Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
This work addresses the challenge of disease screening from ECG data for medical applications, but it is incremental as it adapts existing SSL techniques to a specific domain.
The paper tackles the problem of limited labeled ECG data for disease screening by proposing ST-MEM, a self-supervised learning method that captures spatio-temporal relationships in ECG signals, and it outperforms other SSL baselines in arrhythmia classification tasks.
Electrocardiograms (ECG) are widely employed as a diagnostic tool for monitoring electrical signals originating from a heart. Recent machine learning research efforts have focused on the application of screening various diseases using ECG signals. However, adapting to the application of screening disease is challenging in that labeled ECG data are limited. Achieving general representation through self-supervised learning (SSL) is a well-known approach to overcome the scarcity of labeled data; however, a naive application of SSL to ECG data, without considering the spatial-temporal relationships inherent in ECG signals, may yield suboptimal results. In this paper, we introduce ST-MEM (Spatio-Temporal Masked Electrocardiogram Modeling), designed to learn spatio-temporal features by reconstructing masked 12-lead ECG data. ST-MEM outperforms other SSL baseline methods in various experimental settings for arrhythmia classification tasks. Moreover, we demonstrate that ST-MEM is adaptable to various lead combinations. Through quantitative and qualitative analysis, we show a spatio-temporal relationship within ECG data. Our code is available at https://github.com/bakqui/ST-MEM.