DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making

2025-07-03

AI Summary

Existing medical decision-making frameworks predominantly employ static, single-turn modeling, failing to capture the iterative, interactive, and dynamically evolving nature of real-world clinical diagnosis. Method: We propose DynamiCare—the first multi-agent framework designed for open-ended, dynamic clinical decision-making—accompanied by the MIMIC-Patient dataset. Our approach introduces a novel dynamic agent collaboration mechanism enabling multi-turn patient interviews, real-time policy adaptation, and incremental integration of clinical evidence. The patient agent jointly models large language models and electronic health records, while the clinical agent orchestrates multi-agent collaborative reasoning to simulate authentic clinician–patient interactions. Results: Experiments demonstrate significant improvements in diagnostic accuracy for complex cases and enhanced procedural rationality of decision-making workflows. DynamiCare establishes the first benchmark for dynamic clinical decision-making, advancing both methodology and evaluation in AI-assisted healthcare.

Technology Category

• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

The rise of Large Language Models (LLMs) has enabled the development of specialized AI agents with domain-specific reasoning and interaction capabilities, particularly in healthcare. While recent frameworks simulate medical decision-making, they largely focus on single-turn tasks where a doctor agent receives full case information upfront -- diverging from the real-world diagnostic process, which is inherently uncertain, interactive, and iterative. In this paper, we introduce MIMIC-Patient, a structured dataset built from the MIMIC-III electronic health records (EHRs), designed to support dynamic, patient-level simulations. Building on this, we propose DynamiCare, a novel dynamic multi-agent framework that models clinical diagnosis as a multi-round, interactive loop, where a team of specialist agents iteratively queries the patient system, integrates new information, and dynamically adapts its composition and strategy. We demonstrate the feasibility and effectiveness of DynamiCare through extensive experiments, establishing the first benchmark for dynamic clinical decision-making with LLM-powered agents.

Problem

• Simulates dynamic multi-round medical diagnosis process
• Addresses uncertainty in real-world clinical decision-making
• Integrates iterative specialist interactions for patient care

Innovation

• Dynamic multi-agent framework for medical decisions
• MIMIC-Patient dataset enables patient-level simulations
• Multi-round interactive loop for clinical diagnosis