Update README.md

README.md

@@ -1,91 +1,120 @@
----
-title: Sundew Diabetes Watch - ADVANCED
-sdk: docker
-colorFrom: green
-colorTo: blue
-pinned: true
-emoji: 🌿
-license: mit
----
-# 🌿 Sundew Diabetes Watch — ADVANCED EDITION
-
-**Mission:** Low-cost, energy-aware diabetes risk monitoring for everyone — especially communities across Africa.
-
-This app showcases the **full power of Sundew's bio-inspired adaptive algorithms** with:
-- ✨ **PipelineRuntime** with custom DiabetesSignificanceModel
-- 📊 **Real-time energy tracking** with bio-inspired regeneration
-- 🎯 **PI control threshold adaptation** with live visualization
-- 📈 **Bootstrap confidence intervals** for statistical validation
-- 🔬 **6-factor diabetes risk** computation (glycemic deviation, velocity, IOB, COB, activity, variability)
-- 🤖 **Ensemble model** (LogReg + RandomForest + GBM)
-- 💾 **Telemetry export** for hardware validation workflows
-- 🌍 **89.8% energy savings** vs always-on inference (validated on real CGM data)
-
-## ✅ Proven Results
-
-Tested on 216 continuous glucose monitoring events (18 hours):
-- **Activation Rate**: 10.2% (22/216 events) — intelligently selective
-- **Energy Savings**: 89.8% — critical for battery-powered wearables
-- **Risk Detection**: Correctly identifies hypoglycemia (<70 mg/dL) and hyperglycemia (>180 mg/dL)
-- **Adaptive Thresholds**: PI controller dynamically adjusts from 0.1 to 0.95 based on glucose patterns
-
-## 🚀 Quick Start
-
-1. **Try the demo**: Visit [Sundew Diabetes Watch](https://huggingface.co/spaces/mgbam/sundew_diabetes_watch)
-2. **Upload sample data**: Download [sample_diabetes_data.csv](https://huggingface.co/spaces/mgbam/sundew_diabetes_watch/blob/main/sample_diabetes_data.csv) (or use the synthetic example)
-3. **Watch it work**: See real-time significance scoring, threshold adaptation, and energy tracking
-4. **Experiment**: Adjust Energy Pressure, Gate Temperature, and preset configurations
-
-## How It Works
-
-1. **Upload CGM Data**: CSV with `timestamp, glucose_mgdl, carbs_g, insulin_units, steps, hr`
-2. **Custom Significance Model**: Computes multi-factor diabetes risk score
-3. **Sundew Gating**: Adaptively decides when to run heavy ensemble model
-4. **PI Control**: Threshold auto-adjusts to maintain target activation rate
-5. **Energy Management**: Bio-inspired regeneration + realistic consumption costs
-6. **Statistical Validation**: Bootstrap 95% CI for F1, Precision, Recall
-7. **Telemetry Export**: JSON download for hardware power measurement correlation
-
-## Live Visualizations
-
-- **Glucose Levels**: Real-time CGM data
-- **Significance vs Threshold**: Watch the PI controller adapt!
-- **Energy Level**: Bio-inspired regeneration visualization
-- **6-Factor Risk Components**: Interpretable diabetes scoring breakdown
-- **Performance Dashboard**: F1, Precision, Recall with confidence intervals
-- **Alerts**: High-risk event notifications
-
-## Configuration Presets
-
-- **custom_health_hd82**: Healthcare-optimized (82% energy savings, 0.196 recall)
-- **tuned_v2**: Balanced general-purpose baseline
-- **auto_tuned**: Dataset-adaptive configuration
-- **conservative**: Maximum energy savings (low activation)
-- **energy_saver**: Battery-optimized for edge devices
-
-> **Disclaimer:** Research prototype. Not medical advice. Not FDA/CE approved.
-
-## Developing Locally
-
-```bash
-python -m venv .venv && source .venv/bin/activate  # Windows: .venv\Scripts\activate
-pip install -r requirements.txt
-streamlit run app_advanced.py
-```
-
-## Technical Details
-
-- **Algorithm**: Sundew bio-inspired adaptive gating
-- **Model**: Ensemble (LogReg + RandomForest + GBM)
-- **Risk Factors**: 6-component diabetes-specific significance model
-- **Control**: PI threshold adaptation with energy pressure feedback
-- **Energy Model**: Random regeneration (1.0–3.0 per tick) + realistic costs
-- **Validation**: Bootstrap resampling (1000 iterations) for 95% CI
-
-## References
-
-- [Sundew Algorithms](https://github.com/anthropics/sundew-algorithms)
-- [Documentation](https://huggingface.co/spaces/mgbam/sundew_diabetes_watch/blob/main/CLAUDE.md)
-- [Paper](https://arxiv.org/abs/your-paper-here) (coming soon)
-
-Built with ❤️ for underserved communities worldwide
+---
+title: Sundew Diabetes Commons
+sdk: docker
+colorFrom: blue
+colorTo: green
+pinned: true
+emoji: 🕊️
+license: mit
+---
+
+# 🕊️ Sundew Diabetes Commons  
+### Free, compassionate care for every person, everywhere
+
+> **Our promise:** Diabetes care should be hopeful, human, and free. Sundew Diabetes Commons is an open platform that blends real‑time monitoring, full‑cycle treatment support, and community empowerment. Powered by Sundew’s bio‑inspired adaptive intelligence, it’s designed for clinics, caregivers, and families who refuse to let cost or infrastructure stand in the way of wellness.
+
+---
+
+## 🌍 Why we built this
+
+- **Half a billion** people live with diabetes; far too many go untreated because care is expensive or hard to reach.  
+- **Daily life is demanding**: glucose checks, medication schedules, activity, meals, stress, sleep, and emotional health all intersect.  
+- **We can do better**. Sundew’s adaptive gating conserves energy and compute so life-saving insights stay available—even on low-cost devices in remote communities.
+
+**Sundew Diabetes Commons** unites monitoring, prediction, lifestyle guidance, and social support into a single, open resource.
+
+---
+
+## 🧠 What’s inside
+
+| Pillar | How Sundew helps | Included tools |
+| ------ | ---------------- | -------------- |
+| **Early sensing** | Continuous glucose & vitals intake with Sundew’s adaptive gating | CGM/FGM ingestion, wearable streams, manual diaries |
+| **Full-cycle treatment** | Medication titration, IOB/COB tracking, doctor-ready summaries | Medication planner, automated visit reports, clinician handoff sheets |
+| **Lifestyle & mental health** | Nutrition cues, sleep & activity nudges, mood check‑ins | Recipe library, culturally aware meal prompts, gratitude journal |
+| **Community & access** | Shareable alerts, family dashboards, clinic-ready APIs | Caregiver SMS, telehealth hooks, clinic kiosks |
+| **Equitable coverage** | Works offline, in low-bandwidth, and on <$50 hardware | Lightweight Sundew runtimes, SMS/USSD pipeline, solar-ready builds |
+| **Open innovation** | Everything open-source; mentors & global volunteers welcome | APIs, data guides, governance playbook, deployment recipes |
+
+---
+
+## 🏗️ Platform architecture
+
+1. **Data fabric** – Streams CGM sensors, wearables, and manual logs into a unified timeline.  
+2. **Adaptive core** – Sundew PipelineRuntime gates “heavy” analytics (e.g., ensemble risk scoring) to save power.  
+3. **Insight engines** – Predict hypoglycemia/hyperglycemia, learn daily rhythms, measure recovery, flag medication gaps.  
+4. **Whole-life lens** – Combines medication, movement, nutrition, sleep, mood, and social support.  
+5. **Storytelling layer** – Visual tools that translate data into empathetic care guidance for clinicians and families.  
+6. **Community commons** – APIs, sample deployments, and stewardship to keep care local and contextual.
+
+---
+
+## 🌟 What’s new in this edition
+
+- **Humanitarian thresholds** (maternal populations, paediatrics, low-resource clinics) now configurable through structured configs.  
+- **Bypass safety**, so critical vitals alert even if a probabilistic gate would have skipped them.  
+- **Energy telemetry** exposes percent + raw joules + projected days, for better solar/battery planning.  
+- **Streamlit prototypes** for quick demos and advanced clinics (see `sundew_diabetes_watch_streamlit_app_prototype.py` and `app.py`).  
+- **Unit-tested humanitarian monitor** ensuring bypass safety and energy accounting stay correct.
+
+---
+
+## 🚀 Quick start (free & open)
+
+```bash
+git clone https://github.com/your-org/sundew-algorithms.git
+cd sundew_algorithms/diabetes/sundew_diabetes_watch
+python -m venv .venv && source .venv/bin/activate        # Windows: .venv\Scripts\activate
+pip install -r requirements.txt
+streamlit run app.py
+Short on resources? Try our lightweight prototype:
+
+bash
+
+streamlit run ../sundew_diabetes_watch_streamlit_app_prototype.py
+Everything runs locally, free of charge. No license fees. No cloud lock-in.
+
+💝 For clinics, communities, and families
+Community health workers – Offline-first kits with SMS/USSD alerting and printable action sheets.
+Clinics & hospitals – API integrations, dashboard widgets, and HL7/FHIR-ready summaries.
+Family caregivers – Mobile progress stories, medication reminders, and shared calendars.
+Researchers & students – Open notebooks, synthetic datasets, fairness dashboards, reproducibility guides.
+🔄 Full-cycle support
+Assess – Real-time sensing, rapid detection, contextual risk scoring.
+Act – Personalized treatment and lifestyle recommendations with clear steps.
+Adapt – PI-controlled thresholds recalibrate around each person’s unique rhythms.
+Advance – Telemetry and reports feed continuous improvement across clinics and communities.
+🔐 Privacy, ethics & equity
+Works offline by default; nothing leaves the device unless you opt in.
+De-identified sharing governed by a community-first data pledge.
+Cultural & gender sensitivity baked into messaging and workflows.
+Internationalization support (linguistically and locally customizable).
+Bias monitoring & fairness metrics included in dashboards.
+🛠️ Build with us
+How to help	What to do
+🌱 Contribute code	Issues tagged help-wanted. We pair mentors with first-time contributors.
+🤝 Localize	Add new languages, culturally relevant recipes, and lifestyle guidance.
+📊 Share data	Contribute synthetic or consenting real-world datasets for benchmarking.
+📚 Teach	Host community workshops—even offline. Slides and curricula included.
+💬 Advocate	Partner with NGOs, ministries of health, or grassroots clinics to deploy kits.
+We maintain a Sundew Commons Governance Playbook to keep decisions transparent, equitable, and community-driven.
+
+🔭 Roadmap highlights
+💬 Conversational guidance in major world languages
+🧬 Integration with affordable CGM/FGM hardware
+👶 Specialized modules for paediatric and maternal care
+🧘 AI-driven mindfulness & mental health support
+🔌 Drop-in bridge for national EHR/EMR ecosystems
+🌐 Regional deployment programs led by local stewards
+📝 License
+MIT – because diabetes care should be free.
+
+🙏 Gratitude
+To the clinicians, caregivers, researchers, volunteers, and families shaping this commons: we see you, we thank you, and we’re building this with you.
+
+Sundew Diabetes Commons – powered by empathy, science, and the belief that healthcare belongs to everyone.
+
+vbnet
+
+
+Let me know if you’d like help applying this rewrite to the repo or tailoring it for a specific deployment!