constantjxyz/KERAP
Code repo for paper "KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs"
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.
Stars
12
Forks
3
Language
Python
License
—
Category
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.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents