用动态建模替代静态分类，让模型学会预测心脏疾病演化过程。
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
- 以动作条件的潜空间模型模拟心脏病进展，将病理视为状态转移向量。
- 在MIMIC-IV-ECG数据集上，低资源下比监督学习高0.05以上AUROC。
- 适合关注疾病动态演进与少样本医疗建模的研究者。
医疗自监督学习长期依赖基于不变性的目标，即最大化同一患者不同视图间的相似性。该范式虽对静态解剖有效，但与临床诊断本质矛盾，因数学上迫使模型抑制其本应检测的瞬态病理变化。本文提出转向动作条件的世界模型，学习疾病进展的动力学。通过将LeJEPA框架适配于生理时间序列，将病理定义为作用于患者潜在状态的转移向量。模型可基于疾病发作预测未来心电状态，显式分离稳定解剖特征与动态病理力。在MIMIC-IV-ECG数据集上，该方法在关键分诊任务中超越全监督基线。尤为关键的是，在低资源条件下，其世界模型比监督学习高出0.05以上AUROC。结果表明，建模生物动态提供了远比静态分类更鲁棒的密集监督信号。源代码见https://github.com/cljosegfer/lesaude-dynamics。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。