发表机构
University of Central Florida; Université de Montréal（中佛罗里达大学; 蒙特利尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PrivMeSA通过强化学习控制披露并复用远程经验，在保护隐私的同时提升医学多智能体任务准确率，显著降低再识别风险。
AI 中文摘要
本地部署的临床大语言模型（LLM）智能体可以咨询更强大的远程模型，但这样做存在泄露患者信息的风险。注重隐私的委托将披露决策交由本地智能体负责，然而移除显式标识符并不足够：准标识符可能在多轮咨询和重复患者就诊中累积，从而实现重新识别。我们提出PrivMeSA，一种隐私感知的自进化多智能体系统，它学习控制披露并将远程专业知识保留以供本地复用。本地智能体管理每次就诊并咨询可能请求额外信息的远程专家。强化学习在任务准确性与直接披露和基于注册表的重新识别风险之间取得平衡，隐私评估基于每次就诊的完整出站记录。本地经验记忆将完成的咨询提炼为通用临床指导，并在传输前检索相关经验，使后续病例无需再次远程交换即可复用专业知识。记忆增长无需额外结果标签或参数更新。在基于MIMIC-IV-ED记录构建的急诊科基准上，PrivMeSA相比委托方式将平均任务准确率提高了最多15.8个百分点。在同一设置下，PrivMeSA将个人详细信息披露的病例比例从98.0%降至0.2%，并将患者可被缩小至注册表中十名或更少患者的病例比例从74%降至0%。
英文摘要
Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Privacy-conscious delegation places disclosure decisions with a local agent, yet removing explicit identifiers is insufficient: quasi-identifiers can accumulate across multi-turn consultations and repeated patient visits to enable re-identification. We introduce PrivMeSA, a privacy-aware self-evolving multi-agent system that learns to control disclosure and retains remote expertise for local reuse. A local agent manages each encounter and consults remote specialists that may request additional information. Reinforcement learning balances task accuracy against direct disclosure and registry-based re-identification risk, with privacy evaluated over the complete outbound transcript of each encounter. A local lesson memory distills completed consultations into generalized clinical guidance and retrieves relevant lessons before transmission, allowing subsequent cases to reuse expertise without another remote exchange. Memory grows without additional outcome labels or parameter updates. On an emergency-department benchmark built from MIMIC-IV-ED records, PrivMeSA improves mean task accuracy over delegation by up to 15.8 percentage points. In the same setting, PrivMeSA reduces the disclosure of personal details from 98.0% to 0.2% of cases and the share of cases in which the patient can be narrowed to ten or fewer registry patients from 74% to 0%.
