Driving · 2026-11-06
Learning a patient world model for health system simulation in intensive care
Yingtai Li, Ruoyan Wang, Yu Li, Shaohua Kevin Zhou
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors propose a time-conditioned patient world model (pWM) trained on longitudinal EHRs (MIMIC-IV). The frozen pWM is coupled to a discrete-event virtual ICU via scenario-specific mappings to generate admission, care tasks, and discharge proposals. Experiments show it matches Markov/semi-Markov comparators on aggregate occupancy and directional policy responses, and it recovers a 24-h recovery difference that compact state models miss.
Why it matters
Health system simulation often relies on fit-for-purpose compact state abstractions that may omit history-dependent dynamics and require redesign for new policy questions. The authors’ approach aims to use one shared learned patient representation for multiple ICU simulation scenarios by coupling time-queryable model predictions to operational demand mappings without retraining.
Method
- Learn a time-conditioned patient world model from longitudinal EHRs as sparse state-event sequences over a clinical vocabulary, predicting future states/events across continuous forecast intervals.
- Freeze the trained model and query it at future times during discrete-event simulation; sampled updates are appended to patient history before the next query.
- Couple frozen pWM outputs to scenario-specific mappings for ICU admission demand, organ-support care tasks, and discharge/transfer requests within a virtual ICU.
Abstract (from arXiv)
Designing healthcare strategies requires anticipating their clinical and operational consequences before implementation, a task that often relies on health system simulation. Such a simulation necessitates modeling how patient states evolve and generate care demands. However, conventional approaches typically tailor compact state transitions to a single policy question and omit history-dependent dynamics, thus requiring the redefinition of states and transitions when there is a new question that entails different clinical information. We propose to learn a patient world model from longitudinal EHRs using a neural network to provide a shared clinical representation of patient trajectories that can serve simulation questions across scenarios. Taking ICU operations as an example, we train the model on MIMIC-IV, freeze it, and couple its time-queryable predictions to shared ICU calendars, resources, and queues via scenario-specific mappings, so that one model renders admission demand, care tasks, and discharge proposals across simulations evaluating ICU bed capacity, care dispatch, and post-ICU transfer capacity. Experiments show that our model matches Markov and semi-Markov comparators in aggregate occupancy and directional responses to capacity and dispatch policies. It also reproduces policy gains from replayed observed trajectories. For patients entering the same support state from different prior trajectories, the learned representation captures a 24-h recovery difference (-6.4 predicted versus -6.7 observed percentage points), a contrast missed by compact state models, which propagates into distinct simulated care demand, queue burden, and bed use. These results indicate that a learned world model of patient dynamics has the potential to replace question-specific state models, allowing new care policies to be evaluated by reconfiguring the scenario without model rebuilding.
Related papers
- PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
- Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
- Same Predictions, Different Harms: Causal Auditing of Patient World Models
- PulmoWorld: An Asynchronous Multimodal Medical World Model for Longitudinal Pneumonia Dynamics
- Understanding Trajectory Heterogeneity in Federated World Model Learning
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-11-05 · Indexed by Pub-AI: 2026-11-06 UTC
Learning a patient world model for health system simulation in intensive care
Preprint posted: 2026-11-05 · Original record ↗
- arxiv
- 2611.08392
Explicit source versions (1)
- v1 · 2026-11-05
- Preprint available
Source date: 2026-11-05 · First detected: 2026-11-06 UTC · Historical baseline
Source evidence (2)
- Official evidence ↗ · RSS guid=oai:arXiv.org:2611.08392v1; arxiv:announce_type=new; item pubDate (official metadata)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Designing healthcare strategies requires anticipating their clinical and operational consequences before implementation, a task that often relies on health system simulation. Such a simulation necessitates modeling how patient states evolve and generate care demands. However, conventional approaches typically tailor compact state transitions to a single policy question and omit history-dependent dynamics, thus requiring the redefinition of states and transitions when there is a new question that entails different clinical information. We propose to learn a patient world model from longitudinal EHRs using a neural network to provide a shared clinical representation of patient trajectories that can serve simulation questions across scenarios. Taking ICU operations as an example, we train the model on MIMIC-IV, freeze it, and couple its time-queryable predictions to shared ICU calendars, resources, and queues via scenario-specific mappings, so that one model renders admission demand, care tasks, and discharge proposals across simulations evaluating ICU bed capacity, care dispatch, and post-ICU transfer capacity. Experiments show that our model matches Markov and semi-Markov comparators in aggregate occupancy and directional responses to capacity and dispatch policies. It also reproduces policy gains from replayed observed trajectories. For patients entering the same support state from different prior trajectories, the learned representation captures a 24-h recovery difference (-6.4 predicted versus -6.7 observed percentage points), a contrast missed by compact state models, which propagates into distinct simulated care demand, queue burden, and bed use. These results indicate that a learned world model of patient dynamics has the potential to replace question-specific state models, allowing new care policies to be evaluated by reconfiguring the scenario without model rebuilding.
