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

arXiv: https://arxiv.org/abs/2604.22618 · HTML: https://mlsanity.com/paper/2604.22618/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and surgical world models, one of 11 directions in World models.
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Placed in

- World models / [Medical and surgical world models](https://mlsanity.com/wm/medical-and-surgical-world-models/)

## Builds on (most cited first, 11 of 11)

- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2306.10125/) (2023)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning](https://mlsanity.com/paper/2506.02327/) (2025)
- [Longitudinal Self-Supervised Learning](https://mlsanity.com/paper/2006.06930/) (2020)
- [Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling](https://mlsanity.com/paper/2104.04569/) (2021)
- [CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning](https://mlsanity.com/paper/2504.13820/) (2025)
- [Utilizing Expert Features for Contrastive Learning of Time-Series Representations](https://mlsanity.com/paper/2206.11517/) (2022)
- [Leveraging Time Irreversibility with Order-Contrastive Pre-training](https://mlsanity.com/paper/2111.02599/) (2021)
- [Causal Contrastive Learning for Counterfactual Regression Over Time](https://mlsanity.com/paper/2406.00535/) (2024)

## Built on by (most cited first, 2 of 2)

- [Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning](https://mlsanity.com/paper/2608.21147/) (2026)
- [PatientWM: Towards Generalizable Clinical World Models via Unified Patient States](https://mlsanity.com/paper/2610.17059/) (2026)

## Abstract (arXiv)

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