cs.LGAug 16, 2026

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

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

Organizations: UCLA Computational Medicine · New York University · UCLA Neurosurgery

Abstract

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.

Explore similar work

CardsList
  1. ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data

    May 21, 2026Jiangyuan Wang, Xuyong Chen, Junwei He +3Action-Conditioned World ModelsLatent Dynamics Modeling

  2. PatientWM: Towards Generalizable Clinical World Models via Unified Patient States

    Oct 12, 2026Ziwen Kan, Jie Peng, Bo Yan +5Action-Conditioned World ModelsClinical Prediction

  3. Learning Continuous Patient Trajectories from Electronic Health Records

    Sep 28, 2026Silas Ruhrberg Estévez, Kara Liu, Christopher Chiu +4Longitudinal EHR ModelingFlow-Based Generative Modeling