MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus
This work addresses the critical need for transparent and structured AI-driven diagnostic tools in hepatology, offering an incremental improvement over existing LLM-based approaches for clinicians.
This paper tackles the challenge of accurate and interpretable diagnosis of hepatic diseases by proposing MedCoRAG, a framework that generates diagnostic hypotheses and constructs patient-specific evidence packages using UMLS knowledge graphs and clinical guidelines. The system employs multi-agent collaborative reasoning to achieve a traceable consensus diagnosis, outperforming existing methods and closed-source models in diagnostic performance and reasoning interpretability on MIMIC-IV hepatic disease cases.
Diagnosing hepatic diseases accurately and interpretably is critical, yet it remains challenging in real-world clinical settings. Existing AI approaches for clinical diagnosis often lack transparency, structured reasoning, and deployability. Recent efforts have leveraged large language models (LLMs), retrieval-augmented generation (RAG), and multi-agent collaboration. However, these approaches typically retrieve evidence from a single source and fail to support iterative, role-specialized deliberation grounded in structured clinical data. To address this, we propose MedCoRAG (i.e., Medical Collaborative RAG), an end-to-end framework that generates diagnostic hypotheses from standardized abnormal findings and constructs a patient-specific evidence package by jointly retrieving and pruning UMLS knowledge graph paths and clinical guidelines. It then performs Multi-Agent Collaborative Reasoning: a Router Agent dynamically dispatches Specialist Agents based on case complexity; these agents iteratively reason over the evidence and trigger targeted re-retrievals when needed, while a Generalist Agent synthesizes all deliberations into a traceable consensus diagnosis that emulates multidisciplinary consultation. Experimental results on hepatic disease cases from MIMIC-IV show that MedCoRAG outperforms existing methods and closed-source models in both diagnostic performance and reasoning interpretability.