CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients

TL;DR

CLOCS introduces a contrastive learning framework for cardiac signals that leverages spatial, temporal, and patient data to improve downstream task performance and generalization with limited labels.

Contribution

The paper presents CLOCS, a novel contrastive learning method that incorporates multi-dimensional data to enhance cardiac signal representations and patient-specific analysis.

Findings

Outperforms BYOL and SimCLR in downstream tasks

Achieves strong results with only 25% labeled data

Generates patient-specific similarity metrics

Abstract

The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25\% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.