发表机构
University of North Carolina at Chapel Hill; Foci Labs; Stevens Institute of Technology（北卡罗来纳大学教堂山分校; Foci Labs; 史蒂文斯理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对ICU世界模型的分布外泛化问题，提出PHYSIO WORLD模型，利用药理规则约束干预效应方向，在多数据库分布偏移场景下显著降低分布外预测误差。
AI 中文摘要
预测患者生命体征对干预措施的响应是重症监护领域的核心问题，世界模型可通过学习作为先前动作函数的动态来实现这一点，但此类模型在训练数据之外往往表现脆弱。临床医生会根据患者状态选择药物剂量，因此模型学到的剂量与结局之间的关联与药物实际效果相反，难以泛化到分布外（OOD）的给药实践中。不过，药理信息提供了不同药物的方向效应，这些效应对分布外偏移具有不变性。为解决当前ICU世界模型的分布外敏感性问题，我们提出PHYSIO WORLD，该模型通过两次前向传播来分离干预的效应：一次使用记录的剂量，另一次将这些剂量设为零，差值被投影到由28种药物的70条规则规定的药理可允许效应方向上，幅度则从数据中学习。在来自三个重症监护数据库的队列的五个分布偏移参数下，与预测器、反事实模型和不变性目标相比，PHYSIO WORLD在所有设置中都取得了最低的分布外RMSE，比最强的外部基线提升了8%-12%，同时匹配其骨干模型的分布内误差。反转药理方向会使准确率降至骨干模型以下，而数据挖掘得到的方向几乎无法恢复任何增益，表明改进源于药理知识的内容。该构造可扩展到其他预先已知效应符号且其幅度被治疗分配混淆的场景。
英文摘要
Predicting how a patient's vital signs respond to an intervention is a central question in intensive care. World models can do so by learning dynamics as a function of prior actions. However, such models tend to be brittle outside of training data. Clinicians choose drug dosages based on the patient's state, so the association a model learns between dose and outcome runs opposite to the drug's effect, generalizing poorly to out-of-distribution (OOD) dosing practices. Yet, pharmacological information provides the directional effects of different drugs, which are invariant to OOD shifts. To resolve the OOD sensitivity of current ICU world models, we introduce PHYSIO WORLD, which isolates an intervention's effect by evaluating a forward pass twice: once under recorded doses, and once with those doses set to zero. The difference is projected onto pharmacologically admissible effect directions stated by 70 rules over 28 drugs, leaving the magnitude to be learned from data. Across five distribution-shift parameters over cohorts from three intensive-care databases, and against forecasters, counterfactual models, and invariance objectives, PHYSIO WORLD attains the lowest OOD RMSE in every setting, improving on the strongest external baseline by 8-12%, while matching the in-distribution error of its backbone. Reversing the pharmacological directions degrades accuracy below the backbone, and data-mined directions recover almost no gain, indicating the improvement derives from the content of the pharmacological knowledge. The construction may extend to other settings where the sign of an effect is known in advance and its magnitude is confounded by treatment assignment.
Comments24 pages, 6 figures, 15 tables
