MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus

2026-03-05

AI Summary

This study addresses the persistent challenges of insufficient diagnostic accuracy and lack of interpretability in AI-based liver disease diagnosis. The authors propose MedCoRAG, a novel end-to-end interpretable diagnostic framework that integrates hybrid evidence retrieval with multi-specialist agent collaborative reasoning. The approach generates diagnostic hypotheses from standardized abnormalities and constructs patient-specific evidence packages by leveraging UMLS knowledge graph paths and structured clinical guidelines. Multi-disciplinary diagnostic decisions are achieved through role-specialized agents employing iterative reasoning and consensus mechanisms, emulating real-world case conferences. Evaluated on the MIMIC-IV liver disease dataset, MedCoRAG significantly outperforms existing methods and closed-source models in both diagnostic accuracy and interpretability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Search and Optimization: Metareasoning and Metaheuristics

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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• hepatic disease diagnosis
• interpretability
• evidence retrieval
• multi-agent reasoning
• clinical decision support

Innovation

• Retrieval-Augmented Generation
• Multi-Agent Collaboration
• Knowledge Graph Integration
• Interpretable Diagnosis
• Clinical Decision Support