead electrocardiogram. Oxygen was given to the patients via a face mask as 5 l/min until the end of the operation. Spinal anesthesia was performed at L4–L5 or L3–L4 of the spinal needle of 24-gauge, midline, and at sitting position. After leaving transparent and cerebrospinal fluid, 2.5 cc bupivacaine of 0.5% was injected within 10 s for the anesthesia. Then, the patient was immediately placed at supine position and the patient's head was put 15–20°C above the horizon and no analgesic drug was injected into the patient. The level of sensory block was determined using bilateral pin-prick test in midclavicular line. When the level of block reached to the desired level, the lower limb operation was started. The temperature of the operating room had been maintained at 21–22° and nonoperative parts were covered by a layer of cloth. After the operation, the whole parts of the body were covered by a layer of cotton blanket and then, the patients were transferred to the recovery room. The temperature of recovery room was similar for all patients, and no heating device was individually used for patients. The baseline level of the central and peripheral temperatures was measured. Moreover, immediately before anesthesia (on operating table), immediately after the anesthesia, 5 min after anesthesia, before and after drug injection, every 10 min during the operation, at the onset of entrance to the recovery room, and after recovery at 10, 20, 30, 40, 50, and 60 min, central and peripheral temperatures were measured by tympanic thermometer (OMRON Medizintechnik GmbH, Mannheim, Germany) and an axillary thermometer (BMEcenter.ir, Iran). If the peripheral temperature was below 36°C, hypothermia would be considered. In hypothermic patients, if they had shivering with grade = 4. Meperidine 0.4 mg/kg was administered. To ensure that the study was double-blinded (both patients and physician who recorded the data), drugs were encoded by an operating room staff. All patients received postoperative routine nursing care and in all cases, basic rate of parameters including blood pressure, respiratory rate, heart rate, shivering score (0, no shivering; 1, piloerection or peripheral vasoconstriction but no visible shivering; 2, muscular activity in only one muscle group; 3, muscular activity in more than one muscle group but not generalized; and 4, shivering involving the whole body), pain score, drowsiness score, and vomiting was recorded. The incidence and intensity of shivering was evaluated during intra- and post-operative periods. Hypotension (low systolic pressure below 100 mmHg or 25% reduction in systolic blood pressure compared to patients' baseline pressure) was treated by intravenous Ringer lactate serum and 5 mg intravenous ephedrine. If the heart rate drops below 55 rates, the patients would receive 0.01 mg intravenous atropine per kg of body weight and if necessary, it would be repeated up to a maximum dose of 0.04 mg per kg of body weight. You should declare that as the ephedrine and atropine could alter the body temperature these nausea and vomiting were treated by 10 mg intravenous metoclopramide. All the received drugs, the number of frequency, and their dose were recorded. If patients had shivering Grade 4, meperidine 0.4 mg/kg was administered. The degree of sedation was evaluated as 1, fully awake and oriented; 2, drowsy; 3, eyes closed but rousable to command; 4, eyes closed but rousable to mild physical stimulation; and 5, eyes closed but unrousable to mild physical stimulation. The study data were entered into the computer after collecting and were analyzed using SPSS software version 20. Chi-square test (for comparison of qualitative data between groups), one-way analysis of variance (ANOVA) (for comparison of quantitative date between groups), and repeated measure ANOVA (for comparison of trend of quantities date between groups) with repeated observations, and median test were run to analyze the data.\n\nBODY.RESULTS:\nIn this study, ninety patients undergoing surgery with spinal anesthesia were investigated and assessed that during the study, no patient excluded from the study due to the incidence of unwanted complications such as hemodynamic and in the anesthesia method and all ninety patients were present in the study until the end of the study. In Table 1, the distribution of demographic and general variables of patients in the three groups has been shown. Table 1 Distribution of demographic and general variables in three study groups The investigation of the incidence of shivering in patients in the three groups revealed that within the study period, 31 patients suffered from shivering among which 9, 5, and 17 cases were in the 1 mg/kg hydrocortisone group, 2 mg/kg hydrocortisone group, and placebo group, respectively, and according to the Chi-square test, the difference among the three groups was significant (P = 0.004). Moreover, the intensity of shivering had no significant difference among the three groups (P = 0.046). The distribution of the frequency of the incidence and intensity of shivering in the three groups are given in Table 2. Comparing the incidence and intensity of shivering in binary groups indicated that the two groups of hydrocortisone of 1 mg/kg and 2 mg/kg had no significant difference in terms of the incidence and intensity of shivering (P = 0.23 and P = 0.2, respectively), while the incidence and intensity of shivering had a significant difference between the two groups of hydrocortisone of 1 mg/kg and placebo group (P = 0.039 and P = 0.018, respectively). Moreover, the incidence and intensity of shivering had a significant difference between the two groups of hydrocortisone of 2 mg/kg and placebo group (P = 0.0001 and P = 0.001, respectively). The score of sedation in patients in the three groups had no significant difference from the onset of the induction of anesthesia to 60 min of recovery in none of the studied periods. Within the study period, no patient suffered from drug allergy, whereas out of hydrocortisone group 2 mg/kg, one patient suffered from bradycardia and one patient suffered from hypotension. One of the hydrocortisone 1 mg/kg group and 1 case of hydrocortisone 2 mg/kg group suffered from postoperative nausea and vomiting, while no significant difference was observed among the three groups (P = 0.6). Table 2 Distribution of the frequency of the incidence and intensity of shivering in the three groups Figures 1 and 2 shown the mean central and peripheral temperatures in the three studied groups from the onset of the operation until 60 min of recovery. According to the one-way ANOVA test, the mean central and peripheral temperatures had no significant difference between the three groups in any of the study periods. Furthermore, repeated measure ANOVA indicated that the process of changes in the central and peripheral temperatures had no significant difference among the three groups (P = 0.64 and P = 0.31, respectively). The lowest core and peripheral temperatures were 35.75°C and 35.70°C, respectively, which occurred 90 min after spinal anesthesia. Figures 3 and 4 shown the Mean blood pressure from 0 to 60 min recovery in the three groups (P = 0.82) and Mean heart rate from 0 to 60 min recovery in the three groups (P = 0.77). Repeated measure ANOVA indicated that had no significant difference among the three groups (P = 0.82 and P = 0.77). Figure 1Mean central temperature from 0 to 60 min recovery in the three groups (P = 0.64) Figure 2Mean peripheral temperature from 0 to 60 min recovery in the three groups (P = 0.31) Figure 3Mean blood pressure from 0 to 60 min recovery in the three groups (P = 0.82) Figure 4Mean heart rate from 0 to 60 min recovery in the three groups (P = 0.77)\n\nBODY.DISCUSSION:\nShivering is the involuntary movements of one or several muscle groups and generally occurs in the initial phase of recovery after anesthesia. The incidence of this condition varies between 6.3% and 66% depending on the type and duration of operation, anesthesia technique, and patient's age and gender[12345678910] and has minimum incidence to 40% in patients operation with spinal anesthesia.[1011] With regard to the incidence and clinical significance, shivering has been known as the sixth major problem among from 33 clinical cases with the low rate of morbidity in clinical anesthesiology.[12] Of postoperative complications, the increase in oxygen consumption at the rate of 200–500%, production of CO2, heart rate and stroke volume, and blood pressure can be pointed out that their suppression reduces the metabolic need and myocardial function.[131415161718] Other complications include the increase of intraocular pressure and intracranial pressure, creation of problem in monitoring the patient, and interference with the surgical cares, especially in cases requiring immobilization, for example, secular or nerve anastomosis.[141516] According to the results of our study, three studied groups had no significant difference in terms of demographic variables and operation features such as duration of operation and anesthesia and sensory block level and no confounding effect of the above-mentioned factors was observed on the incidence and intensity of shivering and therefore it may pertain to the fact that the difference in the incidence of postoperative shivering is related to the type and rate of preventive consuming drug. According to the results of our study, the incidence of shivering in the group receiving hydrocortisone including a dose of 1 mg/kg or 2 mg/kg was considerably and significantly less than the control group. On the other hand, patients receiving hydrocortisone had lower shivering; however, no significant difference was observed between the two doses of the drug. A number of pharmaceutical interventions for the treatment and prophylaxis of shivering including clonidine, ketamine, doxapram, tramadol, pethidine, and other opioids have so far been examined (14, 17, and 18). In the study by Pawar et al., in 2011, the effectiveness of hydrocortisone for the prevention of shivering was approved so that the incidence of shivering was 32% in patients receiving hydrocortisone and 82% in the control group.[18] In their study, Yousef and Johnson showed that using hydrocortisone as a preventive drug reduced the incidence of hypothermia; consequently, it reduced the incidence of shivering in patients undergoing an operation.[19] Therefore, according to the obtained results, the overall conclusion of the study is that using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of shivering with spinal anesthesia. However, because limitations of our study such as small sample size, to highly ensure the effect of dose-response of the drug, further studies are recommended.\n\nBODY.CONCLUSION:\nAccording to this study using hydrocortisone at least with the dose of 1 mg/kg as a preventive drug reduced the incidence of intra- and post-operative shivering with spinal anesthesia.\n\nBODY.CONCLUSION.FINANCIAL SUPPORT AND SPONSORSHIP:\nAnesthesiology and Critical Care Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.\n\nBODY.CONCLUSION.CONFLICTS OF INTEREST:\nThe authors have no conflicts of interest.\n\nBODY.AUTHORS’ CONTRIBUTION:\nMRS has planned the study and finalized it; FK, AH, MN, HS, and MRS did the statistical analysis and prepared the first version of the manuscript for publish. All authors read and approved the final manuscript.\n\nQuestion: Compared to received normal saline what was the result of received 1 mg/kg and 2 mg/kg hydrocortisone on Mean central temperature, Mean peripheral temperature, Mean blood pressure, Mean heart rate?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1191	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on mean daily number of moderate to severe hot flushes at week 12?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1192	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on mean proportion of superficial cells?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1193	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on reduction from baseline in the mean proportion of parabasal cells?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1195	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on vaginal pH?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1198	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on sexual function and total scores?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1199	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on lumbar spine bone mineral density (BMD)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1201	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Management of osteoporosis and menopausal symptoms: focus on bazedoxifene/conjugated estrogen combination\n\n ABSTRACT:\nLoss of estrogen production in women during menopause results in a state of estrogen deficiency which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, bone loss, and difficulties with sleep, mood, memory, and sexual activity. The only treatment option currently available to address multiple postmenopausal symptoms in women with an intact uterus is estrogen/progestin-containing hormone therapy (HT). Concerns surrounding side effects and published data regarding the association of HT with the increased risk for breast cancer have induced a decrease in the number of women seeking, initiating, and continuing this type of therapy. A combination containing bazedoxifene and conjugated estrogens (BZA/CE) maintains the established benefits of estrogen therapy for treatment of postmenopausal vasomotor symptoms, vulvovaginal atrophy, and osteoporosis, while certain estrogenic effects, such as stimulation of the uterus and breast, are antagonized without the side effects associated with HT. BZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III trials known as the Selective estrogens, Menopause, And Response to Therapy (SMART) trials. BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms, vulvovaginal atrophy, and a protective effect on the skeleton. These clinical benefits were associated with an acceptable safety profile and an improved tolerability compared with HT. BZA/CE showed a favorable safety profile on the breast, endometrium, and ovaries. The incidence of venous thromboembolism was low and the risk does not appear to be any greater than for CE alone or BZA alone or greater than HT. The incidence of coronary heart disease and cerebrovascular accidents were similar to placebo. The overall incidence of cancer (including breast cancer) was low and similar to placebo. The SMART trials demonstrate that BZA/CE is an alternative option for treating non-hysterectomized, symptomatic, postmenopausal women.\n\nBODY.INTRODUCTION:\nLoss of ovarian estrogen production in women during menopause results in a state of estrogen deficiency1 which has been associated with multiple problems, including vasomotor symptoms, symptoms of vulvovaginal atrophy, and difficulties with sleep, mood, memory, and sexual activity.2 During menopause, these symptoms commonly overlap, presenting as a continuum, and may have a negative impact on a woman's quality of life.3 Menopausal symptoms have also been negatively associated with the ability to work.4 Estrogen deficiency has further been associated with loss of bone mass, often leading to osteoporosis, which is associated with an increased occurrence of skeletal fractures.2 Women who sustain osteoporotic fractures also face a negative impact on their quality of life, often affecting their ability to function and putting them at an increased risk of morbidity and mortality.2,5,6 A variety of therapeutic options are available for the individual symptoms associated with menopause. Estrogen/progestin-containing hormone therapy (HT) is the only currently approved treatment for women with a uterus that holistically addresses the postmenopausal problems of vasomotor symptoms and vulvovaginal atrophy, while maintaining bone mass.3 HT has pharmacologic drawbacks, including vaginal bleeding and breast pain/tenderness, which are the most common reasons for discontinuation of this therapy.7–9 Vaginal bleeding leads to discontinuation of therapy in up to one-third of women and rates of discontinuation can be as high as 68% within the first year of treatment.10 Rates of discontinuation for breast tenderness/pain have been reported to be as high as 40% in some clinical trials.11,12 Progestin-induced irregular vaginal bleeding associated with HT creates distress and often requires additional interventions (ie, transvaginal ultrasonography, endometrial biopsies, and hysteroscopies).13 Increases in breast density associated with progestin-containing HT may lead to mammographic recalls because of difficulty in reading mammogram results. Mammographic recalls also increase anxiety in women, contributing to the decision to discontinue HT.14,15 Women's concerns about the available therapeutic options for postmenopausal symptoms have resulted in a substantial population who are currently untreated.3 The population of postmenopausal women will grow, given the continual increase in the numbers of women approaching menopause and the extended life expectancy of postmenopausal women.1 Thus, for postmenopausal women with a uterus, new therapeutic alternatives with an improved tolerability and safety profile compared with traditional HT are needed to help alleviate vasomotor symptoms and vulvovaginal atrophy symptoms, and to prevent osteoporosis. BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), and represents a new treatment option in the management of menopausal health for women with a uterus. BZA/CE maintains the established benefits of estrogen therapy for menopausal symptoms of vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis, while preventing the stimulatory estrogenic effects on the uterus and estrogenic/progestogenic effects on breast tissue. The rationale for development of BZA/CE was that BZA, acting as an estrogen receptor antagonist in uterine tissue, would inhibit the proliferative effects of estrogen on the endometrium in a manner mechanistically distinct from progestins, and therefore reduce the incidence of irregular uterine bleeding. BZA acts as an estrogen receptor antagonist in breast tissue, so BZA/CE is posited not to induce breast pain or changes in breast density. BZA/CE does not cause morphologic changes in the mammary gland, and it is hypothesized that this is the pharmacologic explanation for the lack of changes in breast pain and density. In vitro and vivo models demonstrate that BZA also inhibits the proliferative stimulatory action of estrogens on breast cancer cells.16 The objective of this review is to present key efficacy and safety findings from the Selective estrogens, Menopause, And Response to Therapy (SMART) trials.17–20\n\nBODY.CLINICAL STUDIES WITH BZA/CE:\nBZA/CE has been evaluated in a series of multicenter, randomized, double-blind, placebo-controlled, and active-controlled Phase III investigations known as the SMART trials (Table 1).17–20 The SMART-1 trial (n = 3,397) was conducted at 94 sites in the United States, Europe, and Brazil and enrolled generally healthy, postmenopausal women aged 40–75 years.17 Eligible subjects had to have an intact uterus, a body mass index (BMI) ≤32.2 kg/m2, and normal endometrial biopsy results at screening. SMART-1 evaluated the efficacy of multiple doses of BZA/CE (combinations of BZA 10 mg, 20 mg, and 40 mg with either CE 0.45 mg or CE 0.625 mg) with regard to uterine protection, vasomotor symptoms, vulvovaginal atrophy, and prevention of osteoporosis.17 The one-year interim results from SMART-1 demonstrated that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg have a low (<1%) incidence of endometrial hyperplasia, while reducing the number and severity of hot flushes, improving symptoms of vulvovaginal atrophy, and preventing bone loss. Therefore, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were selected for further evaluation in other SMART trials.17 The SMART-2 trial (n = 318) was conducted at 43 sites in the United States and enrolled healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. Eligible subjects had to have seven or more moderate to severe hot flushes daily (or at least 50 per week) at screening and be seeking treatment for hot flushes. This study evaluated the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg on vasomotor symptoms compared with the effects of placebo over 12 weeks of treatment. The primary endpoint was change from baseline in the frequency and severity of hot flushes. Secondary endpoints included effects on sleep, quality of life, and satisfaction with treatment.18 The SMART-3 trial (n = 652) was conducted at 66 sites in the United States and enrolled generally healthy, postmenopausal women aged 40–65 years with an intact uterus and a BMI ≤ 34.0 kg/m2. All women had to have a vaginal cytologic smear showing no more than 5% superficial cells, a vaginal pH > 5, and at least one moderate to severe vulvovaginal atrophy symptom at screening. This study examined the effects of BZA 20 mg/CE 0.45 mg and 0.625 mg compared with those of BZA 20 mg alone and placebo on measures of vulvovaginal atrophy over 12 weeks of treatment.19 The SMART-5 trial (n = 1,886) was conducted at 166 sites in the United States, Europe, Latin America, Australia, and New Zealand, and enrolled generally healthy, postmenopausal women aged 40–75 years. Eligible subjects had to have an intact uterus, a BMI ≤ 34 kg/m2, and acceptable endometrial biopsy results at screening. SMART-5 evaluated the efficacy of BZA/CE on uterine protection, prevention of osteoporosis, and effect on breast density.20 This study evaluated the effects of BZA 20 mg/CE 0.45 and 0.625 mg and included CE/medroxyprogesterone acetate (MPA, (Prempro®, Pfizer Pharmaceuticals Inc, New York, NY, USA), BZA, and placebo as comparators. The results of the one-year SMART-4 study (n = 1,061) are not discussed in this review because a different formulation of BZA/CE was evaluated. Regardless, the results of the SMART-4 study were similar to those of the SMART-1 study.17\n\nBODY.EFFICACY ON HOT FLUSHES, HEALTH RELATED-QUALITY OF LIFE, AND SLEEP:\nTwo clinical trials (SMART-1 and SMART-2) evaluated the efficacy of BZA/CE for the treatment of moderate to severe vasomotor symptoms. In these studies, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 were associated with clinically meaningful improvements in vasomotor symptoms as compared with placebo, and the efficacy was comparable with that of available hormonal options (HT and estrogen therapy).17,18 In SMART-2, at week 4, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a significant decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes as compared with placebo. A clinically meaningful reduction of 5–6 hot flushes per day was observed in subjects treated with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg, respectively, compared with a reduction of three hot flushes in the placebo group. At week 12, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg were associated with a decrease (P < 0.001) in the adjusted mean daily number of moderate to severe hot flushes, reaching a 74% and a 80% reduction, respectively, representing a clinically meaningful reduction of approximately 7–8 hot flushes per day, compared with a 51% reduction (representing a reduction of approximately five hot flushes per day) in the placebo group (Figure 1).18 In addition to significant reductions in the number of moderate to severe hot flushes experienced per day, both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated clinically meaningful reductions in the severity of moderate to severe hot flushes compared with subjects who received placebo at week 4 (26% and 29% reduction, respectively) and week 12 (39% to 55% reduction, respectively, P < 0.001, Figure 2).18 Similar results were observed in SMART-1, with evidence of efficacy of BZA/CE for the treatment of vasomotor symptoms present through 2 years of therapy.17 BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 was associated with clinically meaningful improvements in vasomotor symptoms. Comparison with historical data reveals that both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths have an overall comparable efficacy with that of estrogen progestin-containing HT compounds in the relief of moderate to severe hot flushes associated with menopause.21 Both BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated efficacy for both the daily number and severity of moderate to severe hot flushes, regardless of racial characteristics, BMI, and years since menopause of the populations evaluated.18 Health-related quality of life, sleep parameters, and patient satisfaction tools were also used to assess patient response to therapy in the SMART-2 study. Clinically significant improvements were reported with BZA 20 mg/CE 0.45 and 0.625 mg at 12 weeks compared with placebo in the vasomotor function domain of the Menopause-Specific Quality of Life questionnaire and significantly greater satisfaction in the ability to control hot flushes during the day and night according to the Menopause Symptoms Treatment Satisfaction Questionnaire.22 A range of components of the Medical Outcomes Study sleep scale also showed significant improvements with BZA/CE versus placebo, including significant decreases in sleep disturbance and significant increases in sleep adequacy.22 Additionally, BZA/CE improved both indices (sleep problem index 1 and 2) included in the Medical Outcomes Study sleep scale (Figure 3). Statistical mediation modeling demonstrated that BZA/CE affected sleep directly in populations of women with severe vasomotor symptoms, while in less symptomatic women its effect was indirect via improvement in hot flushes.22 In summary, BZA/CE was associated with a clinically meaningful reduction in vasomotor symptoms, comparable with that observed for HT; moreover, this efficacy was correlated with improvements in sleep and menopause-related quality of life.\n\nBODY.EFFECTS ON VULVOVAGINAL ATROPHY:\nTwo studies evaluated the efficacy of BZA/CE on vulvovaginal atrophy, ie, SMART-1 and SMART-3.17,19 In the SMART-3 trial, the efficacy of BZA 20 mg/CE 0.45 and 0.625 mg on vulvovaginal atrophy was evaluated in subjects who had no more than 5% superficial cells at screening on the vaginal smear, a vaginal pH < 5, and presented with a moderate to severe symptom associated with vulvovaginal atrophy.19 BZA 20 mg/CE 0.45 or 0.625 mg showed a significantly greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001). Both BZA/CE groups also showed a significantly greater reduction from baseline in the mean proportion of parabasal cells (P < 0.001) and a significantly greater increase from baseline in the mean proportion of intermediate cells (P < 0.05) compared with placebo at weeks 4 and 12. Additionally, treatment with BZA 20 mg/CE 0.625 mg resulted in a significantly greater decrease from baseline in vaginal pH (P < 0.001) and a greater improvement in the women's most bothersome vulvovaginal atrophy symptoms (P < 0.05) compared with placebo (Figure 4).19 In SMART-1, BZA/CE showed a similar effect on the vaginal epithelium, inducing a greater increase from baseline in the mean proportion of superficial cells compared with placebo (P < 0.001), a greater increase in the mean proportion of intermediate cells (P < 0.001), and a greater decrease in the mean proportion of parabasal cells from baseline compared with placebo (P < 0.001). This maturation of the vaginal epithelium was associated with a statistically significant reduction in the incidence of dyspareunia relative to placebo during weeks 9–12 of therapy (P < 0.001) and in ease of lubrication score from baseline compared with placebo (P < 0.05) on the Arizona Sexual Experiences scale.17,19 Additionally, in SMART-3 (subjects with vulvovaginal atrophy), the Menopause-Specific Quality of Life questionnaire results at week 12 showed significant improvements in sexual function and total scores with both BZA/CE doses versus placebo or BZA 20 mg (P < 0.001). The Menopause Symptoms Treatment Satisfaction Questionnaire results showed that BZA/CE-treated subjects reported significantly greater overall satisfaction with treatment.19\n\nBODY.BONE EFFECTS:\nTwo clinical trials (SMART-1 and SMART-5) evaluated the safety and efficacy of BZA/CE for the prevention of osteoporosis.17,20 Among subjects ≤5 years since menopause (substudy II of SMART-1 and SMART-5), significant (P < 0.001) increases from baseline to month 12 in lumbar spine bone mineral density (BMD) were demonstrated for both the BZA 20 mg/CE 0.45 mg (1.05% and 0.24% in SMART-1 and SMART-5, respectively) and BZA 20 mg/CE 0.625 mg (1.05% and 0.60%, in SMART-1 and SMART-5, respectively) treatment groups compared with placebo (−1.81% and −1.28%, in SMART-1 and SMART-5, respectively).17,20 In addition, in SMART-1, a statistically significant increase in lumbar spine BMD from baseline to month 24 was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with a decrease in lumbar spine BMD in the placebo group (P < 0.001). Raloxifene 60 mg was included as an active comparator in SMART-1; among subjects ≤5 years since menopause, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated a statistically significant greater percentage increase in lumbar spine BMD from baseline to months 12 (P < 0.001) and 24 (P = 0.002 and P = 0.001, respectively) compared with raloxifene 60 mg (Figure 5).17 In SMART-5, BZA 20 mg and CE 0.45 mg/MPA 1.5 mg were included as active comparators. BZA/CE (both doses) showed similar efficacy to CE/MPA and a superior bone effect as compared with BZA 20 mg.20 SMART-1 and SMART-5 demonstrated that treatment with BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg effectively prevented loss of total hip BMD, having a comparable effect to that of raloxifene 60 mg and BZA 20 mg at all time points evaluated. In addition, BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg demonstrated a comparable effect to CE 0.45 mg/MPA 1.5 mg in terms of effects on BMD at the total hip.17,20 The results from subpopulation analyses based on the integrated data from SMART-1 and SMART-5 demonstrate that BZA/CE therapy was efficacious regardless of age groups (<60 years versus ≥60 years), BMI, race, and geographic region in improving lumbar spine and total hip BMD.17,20 To evaluate further the effect of treatment on bone metabolism, serum samples for determination of osteocalcin, procollagen type 1 N-propeptide (P1NP), and C-telopeptide were obtained in SMART-1 and SMART-5.17,20 The observed decreases in bone turnover markers were consistent with the observed improvements in BMD. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated significant decreases from baseline in serum concentrations of C-telopeptide and osteocalcin compared with placebo (P < 0.001) in SMART-1 and SMART-5. In addition, concentrations of P1NP at months 6 and 12 were significantly decreased (P < 0.001) by both doses compared with placebo in SMART-5.17,20 A significantly larger decrease (P < 0.001) in serum concentrations of C-telopeptide and osteocalcin was observed for both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups compared with the raloxifene 60 mg treatment group in SMART-1.17 Similarly, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated greater decreases in serum osteocalcin and serum C- telopeptide and significant decreases in P1NP compared with the BZA 20 mg treatment group. Moreover, in SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated decreases in P1NP and serum osteocalcin that were comparable with the CE 0.45 mg/MPA 1.5 mg treatment group.20 Studies conducted with BZA alone provide important supportive evidence for the long-term efficacy (7-year exposure) of BZA in postmenopausal subjects. Treatment with BZA 20 and BZA 40 mg for 3 years resulted in a statistically significant reduction (P < 0.05) in the incidence of new vertebral fractures compared with placebo which was similar to that observed with raloxifene 60 mg. This positive effect in reduction of new vertebral fractures was observed through 5 and 7 years of treatment.23 Overall, the skeletal effects (changes in lumbar spine and hip BMD and bone turnover markers) observed with BZA/CE therapy were clinically meaningful and greater than for raloxifene and BZA monotherapy and comparable with CE 0.45 mg/MPA 1.5 mg. The increases in BMD and decrease in bone turnover markers observed with BZA/CE as compared with placebo have been associated with a reduction in fracture risk with antiresorptive agents as well as with BZA treatment.\n\nBODY.SAFETY.ENDOMETRIAL SAFETY:\nProtection of the endometrium is of major clinical importance for non-hysterectomized postmenopausal women who receive a therapy containing estrogens. Therefore, the tissue selective activity of the selective estrogen receptor modulator component of BZA/CE is key to endometrial protection.16 The incidence of endometrial hyperplasia with BZA/CE was evaluated in SMART-1 and SMART-5. These studies were of sufficient duration to provide evidence that BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg provides appropriate endometrial protection. Both doses of BZA/CE demonstrated an incidence of endometrial hyperplasia <1%, which was comparable with placebo.17,24 Data obtained using transvaginal ultrasound have also shown neutral effects of BZA/CE on the endometrium. BZA/CE were associated with minimal increases in endometrial thickness from baseline (<1 mm) which were similar to placebo.20 More subjects treated with CE/MPA in the SMART-5 trial had an increase in endometrial thickness of >5 mm compared with BZA/CE or placebo.20 The effects of BZA/CE on endometrial bleeding have also been evaluated in the SMART trials.20,25 In SMART-1 and SMART-5, BZA 20 mg/CE 0.45 and 0.625 mg were associated with high rates of cumulative amenorrhea, similar to placebo. The rates of cumulative amenorrhea over one year were >83%, >87%, and >85% for BZA 20 mg/CE 0.45 mg, BZA 20 mg/CE 0.625 mg, and placebo, respectively, in SMART-1.25 Higher rates of cumulative amenorrhea were observed with BZA 20 mg/CE 0.45 and 0.625 mg (>87% and >84%, respectively) and placebo (>83%) compared with CE/MPA (>54%) in SMART-5 (Figure 6).20\n\nBODY.SAFETY.BREAST SAFETY:\nThe effect of BZA/CE regimens on the incidence of breast pain/tenderness was evaluated in SMART-1, SMART-2, and SMART-5.17,18,20 In these studies, breast pain/tenderness was measured by daily subject diaries. Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths demonstrated an incidence of breast pain/tenderness that was not significantly different compared with placebo, raloxifene 60 mg, and BZA 20 mg.17 In SMART-5, the incidence of breast tenderness in subjects treated with BZA/CE was significantly lower than that in subjects treated with CE 0.45 mg/MPA 1.5 mg (P < 0.001, Figure 7).20 These results are consistent with the relative incidences of adverse events related to breast pain/tenderness and discontinuation rates due to breast pain/tenderness reported by participants in the SMART trials.17–20 In SMART-5, both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg treatment groups demonstrated non-inferiority compared with placebo with regards to mammographic breast density. By contrast, the CE 0.45 mg/MPA 1.5 mg treatment group exhibited a significant increase in breast density compared with the placebo group. BZA/CE treatment did not affect age-related changes in mammographic breast density (ie, natural reduction in breast density throughout the years of menopause). The results demonstrated that, unlike estrogen progestin-containing HT, BZA 20 mg/CE 0.45 mg, and BZA 20 mg/CE 0.625 mg have a neutral (similar to placebo) effect on breast density.20\n\nBODY.SAFETY.GENERAL SAFETY:\nBased on the integrated safety results of the SMART trials, the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths are well tolerated and have an acceptable safety profile, supporting use in generally healthy, postmenopausal women with a uterus.17–20 The incidences of treatment-emergent adverse events, serious adverse events, and discontinuations due to adverse events were similar among the treatment groups. The incidence of venous thromboembolism was low, as expected in this relatively healthy population and consistent with what was reported in the Women's Health Initiative study.26 The risk does not appear to be any greater than for CE alone or BZA alone or greater than for CE/MPA.26,27 The incidences of coronary heart disease and cerebrovascular accidents were similar to those on placebo. The incidence of estrogen-sensitive cancers, including breast cancer, endometrial cancer, and ovarian cancer, was low and similar to placebo. Clinical laboratory tests demonstrated that the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg doses were associated with a favorable lipid profile (decreases in total cholesterol, low-density lipoprotein, increases in high-density lipoprotein) with the exception of an increase in triglyceride levels.20 Both the BZA 20 mg/CE 0.45 mg and BZA 20 mg/CE 0.625 mg dose strengths were associated with an increase from baseline in serum triglycerides which was similar to that reported for estrogen progestin-containing HT.28 No other clinically significant changes in clinical laboratory tests were noted. There were no significant differences in the adjusted mean change in body weight with either BZA/CE dose compared with placebo at one year or at the final on-therapy evaluation; this was the case among subjects in the overall population as well as in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2. The percentages of subjects with body weight changes of potential clinical importance (an increase or decrease from baseline of ≥15% or ≥11 kg) were low and not significantly different between the BZA/CE and placebo groups in the overall population or in the two subgroups of women with a BMI <25 kg/m2 or ≥25 kg/m2.17–20 Changes from baseline in mean systolic blood pressure were less than 2.00 mmHg in the BZA 20 mg/CE 0.45 mg group and BZA 20 mg/CE 0.625 mg group; these changes were similar to those observed for the placebo group. The mean change in systolic blood pressure was comparable with that seen on placebo at all time points evaluated.17–20\n\nBODY.CONCLUSION:\nTreatment with BZA/CE demonstrated clinically meaningful improvements in vasomotor symptoms and vulvovaginal atrophy as well as a protective effect on the skeleton in postmenopausal women seeking treatment for menopausal symptoms, while protecting the endometrium. BZA/CE also showed significant improvements in tolerability compared with HT, as measured by lower rates of uterine bleeding and breast pain. BZA/CE treatment had an effect on breast density similar to placebo. These clinical benefits were associated with an acceptable safety profile. No apparent increased risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer, was observed with either dose strength of BZA/CE. BZA/CE is an alternative option for treating non-hysterectomized, symptomatic postmenopausal women.\n\nQuestion: Compared to placebo what was the result of BZA/CE combines bazedoxifene (BZA), a selective estrogen receptor modulator, with conjugated estrogens (CE), on risk for serious adverse events, such as venous thromboembolism, cardiovascular events, endometrial cancer, or breast cancer,?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
1203	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Antioxidative and antiatherogenic effects of flaxseed, α-tocopherol and their combination in diabetic hamsters fed with a high-fat diet\n\n ABSTRACT:\nOxidative stress has previously been shown to play a role in the pathogenesis of diabetes mellitus (DM) and its complications. In the present study, the effects of supplementation with dietary antioxidants, flaxseed and α-tocopherol were investigated in diabetic golden Syrian hamsters fed with a high-fat diet. Thirty-five golden Syrian hamsters were randomly divided into a control group (C) and four diabetic groups (DM, DM + flax, DM + E and DM + Flax + E). The hamsters received four different diets for a 20-week period, as follows: i) Groups C and DM received a high-fat diet (40% energy as fat), deficient in α-linolenic acid (ALA); ii) the DM + Flax group received a high-fat diet enriched with ground flaxseed 15 g/100 g of food, rich in ALA; iii) the DM + E group received a high-fat diet enriched with vitamin E, 40 mg α-tocopherol/100 g of food; and iv) the DM + Flax + E group received a high-fat diet enriched with flaxseed and vitamin E. The results of serum lipid and oxidative stress analysis suggested that the antiatherogenic effect of flaxseed, α-tocopherol and their combination added to a high-fat diet in diabetic hamsters was based primarily on their antioxidative role, demonstrated by decreased serum lipid peroxidation and increased liver glutathione content. Improvements of serum glucose and non-high-density lipoprotein cholesterol (HDL-C) levels were observed and may have contributed to the prevention of diabetic macroangiopathy evidenced in the histopathological examination. The antioxidant effect of flaxseed was similar to that of α-tocopherol in diabetic hamsters fed a high-fat diet and combined supplementation did not appear to bring more benefits than flaxseed alone. Moreover, the high dose of ground flaxseed alone may have a better cardioprotective effect than α-tocopherol in diabetic hamsters by reducing total cholesterol and non-HDL-C levels and increasing HDL-C levels.\n\nBODY.INTRODUCTION:\nOxidative stress is considered to be significant in the pathogenesis of diabetes-induced cardiovascular disease (CVD), which is associated with an abnormal blood lipid profile, insulin resistance and metabolic syndrome (1). Oxidative stress occurs due to a disturbance of the balance between antioxidant defense mechanisms and the levels of reactive oxygen species (ROS) (2,3). Numerous studies have identified significant alterations in plasma antioxidant vitamins (including vitamins C, E and A), antioxidant enzyme systems [superoxide dismutase (SOD), catalase (CAT) and glutathione peroxidase (GSH-Px)] and in lipid peroxidation in diabetes (4,5). In chronic diabetes mellitus (DM), the stability and reactive capacity of antioxidants seriously affect the long-term complications caused by oxidative stress (6,7). Antioxidants have been shown to reduce complications in DM by preventing free radical-mediated damage (4,8). Dietary supplementation with antioxidants, including vitamins and phenolic compounds obtained from plants, may help to maintain a desirable pro-oxidative/antioxidative balance (9,10). A variety of dietary sources are presently of considerable interest due to their potential health benefits in relation to numerous diseases, including diabetic disorders (11,12). Flaxseed (also known as linseed and Linum usitatissimum), an edible oil seed/grain from a traditional arable crop, has been acknowledged as a functional food (13), and is the focus of considerable attention due to its unique nutrient components and its potential to prevent CVD (14). In addition of being one of the richest plant sources of α-linolenic acid (ALA; ~22% of whole flaxseed), flaxseed is an essential source of lignans (in particular, secoisolariciresinol diglucoside, SDG) (15). SDG has demonstrated extreme radical scavenging activity, thereby protecting polyunsaturated fatty acids from oxidation (16–18). Despite the beneficial effects of SDG, flaxseed consumption has been found to significantly reduce α- and γ-tocopherol concentrations in rats (19) and only vitamin E supplementation was able to restore the plasma concentrations (20). α-tocopherol supplementation has previously been demonstrated to be beneficial in increasing the levels of antioxidant enzymes such as SOD and GSH-Px, and of reduced GSH in diabetes (21–23); however, little is known about the effect of adding vitamin E to a flaxseed-enriched diet on oxidative stress and aortic atherosclerotic lesions in diabetes. In the present study, the effects of dietary flaxseed, α-tocopherol and their combination were investigated on atherosclerotic progression in diabetic hamsters fed a high-fat diet by examining serum lipid concentrations, oxidative stress markers, aortic cholesterol content and aortic histological aspects.\n\nBODY.MATERIALS AND METHODS.ANIMALS:\nA total of 35 male Golden Syrian hamsters were used in the study. The hamsters were purchased from the Cantacuzino National Institute for Research and Development in Microbiology and Immunology (Bucharest, Romania). This study was approved by the Laboratory Animal Care Committee of Grigore T. Popa University of Medicine and Pharmacy (Iaşi, Romania), and the hamsters were maintained in accordance with the general guidelines for the care and use of laboratory animals recommended by the Council of European Communities (24). The hamsters were caged singly and kept in standard laboratory conditions with a controlled temperature (20±2°C) and a 12 h light/12 h dark cycle. Diabetes was induced in the hamsters using streptozotocin (STZ; catalog no. S0130; Sigma-Aldrich, St. Louis, MO, USA) (25). STZ, at a dose of 50 mg/kg body weight, freshly solved in citrate buffer (50 mM, pH 4.5), was administered intraperitoneally, as a single dose in the morning, following a night of fasting. Citrate buffer (50 mM) was prepared from sodium citrate and citric acid (S.C. Chemical Company, Iaşi, Romania) dissolved in distilled water, with adjustment of the pH to 4.5. The control group (C) received an equivalent quantity of citrate buffer (50 mM), administered intraperitoneally. All animals having a blood glucose level >126 mg/dl (7 mmol/l) were considered to be diabetic.\n\nBODY.MATERIALS AND METHODS.GROUPING AND DIETS:\nEach hamster received 15 g food/day and tap water ad libitum. The animals were randomly divided into a control group (C) and four diabetic groups (DM, DM + flax, DM + E and DM + Flax + E). The hamsters received four different diets for a 20-week period, as follows: i) Groups C and DM received a high-fat diet (40% energy as fat), that was deficient in ALA; ii) the DM + Flax group received a high-fat diet enriched with ground flaxseed (Linum usitatissimum; 15/100 g of food), that was rich in ALA; Flaxseed of the Olin variety was provided by the Department of Phytotechny of the Faculty of Agronomy (Iaşi, Romania). iii) the DM + E group received a high-fat diet enriched with vitamin E (40 mg α-tocopherol/100 g of food; Sigma-Aldrich); and iv) the DM + Flax + E group received a high-fat diet enriched with a combination of flaxseed and vitamin E. All four diets had similar carbohydrate, total fiber, protein and fat contents (Table I).\n\nBODY.MATERIALS AND METHODS.ANIMAL NECROPSY AND PROCESSING OF SAMPLES:\nAt the end of the experiment, the animals were sacrificed by cardiac puncture under ketamine anesthesia (100 mg/kg body weight). Blood samples were collected without anticoagulant. Aliquots of serum were frozen and kept at −80°C for subsequent analysis. The liver was immediately removed, rinsed with ice-cold saline, placed in a sealed container, homogenized for biochemical analysis and stored at −20°C until analyzed. The aortas were dissected, rinsed with cold saline and preserved in a phosphate buffer (pH 7.2).\n\nBODY.MATERIALS AND METHODS.SERUM GLUCOSE:\nSerum glucose was measured by enzymatic colorimetric methods on a Tecan microplate reader (Tecan SunriseTM Touchscreen, Männedorf, Switzerland) using the AD1A716 commercially available kits (Audit Diagnostics, Cork, Ireland).\n\nBODY.MATERIALS AND METHODS.SERUM LIPID PROFILE:\nSerum total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C) and triglyceride (TG) levels were measured by enzymatic colorimetric methods on a Tecan microplate reader using the AD1A704, AD1A602 and AD1A306 commercially available kits (Audit Diagnostics). Non-HDL-C levels were calculated by subtracting the level of HDL-C from that of TC.\n\nBODY.MATERIALS AND METHODS.EVALUATION OF CHOLESTEROL CONTENT IN THE AORTA:\nThe aortas of the hamsters in each group were removed. A section of the aortic arch of each animal was soaked in a 10% (v/v) formal saline solution and was stored on ice prior to being stained and fixed. The remainder of the aorta was soaked in phosphate-buffered saline (PBS) and homogenized for biochemical analysis. The lipid content was extracted by treatment with chloroform and methanol followed by centrifugation (26). The extracted lipid was dissolved in ethanol and measured using a AD1A704 cholesterol assay kit (Audit Diagnostics) utilizing absorbance spectrophotometry (Microlab 300, Vital Scientific, Spankeren, Netherlands) at 500 nm wavelength, and the amount quantified as μg/mg wet tissue.\n\nBODY.MATERIALS AND METHODS.PARAMETERS OF OXIDATIVE STRESS:\nSerum and liver thiobarbituric acid reactive substances (TBARS) are indices of lipid peroxidation and oxidative stress. TBARS were determined using the method described by Phelps and Harris (27). The quantity of the TBARS was measured using a Tecan microplate reader at a wavelength of 540 nm. Liver levels of reduced GSH were determined by an enzymatic reaction, based on the oxidation of GSH by 5,5′-dithiobis(2-nitrobenzoic acid) (DTNB), in the presence of GSH reductase and methylenetetrahydrofolate reductase, monitored at a wavelength of 405 nm (28). Liver SOD levels were determined using the method described by Minami and Yoshikawa (29).\n\nBODY.MATERIALS AND METHODS.MORPHOLOGICAL STUDY OF THE AORTA:\nFor evaluation of aortic atherosclerotic lesions by light microscopy, frozen sections of 10 μm thickness were taken from the region of the proximal aorta. The extent of atherosclerosis was visually assessed after cutting the frozen sections at a size of 8–10 mm, fixing them in formalin, briefly washing them with running tap water for 1–10 mins and rinsing with 60% isopropanol prior to staining the sections with Oil Red O (3 mg/ml Oil Red O in 60% acetone and 40% water; Sigma-Aldrich). The samples were then counterstained with hematoxylin and the samples were examined under a light microscope (Olympus BX40, Olympus, Tokyo, Japan).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nData are expressed as the mean ± standard deviation (SD). Univariate statistical analysis was performed using the Student's t-test and Bonferroni's multiple comparison test (Statistical Software Package SPSS®, version 13, SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS.SERUM GLUCOSE:\nThe addition of flaxseed or/and vitamin E to the high-fat diet led to significant reductions of serum glucose levels compared with those in the DM group (Table II).\n\nBODY.RESULTS.SERUM LIPID PROFILE PARAMETERS:\nDiabetes resulted in significant increases in the serum concentrations of TC, TG and non-HDL-C, and a significant reduction of HDL-C concentrations compared with those in the control group. Flaxseed supplementation significantly decreased serum TC and non-HDL-C levels and increased HDL-C levels (Table II) compared with those in the unsupplemented DM group. The addition of vitamin E to the flaxseed-rich diet significantly decreased TC, non-HDL-C and TG levels but did not improved the HDL-C level in diabetic hamsters.\n\nBODY.RESULTS.CHOLESTEROL CONTENT OF THE AORTA:\nAortic cholesterol contents were significantly increased in the DM group fed with a standard diet compared with those in the control group (Table II). Flaxseed or/and vitamin E supplementation of the diet significantly decreased the aortic cholesterol content in the hamsters with DM (Table II).\n\nBODY.RESULTS.PARAMETERS OF OXIDATIVE STRESS:\nThe main findings are summarized in Table III. Serum and liver TBARS, as indices of lipid peroxidation, were significantly increased in the DM group compared with those in the control group, while the addition of flaxseed or a combination of flaxseed and α-tocopherol to the high-fat diet of the hamsters with DM significantly decreased these two markers compared with those in the unsupplemented DM group. Liver GSH levels were significantly diminished in the DM group compared with those in the control group. Flaxseed, α-tocopherol and their combination added to the high-fat diet significantly increased the liver GSH levels in the diabetic hamsters. The increased in liver GSH content was significantly higher in the DM + Flax + E group compared with that in the DM + Flax group. No significant differences of SOD activity in the liver were identified between groups.\n\nBODY.RESULTS.HISTOLOGICAL CHANGES IN AORTIC TISSUES.CONTROL GROUP:\nThe histologic examination of aortal fragments with O-Rd staining revealed discrete thickening of the aortic intimal layer (Fig. 1A).\n\nBODY.RESULTS.HISTOLOGICAL CHANGES IN AORTIC TISSUES.DIABETIC GROUPS:\nThe histologic examination of aortic fragments with O-Rd staining from diabetic hamsters revealed morphologic changes specific to diabetic macroangiopathy (Fig. 1B). Intimal thickening, endothelial discontinuities, lipid drops in the subintimal space, and alterations to the middle layer of the arterial wall were observed. The addition of flaxseed and/or vitamin E to the high-fat diet in diabetic hamsters improved the histological aspects of aortic atherosclerosis described in the diabetic hamsters fed an unsupplemented diet. The aortal tissue in the supplemented groups was characterized by slightly swollen endothelium, with moderate intimal thickening and moderate lipid infiltration of the intima (Fig. 2).\n\nBODY.DISCUSSION:\nIn DM, oxidative stress occurs, primarily due to the increased production of oxygen free radicals and/or a reduction in the antioxidant defense. Numerous studies have demonstrated that an increase in oxidative stress is implicated in the pathogenesis and progression of diabetic vascular lesions (1,4,6). In the present study, the antioxidative and antiatherosclerotic effects of supplementation with flaxseed (15 g Linum usitatissimum/100 g food), α-tocopherol (40 mg α-tocopherol/100 g food), and their combination were investigated in an animal model that replicates human atherosclerotic lesions. Golden Syrian hamsters appear more predisposed to develop atherosclerotic lesions than rats (30), and present many similarities with the lipoprotein metabolism in humans (31). In hamsters, a 15% flaxseed-supplemented diet is similar in energetic load to the 40 g/day dosage used in human trials. In humans, high doses of 40–50 g flaxseed/day, which corresponds to ~10% of total energy intake have been used in trials (32). In the present study, it was hypothesized that adding vitamin E to the flaxseed diet would lead to improved results for oxidative stress and the prevention of atherosclerotic lesions as there is evidence that the consumption of flaxseed reduces vitamin E (19), and only vitamin E supplementation is able to restore the plasma concentration (20). The present study demonstrated that all three diets (flaxseed, α-tocopherol or their combination) had an antiatherogenic effect in diabetic hamsters, suggested by the prevention of histological lesions (reduced intimal lipid infiltration and discrete alterations to the middle layer of the arterial wall) and by the decreased aortic cholesterol content in supplemented diabetic hamsters compared with those in the unsupplemented diabetic group. The antiatherogenic mechanism of the diets used in our experiment may be associated with changes in metabolic parameters, particularly in glucose concentrations and the lipid profile, and oxidative stress. Flaxseed, α-tocopherol, and the combination of flaxseed and α-tocopherol added to the high-fat diet resulted in similar reductions in serum lipid peroxidation in the diabetic hamsters. Liver lipid peroxidation was significantly diminished by supplementation of the diet by flaxseed alone or in combination with α-tocopherol, but not by α-tocopherol supplementation alone. Moreover, all three diets increased the liver GSH content and the highest concentrations were obtained with the combined diet. These results suggest that the higher antioxidant effects of flaxseed plus vitamin E are due to their synergic antioxidant actions. Flaxseed is the richest source of the lignan SDG. SDG isolated from flaxseed has oxygen radical-scavenging properties that have been demonstrated in vitro by direct hydroxyl radical-scavenging activity (18) or by inhibition of lipid peroxidation (16). Vitamin E is known as a major antioxidant in the cellular antioxidant defense system, which acts by interrupting the propagation of free radical chain reactions. The effect of vitamin E against the prooxidant status associated with DM has been demonstrated by the suppression of diabetes-induced increases in ROS and diminishment of lipid peroxidation (33,34). The synergistic effect of flaxseed oil and vitamin E on oxidative stress has also been observed by Deng et al (35) in male Wistar rats fed a high-fat diet. Similar to the findings of previous studies (36), the diabetic hamsters had higher serum concentrations of serum glucose, TC, TG and non-HDL-C, and lower HDL-C concentrations compared with the control group. The addition of flaxseed, α-tocopherol or their combination to the high-fat diet reduced serum concentrations of glucose, TC and non-HDL in diabetic male hamsters (37,38). The hypocholesterolemic effects of flaxseed may be attributed to ALA, lignans (SDG) or the fiber content (39). In agreement with other studies (40), vitamin E significantly reduced serum TG levels in diabetic hamsters fed an atherogenic diet. In the present study, the addition of vitamin E alone or in combination with flaxseed to the high-fat diet resulted in lower serum concentrations of TC, non-HDL and TG but failed to correct the HDL-C concentrations in diabetic hamsters. Another study has reported that in hamsters with experimental STZ-induced DM fed high a saturated fat and cholesterol diet, supplementation with α-tocopherol increased TC and did not change HDL-C (40). The results of the present study suggest that the antiatherogenic effect of flaxseed, α-tocopherol and their combination added to a high-fat diet in diabetic hamsters is based primarily on the antioxidative role of these components. The improvement of serum glucose and non-HDL were evident and could contribute to the prevention of diabetic macroangiopathy. The antioxidant effect of flaxseed was similar to that of α-tocopherol in diabetic hamsters fed a high-fat diet and the combined diet (Flax + E) did not seem to confer more benefits than flaxseed alone. Moreover, the high dose of ground flaxseed alone may have a better cardioprotective effect than α-tocopherol in diabetic hamsters due to the reduction of TC and non-HDL levels and increase in HDL-C levels. Oxidative stress has been proposed as a pathogenic mechanism of diabetic macrovascular complications, and dietary strategies that ameliorate oxidative stress may represent a promising approach to the prevention of atherosclerosis. The flaxseed-enriched diet may regulate the generation of reactive oxygen species and the metabolism of glucose and lipids, and could consequently play a role in the prevention of major cardiovascular complications in diabetic states. Ground flaxseed combined with α-tocopherol does not appear to confer a clear advantage compared with flaxseed alone in the reduction of oxidative stress and vascular lesion formation in experimental diabetes.\n\nQuestion: Compared to received a high-fat diet (40% energy as fat), deficient in ?-linolenic acid (ALA) what was the result of high-fat diet enriched with ground flaxseed 15 g/100 g of food, rich in ALA; or enriched with vitamin E, 40 mg ?-tocopherol/100 g of food on serum glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
1208	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Social Markers of Mild Cognitive Impairment: Proportion of Word Counts in Free Conversational Speech\n\n ABSTRACT:\n\nBackground: Detecting early signs of Alzheimer's disease (AD) and mild cognitive impairment (MCI) during the pre-symptomatic phase is becoming increasingly important for cost-effective clinical trials and also for deriving maximum benefit from currently available treatment strategies. However, distinguishing early signs of MCI from normal cognitive aging is difficult. Biomarkers have been extensively examined as early indicators of the pathological process for AD, but assessing these biomarkers is expensive and challenging to apply widely among pre-symptomatic community dwelling older adults. Here we propose assessment of social markers, which could provide an alternative or complementary and ecologically valid strategy for identifying the pre-symptomatic phase leading to MCI and AD. Methods: The data came from a larger randomized controlled clinical trial (RCT), where we examined whether daily conversational interactions using remote video telecommunications software could improve cognitive functions of older adult participants. We assessed the proportion of words generated by participants out of total words produced by both participants and staff interviewers using transcribed conversations during the intervention trial as an indicator of how two people (participants and interviewers) interact with each other in one-on-one conversations. We examined whether the proportion differed between those with intact cognition and MCI, using first, generalized estimating equations with the proportion as outcome, and second, logistic regression models with cognitive status as outcome in order to estimate the area under ROC curve (ROC AUC). Results: Compared to those with normal cognitive function, MCI participants generated a greater proportion of words out of the total number of words during the timed conversation sessions (p=0.01). This difference remained after controlling for participant age, gender, interviewer and time of assessment (p=0.03). The logistic regression models showed the ROC AUC of identifying MCI (vs. normals) was 0.71 (95% Confidence Interval: 0.54 – 0.89) when average proportion of word counts spoken by subjects was included univariately into the model. Conclusion: An ecologically valid social marker such as the proportion of spoken words produced during spontaneous conversations may be sensitive to transitions from normal cognition to MCI.\n\nBODY.INTRODUCTION:\nHigh value is given to detecting early signs indicating the transition from normal cognitive aging to Mild Cognitive Impairment (MCI) when early intervention and treatment against Alzheimer's disease (AD) could be most effective. However, it is difficult to distinguish early signs of MCI from normal cognitive aging. Although biomarkers such as CSF beta-amyloid, tau and neuroimaging markers have been extensively examined as early indicators of the pathological process for AD, assessing these biomarkers is expensive and challenging to apply widely among pre-symptomatic older adults. Social behavioral markers (which we propose to call \"social markers\", a subset of behavioral biomarkers) offer a cost-effective alternative or complementary tool for detection of the transition from normal cognition to MCI in community dwelling older adults. One area of research that has been receiving a lot of attention is assessment of speech characteristics. Recent rapid technological advancement in the area of social interactions research could potentially serve to facilitate the identification of easily measured aspects of conversation that could reflect early cognitive changes in at risk older adults. This includes social network analysis at the macro level (e.g., who contacts whom and how this network pattern or structural network size changes as individuals transit from normal cognition to MCI) and analysis of spoken language at the micro level [1-4]. The present study is a part of a larger randomized controlled clinical trial (RCT) that assessed whether frequent conversations via webcam and Internet-enabled personal computers could improve cognitive function in older persons with either normal cognition or MCI (ClinicalTirals.gov registration number: NCT01571427). The study protocol and the results has been described in detail elsewhere [5, 6]. Briefly, in the larger intervention trial, social interaction sessions were conducted using semi-structured conversations with trained interviewers for 30~35 minutes a day, 5 days a week for 6 weeks (i.e., 30 sessions) among the intervention group. The intervention group also completed a weekly Internet survey that assessed social engagement activities during the previous week, while the control group was contacted by phone to complete the same weekly survey. This weekly telephone call was the only contact the control group had through the trial. Our primary outcome was to assess changes in cognitive functions measured by neuropsychological tests and our secondary outcome was to assess changes in psychological well-being. The trial showed that adherence to the protocol among the intervention group was high (89%; range, 77%-100%). At the post-trial assessment, the normal cognition group assigned to the intervention improved on tests of language-based executive function (e.g., verbal fluency category) compared to normal controls [5]. During the trial, it came to our attention that interviewers had more difficulty changing conversation topics or ending conversation sessions with some participants. Given that one of our aims of the trial was to standardize the interviews across interviewers, we decided to further investigate the observed variability in conversational flow in this follow-up study. Our hypothesis was that MCI individuals would have an impaired ability to identify social cues required for smooth interactions and would have difficulty taking turns in conversation (e.g., keep talking until being interrupted by interviewers). Previous research indicates that executive functioning underlies many everyday activities that are difficult for individuals with MCI [7]. MCI older adults may not self-monitor conversational content well as compared to cognitively intact older adults. This could result in a larger proportion of words produced by participants (as opposed to the interviewers) during timed conversational sessions among the MCI older adults. Analyses of proportion of words would be a potentially useful and ecologically valid social marker that could be incorporated with other daily markers of everyday cognitive activity such as daily computer usage [8], walking speed and its variability [9], medication adherence [10, 11] time out of house [12] and others associated with early cognitive change that can be monitored over time by using passive and unobtrusive in-home sensing technologies [13]. In the present study, we compared the proportion of total word counts produced by participants among MCI and cognitively intact participants using the recorded conversations from the larger social engagement RCT noted above [5].\n\nBODY.METHODS.PARTICIPANTS:\nEighty-three older adults aged 70 years and older were enrolled and randomized into the intervention and control groups; mean age, 80.5 years and 76% female [5]. The original prevention study's inclusion and exclusion criteria are listed in Table 1. Out of forty-one participants assigned to the intervention group, 33 consented to allow their daily conversational intervention sessions to be transcribed for speech characteristics analyses (n=21 cognitively intact defined as Clinical Dementia Rating (CDR) [14]=0; n=12, MCI defined as CDR=0.5). Additionally, eight subjects (n=6 cognitively intact, n=2 MCI) recruited during a pilot-testing study who went through the same intervention protocol also consented and were included in this study, generating a total of 41 subjects reported here. As described above, the intervention group engaged in 30 to 35 minute semi-structured conversation sessions daily except weekends for six weeks with trained interviewers using Internet connected personal computers with a webcam.\n\nBODY.METHODS.CONVERSATION SESSION FORMAT:\nIn order to take full advantage of a synthetic conversational format, we placed an emphasis on spontaneous responses rather than structured answers (i.e., the participants had to organize their thoughts). We used unstructured conversations such as talking about participants' \"childhood memories\", \"hobbies\", \"siblings and parents\", and \"movies/books\" [5] in addition to conversations generated by showing a daily picture stimuli (e.g., what is happening in this photo and where do you think it was taken?) and story generations (e.g., daily alphabetical conversation: tell me a story about apples, alligators, or alumni). These daily prompts were used uniformly for each session. We randomly selected one recorded session each from the baseline, the 3rd and 6th week of the trial, i.e., three sessions per participant. A single transcriber manually transcribed the conversations to extract word counts spoken by interviewers versus participants. This measure was implemented as one of the strategies to standardize the quality of interviews across interviewers, i.e. that one interviewer did not speak more than the others. Three interviewers were used in this trial. Each interviewer was assigned to talk with a specific participant during the 6 week trial. We assigned MCI and normal participants equally to each interviewer although interviewers were blind to the cognitive status (MCI vs. normal) of participants.\n\nBODY.METHODS.NEUROPSYCHOLOGICAL TESTS:\nIn the original prevention study, pre- and post- trial changes in neuropsychological test scores were primary outcomes. In the current study, we examined the correlation between proportion of words spoken by participants and cognitive functions using the neuropsychological test scores at baseline. The cognitive tests (and cognitive domains they tap) used are as follows:(1) Immediate Memory: the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) Word List Learning [15]; (2) Delayed Memory: CERAD Word List Delayed Recall [15]; (3) Language: composite of verbal fluency for letters (F, A and S) [16]; (4) Psychomotor Speed: Trail Making A [17]; (5) Executive function: Trail Making B [17] and verbal fluency for category animals [16]; (6) Selective Attention/inhibition: Stroop test [16]; and (7) Pre-morbid and general intelligence: Wide Range Achievement Test-Revised (WRAT-R) [18].\n\nBODY.METHODS.STATISTICAL ANALYSES:\nThe proportion of words spoken by participants (out of total word counts in each trial session) was assessed. Student's t-test and Wilcoxon rank sum test were used to examine the differences in baseline characteristics and the relative proportion of words spoken between MCI and cognitively intact participants. Chi-square and Fisher's exact tests were used for categorical variables. We first assessed the spearman's correlation coefficients between the proportion of words spoken by participants and neuropsychological tests and demographic variables. Next, the relationship between cognitive status (MCI vs. intact) and the proportion of words spoken by participants was analyzed using a multivariate generalized estimating equation (GEE) model in order to account for multiple observations per subject. In the GEE model, participant age, gender, years of education, interviewer (creating 2 dummy variables distinguishing 3 interviewers) and assessment time point (creating 2 dummy variables indicating 3rd and 6th week of assessment, respectively) were included in the model. The assessment time point was included to examine if the interview order (baseline, week 3, week 6) showed any systematic differences. Second, we generated a logistic regression model using cognitive status as the outcome and proportion of word counts averaged over the three sessions as the predictor. We examined the Receiver Operating Characteristics Area under the Curve (ROC AUC) of distinguishing MCI subjects from those with intact cognition byproportion of word counts spoken by participants. Goodness of fits in GEE models and logistic regression models were examined through visual inspection of residuals and Hosmer-Lemeshow test, respectively. SAS 9.4 (Cary, NC, USA) was used for the analyses.\n\nBODY.RESULTS:\nBaseline characteristics of the 41 participants are listed in Table 2. Mean Mini-Mental State Examination (MMSE) [19] score at baseline was 26.9 (SD 2.1) among those with MCI; and 28.7 (SD 1.3) among those with normal cognition (p < .01). Category fluency test (semantic fluency, p=0.08) and letter fluency test (phonetic fluency, p=0.31) and stroop test scores (executive function/inhibition, p=0.07) were not significantly different between those with intact cognition and MCI, but other tests were. As for correlations, higher average proportion of words spoken by participants was correlated with older age (p=0.04) and fewer years of education (p=0.04). Among neuropsychological tests, MMSE (global cognition, p=0.02), word-list acquisition (learning, p=0.02) and stroop scores (executive function/inhibition, p=0.02) were negatively correlated with proportion of words spoken by participants. The average proportion of words spoken by participants across the 3 assessment time points was different between the groups (p=0.01) with 68.3% (SD 9.3) among those with MCI and 60.0% (SD 9.3) among cognitively intact. GEE analysis showed that those with MCI have about 6% higher proportion of word counts in a conversational session compared to those with intact cognition (Table 3). Older age (p=0.03) was also associated with higher proportion of word counts. There was no significant difference among assessment time points, although MCI subjects had a tendency of showing lower proportion of word counts at the 3rd and 6th week compared with baseline (i.e., more resembled to those observed among the normal, not in Table). Subjects interviewed by interviewer 2 talked significantly more (p<0.001), compared to those interviewed by interviewer 1, suggesting that Interviewer 2 could be more effective in getting the participants to talk, although we trained each interviewer extensively to standardize interviewer skills [5]. The logistic regression models showed the ROC AUC of identifying MCI (vs. normals) was 0.71 (95% Confidence Interval: 0.54 – 0.89, Odds Ratio for the proportion of word counts = 1.12, p=0.02) when average proportion of word counts spoken by subjects was included univariately into the model. Adding age and education in the model further improved the ROC AUC to 0.84 (95% Confidence Interval: 0.69 – 0.99).\n\nBODY.DISCUSSION:\nHolding conversations involves a synthesis of social and cognitive functions; a person is required to actively construct a representation of what another person is thinking or feeling, what that person believes, what they desire, and what their perspective is on topics and ideas [20, 21]. All of this \"social cognition\" requires remembering what was said a few seconds or minutes before, planning and organizing one's next thoughts, keeping track of the conversation, iterating and updating the interaction, as well asself-monitoring in order to take turns, not interrupt, understand another's feelings and inhibit inappropriate behaviors. Thus, at various times, attention, executive function, inhibition, abstract reasoning, memory and language abilities are simultaneously engaged. We compared proportion of word counts generated by participants out of total word counts, rather than comparing the word counts per se because our interest was in how two people (participants and interviewers) interact with each other in one-on-one conversations and in order to control for total duration of conversational sessions. We found that MCI participants spoke a greater proportion of words during the timed remote video telecommunication conversational sessions than those with normal cognitive function. Past research has examined the complexity, content and acoustic features of spoken language as an indicator of aging or cognitive status by using answers to neuropsychological tests or to specific tasks (e.g., ask subjects to reada paragraph, speech provided in press conferences) [2, 22, 23] To our knowledge, this is the first study attempting to examine interactions between two peoplein a one-on-one conversational setting using the proportion of word counts of MCI in comparison with normal participants. Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) data, discriminatory ability (indicated by the area under the cure (AUC) of the receiver operator curve (ROC)) of biomarkers together with age and gender information in distinguishing MCI from the normal has been reported to range from 0.68 (hippocampal volume, age and gender in the model) to 0.77 (CSF Aβ42, CSF tau, sex and age in the model) [24].Others have found somewhat higher AUC values ranging from 0.70 to 0.96 for fluid biomarkers which may relate to differing methods or characteristics of the samples studied [25-27]. The ROC AUCs in our study using word counts (0.71 with the proportion of word counts alone and 0.84 with the word counts, age and education information) were comparable to many of the currently used biomarkers in the field. Thus we highlight that using the quantitative behavioral biomarker of word counts is particularly promising as an approach to identify populations at risk for decline or to track response to therapies, especially considering that the data collection can be done at home, and does not require invasive or expensive biomarker assessments. Neuropsychological criteria used to define MCI [28] includes objective evidence of impairment on at least two tests within four or more cognitive domains, with scores falling at least 1 standard deviation (SD) or more below age-stratified normative data. The language domain is commonly measured by tests such as the Boston Naming Test [29], letter fluency(phonemic fluency) and category fluency tests (semantic fluency) [16]. In Alzheimer's disease (AD), category fluency has generally been found to be disproportionately impaired, whereas letter fluency ability is less impaired [30, 31], although not all studies agree with this finding [32]. It is hypothesized that the disproportionate impairment in semantic fluency, as opposed to phonemic fluency, could occur because the former relies more on temporal-lobe semantic stores, the area which is affected by AD. Our finding that participants with MCI (the prodromal stage of AD) spoke a higher proportion of word counts in free conversations may be reflecting their subtle decline in semantic fluency abilities. Patients with dementia are known to have high incidence of circumlocutions (i.e., the use of many words where fewer would do) and semantic jargon in their spontaneous speech [33]. We found a somewhat larger difference between MCI and normal groups on a semantic fluency test (p=0.08) than on a phonemic fluency test (p=0.31), although neither difference was statistically significant, likely due to small sample size. Possibly MCI participants may tend to struggle to find the right words and therefore may be more likely to need to substitute words in the conversation to convey their thoughts, especially in the early stage of MCI when phonemic fluency is still preserved, leading to increased proportion of word counts in timed conversations. It is noteworthy that in our study the differences insemantic and phonemic test scores between the MCI participants and those with intact cognition were not significant, while the proportion of words spoken by participants showed a significant difference between the two groups. The latter measure may be more sensitive to cognitive decline than traditional neuropsychological tests and may identify early stage MCI before impairment becomes symptomatic through neuropsychological tests. There are other possible underlying mechanisms that may explain the disproportionate proportion of words contributed to a conversation by MCI participants. Increased word counts among MCI individuals may be due to subtle difficulties with the executive and self-monitoring aspects of conversation. Also MCI participants could have reduced passage-of-time estimation abilities relative to those with normal cognitive function. Thus those with MCI would not be able to anticipate and prepare for the end of the sessions. However, there is some evidence that time estimation is not affected in MCI, although it is associated with aging [34]. There is some evidence that MCI participants may acquire deficits in social cognition such as the ability to make inferences about the cognitive state, emotions and intentions of other people [35, 36]. Misreading of social cues and intent during social exchanges could result in more discursive conversation among MCI participants. Epidemiological evidence suggests that tracking changes in linguistic features may be a promising tool in identifying early signs of AD. The Nun Study found a link between linguistic density (e.g., complexity, vivacity, fluency) in early life (most were in their 20s) and the risk of developing Alzheimer's disease later on, by examining autobiographical essays written by the nuns upon joining the Sisterhood [37]. Other studies also suggest that subtle language impairment occurs long before an MCI diagnosis or at a very early stage of MCI. For example, Oulhaji et al., [38] showed that using the CAMCOG (the Cambridge Cognitive Examination), verbal expression and learning scores at baseline, conducted about 20 years beforehand, were the most significant predictors of incident MCI. Amieva et al., [39] showed that low category fluency test scores can be seen nine years before the clinical diagnosis of Alzheimer's disease. Recent MRI studies have found associations between the size and complexity of real-world social networks and the density of grey matter [3] and amygdala volume [40], providing some support for a link between biomarkers (such as brain structure) and social network size, an indirect measure of how well subjects communicate with others. Research is increasingly focused on identifying AD at the MCI stage, or even earlier, in order to prompt interventions and to access clinical trials with disease-modifying drugs [41]. Clearly, higher-order functional activities have been shown to distinguish those at risk of developing MCI from those remaining cognitively normal [42-44]. Studies utilizing continuous, unobtrusively monitored in-home activity data in a community setting also showed that these ecologically valid activity measures could identify early changes among those who convert to MCI [13]. We have been following seniors at their home over 4 years recording their in-home activities unobtrusively, including decline in computer use at home [8], changes in in-home walking speed and variability [9], and time out of house as an indicator of the amount of social interactions. Current information analysis science can provide objective assessments of the nature of social interactions through the examination of speech characteristics, including sentence complexity, verbal fluency, vocabulary, and acoustic features including affect which was not possible a decade ago [1, 2]. It will take some time to realize the assessment of speech characteristics including developing automatized algorithms to protect privacy, developing a reliable way of recording conversations, storing or transmitting the recorded data for analysis. However, the assessment protocol could be implemented as one of the in-home monitored activities to enhance the prediction of those at-risk of cognitive impairment in communities in the future. The results presented in this report, together with the past observational studies mentioned above, suggest that examining the way older adults interact with each other in conversation could facilitate the development of powerful tools for identifying early signs of MCI in community dwelling older adults. Further studies are required to validate our findings and to create practical applications of assessment protocols. There were some limitations to this study. The sample size was relatively small. Participants were volunteers interested in participating in a behavioral intervention trial and this might limit the generalize ability of the results. The conversation session format used in this study was a remote telecommunications video chat between participants at their home and trained interviewers at the study site. Video chat conversational format differs in some ways from face to face conversation. However, we paid special attention to creating a user-friendly environment, including touch-screen monitors, which eliminated mouse use when receiving calls, a large monitor that allowed eye-to-eye contact during in-person conversations in order to retain attention during the session, and pop-up pictures on the screen to evoke conversations without any effort by the participants. Additionally, previous studies have shown that remote telehealth communication formats can be effective for a variety of assessments and interventions with older adults [45].\n\nBODY.CONCLUSION:\nAn ecologically valid social marker such as the proportion of spoken words produced during free conversation may be sensitive to transitions from normal cognition to MCI and may be able to detect the transitions before any changes in conventional cognitive tests. It could complement biomarker studies in selecting or identifying at-risk participants during their pre-symptomatic phase. Examinations of interactions among subjects in free conversational speech could provide an additional area of research useful for the early identification of MCI.\n\nQuestion: Compared to healthy what was the result of mild cognitive impairment (MCI) on proportion of words out of the total number of words?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased
1210	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: The display effects of patients’ self-assessment on traumatic acute pain on the proportion and timing of analgesics administration in the emergency department\n\n ABSTRACT.BACKGROUND:\nAcute pain assessment in the emergency department (ED) is important in particular during the triage process. Early pain assessment and management improve outcome. The objective of this study was to determine the effects of documentation and display of patient's self-assessment of pain using numerical rating scale (NRS) on analgesic use among adult trauma patients in ED.\n\nABSTRACT.METHODS:\nA randomized control trial was conducted recruiting 216 trauma patients who presented to ED of two tertiary centers. Pain score was done using NRS for all patients. They were randomized into pain score display group or not displayed in the control. The outcome measured were proportion of patients receiving analgesics and timing from triage to analgesic administration.\n\nABSTRACT.RESULTS:\nThe proportion of patients who received analgesics when pain score was displayed was 6.5% more than when pain score was not displayed. This difference was however not statistically significant. However, stratified categorical analysis using chi-square showed that the displayed severe pain group was 1.3 times more likely to receive analgesics compared to the non-displayed group. The mean timing to analgesic administration for the displayed and non-displayed groups were 81.3 ± 41.2 (95% C.I 65.9, 96.7) and 88.7 ± 45.4 (95% C.I 69.0, 108.3), respectively (p > 0.05).\n\nABSTRACT.CONCLUSIONS:\nThe proportion of patients who received analgesics increased when NRS was displayed. However, the pain display has no significant effect on the timing of analgesics.\n\nBODY.1 BACKGROUND:\nThe usual scenario in the emergency department (ED) is an overworked doctor, carefully putting history together, examination, and investigations, to arrive at a diagnosis. This is often done with much time constraints and poor attention paid to acute pain management. However, a physician's primary duty is to comfort, manage, and reduce the suffering of patients. This study attempted to address this contradiction, by introducing a simple intervention in the ED. This is an effort to evaluate the effect of displaying pain score, without any other intervention, on analgesic use. As pain score is recommended as a vital sign in many international protocols, it is in a way asking if we can improve acute pain management if we implement the pain score display at triaging in the ED.\n\nBODY.2 OBJECTIVES:\nThe main aim of this study is to determine the effect of documentation and display of patient self-assessment of pain using numerical rating scale (NRS) on analgesic administration. Specifically, we are looking into the effects of numerical pain score display on the proportion of patients receiving analgesics and the timing of analgesic use.\n\nBODY.3 METHODS:\nThis was a cross-sectional randomization study in the ED of two tertiary teaching hospitals with an average annual patient attendance of 140,000. This study was granted ethical approval by the research and ethical committee of the institution. The following were the inclusion criteria: (a) Adult ≥ 20 years old (b) Patients complaining of acute pain secondary to trauma (c) Patients triaged to non-critical zone only (d) GCS 15/15 The following were the exclusion criteria: (a) Patients with language barrier (b) Patients who were intoxicated (c) Patients with altered mental status or psychiatric illness (d) Patient under police custody (e) Patients with potentially life-threatening diseases or injuries (f) Non-traumatic causes of acute pain Patients were carefully selected among whom who have likelihood of presenting with significant acute pain secondary to trauma, while avoiding interference with evaluation and care of patients with potentially life-threatening illness or injury. All patients attending the ED would be triaged by a triage officer at the entrance of the department. Critical patients would be admitted to the resuscitation bay immediately after the triage decision had been made. The semi-critical and non-critical patients would be triaged further including the pain scoring assessment. Acute pain assessment by using NRS is a part of a vital sign monitoring parameter included into the triage protocol of the department. Patients would be given analgesics at the triage counter if they presented with moderate to severe pain. Patients would be up-triaged and admitted to the treatment cubicle if they developed worsening of pain while waiting to be seen by doctors. Only patients who were able to give consent and had a clear mind to understand and do pain assessment were included in the study. Randomization was done prior to selection of patients. Patients were assigned to display pain score and non-display pain score groups, using a computer-generated randomization method, in blocks of four. These randomized selections were sealed in opaque brown, non-transparent, numbered envelop and arranged in ascending order. The envelopes were opened only after pain assessment was done and documented by researcher. The researcher and the triage officer were blinded to the randomization while doing the pain score and initial data collection. This was important to avoid bias when pain score was being performed. Verbal consent was obtained from each patient. The sample size was calculated by using the following parameters:(1)Po=0.5(2)Pi=0.3where α = 0.05 (95% CI), study power = 0.8 (80% ), two proportion samples Po = 0.5 and Pi = 0.3, and M = 1. The sample size required were 220 patients (110 per arm) including the 10% dropout.\n\nBODY.3 METHODS.3.1 DATA COLLECTION:\nThe NRS was used as the pain scale assessment tool as this has been assessed as the best tool to be used among trauma patients in the ED. (Figure 1) [1]. A bold red marker pen was used to display the pain score. A yellow sticker measuring 10 × 7 cm was used to attach the pain score at the top right hand corner of the front cover of medical case notes. This pain score was displayed prominently in the patients' medical clerk sheet in one group and not displayed in another group. Figure 1Numerical rating scale (NRS). Pain assessment was done at triage after chief complaint and vital signs were assessed. This was done by the patients, without relying on physicians' impression. This is as suggested by the Canadian Association of Emergency Physicians (CAEP) consensus document on emergency pain management [2]. Instructions on how to do a pain score was explained to the patients by the researcher. Instruction was given by using local languages and dialects. Relatives were discouraged from translating or trying to answer for the patient. The numerical rating scale was shown to the patient. Patients were asked to give pain score value according to their own assessment of pain severity. They were excluded from the study if they did not understand the instructions after being repeated twice. The data was entered into the data collection form. Based on the previous study carried out by Silka et al., we decided that the NRS score of 7 to 10 is severe pain, NRS score of 4 to 6 is clinically significant moderate pain, and any score of 3 and below is mild pain. Data entry and analysis were done using Statistical Packages for Social Science (SPSS) version 12.0.1 software which was registered by the institution. Numerical pain score was converted to categorical variable. Chi-square test was used in the analysis of the differences of analgesic administration between the displayed pain score and not displayed pain score groups. The confounding effect of pain severity on this relationship was analyzed by using Mantel-Hanszel estimate. Timing to analgesics was presented as mean and analyzed by using ANOVA test. Statistical significance was considered at p value of less than 0.05. Data exploration was done using descriptive statistics and presented as charts and tables for each variable.\n\nBODY.4 RESULTS:\nThe number of patients who met all criteria was 216. Finally, there were 107 patients (50.5%) in the study group and 99 (49.5%) patients in the control group after exclusion due to various reasons. The general demographic data comparison between the two study groups is as shown in Table 1. There is no significant difference in the gender distribution, age group, education, mechanism of injury, and pain score between the study groups (p > 0.05). Majority of patients who presented with acute pain in this study group were in the range of 20 to 29 years of age (n = 99, 49.5%). The distribution of the pain score groupings in the displayed NRS group for the mild, moderate, and severe pain are 12.9% (n = 13), 46.5% (n = 47), and 40.6% (n = 41), respectively. Likewise, the distribution of the pain score groupings in the non-displayed NRS group for the mild, moderate, and severe pain are 17.2% (n = 17), 49.5% (n = 49), and 33.3% (n = 33), respectively. The proportion of patients who received parenteral analgesics for mild, moderate, and severe pain in displayed group was 7.7%, 21.7%, and 47.6%, respectively (p < 0.05). Likewise, there is an increment of proportion who received analgesics in the non-displayed group from 23.5% to 31.3% with increasing pain severity (p < 0.05). The proportion of patients who received analgesics when pain score was displayed was 6.5% more than when pain score was not displayed. This difference was however not statistically significant (p = 0.30) (Figure 2 and Table 2). Table 1 Demographic comparison between the study and control groups Variables Non-display (control) group ( n \n = 99) Display (trial) group ( n \n = 107) \n p \n value Age in years (mean) 35.6 38.6 0.639 Gender distribution ( n = Male or Female) Male = 70 (70.1%) Male = 73 (68.2%) 0.242 Female = 29 (29.2%) Female = 34 (31.8%) Education at minimum secondary school level 59 (59.6%) 64 (59.8%) 0.662 Mean (s.d) pain score (NRS) 5.7 (1.9) 6.1 (2.6) 0.300 Severe pain score (more than 7) ( n ) 33 (33.3%) 41 (38.3%) 0.492 Motor vehicle crash patients ( n ) 51 (51.5%) 42 (39.3%) 0.621 Patients received intravenous analgesics ( n ) 49 (49.5%) 58 (54.2%) 0.310 Figure 2Bar chart showing percentage of patients who received analgesics in trial versus control group. Table 2 Odd ratio of patients receiving analgesics Crude odd ratio Weighted odd ratio \n p \n value Displayed pain score × Receiving analgesics 1.396 0.30 Pain group a displayed pain score × Receiving analgesics 1.306 0.42 a Confounder effect of variable (confounder effect of pain severity on displayed pain score was analyzed using Mantel-Hanszel estimate). The mean timing (in minutes) to analgesic administration for the displayed and non-displayed groups were 81.3 ± 41.2 (95% C.I 65.9, 96.7) and 88.7 ± 45.4 (95% C.I 69.0, 108.3), respectively (p = 0.538). The distribution of timing of analgesics according to the severity of pain is as shown in Table 3. Table 3 Test results of analysis of timing to analgesics by displayed stratified Pain Score using ANOVA Display pain score Mean (minutes) Std. deviation 95% CI (upper, lower) Minimum Maximum Pain score 4 to 6 (displayed) 84.2 51.8 16.4, 47.2 20.0 190.0 Pain score 4 to 6 (not displayed) 89.6 40.4 55.8, 123.4 25.0 170.0 Pain score > 6 (displayed) 80.8 36.0 8.0, 63.9 20.0 165.0 Pain score > 6 (not displayed) 94.3 48.6 72.7, 96.3 25.0 174.0 p = 0.946. \n\nBODY.5 DISCUSSION:\nPainful suffering is neither a diagnosis nor a disease. Nevertheless, it is a condition experienced by patients posttrauma that needs to be attended to attentively. Over the last few years, there has been much progress in the understanding of the pathophysiology of pain and its effect on disease and healing. More importantly, evidence has emerged on the detrimental effect of neglecting pain on disease progression and patient recovery [3],[4]. There have been many attempts to introduce ways to improve pain management in the ED. Great steps to improving pain and suffering in a patient start with understanding what pain means to the patient. Pain is what the patient states it is. Physicians must respect this. A diverse spectrum of psychological, sociocultural, temporal, and situational variables affects how people perceive and express their pain [5],[6]. The patients' self-report is the most reliable indicator of the presence and intensity of pain. Health care professionals often fail to routinely assess and document pain. Physicians should trust the patients' subjective reports of pain unless there is evidence to the contrary [7],[8]. Few studies had shown the positive effects of pain score display on analgesic use in the ED. In a retrospective study by Nelson, the effect of introducing a mandated verbal numeric pain scale on the incidence and timing of analgesic administration in trauma and non-trauma patients in the ED was studied. Analgesic use increased from 25% to 36%, and analgesics were administered more rapidly after the scale was introduced [9],[10]. Considering the positive results shown by these studies, it was felt that a randomized control study to determine the effect of documentation and display of patient self-assessment of pain using NRS, on analgesic administration was an important move to increase the evidence of the importance of pain score as a fifth vital sign in triage. In this study, a detailed analysis of the three different pain score groups, minimal, moderate, and severe pain, has shown that with the increasing pain score, more patients received analgesics. This is more frequent in the displayed pain score group. In Silka's study in 2004, no patient who reported mild pain received analgesics, whereas 72% of patients with moderate to severe pain did receive analgesics. A similar study was done in 2004 by Thomas. That study used the visual analog scale (VAS), which was displayed at the patient's ED chart and placed at the head of the ED stretcher. The study by Thomas showed that 63% of patients in the group with graphical display of VAS score received analgesics compared to 58.7% in tabulation group and 55.7% in the control group [11],[12]. Our study has found that analgesic administration is significantly associated with increasing severity of pain. This study gives the benefit of knowing what the pain score was in all patients. In patients where pain score was not displayed, a significant proportion of patients with moderate and severe pain still received analgesics. This shows that there are other factors influencing the attending medical officer to prescribe analgesics. Clinical judgment, the doctors' own assessment of pain, seems to have played a significant role here. What can be concluded here is that more patients received analgesics with increasing severity of pain, whether the pain score was displayed or not. It is not only the awareness of a displayed pain score that increased the likelihood of analgesics but also the clinical judgment of the presence of pain is an important factor. However, in this study, the displayed pain score did not affect the timing to analgesics compared to when pain score was not displayed. The study by Silka also showed no difference in the timing to first analgesics when comparing those patients with or without VPS. Pain assessment using NRS at the time of triage and prominent display of the pain score in patient medical record did not alter the timeliness of analgesic administration. Time to analgesics has not been studied in the ED in this country previously as far as the author's awareness. There is no nationwide system currently in place to triage a patient with a high pain score to see the doctor earlier. There are also no guidelines to administer analgesics earlier in patients with high pain score, while they wait for doctors. These are the measures that could be introduced to reduce the time the patient is in pain while waiting for analgesic administration.\n\nBODY.5 DISCUSSION.5.1 LIMITATIONS:\nThe main limitation of this study is the practice of analgesic administration in the ED being influenced by the awareness that the study is going on. The presence of the researcher in the triage and the new sticky label on the medical case notes with the pain score developed the awareness that they were being monitored. Perhaps this created some pressure to give more analgesia than usual or otherwise. This inevitable Hawthorne effect was counterbalanced by the utilization of a control group. Notably, patients and physician were blinded to the study null hypothesis. Only patient factors that influenced pain score and analgesic administration were studied. Factors regarding the doctors' experience or knowledge of pain management were not analyzed. These factors could not be studied as there was a high turnover of doctors in the ED and many different doctors work for the three shifts. Other factors that may influence analgesic administration include the number of doctors on duty and the number of patients on the days of study or particular shift. If there were many patients and the doctors were very busy, they might ignore the pain score and try to work fast in their limited time per patient. The time of the day when the study was conducted may also affect the outcome. These were not considered in the study.\n\nBODY.6 CONCLUSIONS:\nThis study has determined the effect of documentation and display of patient self-assessment of pain using NRS on analgesic administration. The proportion of patients who received analgesics increased when NRS was displayed. However, the pain display has no significant effect on the timing of analgesics.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS’ CONTRIBUTIONS:\nNHR involved in the conception of the study and preparing the manuscript. CA involved in data collection and statistical analysis. Both authors read and approved the final manuscript.\n\nQuestion: Compared to not displayed in the control. what was the result of pain score display group on The mean timing to analgesic administration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
891	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Randomized Trial Comparing Esomeprazole and Rabeprazole in First-line Eradication Therapy for \n\n ABSTRACT.OBJECTIVE :\nCYP2C19 metabolic activity influences the efficacy of Helicobacter pylori eradication therapies comprising PPIs. Rabeprazole (RPZ) and esomeprazole (EPZ) are PPIs not extensively metabolized by CYP2C19. The aim of this study was to elucidate whether or not first-line triple therapies using RPZ or EPZ are equally effective in Japanese patients with different CYP2C19 genotypes. \n\nABSTRACT.METHODS :\nTwo-hundred patients infected with H. pylori were randomized to receive one of the following regimens: amoxicillin (750 mg), clarithromycin (200 mg), and either esomeprazole (20 mg) (EAC group) or rabeprazole (10 mg) (RAC group), twice a day for one week. The CYP2C19 polymorphisms were determined by polymerase chain reaction and the serum level of pepsinogens was measured. \n\nABSTRACT.RESULTS :\nThe eradication rates of the EAC and RAC regimens were 79.8% (95% confidential interval: 71.7-89.0%) and 74.7% (66.0-83.4%), respectively, in a per protocol (PP) analysis (p=0.488). The eradication rates of the EAC and RAC regimens were not significantly different between patients with the homo EM genotype (p=0.999) or hetero IM or PM genotypes (p=0.286). A lower PG I/II ratio was associated with lower eradication rates (p=0.025). \n\nABSTRACT.CONCLUSION :\nAlthough the eradication rate was less than 80%, the EAC and RAC regimens were equally effective in each CYP2C19 genotype group. The PG I/II ratio was associated with the results of EAC and RAC therapy in this series of patients. \n\nBODY.INTRODUCTION:\n\nHelicobacter pylori infection has been associated with gastro-duodenal and systematic diseases, and the eradication of H. pylori infection has been shown to reduce the risk of gastric cancer (1, 2). In 2014, the International Agency for Research on Cancer suggested that the eradication of H. pylori should be considered as a strategy for preventing gastric cancer (3). The Japanese health insurance system approved efforts to eradicate H. pylori for all infected patients to eliminate gastric cancer in 2013 (4), and the number of patients receiving eradication therapy is on the rise. Since the approval of H. pylori eradication in November 2000, first-line eradication therapy has consisted of one week of triple therapy with a proton pump inhibitor (PPI), amoxicillin (AMOX) and clarithromycin (CLA) (5). In this therapy, the role of the PPI is to achieve a high intragastric pH for acid-labile antibiotics. PPIs are known to stabilize AMOX in the gastric mucus and the eradication rates of regimens containing AMOX are affected by the dose of PPI (6). The effect of PPIs such as omeprazole (OPZ) or lansoprazole (LPZ) are affected by the metabolic activity of the hepatic enzyme, cytochrome P450 (CYP) 2C19 (7). Indeed, some previous reports have shown lower eradication rates of triple therapy with OPZ or LPZ in patients with wild-type CYP2C19 compared to that in patients with a mutated genotype (8, 9). In contrast, later PPIs such as rabeprazole (RPZ) and esomeprazole (EPZ) have less CYP2C19-mediated metabolism than OPZ or LPZ (10, 11), and a meta-analysis showed that EPZ and RPZ had higher eradication rates than LPZ or OPZ in the treatment of H. pylori infection (12). However, in Japan, the efficacy of triple therapy with RPZ or EPZ in association with CYP2C19 genetic polymorphism has never been compared in a prospective, randomized trial. In the present study, we conducted a prospective, open, randomized multi-center trial to elucidate whether or not triple therapies using RPZ or EPZ are equally effective in patients with different CYP2C19 genotypes. We also examined the association between several factors, including serum level of pepsinogens, and the results of triple therapy using EPZ or RPZ.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nPatients who received upper GI endoscopy at any of eight institutes in Aomori Prefecture were enrolled in the study from May through September 2014. The presence of H. pylori was confirmed with a rapid urease test, 13C-urea breath test (UBT), stool antigen test or serum or urine antibody. Patients who met any of the following criteria were excluded from the study: [1] age under 16 years or over 70 years; [2] received antibiotic and/or PPI treatment(s) within 2 weeks of study commencement; [3] active peptic ulcer(s); [4] a history of gastric surgery; [5] a history of H. pylori eradication therapy; or [6] suspected of having malignant disease(s). A total of 200 patients were registered and 1 patient in the RPZ group was excluded due to severe heart disease (Fig. 1). The characteristics of the patients who completed the study are shown in Table 1. All patients gave their written informed consent before receiving eradication therapy. Peripheral blood was obtained and leukocytes were used for the CYP2C19 genotype analysis. Genotyping procedures for identifying the CYP2C19 wild-type gene and two mutated alleles, CYP2C19m1 and CYP2C19m2, were performed by a PCR-restriction fragment length polymorphism (PCR-RFLP) method with allele-specific primers (13). Serum samples were stored at -20°C and the titer of IgG antibody to H. pylori was determined by an enzyme immunoassay (E-plate; Eiken, Tokyo, Japan) and the levels of pepsinogen (PG) I and PG II by a radioimmunoassay. Figure 1.Assignment of patients and subsequent study flow. The study enrolled 200 patients at 8 medical institutes in Aomori Prefecture. The patients were randomly assigned to either the EAC group (n=99) or the RAC group (n=100). Table 1. Characteristics of the Patients who Completed the Regimen. EAC RAC Total p value Number 94 95 189 Sex Men 43 (45.7) 47 (49.5) 90 (47.6) 0.663 Women 51 (54.3) 48 (50.5) 99 (52.4) Age (years) <40 8 ( 8.5) 7 ( 7.4) 15 ( 7.9) 0.800 ≥40 86 (91.5) 88 (92.6) 174 (92.1) Smoking Non 73 (77.7) 75 (78.9) 148 (78.3) 0.861 Current 21 (22.3) 20 (21.1) 41 (21.7) Drinking Non 43 (45.7) 46 (48.4) 89 (47.1) 0.771 Current 51 (54.3) 49 (51.6) 100 (52.9) PG I (ng/mL) <49.0 23 (24.2) 26 (27.7) 49 (25.9) 0.753 49.0≤<69.0 24 (25.3) 25 (26.6) 49 (25.9) 69.0≤<89.0 17 (17.9) 19 (20.2) 36 (19) 89.0< 31 (32.6) 24 (25.5) 55 (29.2) PG II (ng/mL) <15.0 17 (17.9) 26 (27.7) 43 (22.8) 0.270 15.0≤<23.0 29 (30.5) 30 (31.9) 59 (31.2) 23.0≤<31.0 19 (20.0) 18 (19.1) 37 (19.6) 31.0< 30 (31.6) 20 (21.3) 50 (26.4) PG I/II ratio <2.2 25 (26.3) 19 (20.2) 44 (23.3) 0.370 2.2≤<2.9 25 (26.3) 19 (20.2) 44 (23.3) 2.9≤<3.6 16 (16.8) 23 (24.5) 39 (20.6) 3.6< 29 (30.6) 33 (35.1) 62 (32.8) CYP2C19 homo EM 30 (31.9) 30 (31.6) 60 (31.7) hetero IM/PM 64 (68.1) 65 (68.4) 129 (68.3) 0.999 anti-Hp antibody <24 34 (36.2) 28 (29.5) 62 (32.8) 0.514 (U/mL) 24≤<46 29 (30.9) 36 (37.9) 65 (34.4) ≥46 31 (33.0) 31 (32.6) 62 (32.8) N, (%) \n\nBODY.MATERIALS AND METHODS.ERADICATION THERAPY:\nPatients were randomly assigned to one of the following eradication therapy groups: [1] EAC group: EPZ (20 mg) twice a day (bid), AMPC (750 mg) bid, and CLA (200 mg) bid for one week; or [2] RAC group: RPZ (10 mg) bid, AMPC (750 mg) bid, and CLA (200 mg) bid for one week. After completing the treatment, any PPIs and other anti-ulcer agents that might affect the viability of H. pylori or urease activity were not used. Eradication assessment using a UBT (14) or stool antigen test (15) was performed 6 (±2) weeks after the completion of eradication therapy. One patient in the RAC group could not complete the regimen due to severe itching. During the treatment, eruption was observed in three patients, loose stool was recorded in two patients, and one patient complained of a metallic taste. However, these patients completed their regimens. Five patients in the EAC group and four patients in the RAC group did not visit the hospital and dropped out.\n\nBODY.MATERIALS AND METHODS.ETHICS ASSIGNMENT:\nThe unit of randomization was the individual, and the allocation sequence was generated by an unaffiliated person at the Hirosaki University Hospital who was blinded to the details of the study. This study was approved by Hirosaki University Medical Ethics Committee and registered to UMIN Clinical Trials Registry (UMIN000014366).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nDifferences between the groups were compared using the χ2 test. A p value of <0.05 was considered significant.\n\nBODY.RESULTS:\nThe eradication rates of the EAC and RAC regimen groups were 79.8% [95% confidential interval (CI): 71.7-89.0%] and 74.7% (66.0-83.4%) for the per protocol (PP) analysis and 75.8% (67.4-84.2%) and 71.0% (62.1-79.9%) for the intention-to-treat (ITT) analysis, respectively (Fig. 2A). No significant differences were observed between the two regimens. Regarding the CYP2C19 genetic polymorphism status, 62 patients were assigned to the homozygous extensive metabolizer (homo EM) group, 102 patients with 1 mutation were assigned to the heterozygous intermediate metabolizer group (hetero IM), and 35 patients with 2 mutations were assigned to the poor metabolizer (PM) group. Fig. 2B shows the PP-based eradication rates in relation to the CYP2C19 polymorphism. The eradication rate of the EAC and RAC regimens in the homo EM patients was 73.3% (CI: 57.5-89.1%) and 76.7% (CI: 61.6-91.8%), respectively. In the hetero IM and PM patients, the eradication rate of the EAC regimen was 82.8% (73.6-92.0%), and that of the RAC regimen was 73.8% (63.1-84.5%). The eradication rates of the EAC and RAC regimen groups were not significantly different between the patients with homo EM genotype and those with hetero IM or PM genotype. The eradication rates of homo EM patients were not markedly different from those of the hetero IM or PM patients in the EAC (p=0.287) or RAC (p=0.999) regimen groups. Figure 2.(A) The eradication rates of EAC and RAC therapy by a per-protocol (PP) analysis or intention-to-treat analysis. (B) The eradication rates of EAC and RAC therapy by a PP analysis in patients with homo EM versus those with hetero IM or PM. Table 2 shows the association between the patients' characteristics and the results of eradication therapy in 189 patients who completed the protocol. No factors were associated with the results of eradication therapy. Table 3 shows the association between the serum pepsinogen levels and the results of eradication therapy. Although the levels of PG I and II were not significantly associated with the treatment results, the eradication rates tended to increase with an increasing PG I/II ratio (p=0.025). The eradication rate was 68.2% in the 44 patients with a PG I/II ratio lower than 2.2 and 84.2% in those with a PG I/II ratio higher than 2.9. Table 2. Patients’ Characteristics and the Results of Eradication Therapy. Eradication p value failure success Sex Men 19 (21.1) 71 (78.9) 0.729 Women 24 (24.2) 75 (75.8) Age (years) <40 4 (26.7) 11 (73.3) 0.749 ≥40 39 (22.4) 135 (77.6) Smoking Non 34 (23) 114 (77) 0.999 Current 9 (22) 32 (78) Drinking Non 17 (19.1) 72 (80.9) 0.299 Current 26 (26) 74 (74) CYP2C19 homo EM 15 (25) 45 (75) 0.710 Hetero IM+PM 28 (21.7) 101 (78.3) anti-Hp antibody <24 14 (22.6) 48 (77.4) 0.997 (U/mL) 24≤<46 15 (23.1) 50 (76.9) ≥46 14 (22.6) 48 (77.4) N, (%) Table 3. Level of Pepsinogens and the Results of Eradication Therapy. eradication p value success (N) failure (N) rate (%) PG I (ng/mL) <49.0 35 14 71.4 0.177 49.0≤<69.0 37 12 75.5 69.0≤<89.0 29 7 80.6 89.0< 45 10 81.8 PG II (ng/mL) <15.0 35 8 81.4 0.573 15.0≤<23.0 46 13 78.0 23.0≤<31.0 26 11 70.3 31.0< 39 11 78.0 PG I/II ratio <2.2 30 14 68.2 0.025 2.2≤<2.9 31 13 70.5 2.9≤<3.6 33 6 84.6 3.6< 52 10 83.9 \n\nBODY.DISCUSSION:\nEPZ has been the most popular PPI worldwide for more than 10 years. However, in Japan, the use of EPZ was only just approved in September 2011, and thus relatively few studies have examined the efficacy of EPZ in H. pylori eradication therapy compared with other PPIs in a Japanese population. The present study is the first prospective randomized study to compare the efficacy of EPZ and RPZ in first-line eradication therapy for H. pylori infection among Japanese patients with different CYP2C19 genotypes. Suppression of gastric acid is important for the eradication therapy of H. pylori infection (6, 16). Better eradication rates have been observed in PM patients undergoing PPI-based triple therapies using OPZ or LPZ than in EM patients (7, 8). Similarly, a recent meta-analysis showed that CYP2C19 loss-of-function variants are associated with increased H. pylori eradication rates in patients receiving these therapies (17). In this study, the eradication rates in EM patients were not significantly different from those in IM and PM patients receiving the EAC and RAC regimens. Therefore, the genotyping of CYP2C19 is not necessary for first-line eradication therapy when EPZ or RPZ are used with AMOX and CLA. However, even the highest eradication rate, which was observed in the IM and PM patients treated with EAC regimen, remained 82.8%. Generally, regimens with >90% eradication rate are recognized as effective (18). The results of this study indicate that 7-days of EAC and RAC regimens both had an insufficient effect without testing susceptibility to antibiotics. Indeed, the European guideline suggests that EAC and RAC regimens should last 10-14 days and PPIs should be administered at high dose (19). Furthermore, EAC and RAC regimens containing higher doses of EPZ or RPZ had higher eradication rates (20). To use EAC and RAC regimens as the first-line therapy, a longer duration and higher dose of EPZ or RPZ as well as testing for CLA resistance should be approved by the Japanese health insurance system. The most common cause of failure of first-line therapy is bacterial resistance to CLA (3). Determining CLA resistance is important for predicting the results of triple therapy. However, bacterial culture is not always available. Therefore, it would be useful to determine other factors associated with the results of first-line therapy using RPZ or EPZ. Recently, ABC classification for the risk of gastric cancer has been introduced by many health surveys (21). In this classification, patients are tested serum antibody to H. pylori with the serum levels of PGs. Therefore, information about the serum level of PGs is available for these patients before starting eradication therapy. The results of the present study showed that a lower PG I/II ratio was associated with failure of EAC or RAC therapy. Generally, low levels of PG I reflect mucosal atrophy of the gastric corpus, while higher levels of PG II reflect more severe gastric mucosal inflammation. The PG I/II ratio increases after successful eradication (22) and is usually high in patients not infected by H. pylori (23). Therefore, the present results suggest that failure of H. pylori eradication by EAC or RAC therapy might be more frequent in stomachs with advanced mucosal atrophy and persistent inflammation. However, a previous study showed that a low pepsinogen I/II ratio was associated with successful eradication in a different eradication regimen (24). Further studies are required to determine whether or not the serum level of PGs is associated with the results of eradication therapy and to elucidate whether or not alternative therapy is required for patients who have a lower level of PG I/II. The limitation of this study is the lack of information about bacterial susceptibility to antibiotics. As already mentioned, resistance to CLA is the most common cause for the failure of first-line therapy (5). However, bacterial culture is not always successful, and it takes more than 10 days to obtain the results of susceptibility to antibiotics in most medical institutions. Furthermore, at present, the tests for neither the susceptibility of H. pylori to antibiotics nor the detection of the point mutation of bacterial 23S rRNA gene are covered by the Japanese health insurance system. For many patients, the extra cost and longer duration before starting treatment are not acceptable. In addition, AMOX-resistant H. pylori is very rare in Japan (5). We therefore did not examine bacterial susceptibility to antibiotics in this study. Since this study is a prospective randomized trial, the influence of bacterial susceptibility on the differential eradication rates between EAC and RAC therapies would be minimal. However, we cannot exclude the possibility that a higher CLA resistance rate caused the lower eradication rate in patients with a lower PG I/II ratio. In conclusion, both the EAC and RAC regimens were safe and similarly effective as first-line eradication therapies for H. pylori infection, regardless of CYP2C19 genotype. However, the eradication rates of both therapies were insufficient under the current approval of the Japanese health insurance system. The PG I/II ratio seems to be associated with the results of EAC or RAC therapy.\n\nBODY:\nThe authors state that they have no Conflict of Interest (COI).\n\nQuestion: Compared to amoxicillin (750 mg), clarithromycin (200 mg), and rabeprazole (10 mg) (RAC group), twice a day for one week. what was the result of amoxicillin (750 mg), clarithromycin (200 mg), and either esomeprazole (20 mg) (EAC group), twice a day for one week. on Eradication of H. pylori with homo EM genotype and those with hetero IM or PM genotype.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: no significant difference\n" } ]	no significant difference
892	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Non-Invasive Brain Stimulation for Children with Autism Spectrum Disorders: A Short-Term Outcome Study\n\n ABSTRACT:\nNon-Invasive Brain Stimulation (NIBS) is a relatively new therapeutic approach that has shown beneficial effects in Autism Spectrum Disorder (ASD). One question to be answered is how enduring its neuromodulatory effect could be. Twenty-four patients with ASD (mean age: 12.2 years) received 20 sessions of NIBS over the left dorsolateral prefrontal cortex (L-DLPFC). They were randomized into two groups with two (G1) or three (G2) clinical evaluations before NIBS. Both groups had a complete follow-up at six months after the intervention, with the aim of determining the short-term outcome using the total score on the Autism Behavior Checklist, Autism Treatment Evaluation Checklist, and the Autism Diagnostic Interview. Transcranial Direct Current Stimulation (tDCS) was used in ASD patients aged <11 years, and repetitive Transcranial Magnetic Stimulation (rTMS) for 11–13-year-olds. Observation points were at one, three, and six months after completing all the sessions of NIBS. A significant reduction in the total score on the three clinical scales was observed and maintained during the first six months after treatment, with a slight and non-significant tendency to increase the scores in the last evaluation. Twenty sessions of NIBS over the L-DLPFC improves autistic symptoms in ASD children, with a lasting effect of six months.\n\nBODY.1. INTRODUCTION:\nAutism Spectrum Disorders (ASD) still pose challenges for neuroscience for many reasons; one of these is how to apply the advances in neuroscience to understanding and treating ASD by improving diagnosis, interventions, and treatments. To date, diagnosis is made on clinical bases in the absence of a true biomarker for diagnosis and a better therapeutic approach. Different pharmacological and non-pharmacological therapies have shown positive results but are far from leading to a significant improvement in the core symptoms of patients with ASD. A high incidence of brain anomalies had been described by different methods in autistic patients in comparison with neurotypical patients, including MRI techniques and anatomic studies [1,2,3]. One interesting feature described by Casanova et al. was the abnormal structure in cortical mini-columns, with poor neuropil development in ASD patients, which probably accounts for intracortical inhibitory dysfunction [1,4]. Alterations in the GABAergic signaling pathway may characterize autistic neurobiology, which seems to not simply be related to a decreased GABA concentration, but probably to perturbations in key components of the GABAergic pathway beyond GABA levels, such as receptors and inhibitory neuronal density [5]. There is also some research exploring functional intracortical inhibition in motor areas of ASD patients that reinforce these ideas; nevertheless, its functional expression in terms of modulation by means of paired pulse stimulation protocol with TMS is really less remarkable than was expected, and it has been demonstrated in only a fraction of the ASD population [6]. In other experiments, indirect evidence has been described related to an aberrant plasticity based on an imbalanced excitatory and inhibitory cortical tone as well as biased GABAergic dysfunction [7]. Casanova et al. were the first to propose the use of Non-Invasive Brain Stimulation (NIBS) for ASD patients, based on the possibility that low-frequency repetitive TMS could somehow improve GABAergic neurotransmission; in their case, low-frequency repetitive Transcranial Magnetic Stimulation (rTMS) was used as a way to improve intracortical inhibition in ASD patients. They applied one weekly session over 12 weeks in a group of 25 ASD patients and described an increase in gamma activity in the EEG evoked by a visual processing paradigm, with changes in Event Related Potential (ERP), improved error monitoring, and correction function in a visual recognition task after the intervention [8,9]. There are just a few other studies providing evidence of the potential efficacy of both rTMS and transcranial direct current stimulation (tDCS) in ASD (excluding case reports). Unfortunately, most of the trials are limited to a low number of sessions (not more than 15 in the best-case scenario), and it was not known how enduring the modulatory effect was [10,11,12,13]. Dorsolateral prefrontal cortex (DLPFC) is the preferred target for many other clinical conditions, thus also in ASD based on its connections with other cortical and subcortical structures. Nevertheless, other considerations are valid about the feasibility for the selection of other targets [1,14]. Studies in ASD patients using low-frequency rTMS over the left DLPFC (L-DLPFC) have shown a significant improvement in some components of event-related cortical potentials (N200 and P300) as well as a significant reduction in response errors during cognitive tasks, repetitive behavior, and irritability [9]. Other authors using cathodal tDCS over the L-DLPFC have also reported beneficial effects for ASD in young adults. Curiously, there is also a published work of a trial with anodal stimulation over DLPFC reporting improvement in autistic symptomatology [10,11]. If we accept the hypothesis that an intra-cortical inhibitory dysfunction exists in ASD patients that can contribute to several dysfunctions in the motor, sensorial, and cognitive domains, we can expect some improvement in autistic behavior after applying brain-stimulating protocols that may potentiate intracortical inhibition, probably increasing the amount of available endogenous GABA in neuronal networks related to the stimulation target. In previous experiments, low-frequency rTMS and cathodal stimulation over the left DLPFC in children with ASD were associated with an improvement in autistic behavior one week after completing 20 sessions of transcranial stimulation [15,16]. One important question is how lasting this effect would be; in the present study, we describe the short-term clinical response during the first six months after treatment. We hypothesized that 20 sessions of NIBS over the L-DLPFC are expected to have a lasting positive neuromodulatory effect in patients with ASD.\n\nBODY.2. MATERIALS AND METHODS.2.1. STUDY DESIGN:\nA controlled, randomized, and partial crossover trial was carried out in 24 children with ASD. Fifteen patients received the intervention after two clinical evaluations within one month (group 1, G1); nine patients started receiving the intervention after two months with three evaluation points at one-month intervals (group 2, G2). We assume that according to the stimulation protocol to be used (one daily session, up to a total of 20), it would be difficult to determine a washout period and patients from G2 ran in parallel to patients from G1 while they were receiving the intervention.\n\nBODY.2. MATERIALS AND METHODS.2.2. SAMPLE SELECTION AND GROUP DISTRIBUTION:\nChildren with ASD were recruited from the ambulatory service of the International Center for Neurological Restoration and Marfán-Borrás Hospital, from November 2015 to October 2016. Their diagnosis was made based on DSM-V diagnostic criteria, with the consensus of a multidisciplinary team including two Child Psychiatrists and two Neuropediatric Specialists. Only patients with a slight or moderate grade of severity were included according to their clinical characteristics, with stability during the last two months, and no changes in their therapeutic scheme in either pharmacologic or non-pharmacologic interventions. Diagnosis was confirmed by the results of the Childhood Autism Rating Scale (CARS) [17] and the Autism Diagnostic Interview, Revisited Edition (ADI-R, diagnostic algorithm) [18]. Patients with severe autistic behavior were excluded, as well as patients with concurrent epilepsy. Patients with unclear diagnosis or with diagnostic disagreement between neurologist and psychiatrist opinion were also excluded. If any change was needed in their therapeutic scheme, the patient was also excluded from the trial. We applied a simple randomization technique to assign patients to G1 (early intervention group, after one month of follow-up) or G2 (intervention after two months of follow-up).\n\nBODY.2. MATERIALS AND METHODS.2.3. CLINICAL EVALUATION:\nThree main clinical scales were used as outcome measurements for all patients, according to their parent opinions: ADI-R (algorithm for current condition), the Autism Behavioral Checklist (ABC) [19], and the Autism Treatment Evaluation Checklist (ATEC) [20]. All the scales were applied by a Child Psychiatrist who was not involved in the intervention, and patients were evaluated at one, three, and six months after completing the 20 sessions. The Global Clinical Impression Scale (GCIS) [21] was also applied as a complementary, more qualitative evaluation. The Wilcoxon matched pair test and Mann–Whitney U test were used either for intra- or between-group comparisons at the different evaluation moments (α = 0.05).\n\nBODY.2. MATERIALS AND METHODS.2.4. NEUROPHYSIOLOGICAL EVALUATION.2.4.1. FUNCTIONAL BRAIN CONNECTIVITY:\nAn electroencephalogram (EEG) based connectivity analysis was carried out in all the ASD patients, but only 15 good-quality EEG recording were obtained for connectivity analysis (nine from the tDCS group and six from the rTMS group). EEG traces taken one week before starting the intervention and one week after finishing it were analyzed. Significant windows were selected from the EEG trace in open eyes state (38 from each patient), because they were more often artifact-free than the closed-eyes state. We used a 19-electrode montage including Fp1, Fp2, F7, F8, F3, F4, C3, C4, T5, T6, T3, T4, P3, P4, O1, O2, Fz, Cz, and Pz, from the 10/20 system. Electrode Impedance was kept below 5 kΩ. Functional connectivity was analyzed based on the synchronization likelihood between electrodes for the five frequency bands: δ (1–3.9 Hz), θ (4–7.9 Hz) α (8–12.9 Hz), β (13–29.9 Hz), and γ (30–35 Hz) [22]. Mathematical analysis was developed with connectivity algorithms implemented in MATLAB v.7.7 R2008b. Significant connectivity (p < 0.05) in each frequency band was represented on an X/Y coordinate according to the 10/20 system for each brain stimulation modality independently, and the results by group were represented over the scalp surface map.\n\nBODY.2. MATERIALS AND METHODS.2.4. NEUROPHYSIOLOGICAL EVALUATION.2.4.2. EVENT-RELATED POTENTIALS:\nOnly in six children was it possible to carry out a passive oddball paradigm for P300 Event-Related Potentials (ERPs) before the intervention; four of them received tDCS and two rTMS. Patients were seated in a sound- and light-attenuated room while a paradigm was conducted consisting of 200 stimuli, 80% frequent (500 Hz) and 20% infrequent target (1000 Hz) tones, delivered through headphones while children were watching a silent movie. In the passive version of the oddball task the subject ́s attention is usually directed away from the sequence of standard and deviant tones toward another, moderately demanding task, usually in a different modality [23]. We proposed a version of this paradigm considering the characteristics of the autistic children, with poor collaboration. All stimuli (50 ms; 5 ms rise and fall time) were presented binaurally with an inter-stimulus interval of 1300 ms. To record the auditory P300 ERPs, 19 surface electrodes (Ag/ClAg) were attached to the scalp according to the international electrode placement 10–20 system (Fp1, Fp2, F3, F4, F7, F8, C3, C4, T3, T4, T5, T6, P3, P4, O1, O2, Fz, Cz, Pz), with additional electrodes for EOG (lateral to the outer canthus of the right eye and above the middle of the left eyebrow), and referenced to the linked earlobe. The electrode impedance was kept below 5 kΩ. EEG data were off-line averaged (100 ms prior and 700 ms after stimulus onset), and P300 latency and amplitude were quantified at Fz, Cz, and Pz. A continuous acquisition system was employed (Medicid 5, Neuronic SA, Cuba) and EEG data were EOG-corrected offline. The sampling rate of all channels was 200 Hz. To assure auditory system normality, Auditory Brainstem Response was previously recorded. The stimuli were 0.1 ms alternating clicks delivered through a headphone (DR-531B-7, Elegas Acous Co. Ltd., Tokyo, Japan). The records were obtained using the evoked potentials measuring system Neuropack M1 (Nihon Kohden, Tokyo, Japan). P300 ERPs were obtained before and after NIBS, and P300 latency and amplitude values from the two evaluations were compared (from Fz electrode position; Wilcoxon matched pairs test, α < 0.05). All measurements were of the difference wave (infrequent wave minus frequent wave) and in this case, due to the low number of patients' recordable P300, the analysis was performed considering all patients as a single group.\n\nBODY.2. MATERIALS AND METHODS.2.5. INTERVENTION:\nPatients received one daily session of NIBS, from Monday to Friday, for a total of 20 sessions. tDCS was used in patients 10 years old or younger, and rTMS in patients 11 and older. The reason for using tDCS in younger children instead of rTMS was that in this case a major degree of collaboration is needed to assure effective focal stimulation over the selected target (left dorsolateral prefrontal cortex, L-DLPFC). During the stimulation sessions patients, were comfortably seated while watching TV cartoons of their preference or listening to music and playing with small, simple toys.\n\nBODY.2. MATERIALS AND METHODS.2.5. INTERVENTION.2.5.1. TRANSCRANIAL DIRECT CURRENT STIMULATION (TDCS):\ntDCS was only used in patients 10 years old or younger (Neuroconn tDCS stimulator, München, Germany). A cathode was positioned over F3 (10/20 international EEG electrode system), and an anode over the proximal right arm. The stimulation intensity was 1 mA, and was maintained for 20 min. Each electrode pad was humidified with a 0.9% NaCl solution.\n\nBODY.2. MATERIALS AND METHODS.2.5. INTERVENTION.2.5.2. REPETITIVE TRANSCRANIAL MAGNETIC STIMULATION (RTMS):\nrTMS was used in patients older than 10 years and 11 months (MagStim Rapid2, Whitland, UK). A butterfly coil with air cooling system (MagStim Double 70 mm Air Film Coil) was used. The center of the coil was located over F3, back handed 45° from the midline, and a total of 1500 pulses were delivered in each session, at 1 Hz of frequency and an intensity of 90% of the resting motor threshold (i.e., the minimum stimulation intensity required to elicit a discernible hand muscle response in at least three of five consecutive pulses) [24]. Sessions were subdivided into four trains of 375 pulses, with a 1-min interval between each allowing for free movement of the head and neck. Most of the patients rejected the use of earplugs, and in the best-case scenario they agreed to listen to music by wearing headphones from their own devices.\n\nBODY.2. MATERIALS AND METHODS.2.6. ETHICAL CONSIDERATIONS:\nAll the procedures followed the rules of the Declaration of Helsinki of 1975 for human research, and the study was approved by the scientific and ethics committee from the International Center for Neurological Restoration (CIREN37/2015). Parents gave written informed consent for their children to be considered for inclusion in the study, and where possible children also gave their consent.\n\nBODY.3. RESULTS.3.1. CHANGE IN CLINICAL SCALES ONE MONTH AFTER THE INTERVENTION:\nAs a global result (G1 + G2), a significant decrease in the total score was observed in ADI-R, ABC, and ATEC scales one month after the intervention (Wilcoxon matched pair test; ABC, Z = 3.823, p = 0.000131; ADI-R, 3.337, p = 0.000846; ATEC, Z = 3.723, p = 0.000196). Figure 1a represents the global scores for the three main clinical scales we applied for the evaluation of autism behavior. The values are in correspondence with qualitative changes described by their relative uniqueness in socialization and communication domains, and with the GCIS (pre-intervention: 3.47 ± 0.6; post-intervention: 2.95 ± 0.2. Wilcoxon pair series test: Z = 2.803, p = 0.005062). All of the patients' autistic behavior improved according to the scale results observed one month after the intervention. A comparison between the change in the total score of clinical scales did not show any significant differences correlated with the use of tDCS and rTMS (Mann–Whitney U Test, p > 0.05). Initial evaluation did not show any differences in the total score between groups when we looked for any evidence of age-dependent characteristics in both groups. The clinical response to NIBS was apparently independent of group age and type of intervention (See Figure 1b). Figure 2 shows that no significant differences were observed between G1 and G2 in the initial clinical scale scores before the intervention (Mann–Whitney U test, p > 0.05); but values observed in G1 after NIBS showed a very important change when compared with the initial values (Wilcoxon; ABC, Z = 3.823, p = 0.000132; ADI-R, Z = 3.550, p = 0.000385 ;ATEC, Z = 5.526, p = 0.000241); the same behavior was seen in G2 after the intervention (Wilcoxon; ABC, Z = 3.295, p = 0.000982; ADI-R, Z = 3.588, p = 0.009633; ATEC, Z = 3.179, p = 0.001474).\n\nBODY.3. RESULTS.3.2. CHANGE IN CLINICAL SCALES DURING THE FIRST SIX MONTHS AFTER THE INTERVENTION:\nPost-intervention follow-up was extended over six months. For both groups G1 and G2, NIBS induced a significant change in clinical scale scores (See Figure 2), and both groups maintained approximately the same values until the sixth month after NIBS, when there was a slight tendency for the total score in ABC, ADI-R, and ATEC to increase, but their punctuation remained lower than the observed values before treatment (See Figure 2). According to their parents' opinion, stereotypes intensity and variety increased in frequency and number in many patients around the sixth month, but in clinical scales there were not any significant changes in specific domains. Group 1 had lower values for all the scales one month after NIBS (solid lines); the same happened with G2 patients running in parallel, but only since the fourth month and ahead of follow-up (also one month after NIBS; dashed lines).\n\nBODY.3. RESULTS.3.3. EEG-BASED BRAIN FUNCTIONAL CONNECTIVITY ANALYSIS:\nAn increase in brain functional connectivity was observed after NIBS for patients who received either tDCS or rTMS, especially for higher frequencies: α, β, and γ bands showed the greatest increase, with a large increment in the number of 10/20 system points functionally related. The analysis of the effect in functional connectivity showed that the group that received rTMS accounted for the most significant changes when initial and final values were compared (see Figure 3).\n\nBODY.3. RESULTS.3.4. ERP ANALYSIS:\nRecordings were possible in only six patients in the initial evaluation; thus, after the intervention, only activity in those patients who collaborated during the task was recorded. All patients had a normal auditory brainstem response according to the normative laboratory data, but one patient had no ERP response. The P300 component showed a scalp distribution in the frontal and central regions, maximal in Fz. There was a shortening of P300 latency after treatment, with statistically significant differences with respect to the basal response (Wilcoxon matched pairs test, p = 0.043). P300 amplitude did not show statistically significant differences after treatment, even though the average value in the group was higher after the intervention (see Figure 4). The prolonged latency and low amplitude may be in agreement with the abnormal connectivity of the frontal lobes seen in ASD subjects [25], and engaged with attention circuits. The improvement of these parameters after NIBS might be a consequence of the improvement in functional connectivity and probably correlated with positive clinical changes in attentiveness, concentration, and speed of answering questions from a parent.\n\nBODY.4. DISCUSSION:\nOur results reproduce similar neuromodulatory effects to those reported previously by two other research groups who used the same target (L-DLPFC), applying either rTMS or tDCS [9,11,26]. Casanova et al. pioneered the use of therapeutic NIBS in autism and described the effects of one weekly low-frequency rTMS (1 Hz) during 12 weeks in 25 ASD children and adolescents. In that study they reported a significant reduction in repetitive and restricted behavior patterns and irritability, but no changes in social awareness or hyperactivity. They also described an increase in the amount of gamma activity in the EEG, shortening of the P300 component of ERP, and an increase of amplitude in the group receiving the intervention [9]. They used 150 TMS pulses per session, one session per week, and 12 sessions in total. In our study, the number of stimuli per session and the total number of sessions were considerably higher; this is in correspondence with recommended practical aspects for conventional use of NIBS in other diseases such as depression, obsessive compulsive disorder, chronic pain, etc., in order to obtain a sustained effect [27,28]. This could likely explain the significant clinical improvement in our group, not only in the abovementioned domains, but also in social aspects and communication. We also were able to establish that NIBS' effects persisted into the sixth month after completion of treatment, a result that, as far as we know, has never been reported by any other group; this is a very important finding because it would probably indicate that patients would need a new treatment cycle (e.g., a second cycle of NIBS) six months after the previous intervention to maintain clinical improvement. Of course, it would also be interesting to know how the behavior of our patients will develop over the next six months and the forthcoming years (long-term outcome). Another interesting double-blind and randomized trial in adult ASD patients was published by Enticott et al. using the dorsomedial prefrontal cortex as the target, and stimulating with the HAUT coil, which makes it possible to reach deep structures in the brain [12]. They applied 10 daily sessions of 5 Hz, 1500 pulses at resting motor threshold intensity. The clinical response was evaluated immediately after the intervention and one month later, and they reported a significant reduction in social relating symptoms (relative to sham participants) for both post-treatment assessments. Those in the active condition also showed a reduction in self-oriented anxiety during difficult and emotional social situations from pre-treatment to one-month follow-up. They suggested the need to use extended protocols such as those used to treat depression, and we agree that it is essential to achieving lasting effects for both NIBS methods, rTMS or tDCS [28]. D'Urso et al. published the results of an open pilot study using cathodic tDCS over the L-DLPFC in 10 young adults (18–25 years old) with 10 daily sessions of 1.5 mA, with evaluation two weeks after the intervention. They reported an improvement in autistic behavior of 26.7% according to the change observed in the clinical scale they applied; only two patients did not change their initial scale values, while the rest of the group improved in their symptoms [11]. There are two main differences in the tDCS protocol we applied in younger children (5–10 years old): first, again we used a higher number of sessions and second, the stimulation intensity in our case was 1 mA. NIBS in children seems to be as safe as in the adult population, so the same safety guidelines are indicated for its use in any population [29,30]. It is important to mention that in the case of tDCS, there is not enough evidence about the safety of 2 mA in young people (<18 years old), and most research has been done using 1 mA; however, there are also a few papers describing the absence of adverse effects with the use of 2 mA in pediatric patients [13]. In another interesting article, Amatachaya et al. described the effects of anodal tDCS over L-DLPF, with improvement in autistic behavior in 20 children with ASD. They designed a randomized, double-blind crossover and sham-controlled trial, applying 1 mA anodal tDCS over five consecutive days, and a washout period of four weeks This result reactivates the essential research question as to whether the clinical, biochemical, and physiological effects are polarity-dependent or not [10,31,32,33,34,35]. There are results from clinical trials with other diseases and physiological studies in which the opposite effects of cathodic and anodic tDCS have been well documented [35,36]. Our results using cathodic tDCS or low-frequency rTMS over the L-DLPFC share the same theoretical basis developed by Casanova et al. and D'Urso et al., though we studied a low sample number (24 patients), and by design we employed an open trial without the use of placebo stimulation. Nevertheless, the results are reproducible in G1 and G2, with patients being their own controls from the start of the intervention. We also had the opportunity to compare the effects of low-frequency rTMS and cathodic tDCS at the same time, but in ASD patients of different ages and with our experimental design we demonstrated that there are no differences, at least not in their clinical effects. Certainly, there was an important effect achieved by increasing functional connectivity with the use of both the stimulating methods, rTMS and tDCS, with a clear superiority of rTMS-induced changes. Of course, more research is needed to draw well-documented conclusions. Other authors have described improvements in particular aspects of adult ASD patients such as working memory and better syntax acquisition following single-dose anodal tDCS over the left and right dorsolateral prefrontal cortex (first case) or exclusively over the left dorsolateral prefrontal cortex [13,37] There were also positive changes in P300 ERP, but due to the low number of subjects in whom it was possible to carry out the passive oddball paradigm, we cannot make any comparison between the two different stimulating methods. Unfortunately, sample sizes for EEG-based connectivity analysis and ERP paradigm could not include all the patients, because, in close relationship with the complexity of the used method, when we carried out their initial electrophysiological evaluation (before intervention), not all recordings had a high enough quality for analysis.\n\nBODY.5. CONCLUSIONS:\nTwenty sessions of NIBS over L-DLPFC improves autistic symptoms in ASD children, with a lasting effect of six months.\n\nQuestion: Compared to before Non-Invasive Brain Stimulation (NIBS) what was the result of after Non-Invasive Brain Stimulation (NIBS) on ADI-R (algorithm for current condition), the Autism Behavioral Checklist (ABC), and the Autism Treatment Evaluation Checklist (ATEC) after 1 month?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly decreased\n" } ]	significantly decreased
896	[ { "role": "user", "content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by Article:, which contains the Abstract and Body sections of a randomized controlled trial. Question: will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\nArticle: \n\nTITLE: Belatacept-Based Immunosuppression in \n\n ABSTRACT:\nThis exploratory phase II study evaluated the safety and efficacy of belatacept in de novo adult liver transplant recipients. Patients were randomized (N = 260) to one of the following immunosuppressive regimens: (i) basiliximab + belatacept high dose [HD] + mycophenolate mofetil (MMF), (ii) belatacept HD + MMF, (iii) belatacept low dose [LD] + MMF, (iv) tacrolimus + MMF, or (v) tacrolimus alone. All received corticosteroids. Demographic characteristics were similar among groups. The proportion of patients who met the primary end point (composite of acute rejection, graft loss, death by month 6) was higher in the belatacept groups (42–48%) versus tacrolimus groups (15–38%), with the highest number of deaths and grafts losses in the belatacept LD group. By month 12, the proportion surviving with a functioning graft was higher with tacrolimus + MMF (93%) and lower with belatacept LD (67%) versus other groups (90%: basiliximab + belatacept HD; 83%: belatacept HD; 88%: tacrolimus). Mean calculated GFR was 15–34 mL/min higher in belatacept-treated patients at 1 year. Two cases of posttransplant lymphoproliferative disease and one case of progressive multifocal leukoencephalopathy occurred in belatacept-treated patients. Follow-up beyond month 12 revealed an increase in death and graft loss in another belatacept group (belatacept HD), after which the study was terminated.\n\nBODY.INTRODUCTION:\nLiver transplantation is a life-saving procedure for patients with end-stage liver disease (ESLD) that improves overall survival and quality of life (1,2). Liver transplant (LT) recipients are at increased risk for cardiovascular disease, and chronic kidney disease (CKD; (3–7)). Stage 4 or 5 CKD has been reported in ∼18% of LT recipients by 5 years posttransplant (4) and is associated with increased morbidity and mortality (4–7). Data from 1997 to 2008 in the Organ Procurement Transplant Network/United Network for Organ Sharing (OPTN/UNOS) database showed a threefold increased rate of kidney transplantation in patients who previously received LT (8). While the causes of CKD in LT patients are multifactorial, including pretransplant and peritransplant factors like hepatitis C virus (HCV), diabetes and hepatorenal syndrome, calcineurin inhibitors (CNIs) appear to be significant contributing factors (4,7,9–11). In the OPTN/UNOS analysis, ∼50% of LT patients who received a kidney transplant had a diagnosis consistent with CNI toxicity (8). Thus, there is a need for immunosuppressive regimens that provide efficacy while avoiding the nephrotoxic, cardiovascular and metabolic risks of CNIs in LT recipients. Belatacept, a selective costimulation blocker (12), is designed to provide effective immunosuppression and avoid both renal and nonrenal toxicities associated with CNIs. Results from two phase III clinical trials in kidney transplant recipients found that belatacept-based immunosuppression was associated with similar rates of patient and graft survival, significantly better renal function and an improved cardiovascular/metabolic risk profile versus cyclosporine-based therapy ≤3 years after transplantation (13–17). Higher rates and grades of acute rejection (AR) were observed in belatacept-treated patients receiving standard-criteria donor kidneys (13,15). Posttransplant lymphoproliferative disease (PTLD) with central nervous system (CNS) involvement, primarily in patients seronegative for Epstein–Barr virus (EBV) at the time of transplant and progressive multifocal leukoencephalopathy (PML) were the most serious adverse events (AEs) reported in belatacept-treated patients (13,14,18). The objective of this exploratory, phase II study was to evaluate the efficacy and safety of belatacept in adult recipients of first LTs from a deceased donor. To identify an optimal immunosuppressive regimen in LT recipients, three belatacept regimens were studied and compared with two tacrolimus regimens. In addition, a follow-up long-term extension (LTE) study (i.e. ≥12 months) was conducted to assess longer-term safety and tolerability. The LTE study was terminated in 2011 (when patients were ∼2 years posttransplant) because of worse patient and graft survival in two of the three belatacept treatment groups. Both the 12-month results and those from the LTE are reported herein.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis was a randomized, partially blinded, active-controlled, parallel group, multicenter, phase II clinical trial in adult recipients of first LTs (ClinicalTrials.gov: NCT00555321). Three belatacept regimens were studied, representing a stepwise decrease in the level of overall immunosuppression, and compared with the approved immunosuppressive regimen (tacrolimus alone) and the most widely used immunosuppressive regimen (tacrolimus + mycophenolate mofetil [MMF]) in LT. This exploratory study intended to assess the comparability of a belatacept-based regimen with a tacrolimus-based regimen in terms of AR, graft loss and death. Immediately before transplantation, patients were randomized to one of the following treatment groups: (i) basiliximab + belatacept high dose (HD) + MMF; (ii) belatacept HD + MMF; (iii) belatacept low dose (LD) + MMF; (iv) tacrolimus + MMF or (v) tacrolimus alone. Subjects were randomized in a 1:1:1:1:1 ratio using an interactive voice response system with centralized randomization and stratified by HCV status (yes or no) in blocks of five. All patients received corticosteroid therapy for the first 3 months. The trial was fully blinded to patients and study personnel with respect to belatacept dosing regimen (HD or LD) and basiliximab assignment (through the use of placebo infusions), open-label to belatacept or tacrolimus treatment and open-label between the two tacrolimus groups. The study duration was 12 months with an LTE (study was initiated January 22, 2008 and completed May 2, 2011). An external Data Monitoring Committee (DMC) comprising a chair and four members (specialty physicians and one statistician) reviewed emerging safety and efficacy data on a regular basis. The study was conducted in accordance with the Declaration of Helsinki and was consistent with International Conference on Harmonisation Good Clinical Practice and applicable regulatory requirements. The study protocol and amendments were reviewed and approved by the institutional review board/independent ethics committee for each site before initiation of the study (see Table S1 for enrollment by site).\n\nBODY.MATERIALS AND METHODS.PATIENTS AND INTERVENTIONS:\nThe study population included adults of 18–70 years of age, who were recipients of first LTs from a deceased donor (see Table 1 for additional inclusion and exclusion criteria). Belatacept was administered via intravenous (IV) infusion. Table 1 Study inclusion and exclusion criteria Inclusion criteria Exclusion criteria Adults of 18–70 years of age, who were recipients of first LTs from a deceased donor Donation after cardiac death Informed consent from all patients Living-donor recipients Additional inclusion criteria Split liver recipients Reliable IV access Recipients of organs ABO compatible donor-recipient pairs From donors <12 years or >65 years of age Patients with hepatocellular carcinoma meeting Milan criteria (one nodule ≤5 cm in diameter or three or fewer nodules, with none >3 cm in diameter) With anticipated cold ischemia time >14 h From donors who were positive for HBV or HCV when recipients were negative for HBV or HCV, respectively From donors with known human immunodeficiency virus infection Patients receiving dialysis before LT for ≥2 consecutive weeks before enrollment or who were anticipated to have prolonged dialysis posttransplant Patients with known intrinsic kidney disease (e.g. a urine protein/creatinine ratio >150 mg/g or presence of an abnormal number of red blood cells or granular casts in urine) AND a calculated GFR (cGFR) <40 mL/min/1.73 m 2 body surface area (modified MDRD) within 1 month of enrollment Patients with acute liver failure, hypercoagulable state or malignancy within the previous 5 years (except for nonmelanoma skin cancer cured by local resection or hepatocellular carcinoma as defined above) Patients who were seronegative for Epstein–Barr virus (subsequent study amendment) HBV, hepatitis B virus; HCV, hepatitis C virus; IV, intravenous; LT, liver transplant. \n\nBODY.MATERIALS AND METHODS.PATIENTS AND INTERVENTIONS.HD REGIMENS (GROUPS 1 AND 2):\nBelatacept 10 mg/kg was given on days 1 (day of transplant), 3 and 5, and weeks 2, 4, 6, 8, 10, 12, 16, 20 and 24 for the first 6 months and then 5 mg/kg every 4 weeks from months 7–12.\n\nBODY.MATERIALS AND METHODS.PATIENTS AND INTERVENTIONS.LD REGIMEN (GROUP 3):\nBelatacept 10 mg/kg was given on days 1, 3 and 5, and weeks 2, 4, 8 and 12 for the first 3 months and then 5 mg/kg every 4 weeks from months 3–12. The belatacept doses in the present study were different from those studied in renal transplant recipients in that an additional belatacept dose was administered on day 3 in all belatacept treatment groups, and one additional dose was allowed for excessive bleeding (>3L) or ascites loss (>4L) during the first 2 weeks following LT. Eight patients in the basiliximab + belatacept HD + MMF group, 9 patients in the belatacept HD + MMF group and 10 patients in the belatacept LD + MMF group received an additional dose of belatacept for bleeding or ascites. Tacrolimus (groups 4 and 5) was administered orally at an initial dose of 0.10–0.15 mg/kg/day after transplantation; doses were adjusted to achieve target trough concentrations between 6 and 12 ng/mL. Basiliximab induction (20 mg IV) was given to patients in group 1 only (belatacept HD regimen) on days 1 and 5. Patients in groups 1 through 4 received MMF at 2 g/day orally, which was later amended to 1 g/day after a case of PML was reported in a patient receiving belatacept HD + MMF. At that time, all but two had received ≥6 months of study treatment. All patients received tapered corticosteroids (Figure 1). Figure 1Patient disposition and dosing. All patients received corticosteroids on days 1–5, which was tapered to ≤10 mg/day by day 30 and ≤5 mg/day by day 90. Thereafter, withdrawal of corticosteroids was at the discretion of the investigator. HD, high dose; LD, low dose; MMF, mycophenolate mofetil. All patients received antiviral prophylaxis for cytomegalovirus (CMV) and herpes simplex virus for ≥3 months posttransplant and for 3 months upon administration of T cell–depleting agents. Additionally, all patients were to receive a 6-month course of prophylaxis for Pneumocystis jiroveci pneumonia.\n\nBODY.MATERIALS AND METHODS.OUTCOMES:\nThe primary end point was the composite incidence of AR, graft loss and death at 6 months after transplantation. AR was included in the composite end point if it was clinically suspected and proven via biopsy. All biopsies for suspected AR were assessed by a central histopathologist blinded to treatment assignment using the Banff schema for grading of LT rejection and rejection activity index for staging (19). Graft loss was defined as impairment of liver function that resulted in patient death or re-transplantation. Secondary end points included the incidence, severity, treatment and outcome of AR by 12 months; graft loss and death by 12 months; change in renal function over time as determined by measured GFR (mGFR) and calculated GFR (cGFR; MDRD methodology); incidence of HCV recurrence by 12 months, defined as histologic confirmation on liver biopsy scored by the Ishak (modified Knodell) system, a score of ≥5 of 18 on modified histological activity index grading, and a fibrosis score of ≥2 of 6 (20). Incidence rates of cardiovascular and metabolic comorbidities (i.e. posttransplant diabetes mellitus, dyslipidemia and hypertension) and the overall safety of the belatacept-based regimens were also evaluated. Liver allograft biopsies (confirmed by a central pathology laboratory) were obtained at baseline and at 12 months to assess histology. Biopsies were also performed in patients who met protocol-specified criteria for clinical suspicion of AR or HCV recurrence.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSES:\nA statistical analysis plan was prepared prior to unblinding this study. The purpose of the study was to provide initial clinical experience regarding the efficacy and safety of belatacept in LT recipients and identify a belatacept-based regimen with an acceptable composite rate of AR, graft loss and death. Therefore, statistical testing was not prespecified and the study was not powered to demonstrate a difference between treatment groups. A calculated sample size of 50 patients per treatment group was determined to provide initial data regarding safety and efficacy. If the observed primary end point (composite incidence of AR, graft loss and death by 6 months) for a belatacept-based group was 40%, it was estimated that the two-sided 95% confidence interval (CI) of this incidence would extend from 26.4% to 53.6%, which would be within the general range observed in large LT studies that used CNI-based immunosuppression (21,22). Analyses were performed on the intent-to-treat population (i.e. those who were randomized and received a transplant). Most analyses were descriptive in nature, using point estimates and 95% CIs. mGFR was assessed via iothalamate at months 2 (baseline) and 12. cGFR was assessed pretransplant and at 1, 2, 3, 6 and 12 months.\n\nBODY.RESULTS:\nA total of 260 patients at 39 centers worldwide were randomized, of whom 250 received a transplant and were treated. A total of 164 patients completed 12 months of treatment (Figure 1). Demographic and baseline characteristics were generally similar across treatment groups (Table 2). The mean age was 54 years, and 46% of patients were HCV-positive. The primary reasons for discontinuing treatment, as defined by the study investigators, were AEs and lack of efficacy in the belatacept groups and AEs in the tacrolimus groups. Table 2 Demographic characteristics of recipients by treatment group Characteristic Basiliximab + belatacept HD + MMF Belatacept HD + MMF Belatacept LD + MMF Tac + MMF Tac (n = 50) (n = 48) (n = 49) (n = 53) (n = 50) Mean age, years 54.0 53.4 55.2 53.0 54.7 Sex, male, % 78 71 63 87 84 Race, % White 88 83 94 93 86 Black 8 6 2 6 4 Cause of ESLD, % Noncholestatic cirrhosis 76 69 67 74 82 HCV-positive, % 46 48 43 47 48 Mean MELD score 22.6 21.1 20.6 24.3 21.6 Hepatorenal syndrome, % 10 10 10 13 6 ESLD, end-stage liver disease; HCV, hepatitis C virus; HD, high dose, LD, low dose; MELD, Model for End-Stage Liver Disease; MMF, mycophenolate mofetil; Tac, tacrolimus. An imbalance in the frequency of deaths and graft losses in the belatacept LD group early in the study was noted by the DMC. Based on the DMC recommendation, randomization to the belatacept LD group was stopped. Study enrollment, however, was nearly complete (247/250 patients), and patients were permitted to remain on the belatacept LD regimen at the discretion of the investigator. Randomization into the other four treatment groups continued.\n\nBODY.RESULTS.OUTCOMES: COMPOSITE END POINT, DEATH, GRAFT LOSS AND AR.COMPOSITE END POINT:\nAt the time of the primary analysis at month 6, the incidence rates of the composite end point were higher in the belatacept groups (42–48%) than in the tacrolimus groups (15–38%) (Table 3). This difference was primarily driven by a higher number of AR episodes in the belatacept groups than in the tacrolimus groups. At month 12, patient and graft survival were highest in the tacrolimus + MMF group and lowest in the belatacept LD group. The proportion of patients surviving with a functioning graft was 90%, 83% and 67% in the basiliximab + belatacept HD, belatacept HD, and belatacept LD groups, respectively, and 93% and 88% in the tacrolimus + MMF and tacrolimus groups, respectively. Table 3 Outcomes: composite end point (death, graft loss and AR) by 6 months (primary end point) and 12 months and AR up to month 12 Composite end point Basiliximab + belatacept HD + MMF Belatacept HD + MMF Belatacept LD + MMF Tac + MMF Tac (n = 50) (n = 50) (n = 48) (n = 49) (n = 53) 6 months (primary end point), n (%) 24 (48.0) 20 (41.7) 23 (46.9) 8 (15.1) 19 (38.0) Difference from Tac + MMF, % (95% CI) 32.9 (16.1–49.8) 26.6 (9.6–43.5) 31.8 (14.8–48.5) — — Difference from Tac, % (95% CI) 10.0 (−8.7–29.6) 3.7 (−15.3–23.2) 8.9 (−9.8–28.4) — — AR, n 20 15 15 5 15 Death, n 4 4 6 1 3 Graft loss, n 2 2 6 4 3 Survival with a functioning graft, n (%) 45 (90.0) 43 (89.6) 38 (77.6) 49 (92.5) 45 (90.0) (95% CI) (81.7–98.3) (80.9–98.2) (65.9–89.2) (85.3–99.6) (81.7–98.3) 12 months, n (%) 26 (52.0) 23 (47.9) 26 (53.1) 10 (18.9) 20 (40.0) AR, n 22 16 16 7 15 Death, n 4 7 10 1 4 Graft loss, n 2 2 8 4 4 Survival with a functioning graft, n (%) 45 (90.0) 40 (83.3) 33 (67.3) 49 (92.5) 44 (88.0) (95% CI) (81.7–98.3) (72.8–93.9) (54.2–80.5) (85.3–99.6) (79.0–97.0) AR (centrally read) up to month 12, n (%) Patients with AR 22 (44.0) 16 (33.3) 16 (32.7) 7 (13.2) 15 (30.0) Treated, n/N (%) 12/22 (54.5) 12/16 (75.0) 8/16 (50.0) 5/7 (71.4) 12/15 (80.0) Corticosteroids only, n (%) 12 (24.0) 7 (14.6) 8 (16.3) 4 (7.5) 10 (20.0) Initial lymphocyte-depleting therapy, n (%) 0 (0) 3 (14.6) 0 (0) 0 (0) 0 (0) Grade of AR, n (%) I 15 (30.0) 7 (14.6) 7 (14.3) 6 (11.3) 7 (14.0) II 7 (14.0) 8 (16.7) 8 (16.3) 1 (1.9) 6 (12.0) III 0 (0) 1 (2.1) 1 (2.0) 0 (0) 2 (4.0) Death or graft loss in patients with AR, n 1 1 6 1 1 AR, acute rejection; CI, confidence interval; HD, high dose, LD, low dose; MMF, mycophenolate mofetil; Tac, tacrolimus. \n\nBODY.RESULTS.OUTCOMES: COMPOSITE END POINT, DEATH, GRAFT LOSS AND AR.DEATH:\nAt the 6-month primary analysis, a higher number of deaths was observed in patients treated with belatacept (basiliximab + belatacept HD [n = 4], belatacept HD [n = 4], belatacept LD [n = 6]) than in those treated with tacrolimus (tacrolimus + MMF [n = 1], tacrolimus [n = 3]). A similar pattern was also observed at 12 months posttransplant (Table 3). The causes of death reported in more than one patient included multisystem organ failure (n = 7), sepsis (n = 7), gastrointestinal bleeding (n = 2) and myocardial infarction (n = 2). In two cases, the cause of death was unknown (Table 4). Table 4 Causes of death Treatment group Age/sex Reported cause of death Study day Basiliximab + belatacept HD + MMF 57/M Sepsis 18 61/M Myocardial infarction 23 49/M Multiple system organ failure 25 56/M Sepsis 127 Belatacept HD + MMF 43/M Sepsis 24 37/M Sepsis 84 62/F Multiple system organ failure 111 47/M Gastrointestinal bleed 147 62/F Unknown 274 58/M Unknown 278 51/M PML 322 Belatacept LD + MMF 65/M Multiple system organ failure 2 59/F Colon perforation 8 48/M Acute hepatic failure 16 63/F Pulmonary failure 21 53/M Sepsis 65 50/M Gunshot injury 117 58/F Multiple system organ failure 202 55/M Multiple system organ failure 208 65/F Multiple system organ failure 339 51/M PTLD 364 Tacrolimus + MMF 54/M Sepsis 168 Tacrolimus 49/M Myocardial infraction 34 52/M Multiple system organ failure 63 46/M Gastrointestinal bleed 68 49/M Sepsis 286 F, female; HD, high dose, LD, low dose; M, male; MMF, mycophenolate mofetil; PML, progressive multifocal leukoencephalopathy; PTLD, posttransplant lymphoproliferative disease. \n\nBODY.RESULTS.OUTCOMES: COMPOSITE END POINT, DEATH, GRAFT LOSS AND AR.GRAFT LOSS:\nBy month 6, numerically fewer cases of death-censored graft loss were reported in the belatacept HD groups (n = 1 each) than in the belatacept LD group (n = 5) and tacrolimus groups (tacrolimus + MMF [n = 3]; tacrolimus [n = 2]). At month 12, a similar pattern was observed. Across treatment groups, ∼50% of graft losses occurred within the first month posttransplant, the main causes of which were primary nonfunction (n = 5) and arterial thrombosis (n = 4).\n\nBODY.RESULTS.OUTCOMES: COMPOSITE END POINT, DEATH, GRAFT LOSS AND AR.ACUTE REJECTION:\nOverall, AR (centrally read) was more common in the belatacept groups than in the tacrolimus groups (Table 3). At the month 6 primary analysis, the percent of patients with AR in the basiliximab + belatacept HD, belatacept HD and belatacept LD groups was 40%, 31% and 31%, respectively, versus 9% and 30% for the tacrolimus + MMF and tacrolimus groups, respectively. Most episodes of AR (57–94%) occurred early after transplant (i.e. by month 3) and were mild to moderate in severity (Banff grade I or II). Among patients with AR, ∼50% received treatment for AR in the basiliximab + belatacept HD and belatacept LD groups, while 70–80% received treatment in the other three groups. The majority of patients who were treated for AR received corticosteroids only.\n\nBODY.RESULTS.OUTCOMES: COMPOSITE END POINT, DEATH, GRAFT LOSS AND AR.ANALYSIS BY HCV STATUS:\nIn HCV-positive patients, the percent with AR by month 6 in the belatacept groups ranged from 33% to 39% versus 12% and 38% for the tacrolimus + MMF and tacrolimus groups, respectively. In patients who were HCV-negative, the percent with AR by month 6 in the belatacept groups was 29–41% versus 7% and 23% for the tacrolimus + MMF and tacrolimus groups, respectively.\n\nBODY.RESULTS.SAFETY:\nSerious AEs, including serious infections and malignancies, occurred with a similar frequency across all treatment groups (Table 5). The most commonly reported serious AEs across all groups included pneumonia, sepsis, biliary strictures, cholangitis, pyrexia and acute renal failure. The most common serious infections resulted from CMV, fungal and mycobacterial pathogens. One fatal case of PML occurred ∼6 months after transplantation in a patient receiving belatacept HD and higher than recommended doses of MMF (3–4 g/day for 7.5 weeks). Table 5 Adverse events and events of interest at 12 months Events Patients Basiliximab + belatacept HD + MMF Belatacept HD + MMF Belatacept LD + MMF Tac + MMF Tac (n = 50) (n = 48) (n = 49) (n = 53) (n = 50) HCV at baseline, n 23 23 21 25 24 HCV recurrence, 1 n (%) 14 (60.9) 7 (30.4) 6 (28.6) 13 (52.0) 9 (37.5) Serious adverse events, n (%) 28 (56.0) 29 (60.4) 37 (75.5) 40 (75.5) 35 (70.0) Infections and infestations 11 (22.0) 12 (25.0) 13 (26.5) 12 (22.6) 12 (24.0) Malignancies, n 1 0 2 2 2 PTLD 1 2 0 1 0 0 All infections and infestations, n (%) 32 (64.0) 39 (81.3) 30 (61.2) 31 (58.5) 29 (58.0) Bacterial 5 (10.0) 11 (22.9) 11 (22.4) 6 (11.3) 13 (26.0) Fungal infections 6 (12.0) 9 (18.8) 14 (28.6) 6 (11.3) 5 (10.0) Viral infections 3 10 (20.0) 11 (22.9) 14 (28.6) 9 (17.0) 7 (14.0) CMV 5 (10.0) 4 (8.3) 10 (20.4) 4 (7.5) 1 (2.0) Herpes 3 (6.0) 3 (6.3) 4 (8.2) 3 (5.7) 2 (4.0) Adverse events of nervous system disorders, n (%) 23 (46.0) 19 (39.6) 15 (30.6) 34 (64.2) 34 (68.0) Headache 10 (20.0) 8 (16.7) 5 (10.2) 14 (26.4) 14 (28.0) Tremor 2 (4.0) 2 (4.2) 4 (8.2) 17 (32.1) 13 (26.0) Adverse events of renal and urinary disorders, n (%) Renal failure 1 (2.0) 4 (8.3) 3 (6.1) 5 (9.4) 14 (28.0) Acute renal failure 2 (4.0) 5 (10.4) 2 (4.1) 13 (24.5) 8 (16.0) Renal impairment 0 (0) 1 (2.1) 0 (0) 1 (1.9) 8 (16.0) CMV, cytomegalovirus; HAI, histological activity index; HCV, hepatitis C virus; HD, high dose, LD, low dose; MMF, mycophenolate mofetil; PML, progressive multifocal leukoencephalopathy; PTLD, posttransplant lymphoproliferative disease; Tac, tacrolimus. 1 HCV recurrence confirmed histologically by central pathologist; modified HAI grading score ≥5/18 and fibrosis score ≥2. 2 PTLD case occurred after month 12. 3 One case of PML in belatacept HD + MMF. Malignancies were reported in 2–4% of belatacept patients and in 4% of patients receiving tacrolimus-based treatments. Two cases of PTLD were reported in belatacept-treated patients (one in the belatacept LD group at 11 months posttransplant and one in the basiliximab + belatacept HD group after month 12), both of which involved the liver. Neither case involved the CNS; both patients were EBV-seropositive at the time of transplantation. One patient died as a result of PTLD; the other was treated with chemotherapy and is alive with a functioning graft. Overall, most infections were mild or moderate in severity (Table 5); urinary tract infections were the most common. Patients in the belatacept LD group had numerically higher rates of viral and fungal infections (Table 5), most of which were nonserious. A similar proportion of patients across all treatment groups experienced at least one AE. AEs related to neurotoxicity (i.e. headache and tremor) occurred less frequently in patients receiving belatacept-based regimens versus tacrolimus-based regimens (Table 5).\n\nBODY.RESULTS.HCV RECURRENCE:\nApproximately 72% (153/212) of patients with a functioning graft at month 12 had biopsies available for evaluation. Recurrence of HCV among patients who were HCV-positive at baseline was higher in the basiliximab + belatacept HD (61%) and tacrolimus + MMF (52%) groups versus the other treatment groups (29–38%) (Table 5).\n\nBODY.RESULTS.RENAL FUNCTION:\nMean cGFR at baseline was 66–80 mL/min. The differences in cGFR between the belatacept-treated patients and tacrolimus-treated patients were observed as early as month 1 and persisted through month 12 (15–34 mL/min/1.73 m2 higher in each belatacept group vs. the tacrolimus groups at month 12) (Figure 2). By month 12 in the intent-to-treat analysis, mean mGFR was 89–93 mL/min in the belatacept HD groups and 71–75 mL/min in the belatacept LD and tacrolimus groups. An on-treatment analysis revealed similar findings at 12 months (mean cGFR was 88 mL/min for basiliximab + belatacept HD; 100 mL/min for belatacept HD; 94 mL/min for belatacept LD; 67 mL/min for tacrolimus + MMF and 62 mL/min for tacrolimus). The proportion of patients with >10 mL/min improvement in cGFR from baseline to month 12 was 47–65% in the belatacept groups versus 12–27% in the tacrolimus groups. Figure 2Mean calculated GFR (MDRD methodology) over time (intent-to-treat analysis, as observed data with no imputation for missing values). All calculated GFR >200 were truncated at 200 mL/min. HD, high dose; LD, low dose; MMF, mycophenolate mofetil.\n\nBODY.RESULTS.CARDIOVASCULAR/METABOLIC PROFILE AT 12 MONTHS:\nSystolic and diastolic blood pressures at 12 months were lower among patients receiving belatacept (121–127 mmHg and 75–77 mmHg, respectively) versus those receiving tacrolimus-based regimens (137–138 mmHg and 80 mmHg, respectively). Serum lipids increased from baseline in all treatment groups, with triglyceride levels increasing more in the tacrolimus groups and LDL levels increasing more in the belatacept groups (data not shown). The incidence of new-onset diabetes mellitus (i.e. ≥30 days of treated diabetes in patients without a diagnosis of diabetes before randomization) was somewhat lower in the belatacept HD and LD groups (16% and 14%, respectively) versus patients receiving basiliximab + belatacept HD (36%), tacrolimus + MMF (24%), and tacrolimus (38%).\n\nBODY.RESULTS.PHARMACOKINETICS:\nThe pharmacokinetics of belatacept in LT recipients was similar to those in kidney transplantation recipients receiving a similar dosing regimen (23). The pattern of minimum belatacept concentration values with the HD and LD regimens in the early posttransplant period were consistent with the differences between the two regimens. Steady-state trough serum concentrations of belatacept in the maintenance phase (during 5-mg/kg dosing) were similar between the HD and LD regimens. Mean serum trough concentrations of belatacept and tacrolimus, and mean daily MMF and steroid doses are shown in Figure 3. Some of the patients who received additional belatacept to compensate for fluid loss went on to experience death or graft loss, but results were mixed and potentially confounded by intra- and postoperative complications. In the overall study population, there was no association between trough belatacept levels and death or graft loss. Figure 3Serum trough levels and mean daily dosing at specified time points. Concentrations of belatacept in human serum were determined using a validated enzyme-linked immunosorbent assay (ELISA) by PPD (Richmond, VA). (A) Mean serum trough levels of belatacept. (B) Mean daily dose of MMF. (C) Mean serum trough levels of tacrolimus. (D) Mean daily dose of steroids. HD, high dose; LD, low dose; M, month; MMF, mycophenolate mofetil; W, week.\n\nBODY.RESULTS.DONOR-SPECIFIC ANTIBODIES:\nAll treatment groups had patients who tested positive for donor-specific antibodies (DSA) at baseline (Table 6). By 12 months after transplantation, the number of patients with DSA decreased in two belatacept groups (HD and LD), remained the same in two groups (basiliximab + belatacept HD and tacrolimus), and increased in one group (tacrolimus + MMF) (Table 6). There were few cases of de novo DSA in all groups. Table 6 DSA: number of patients with detectable antidonor HLA antibodies Patients with DSA/patients in analysis, n (%) Basiliximab + belatacept HD + MMF Belatacept HD + MMF Belatacept LD + MMF Tac + MMF Tac Baseline DSA (pretransplant) 5/48 (10) 5/46 (11) 8/48 (17) 3/50 (6) 4/49 (8) Total DSA by month 12 5/47 (11) 3/47 (6) 4/43 (9) 8/52 (15) 4/45 (9) De novo DSA 1 by month 12 3/47 (6) 1/47 (2) 1/43 (2) 6/52 (12) 3/45 (7) DSA, donor-specific antibodies; HD, high dose, LD, low dose; MMF, mycophenolate mofetil; Tac, tacrolimus. 1 De novo DSA was defined as appearance of antibody to a new HLA specificity following transplantation. \n\nBODY.RESULTS.LONG-TERM EXTENSION:\nOf the 164 patients who completed 1 year of treatment, 145 entered the LTE phase (Figure 4). During the LTE, additional deaths and graft losses were noted in the belatacept HD group (n = 4). Because of the cumulative number of deaths and graft losses in two of the three belatacept groups relative to the tacrolimus groups, the DMC recommended termination of the LTE study. Although a causal relationship to belatacept could not be clearly established, it could also not be rejected. All patients who were currently on belatacept were switched to standard-of-care immunosuppression. Figure 4Patient disposition in LTE. HD, high dose; LD, low dose; LTE, long-term extension; MMF, mycophenolate mofetil. Based on these findings, a comprehensive assessment of the deaths observed in belatacept-treated patients was conducted, and a series of post hoc analyses were performed. Factors evaluated included demographic characteristics, donor age, baseline disease status, mean Model for End-Stage Liver Disease score, and belatacept trough concentrations. Deaths and graft losses were not evenly distributed among the centers. No demographic or disease-related risk factors were predictive of death associated with belatacept, and similarly, no clear explanation for the higher rates of death observed in the belatacept HD and LD groups was identified. Death and graft loss in the subset of patients who were HCV-positive at the time of transplantation were numerically higher in the belatacept groups at month 6 but comparable with the tacrolimus groups at month 12.\n\nBODY.DISCUSSION:\nThis phase II, randomized, multicenter study was the first clinical trial to explore the use of belatacept in LT recipients. The primary objective was to evaluate the safety and efficacy of belatacept relative to tacrolimus, as reflected by the incidence of AR, graft loss and death in de novo LT recipients. At the conclusion of this study, two of three belatacept groups had higher rates of death and graft loss relative to the standard-of-care control group tacrolimus + MMF. All three belatacept groups also had higher rates of AR, and there was an increase in viral and fungal infections, the majority of which were not serious. Two cases of PTLD and one case of PML were reported in belatacept-treated patients. The two belatacept HD groups had substantially better mGFR than the remaining three groups, while all three belatacept groups had better cGFR. There was also evidence of fewer neurotoxicity events in the belatacept groups. A high rate of discontinuation was observed in the belatacept treatment groups, such that by the time of the 12-month assessment, ∼40% of patients had discontinued assigned belatacept therapy. In contrast to the findings in renal transplant recipients, which showed comparable patient and graft survival relative to the CNI cyclosporine (13–17), this exploratory study in LT recipients demonstrated increased rates of death and graft loss in two of three belatacept groups compared with tacrolimus (different CNI comparator). Multiple factors may account for differences in survival outcomes between kidney transplant and LT recipients, including organ-specific aspects of alloimmune responses (24,25). In the present study, it is notable that basiliximab did not lead to a lower rate of rejection versus placebo in the two belatacept HD groups. There are several hypotheses, including the role of CD28-independent T cells and/or inhibition of regulatory pathways that could explain this observation (26). Further studies are required to understand the mechanism and contribution of these factors to AR in the setting of belatacept therapy. Important nonimmunologic differences include the degree of illness at the time of transplantation, extent of surgical trauma and massive perioperative fluid shifts. Doses of belatacept in this study were higher than those used in the kidney transplant trials, with the assumption that perioperative fluid shifts and fluid losses would necessitate additional belatacept. There was no association between trough belatacept levels and death or graft loss. This was expected, given that there is no exposure–response relationship in the kidney transplant setting, such that therapeutic drug monitoring is not needed with belatacept treatment. While preservation of renal function was a key finding in the pivotal phase III clinical trials of belatacept in renal transplant recipients, the magnitude of the renal function difference in the current study highlights the capacity for native kidneys to recover substantial function following LT in the absence of CNI exposure. The tendency toward more viral and fungal infections observed in belatacept-treated patients raises the possibility of overimmunosuppression in some patients, as observed with regimens that include MMF (27). This finding is somewhat paradoxical, however, given the higher rates of AR in the belatacept groups, which would suggest underimmunosuppression or immunomodulatory effects not yet understood in the context of LT. It is also possible that the management of AR placed patients at risk for subsequent infectious complications. The standard treatment for rejection may have been more intense than was needed in belatacept-treated patients, suggesting that overimmunosuppression may be part of the explanation for the infectious complications. The limited number of patients and events preclude the ability to definitively interpret the relative contributions of overimmunosuppression versus underimmunosuppression. LT recipients are an inherently complex population, with diverse and serious underlying medical concerns that have the potential to adversely affect posttransplant outcomes. Distinguishing the contribution of belatacept alone or an interaction between belatacept and such factors in the context of this phase II study is not feasible. An additional limitation of the study includes the open-label design (belatacept vs. tacrolimus assignments). Findings from this phase II study did not allow for the identification of a safe and effective dose or a regimen for further development of belatacept fulfilling the substantial need for nonnephrotoxic immunosuppressive therapy in LT recipients.\n\nQuestion: Compared to tacrolimus groups what was the result of belatacept groups on Mean calculated GFR at 1 year.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n" } ]	[ { "role": "assistant", "content": "Answer: significantly increased\n" } ]	significantly increased

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.