ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data

• URL: http://arxiv.org/abs/2605.21963v1
• Date: Thu, 21 May 2026 03:50:17 GMT
• Title: ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data
• Abstract summary: We propose an action-conditioned latent world-model framework for learning patient trajectories from longitudinal care data.<n>We instantiate CMWM for annual estimated glomerular filtration rate (eGFR) trajectory forecasting in chronic kidney disease (CKD)<n>The framework is not CKD-specific its architecture, loss design, and training protocol apply to any chronic condition that can be cast as periodic clinical state interleaved with structured and conversational interventions.
• Score: 1.995753801570114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-disease care, yet existing electronic health record (EHR) models are predominantly discriminative, and general-purpose large language models drift under repeated interventions. We propose the \textbf{ChronoMedicalWorld Model (CMWM)}, an action-conditioned latent world-model framework for learning patient trajectories from longitudinal care data. CMWM couples a joint-embedding state encoder with a wide action encoder that admits both structured intervention indicators and free-text communication embeddings, and trains a recurrent latent transition module under a six-term objective: next-observation supervision, next-latent prediction, SIGReg latent regularisation, and three physiology-aware shape priors (slope, continuity, large-jump penalty). A closed-loop rollout-prefix protocol matches training to deployment, so the model is optimised against the same multi-step error it exhibits at inference. As a concrete case study, we instantiate CMWM for annual estimated glomerular filtration rate (eGFR) trajectory forecasting in chronic kidney disease (CKD). On a 2{,}232-patient nephrology cohort, the CKD instantiation achieves a dynamic-50\% history rollout test mean absolute error (MAE) of 7.384 and root-mean-square error (RMSE) of 10.256, against 7.964 and 11.069 for a tuned GPT-5.5 structured-prompting baseline ($-7.28\%$ MAE, $-7.35\%$ RMSE), with the gain dominated by the dialogue portion of patient--health-coach communication. The framework is not CKD-specific: its architecture, loss design, and training protocol apply to any chronic condition that can be cast as periodic clinical state interleaved with structured and conversational interventions.

Related papers

• MultiSigBERT: Beyond Survival Analysis through Multimodal and Sequential Modeling in Oncology [1.4526244723917887]
  We propose MultiSigBERT, a unified framework for sequential survival modeling in oncology.<n>Here, narrative medical reports are converted into sentence geometric embeddings by extracting and averaging contextual word embeddings.<n>These representations are then compressed via modality-specific PCA and geometric embeddings to form joint temporal trajectories.<n>The computed Signature features are finally incorporated as high dimensional features into a LASSO-regularized Cox model to estimate individualized risk scores.
  arXiv  Detail & Related papers  (2026-08-17T12:44:38Z)
• Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology [8.701738697134955]
  Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint.<n>We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events.
  arXiv  Detail & Related papers  (2026-08-13T17:38:13Z)
• Multimodal Deep Learning for Early Prediction of Patient Deterioration in the ICU: Integrating Time-Series EHR Data with Clinical Notes [0.0]
  Early identification of patients at risk for clinical deterioration in the intensive care unit (ICU) remains a critical challenge.<n>We present a multimodal deep learning approach that combines structured time-series data (vital signs and laboratory values) with unstructured clinical notes to predict patient deterioration within 24 hours.<n>Our architecture employs a bidirectional LSTM encoder for temporal patterns in physiologic data and ClinicalBERT embeddings for clinical notes, fused through a cross-modal attention mechanism.
  arXiv  Detail & Related papers  (2026-03-16T01:50:08Z)
• Personalized Longitudinal Medical Report Generation via Temporally-Aware Federated Adaptation [43.13545436728014]
  FedTAR is a framework that integrates demographic-driven personalization with time-aware global aggregation.<n>Experiments on J-MID (1M exams) and MIMIC-CXR demonstrate consistent improvements in linguistic accuracy, temporal coherence, and cross-site generalization.
  arXiv  Detail & Related papers  (2026-02-23T10:14:36Z)
• The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR [3.9541492005870604]
  We introduce SMB-Structure, a world model for structured EHR that grounds a joint-embedding prediction architecture (JEPA) with next-token prediction (SFT)<n>We validate across two large-scale cohorts: Memorial Sloan Kettering (23,319 oncology patients; 323,000+ patient-years) and INSPECT (19,402 pulmonary embolism patients)
  arXiv  Detail & Related papers  (2026-01-29T18:49:37Z)
• Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis [42.483536109820434]
  We introduce Dementia-R1, an RL-based framework for longitudinal dementia prognosis from unstructured clinical notes.<n>Our approach adopts a Cold-Start RL strategy that pre-trains the model to predict verifiable clinical indices extracted from patient histories.<n>Extensive experiments demonstrate that Dementia-R1 achieves an F1 score of 77.03% on real-world unstructured clinical datasets.
  arXiv  Detail & Related papers  (2026-01-06T13:44:04Z)
• ECG-RAMBA: Zero-Shot ECG Generalization by Morphology-Rhythm Disentanglement and Long-Range Modeling [0.6875312133832079]
  ECG-RAMBA is a framework that separates morphology and rhythm and re-integrates them through context-aware fusion.<n>It shows consistent cross-dataset performance on PTB-XL.
  arXiv  Detail & Related papers  (2025-12-29T10:14:52Z)
• CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space [49.74032713886216]
  CLARITY is a medical world model that forecasts disease evolution directly within a structured latent space.<n>It explicitly integrates time intervals (temporal context) and patient-specific data (clinical context) to model treatment-conditioned progression as a smooth, interpretable trajectory.
  arXiv  Detail & Related papers  (2025-12-08T20:42:10Z)
• Chronic Kidney Disease Prognosis Prediction Using Transformer [2.054117570146147]
  Chronic Kidney Disease (CKD) affects nearly 10% of the global population and often progresses to end-stage renal failure.<n>We present a transformer-based framework for predicting CKD progression using multi-modal electronic health records.
  arXiv  Detail & Related papers  (2025-11-04T07:52:17Z)
• Predicting Fetal Outcomes from Cardiotocography Signals Using a Supervised Variational Autoencoder [1.8352113484137627]
  We develop and interpret a supervised variational autoencoder (VAE) model for classifying cardiotocography (CTG) signals based on pregnancy outcomes.
  arXiv  Detail & Related papers  (2025-09-08T10:54:04Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• Deep State-Space Generative Model For Correlated Time-to-Event Predictions [54.3637600983898]
  We propose a deep latent state-space generative model to capture the interactions among different types of correlated clinical events. Our method also uncovers meaningful insights about the latent correlations among mortality and different types of organ failures.
  arXiv  Detail & Related papers  (2024-07-28T02:42:36Z)
• Foresight -- Deep Generative Modelling of Patient Timelines using Electronic Health Records [46.024501445093755]
  Temporal modelling of medical history can be used to forecast and simulate future events, estimate risk, suggest alternative diagnoses or forecast complications. We present Foresight, a novel GPT3-based pipeline that uses NER+L tools (i.e. MedCAT) to convert document text into structured, coded concepts.
  arXiv  Detail & Related papers  (2022-12-13T19:06:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.