bsenst / llm-enhanced-ehr

Contribution to the LabLabAI AI Challenge Hackathon October 2023

llm-enhanced-ehr

Contribution to the LabLabAI AI Challenge Hackathon October 2023. The application should allow the user to interact with a large language model (GPT-3.5, GPT-4) and support working on synthetic health data that comes in the electronic health record interoperability format FHIR.

Project Team Page & Project Submission Page

Run the application

git clone https://github.com/bsenst/llm-enhanced-ehr

cd llm-enhanced-ehr

pip install -r streamlit/requirements.txt

streamlit run streamlit/app.py

ToDo

• explore synthea dataset
• create a user interface to display (parts of the) synthea data (streamlit, openehr, openemr)
• integrate LLM (clarifai, sketch)
• connect synthea data with LLM (langchain, llama-index, RAG)
• define workflows/queries, document examples
• prepare submission - screenrecording, presentation

Optional features:

• set up free database to store user feedback (streamlit feedback)
• implement LangChain extraction pipeline to turn unstructured to structured medical notes (ideally FHIR format)