MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot

Retrieval-augmented generation (RAG) is a well-suited technique for retrieving privacy-sensitive Electronic Health Records (EHR).It can serve as a key module of the healthcare copilot, helping reduce misdiagnosis for healthcare practitioners and patients.However, the diagnostic accuracy and specificity of existing heuristic-based RAG models used in the medical domain are inadequate, particularly for diseases with similar manifestations.This paper proposes MedRAG, a RAG model enhanced by knowledge graph (KG)-elicited reasoning for the medical domain that retrieves diagnosis and treatment recommendations based on manifestations.MedRAG systematically constructs a comprehensive four-tier hierarchical diagnostic KG…

• NR
  National Research Foundation
• NR
  National Research Foundation Singapore

  Awards: NRF-NRFI05-2019-0002, RIE2025
• NT
  Nanyang Technological University

  Award: Tier 1
• KO
  Knut och Alice Wallenbergs Stiftelse