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

2025-02-06

AI Summary

Current medical RAG models exhibit insufficient accuracy and specificity in differential diagnosis of similar diseases, leading to high misdiagnosis rates. To address this, we propose KG-RAG—a knowledge graph (KG)-guided retrieval-augmented generation framework. KG-RAG introduces a novel four-tier hierarchical diagnostic KG that enables semantic matching with electronic health records (EHRs), dynamically fuses retrieved evidence with disease-discriminative features, and integrates an LLM-driven multi-step reasoning module with an active questioning mechanism. Evaluated on the DDXPlus benchmark and a private chronic pain dataset (CPDD), KG-RAG significantly reduces misdiagnosis rates and achieves superior diagnostic specificity compared to state-of-the-art RAG baselines. The implementation is publicly available.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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 encompassing critical diagnostic differences of various diseases. These differences are dynamically integrated with similar EHRs retrieved from an EHR database, and reasoned within a large language model. This process enables more accurate and specific decision support, while also proactively providing follow-up questions to enhance personalized medical decision-making. MedRAG is evaluated on both a public dataset DDXPlus and a private chronic pain diagnostic dataset (CPDD) collected from Tan Tock Seng Hospital, and its performance is compared against various existing RAG methods. Experimental results show that, leveraging the information integration and relational abilities of the KG, our MedRAG provides more specific diagnostic insights and outperforms state-of-the-art models in reducing misdiagnosis rates. Our code will be available at https://github.com/SNOWTEAM2023/MedRAG

Problem

• Improves diagnostic accuracy in healthcare using RAG.
• Integrates knowledge graphs for disease differentiation.
• Reduces misdiagnosis with advanced reasoning models.

Innovation

• Knowledge graph-enhanced RAG model
• Four-tier hierarchical diagnostic KG
• Dynamic EHR-KG integration reasoning