Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
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…
By Simon A. Lee, Jiahang Hank Sha, Soomin Chung, Kai Akamatsu, Eran Halperin, Jeffrey N. ChiangarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 21, 2026.
Comments
Sign in to join the discussion.