pat-jj/KARE
[ICLR'25] Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
This project helps healthcare professionals and researchers create more accurate patient outcome predictions. It takes Electronic Health Record (EHR) data and combines it with medical knowledge from sources like PubMed and UMLS to build a rich, interconnected knowledge base. The output is an enhanced predictive model that can anticipate patient outcomes such as mortality or readmission.
No commits in the last 6 months.
Use this if you are a healthcare data scientist or clinical researcher looking to improve the accuracy of your predictive models by integrating extensive medical knowledge with patient records.
Not ideal if you need a quick, low-cost solution and don't require the highest predictive performance or custom knowledge graph integration.
Stars
55
Forks
8
Language
Python
License
—
Category
Last pushed
Apr 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/pat-jj/KARE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
snap-stanford/stark
(NeurIPS D&B 2024) STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
cefriel/competence-kg
A tutorial on Knowledge Graphs discussing how to model the employee competences within a company
TIGER-AI-Lab/KB-BINDER
"Few-shot In-context Learning for Knowledge Base Question Answering" [ACL2023]
HKUST-KnowComp/FolkScope
Codes and Datasets for the ACL2023 Findings Paper: FolkScope: Intention Knowledge Graph...
rsinghlab/K-Paths
Official Implementation of K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug...