MedRoute: 基于强化学习的多智能体医疗诊断动态专家路由
MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis
- Institute of Artificial Intelligence, University of Central Florida, Orlando, United States（中佛罗里达大学人工智能研究所，奥兰多，美国）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出MedRoute框架，通过强化学习动态选择专家进行医疗诊断，提升诊断准确性，优于现有基线方法。
AI中文摘要：
利用大多模态模型（LMMs）的医疗诊断能力日益受到关注，因其能提供精确诊断。然而，这些模型通常过于通用，无法适应真实医疗场景中的广泛疾病。在临床实践中，诊断由多个专家共同完成，每个专家提供专业领域知识。为此，本文提出MedRoute框架，采用动态多智能体LMM系统，其中每个智能体扮演医疗专家角色。此外，我们添加了一位经过强化学习训练的全科医生作为动态专家选择器，以及一个生成最终决策的调解器。通过文本和图像医疗数据集的广泛评估，证明了诊断准确性的提升，优于现有最佳基线方法。我们的工作为未来研究奠定了坚实基础。代码和模型可在https://github.com/UCF-CRCV/MedRoute/上获取。
英文摘要：
Medical diagnosis using Large Multimodal Models (LMMs) has gained increasing attention due to capability of these models in providing precise diagnoses. These models generally combine medical questions with visual inputs to generate diagnoses or treatments. However, they are often overly general and unsuitable under the wide range of medical conditions in real-world healthcare. In clinical practice, diagnosis is performed by multiple specialists, each contributing domain-specific expertise. To emulate this process, a potential solution is to deploy a dynamic multi-agent LMM framework, where each agent functions as a medical specialist. Current approaches in this emerging area, typically relying on static or predefined selection of various specialists, cannot be adapted to the changing practical scenario. In this paper, we propose MedRoute, a flexible and dynamic multi-agent framework that comprises of a collaborative system of specialist LMM agents. Furthermore, we add a General Practitioner with an RL-trained router for dynamic specialist selection, and a Moderator that produces the final decision. In this way, our framework closely mirrors real clinical workflows. Extensive evaluations on text and image-based medical datasets demonstrate improved diagnostic accuracy, outperforming the state-of-the-art baselines. Our work lays a strong foundation for future research. Code and models are available at https://github.com/UCF-CRCV/MedRoute/.
