Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies
2026-06-15 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors explain that medical diagnosis and treatment change over time, but current AI mostly gives static results without showing how a patient's health might change or respond to different treatments. They review the idea of 'medical world models,' AI systems that simulate how diseases evolve and help doctors decide on treatments by predicting future outcomes. The paper suggests combining three main abilities—understanding patient states, modeling how diseases progress, and supporting treatment decisions—to create better AI tools. They also discuss challenges in turning simulations into tools useful for real clinical settings.
medical AIpatient-state dynamicsdisease simulationtreatment-effect estimationreinforcement learningdigital twinslongitudinal modelingclinical decision supportworld models
Authors
Ke Liu, Mengxuan Li, Yanyi Bao, Tianyun Zhang, Chong Chu, Jiajun Bu, Haishuai Wang
Abstract
Medical diagnosis and treatment are dynamic processes in which patient states evolve over time and clinical interventions alter future outcomes. Although current medical AI can detect disease, estimate risk and generate reports, many systems still return static labels or scores, offering limited insight into how illness may progress or how alternative interventions may reshape its trajectory. Medical world models adapt the world-model idea from artificial intelligence to healthcare by learning internal simulators of patient-state dynamics. Their long-term goal is to help clinicians anticipate deterioration, compare treatment-conditioned futures and tailor care to individual patients. Yet relevant work remains scattered across foundation models, longitudinal modelling, disease simulation, treatment-effect estimation, reinforcement learning and digital twins. To bridge this gap, this review outlines a roadmap for advancing medical AI from isolated diagnosis and prediction toward medical world models that simulate disease evolution and support intervention decisions. This roadmap is organized around three coupled capabilities: patient-state construction, clinical dynamics modelling and intervention decision support. Across representative systems, the comparison highlights what each capability contributes and how partial components can be integrated into more mature perception--dynamics--planning systems. Finally, we identify the challenges involved in turning plausible rollouts into clinically useful simulators. Related literature is available at https://github.com/1999kevin/awesome_medical_world_models.