arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.23862cs.LG
收藏

基于动作条件世界模型的电子病历患者轨迹预测

Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models

UCLA Computational Medicine(加州大学洛杉矶分校计算医学系);New York University(纽约大学);UCLA Neurosurgery(加州大学洛杉矶分校神经外科)

Simon A. Lee, Jiahang Hank Sha, Soomin Chung, Kai Akamatsu, Eran Halperin, Jeffrey N. Chiang

AI总结:

该研究提出EHR WM模型,以动作条件世界模型处理电子病历,通过状态动作条件转移算子建模患者轨迹,参数规模较基础模型小30倍,在相关任务中性能具竞争力且动作敏感。

摘要:

我们提出了一种用于电子病历(EHR)的预测世界模型,该模型将患者病史表示为动作条件下的潜在轨迹。与仅通过自回归令牌预测来建模临床事件不同,我们的框架明确将患者状态与观察到的临床动作分离,并通过状态和动作条件转移算子学习其演化。其核心是一个依赖状态的线性化预测器,该预测器传播潜在患者状态的局部变化,支持时间分辨预测、多步回滚以及动作条件模拟。经验证,生成的潜在轨迹保留了下游预测信号、时间结构以及编码器衍生表示中存在的亚组水平统计关系。我们进一步将自由运行回滚解码为原始临床特征空间,并使用任务匹配的预测基线将未来临床测量值与观察值进行评估,证明学习到的动态保留了超出潜在空间一致性的预测信息。在二分类和事件时间任务中,EHR WM 相对于规模大得多的 EHR 基础模型实现了具有竞争力的性能(尽管依赖于任务),同时参数规模小 30 倍。最后,对观察到的动作序列进行扰动会在生成的轨迹中产生相应变化,证明了学习到的动态的动作敏感性。总之,这些结果支持世界建模作为一种互补框架,用于从纵向 EHR 中学习患者演化的显式时间索引表示。

英文摘要:

We introduce a predictive world model for electronic health records (EHR) that represents patient histories as action conditioned latent trajectories. Rather than modeling clinical events solely through autoregressive token prediction, our framework explicitly separates patient states from observed clinical actions and learns their evolution through a state and action conditioned transition operator. At its core is a state dependent linearization predictor that propagates local changes in latent patient state, enabling time resolved prediction, multi step rollout, and action conditioned simulation. Empirically, we show that generated latent trajectories preserve downstream predictive signal, temporal structure, and subgroup level statistical relationships present in encoder derived representations. We further decode free running rollouts into the original clinical feature space and evaluate future clinical measurements against observed values using task matched forecasting baselines, demonstrating that the learned dynamics retain predictive information beyond latent space agreement. Across binary classification and time to event tasks, EHR WM achieves competitive, though task dependent, performance relative to substantially larger EHR foundation models while using a 30x smaller parameter footprint. Finally, perturbing observed action sequences produces corresponding changes in generated trajectories, demonstrating the action sensitivity of the learned dynamics. Together, these results support world modeling as a complementary framework for learning explicit, time indexed representations of patient evolution from longitudinal EHR.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑