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

2026-02-03

AI Summary

This work addresses the challenge of maintaining patient state consistency in long-term clinical trajectory simulation with large language models, where error accumulation under intervention sequences remains a critical limitation. To this end, we propose the first causal temporal world model for healthcare grounded in real-world electronic health records (EHRs), accompanied by EHRWorld-110K—a large-scale longitudinal clinical dataset. Our patient-centered model explicitly captures the temporal causal relationships between disease progression and treatment responses through causal sequence modeling. Evaluated on long-horizon simulations, it significantly outperforms baseline approaches in terms of state stability, capability to model rare yet clinically significant events, and computational efficiency during inference.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Reasoning under Uncertainty: Causality

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Large language models for search

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.

Problem

• world models
• long-horizon clinical trajectories
• patient state consistency
• error accumulation
• clinical simulation

Innovation

• world model
• long-horizon simulation
• causal sequential modeling
• electronic health records
• patient-centric modeling