将AI从孤立助手转变为多方协作决策中介，提升医疗团队协同效率。
Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators
- 将AI定位为多角色医疗协作中的协调者，而非独立工具。
- 实证显示碎片化认知与目标错位是依从性差的主因，孤立使用AI无效。
- 提出可保留人类决策权的协作框架，促进共同理解与信息共享。
基于大语言模型的健康智能体正被健康消费者和临床人员用于解读健康信息并指导决策。然而，当前多数医疗AI系统以孤立模式运行，仅服务单一用户，忽视了医疗中多利益相关方互动的核心特征。这种使用方式易导致理解碎片化，加剧患者、照护者与临床医生之间的目标分歧。本文重新定义AI角色：不作为独立助手，而是嵌入多方诊疗互动中的协作中介。通过一个经临床验证的虚构儿科慢性肾病案例研究，我们发现依从性下降源于情境认知割裂与目标错位，而通用型AI工具的孤立使用无法弥合这些协作缺口。为此，我们提出一种概念性框架，旨在设计能够揭示上下文信息、调和认知模型、搭建共享理解的AI协作机制，同时保障人类的最终决策权。
原文摘要 · Abstract (English)
Large language model based health agents are increasingly used by health consumers and clinicians to interpret health information and guide health decisions. However, most AI systems in healthcare operate in siloed configurations, supporting individual users rather than the multi-stakeholder relationships central to healthcare. Such use can fragment understanding and exacerbate misalignment among patients, caregivers, and clinicians. We reframe AI not as a standalone assistant, but as a collaborator embedded within multi-party care interactions. Through a clinically validated fictional pediatric chronic kidney disease case study, we show that breakdowns in adherence stem from fragmented situational awareness and misaligned goals, and that siloed use of general-purpose AI tools does little to address these collaboration gaps. We propose a conceptual framework for designing AI collaborators that surface contextual information, reconcile mental models, and scaffold shared understanding while preserving human decision authority.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。