Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction

TL;DR

This paper introduces a pathology-aware contrastive learning framework for ECG reconstruction that improves accuracy and generalization by incorporating clinical labels and filtering irrelevant anatomical variations.

Contribution

It presents a novel multi-view contrastive learning approach that leverages pathology information to enhance ECG reconstruction across diverse datasets.

Findings

Achieves approximately 76% reduction in RMSE on PTB-XL dataset.

Demonstrates superior generalization in cross-dataset evaluation.

Effectively filters anatomical nuisance variables through mutual information maximization.

Abstract

Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction.