Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis

TL;DR

This paper introduces MDTRoom, an interactive system that structures multi-agent discussions for clinical diagnosis, enhancing clinician understanding and intervention in complex, multidisciplinary diagnostic processes.

Contribution

The paper presents a novel interactive workspace that externalizes and visualizes multi-agent debate data to improve clinician engagement and oversight.

Findings

MDTRoom enables efficient inspection of agent reasoning.

Clinicians can intervene and guide agent deliberation more effectively.

The system improves collaboration between clinicians and AI agents.

Abstract

Rare disease diagnosis is inherently challenging due to heterogeneous symptoms, limited clinical familiarity, and fragmented evidence across specialties. Recent large language model (LLM)-based agentic systems have shown promise by simulating multidisciplinary team discussions to generate and evaluate diagnostic hypotheses. However, fully automated diagnosis remains unrealistic, and existing human-in-the-loop approaches provide limited support for effective clinician-agent collaboration. In practice, clinicians are often presented with final diagnostic outputs and lengthy, unstructured agent discussion logs, making it difficult to inspect reasoning, intervene in a timely manner, or guide agent deliberation effectively. To address these challenges, we developed MDTRoom, an interactive system that transforms multi-agent discussions from linear transcripts into a structured, inspectable workspace. The system externalizes patient data, evidence provenance, hypothesis evolution, and inter-agent conflicts as interconnected visual objects, enabling clinicians to efficiently examine, intervene in, and guide agent reasoning. Our evaluation demonstrates the effectiveness of MDTRoom in supporting clinician-agent collaboration.