ritaranx/RAM-EHR

[ACL 2024] This is the code for our paper ”RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records“.

24
/ 100
Experimental

Combines retrieval-augmented generation with hypergraph neural networks to enhance clinical predictions on EHR data, integrating external medical knowledge from MeSH, DrugBank, and PubMed. The approach leverages both structured patient visit graphs and language models for prediction, with knowledge summaries generated via GPT-3.5. Includes synthetic MIMIC-III examples and utilities for querying external medical databases to augment sparse clinical codes with contextual information.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 8 / 25

How are scores calculated?

Stars

41

Forks

3

Language

Python

License

MIT

Last pushed

Sep 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ritaranx/RAM-EHR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.