# Medical NER based on Bert in Norwegian

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmedical-ner-based-on-bert-in-norwegian%2F44037%3E%5C
**Category:** Research\
**Created:** [June 21, 2023, 12:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmedical-ner-based-on-bert-in-norwegian%2F44037 "2023-06-21T12:17:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hesamossanloo](https://avatars.discourse-cdn.com/v4/letter/h/6de8d8/32.png) [@hesamossanloo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhesamossanloo)%5C
**Post date:** [June 21, 2023, 12:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmedical-ner-based-on-bert-in-norwegian%2F44037%2F1 "2023-06-21T12:17:21Z")

</div>

Hi, community. I am trying to build an app that extracts Patient Sensitive Data, Diagnoses, Procedures, and Treatments from a Patient Note. The Patient notes are in Norwegian. My goal is to reach 90%+ accuracy. What do you recommend on how to achieve this?  
Should I fine-tune it into English first and then translate it into Norwegian? Or should I fine-tune directly based on Norwegian data?

Please consider that I can access a high volume of already anonymized quality patient data in English and a minimal volume not anonymized in Norwegian.

Looking forward to your feedback 🤗
