Research

Paper

AI LLM March 05, 2026

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

Authors

Zheng Li, Jiayi Xu, Zhikai Hu, Hechang Chen, Lele Cong, Yunyun Wang, Shuchao Pang

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.

Metadata

arXiv ID: 2603.05129
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05129v1</id>\n    <title>MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus</title>\n    <updated>2026-03-05T12:58:45Z</updated>\n    <link href='https://arxiv.org/abs/2603.05129v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05129v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-05T12:58:45Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Zheng Li</name>\n    </author>\n    <author>\n      <name>Jiayi Xu</name>\n    </author>\n    <author>\n      <name>Zhikai Hu</name>\n    </author>\n    <author>\n      <name>Hechang Chen</name>\n    </author>\n    <author>\n      <name>Lele Cong</name>\n    </author>\n    <author>\n      <name>Yunyun Wang</name>\n    </author>\n    <author>\n      <name>Shuchao Pang</name>\n    </author>\n  </entry>"
}