DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making
This addresses the need for more realistic interactive medical decision-making systems, though it appears incremental as it builds on existing multi-agent and LLM approaches.
The paper tackles the problem that existing medical AI frameworks focus on single-turn tasks with full case information, which diverges from real-world diagnostic processes that are uncertain and iterative. They introduce DynamiCare, a dynamic multi-agent framework that models clinical diagnosis as a multi-round interactive loop, and demonstrate its feasibility and effectiveness through experiments, establishing the first benchmark for dynamic clinical decision-making with LLM-powered agents.
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.