返回全部动态
Google DeepMind 推出 AI 联合临床医生，强化医疗 AI 安全与评估
原标题：Enabling a new model for healthcare with AI co-clinician
AI 摘要
Google DeepMind 发布了 AI co-clinician 项目，这是一种用于临床环境的 AI 系统，采用双智能体架构（Planner 和 Talker）以确保安全边界，并优先进行临床级证据的验证和引用检查。目前正与美国、印度、澳大利亚等地的学术和医疗机构合作进行分阶段评估，但现阶段不用于疾病诊断或治疗。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Engineering trust with safeguards for clinical-grade AI The transition and deployment of AI into clinical environments requires uncompromising architectural and operational safeguards. In our research on simulations of patient-facing telemedical conversations, AI co-clinician uses a dual-agent architecture: a "Planner" module continuously monitors the conversation, verifying that the "Talker" agent stays within safe clinical boundaries. Similarly, to meet doctors’ needs AI co-clinician prioritiz
发布时间：2026-04-30 20:14
抓取时间：2026-09-07 04:48
来源机构：Google DeepMind