Foundation Model for Cardiac Time Series via Masked Latent Attention
This work addresses the challenge of cardiovascular diagnosis using ECGs, representing an incremental improvement by leveraging cross-lead connections for better representation learning.
The paper tackled the problem of learning transferable ECG representations by introducing a foundation model that exploits structural redundancy across leads, resulting in improved performance in predicting ICD-10 codes compared to existing methods.
Electrocardiograms (ECGs) are among the most widely available clinical signals and play a central role in cardiovascular diagnosis. While recent foundation models (FMs) have shown promise for learning transferable ECG representations, most existing pretraining approaches treat leads as independent channels and fail to explicitly leverage their strong structural redundancy. We introduce the latent attention masked autoencoder (LAMAE) FM that directly exploits this structure by learning cross-lead connection mechanisms during self-supervised pretraining. Our approach models higher-order interactions across leads through latent attention, enabling permutation-invariant aggregation and adaptive weighting of lead-specific representations. We provide empirical evidence on the Mimic-IV-ECG database that leveraging the cross-lead connection constitutes an effective form of structural supervision, improving representation quality and transferability. Our method shows strong performance in predicting ICD-10 codes, outperforming independent-lead masked modeling and alignment-based baselines.