FedEHR-Agents：面向自动化EHR建模的联邦智能体优化框架
原标题：FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling
AI 摘要
FedEHR-Agents 提出了一种以经验为中心的联邦智能体优化框架，用于自动化电子健康记录（EHR）建模。每个医院部署一个临床智能体，通过历史记忆、任务评估和 TextGrad 提示优化来提炼本地建模经验，联邦服务器则进行证据引导的经验聚合，生成全局元提示。在真实多医院基准上的实验表明，该方法在多种临床预测任务中优于本地和联邦基线，并展示了建模经验作为协作对象的潜力。
正文节选
FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling Abstract. Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling workflows. However, agents deployed at individual hospitals remain constrained by institution-specific data and modeling environments, while direct cross-hospital collaboration is restricted by the sensitivity of patient-level EHR data. Although federated learning