本地部署医疗AI智能体用于可靠临床决策
研究开发并评估了一种完全本地部署的临床AI智能体,采用多视角可靠性框架支持选择性自主。在两个MIMIC-IV衍生基准上,七病任务准确率90.04%,四病任务83.8%。诊断行为一致性对正确性判别最强(AUC=0.860),一致性阈值0.90时保留49.4%病例且诊断准确率98.9%。
要点
- 本地部署智能体七病任务准确率90.04%,接近云端基线
- 诊断行为一致性是判别正确性的最强指标(AUC=0.860)
- 一致性阈值0.90可保留49.4%病例,准确率达98.9%
核心结论
- 完全本地部署的临床AI智能体结合多视角可靠性框架,可支持选择性自主决策。
- 决策时可靠性信号能识别低风险子集自主处理,其余转人工复核。
研究设计与样本
- 开发并评估完全本地部署的临床智能体,耦合本地操作控制与多视角可靠性框架。
- 在两个MIMIC-IV衍生基准上评估七病任务和四病任务的表现。
主要发现
- 七病任务准确率90.04%,四病任务准确率83.8%,主要基准上接近云端基线。
- 诊断行为一致性对正确性判别最强(AUC=0.860),压力测试下仍有信息量(AUC=0.875)。
- 一致性阈值0.90时,49.4%病例被保留,诊断准确率98.9%。
临床怎么用
- 利用决策时可靠性信号筛选低风险病例进行自主处理,其余转人工复核。
- 本地部署满足机构治理要求,支持选择性自主的临床落地。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Autonomous clinical artificial intelligence (AI) agents powered by large language models (LLMs), meaning systems that can complete a diagnostic workflow without continuous human input, are increasingly capable of supporting complex reasoning and decision-making. Clinical translation, however, remains limited by two unmet requirements: institutionally governed deployment and reliable decision-time uncertainty estimation. Here we developed and evaluated a fully on-premise clinical agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy. Across two Medical Information Mart for Intensive Care IV (MIMIC-IV)-derived benchmarks, the agent achieved 90.04% accuracy on a seven-disease task and 83.8% accuracy on a four-disease task, approaching a cloud baseline on the primary benchmark. To assess decision-time reliability, we quantified internal-likelihood, language-based and behavioral-stability measures for diagnosis and reasoning. Diagnostic behavioral consistency provided the strongest discrimination of correctness (area under the curve (AUC) = 0.860) and remained informative under stress testing (AUC = 0.875). At a consistency threshold of 0.90, 49.4% of cases were retained at 98.9% diagnostic accuracy. These findings support a practical framework for institutionally governed clinical agents in which decision-time reliability signals identify a lower-risk subset for autonomous handling and defer the remainder for review.
引用
- Zhang L, Wölflein G, Ferber D, et al. On-premise medical AI agents for reliable clinical decision-making. Nat Med. 2026. PMID: 42744896. doi:10.1038/s41591-026-04609-x
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。