New TRACER framework enhances clinical risk prediction using knowledge graphs and RAG

Researchers have developed TRACER, a novel framework designed to improve clinical risk prediction by integrating heterogeneous external knowledge with Electronic Health Records (EHRs). TRACER constructs a medical knowledge graph that incorporates disease severity information from medical literature. It then retrieves relevant patient progression paths from this graph, extracts key events from unstructured clinical notes, and augments patient context with similar cases. Experiments conducted on the MIMIC-III and MIMIC-IV datasets showed significant improvements, with Macro F1 scores increasing by up to 28.5% for mortality prediction and 19.7% for readmission prediction. AI

IMPACT Enhances clinical risk prediction accuracy by integrating external knowledge and patient data.

RANK_REASON The cluster contains a research paper detailing a new framework for clinical risk prediction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• MIMIC-III
• MIMIC-IV
• ScienceCast
• TRACER

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →