constantjxyz/KERAP

Code repo for paper "KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs"

27
/ 100
Experimental

This project helps medical professionals predict a patient's future health risks by analyzing their past medical data, like electronic health records (EHRs). It takes patient records and a biomedical knowledge graph as input, then uses a sophisticated reasoning process to provide highly accurate disease diagnoses. Physicians, clinical researchers, and healthcare data analysts would use this to support early intervention and personalized patient care.

No commits in the last 6 months.

Use this if you need to perform zero-shot diagnosis prediction, meaning predicting conditions without prior training examples for specific diagnoses, by leveraging existing patient data and extensive medical knowledge graphs.

Not ideal if you require real-time, instantaneous diagnostic predictions in an emergency setting or if you do not have access to structured electronic health records and a comprehensive biomedical knowledge graph.

medical-diagnosis electronic-health-records clinical-prediction healthcare-analytics patient-risk-assessment
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Python

License

Last pushed

Mar 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/constantjxyz/KERAP"

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