Saved in:
Bibliographic Details
Main Authors: Li, Zheng, Xu, Jiayi, Hu, Zhikai, Chen, Hechang, Cong, Lele, Wang, Yunyun, Pang, Shuchao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.05129
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910042393935872
author Li, Zheng
Xu, Jiayi
Hu, Zhikai
Chen, Hechang
Cong, Lele
Wang, Yunyun
Pang, Shuchao
author_facet Li, Zheng
Xu, Jiayi
Hu, Zhikai
Chen, Hechang
Cong, Lele
Wang, Yunyun
Pang, Shuchao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05129
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus
Li, Zheng
Xu, Jiayi
Hu, Zhikai
Chen, Hechang
Cong, Lele
Wang, Yunyun
Pang, Shuchao
Artificial Intelligence
Multiagent Systems
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.
title MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2603.05129