基于潜在随机微分方程的临床时间序列生成建模

来自电子健康记录和医学登记册的临床时间序列数据提供了 unprecedented 的机会来理解患者轨迹并为医疗决策提供信息。然而，利用此类数据面临诸多挑战，包括不规则抽样、复杂潜在生理以及测量和疾病进程中固有的不确定性。为了应对这些挑战，我们提出一种基于潜在神经随机微分方程（SDEs）的生成式建模框架，将临床时间序列视为 Underlying 受控随机动力学系统的离散时间部分观测。我们的 methods models latent dynamics via neural SDEs with modality-dependent emission models, while performing state estimation and parameter learning through variational inference. This formulation naturally handles irregularly sampled observations, learns complex non-linear interactions, and captures the stochasticity of disease progression and measurement noise within a unified scalable probabilistic framework. We validate the framework on two complementary tasks: (i) individual treatment effect estimation using a simulated pharmacokinetic-pharmacodynamic (PKPD) model of lung cancer, and (ii) probabilistic forecasting of physiological signals using real-world intensive care unit (ICU) data from 12,000 patients. Results show that our framework outperforms ordinary differential equation and long short-term memory baseline models in accuracy and uncertainty estimation. These results highlight its potential for enabling precise, uncertainty-aware predictions to support clinical decision-making.