Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MedCollab: Causal-Driven Multi-Agent Collaboration for Full-Cycle Clinical Diagnosis via IBIS-Structured Argumentation

Yuqi Zhan, Xinyue Wu, Tianyu Lin, Yutong Bao, Xiaoyu Wang, Weihao Cheng, Huangwei Chen, Feiwei Qin, Zhu Zhu

TL;DR

Evaluated on real-world clinical datasets, MedCollab significantly outperforms pure LLMs and medical multi-agent systems in Accuracy and RaTEScore, demonstrating a marked reduction in medical hallucinations.

Abstract

Large language models (LLMs) have shown promise in healthcare applications, however, their use in clinical practice is still limited by diagnostic hallucinations and insufficiently interpretable reasoning. We present MedCollab, a novel multi-agent framework that emulates the hierarchical consultation workflow of modern hospitals to autonomously navigate the full-cycle diagnostic process. The framework incorporates a dynamic specialist recruitment mechanism that adaptively assembles clinical and examination agents according to patient-specific symptoms and examination results. To ensure the rigor of clinical work, we adopt a structured Issue-Based Information System (IBIS) argumentation protocol that requires agents to provide ``Positions'' backed by traceable evidence from medical knowledge and clinical data. Furthermore, the framework constructs a Hierarchical Disease Causal Chain that transforms flattened diagnostic predictions into a structured model of pathological progression through explicit logical operators. A multi-round Consensus Mechanism iteratively filters low-quality reasoning through logic auditing and weighted voting. Evaluated on real-world clinical datasets, MedCollab significantly outperforms pure LLMs and medical multi-agent systems in Accuracy and RaTEScore, demonstrating a marked reduction in medical hallucinations. These findings indicate that MedCollab provides an extensible, transparent, and clinically compliant approach to medical decision-making.

MedCollab: Causal-Driven Multi-Agent Collaboration for Full-Cycle Clinical Diagnosis via IBIS-Structured Argumentation

TL;DR

Evaluated on real-world clinical datasets, MedCollab significantly outperforms pure LLMs and medical multi-agent systems in Accuracy and RaTEScore, demonstrating a marked reduction in medical hallucinations.

Abstract

Large language models (LLMs) have shown promise in healthcare applications, however, their use in clinical practice is still limited by diagnostic hallucinations and insufficiently interpretable reasoning. We present MedCollab, a novel multi-agent framework that emulates the hierarchical consultation workflow of modern hospitals to autonomously navigate the full-cycle diagnostic process. The framework incorporates a dynamic specialist recruitment mechanism that adaptively assembles clinical and examination agents according to patient-specific symptoms and examination results. To ensure the rigor of clinical work, we adopt a structured Issue-Based Information System (IBIS) argumentation protocol that requires agents to provide ``Positions'' backed by traceable evidence from medical knowledge and clinical data. Furthermore, the framework constructs a Hierarchical Disease Causal Chain that transforms flattened diagnostic predictions into a structured model of pathological progression through explicit logical operators. A multi-round Consensus Mechanism iteratively filters low-quality reasoning through logic auditing and weighted voting. Evaluated on real-world clinical datasets, MedCollab significantly outperforms pure LLMs and medical multi-agent systems in Accuracy and RaTEScore, demonstrating a marked reduction in medical hallucinations. These findings indicate that MedCollab provides an extensible, transparent, and clinically compliant approach to medical decision-making.
Paper Structure (11 sections, 6 equations, 3 figures, 2 tables)

This paper contains 11 sections, 6 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology: MedCollab
  3. Preliminaries: Dynamic Agent Recruitment
  4. IBIS-Structured Argumentation for Diagnostic Reasoning
  5. Hierarchical Disease Causal Chain (HDCC) Construction
  6. Consensus Optimization and Logic Auditing
  7. Experiments and Results
  8. Experimental Setup
  9. Main Results and Analysis
  10. Ablation Study
  11. Conclusion

Figures (3)

  • Figure 1: MedCollab workflow with key parts of the final report highlighted in red.
  • Figure 2: The pipeline of MedCollab. The framework autonomously navigates clinical diagnosis through dynamic agent recruitment, IBIS-structured argumentation for traceable reasoning, and the construction of a HDCC optimized by GP-led consensus.
  • Figure 3: Radar chart comparison of multidimensional report quality metrics (BLEU, ROUGE-L, and RaTEScore) across four clinical dimensions (DB, DD, TX, and TP) on ClinicalBench and MIMIC-IV.