A Survey of Augmentation Techniques for Enhancing ECG Representation through Self-Supervised Contrastive Learning

The electrocardiogram (ECG) is the most common clinical tool to measure the electrical activity of the heart. Despite its ubiquity and utility, traditional ECG analysis methods are limited to primarily human interpretation. Machine learning tools can be employed to automate detection of diseases, and to detect patterns that are not available to traditional ECG analysis. However, contemporary machine learning tools are limited by requirements for large labeled datasets, which can be scarce for rare diseases. Self-supervised learning (SSL) can address this data scarcity. We implemented the momentum contrast (MoCo) framework, a form of SSL, using a large clinical ECG dataset. We then assessed the learning using Low Left Ventricular Ejection Fraction (LVEF) detection as the downstream task. We compared the SSL improvement of LVEF classification across different input augmentations. We observed that optimal augmentation hyperparameters varied substantially based on the training dataset size, indicating that augmentation strategies may need to be tuned based on problem and dataset size.