Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Tasks

TL;DR

This paper introduces an adversarial masking technique for ECG data augmentation that enhances the generalizability of self-supervised models, especially in data-scarce scenarios, outperforming existing methods.

Contribution

The paper proposes a novel adversarial masking approach for ECG data augmentation that improves model transferability and outperforms state-of-the-art methods in limited data settings.

Findings

Adversarial masking improves accuracy over random augmentations.

Outperforms 3KG augmentation in data-scarce regimes.

Enhances generalizability for arrhythmia and gender classification.

Abstract

Medical datasets often face the problem of data scarcity, as ground truth labels must be generated by medical professionals. One mitigation strategy is to pretrain deep learning models on large, unlabelled datasets with self-supervised learning (SSL). Data augmentations are essential for improving the generalizability of SSL-trained models, but they are typically handcrafted and tuned manually. We use an adversarial model to generate masks as augmentations for 12-lead electrocardiogram (ECG) data, where masks learn to occlude diagnostically-relevant regions of the ECGs. Compared to random augmentations, adversarial masking reaches better accuracy when transferring to to two diverse downstream objectives: arrhythmia classification and gender classification. Compared to a state-of-art ECG augmentation method 3KG, adversarial masking performs better in data-scarce regimes, demonstrating the generalizability of our model.