https://github.com/bsenst/llm-enhanced-ehr
Contribution to the LabLabAI AI Challenge Hackathon October 2023
https://github.com/bsenst/llm-enhanced-ehr
ehr-notes langchain-python llm-inference streamlit-ui
Last synced: about 1 month ago
JSON representation
Contribution to the LabLabAI AI Challenge Hackathon October 2023
- Host: GitHub
- URL: https://github.com/bsenst/llm-enhanced-ehr
- Owner: bsenst
- License: apache-2.0
- Created: 2023-10-11T19:52:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-16T20:23:33.000Z (over 1 year ago)
- Last Synced: 2025-04-22T23:12:21.527Z (about 1 month ago)
- Topics: ehr-notes, langchain-python, llm-inference, streamlit-ui
- Language: Jupyter Notebook
- Homepage: https://llm-enhanced-ehr.streamlit.app/
- Size: 73.2 KB
- Stars: 7
- Watchers: 1
- Forks: 4
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# llm-enhanced-ehr
Contribution to the [LabLabAI AI Challenge Hackathon](https://lablab.ai/event/ai-challenge-with-gpt-3-5-codex-dall-e-and-whisper-api) 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](https://lablab.ai/event/ai-challenge-with-gpt-3-5-codex-dall-e-and-whisper-api/fritzlabs) &
[Project Submission Page](https://lablab.ai/event/ai-challenge-with-gpt-3-5-codex-dall-e-and-whisper-api/fritzlabs/llm-enhanced-medical-notes)
# Run the application
```bash
git clone https://github.com/bsenst/llm-enhanced-ehr
```
```bash
cd llm-enhanced-ehr
```
```bash
pip install -r streamlit/requirements.txt
```
```bash
streamlit run streamlit/app.py
```
# ToDo
- [X] explore [synthea dataset](https://github.com/synthetichealth/synthea)
- [X] create a user interface to display (parts of the) synthea data ([streamlit](https://streamlit.io), [openehr](https://openehr.org), [openemr](https://www.open-emr.org))
- [X] integrate LLM ([clarifai](https://www.clarifai.com), [sketch](https://pypi.org/project/sketch/))
- [X] connect synthea data with LLM ([langchain](https://www.langchain.com/), [llama-index](https://www.llamaindex.ai/), RAG)
- [X] define workflows/queries, document examples
- [X] prepare submission - screenrecording, presentation
Optional features:
- [ ] set up free database to store user feedback ([streamlit feedback](https://github.com/trubrics/streamlit-feedback))
- [ ] implement [LangChain extraction pipeline](https://python.langchain.com/docs/use_cases/extraction) to turn unstructured to structured medical notes (ideally FHIR format)