EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical Trajectories

TL;DR

EHRWorld is a causal, patient-centric world model trained on longitudinal EHR data that outperforms large language models in simulating long-term clinical trajectories and disease progression.

Contribution

The paper introduces EHRWorld, a novel causal sequential training paradigm and a large-scale clinical dataset, enabling more accurate and stable long-horizon medical simulations.

Findings

EHRWorld outperforms naive LLM baselines in long-term clinical simulation.

EHRWorld achieves better modeling of sensitive clinical events.

EHRWorld demonstrates improved reasoning efficiency in medical trajectory prediction.

Abstract

World models offer a principled framework for simulating future states under interventions, but realizing such models in complex, high-stakes domains like medicine remains challenging. Recent large language models (LLMs) have achieved strong performance on static medical reasoning tasks, raising the question of whether they can function as dynamic medical world models capable of simulating disease progression and treatment outcomes over time. In this work, we show that LLMs only incorporating medical knowledge struggle to maintain consistent patient states under sequential interventions, leading to error accumulation in long-horizon clinical simulation. To address this limitation, we introduce EHRWorld, a patient-centric medical world model trained under a causal sequential paradigm, together with EHRWorld-110K, a large-scale longitudinal clinical dataset derived from real-world electronic health records. Extensive evaluations demonstrate that EHRWorld significantly outperforms naive LLM-based baselines, achieving more stable long-horizon simulation, improved modeling of clinically sensitive events, and favorable reasoning efficiency, highlighting the necessity of training on causally grounded, temporally evolving clinical data for reliable and robust medical world modeling.