Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs

• URL: http://arxiv.org/abs/2604.22618v1
• Date: Fri, 24 Apr 2026 14:47:52 GMT
• Title: Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
• Abstract summary: We propose a shift towards Action-Conditioned World Models that learn to simulate the dynamics of disease progression.<n>By predicting the future electrophysiological state of the heart given a disease onset, our model explicitly disentangles stable anatomical features from dynamic pathological forces.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised learning in healthcare has largely relied on invariance-based objectives, which maximize similarity between different views of the same patient. While effective for static anatomy, this paradigm is fundamentally misaligned with clinical diagnosis, as it mathematically compels the model to suppress the transient pathological changes it is intended to detect. We propose a shift towards Action-Conditioned World Models that learn to simulate the dynamics of disease progression, or Event-Conditioned. Adapting the LeJEPA framework to physiological time-series, we define pathology not as a static label, but as a transition vector acting on a patient's latent state. By predicting the future electrophysiological state of the heart given a disease onset, our model explicitly disentangles stable anatomical features from dynamic pathological forces. Evaluated on the MIMIC-IV-ECG dataset, our approach outperforms fully supervised baselines on the critical triage task. Crucially, we demonstrate superior sample efficiency: in low-resource regimes, our world model outperforms supervised learning by over 0.05 AUROC. These results suggest that modeling biological dynamics provides a dense supervision signal that is far more robust than static classification. Source code is available at https://github.com/cljosegfer/lesaude-dynamics

Related papers

• Biological Amnesia in ICU Time-Series Prediction: A Drift-Adaptive Two-Stream Architecture with Temporal Retrieval [0.0]
  We propose an adaptive clinical intelligence architecture for ICU intervention prediction.<n>The architecture structurally decouples physiological from treatment representations, confining parameter updates to the treatment stream.<n>This architecture offers a template for governable, interpretable deployment of adaptive models in high-stakes clinical environments.
  arXiv  Detail & Related papers  (2026-07-21T12:07:36Z)
• MARVEL: Universal Murray's Law-informed Vessel Tree Segmentation and Topology Estimation [75.40785674602147]
  Deep learning methods for vascular segmentation often neglect biophysical constraints.<n>This leads to physiologically implausible branching and misclassification vascular trees.<n>We introduce MARVEL, a backbone-agnostic framework that integrates biophysical priors into vascular tree extraction.
  arXiv  Detail & Related papers  (2026-05-25T02:32:29Z)
• ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation [30.72000718768186]
  We propose an ECG World Model for action-conditioned predictive simulation of cardiac electrophysiology.<n>Our framework features a principled integration of physiological ordinary differential equation (ODE) priors into latent diffusion dynamics.<n>We evaluate our method across diverse settings, including controlled drug-response scenarios and real-world clinical records.
  arXiv  Detail & Related papers  (2026-05-17T18:14:07Z)
• 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)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation [17.33607122354623]
  Understanding disease progression is a central clinical challenge with implications for early diagnosis and personalized treatment.<n>We propose to treat the disease dynamic as a velocity field and leverage Flow Matching (FM) to align the temporal evolution of patient data.<n>We present $$-LFM, a framework for modeling patient-specific latent progression with flow matching.
  arXiv  Detail & Related papers  (2025-12-09T23:13:54Z)
• 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)
• SGEMAS: A Self-Growing Ephemeral Multi-Agent System for Unsupervised Online Anomaly Detection via Entropic Homeostasis [0.0]
  We introduce SGEMAS (Self-Growing Ephemeral Multi-Agent System), a bio-inspired architecture that treats intelligence as a dynamic thermodynamic process.<n>In a challenging inter-patient, zero-shot setting, the final SGEMAS v3.3 model achieves a mean AUC of 0.570 +- 0.070, outperforming both its simpler variants and a standard autoencoder baseline.
  arXiv  Detail & Related papers  (2025-12-08T00:43:51Z)
• A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context [0.0]
  We propose a Transformer model combined with a Laplace diffusion technique to model heart rate fluctuations driven by physical activity of the patient.<n>The model captures both long-term patterns and activity-specific heart rate dynamics by incorporating contextualized embeddings and dedicated encoder.
  arXiv  Detail & Related papers  (2025-08-20T06:42:38Z)
• Individualized Dosing Dynamics via Neural Eigen Decomposition [51.62933814971523]
  We introduce the Neural Eigen Differential Equation algorithm (NESDE) NESDE provides individualized modeling, tunable generalization to new treatment policies, and fast, continuous, closed-form prediction. We demonstrate the robustness of NESDE in both synthetic and real medical problems, and use the learned dynamics to publish simulated medical gym environments.
  arXiv  Detail & Related papers  (2023-06-24T17:01:51Z)
• An Optimal Control Approach to Learning in SIDARTHE Epidemic model [67.22168759751541]
  We propose a general approach for learning time-variant parameters of dynamic compartmental models from epidemic data. We forecast the epidemic evolution in Italy and France.
  arXiv  Detail & Related papers  (2020-10-28T10:58:59Z)
• Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes [102.02672176520382]
  Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. We develop deep diffusion processes to model "dynamic comorbidity networks"
  arXiv  Detail & Related papers  (2020-01-08T15:47:08Z)

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.