Unlocking Telemetry Potential: Self-Supervised Learning for Continuous Clinical Electrocardiogram Monitoring
This work addresses the challenge of scarce labels for continuous patient monitoring in ICUs, enabling medically useful predictions in smaller cohorts, though it is incremental as it applies existing self-supervised methods to a new data type.
The paper tackled the problem of limited labeled data for continuous clinical ECG monitoring by applying self-supervised learning to pretrain deep networks on 147,000 hours of unlabeled ECG telemetry data, resulting in significantly improved performance on four downstream tasks compared to direct supervised learning.
Machine learning (ML) applied to routine patient monitoring within intensive care units (ICUs) has the potential to improve care by providing clinicians with novel insights into each patient's health and expected response to interventions. This paper applies deep learning to a large volume of unlabeled electrocardiogram (ECG) telemetry signals, which are commonly used for continuous patient monitoring in hospitals but have important differences from the standard, single time-point 12-lead ECG used in many prior machine learning studies. We applied self-supervised learning to pretrain a spectrum of deep networks on approximately 147,000 hours of ECG telemetry data. Our approach leverages this dataset to train models that significantly improve performance on four distinct downstream tasks compared with direct supervised learning using labeled data. These pretrained models enable medically useful predictions and estimates in smaller patient cohorts that are typically limited by the scarcity of labels. Notably, we demonstrate that our pretrained networks can continuously annotate ECG telemetry signals, thereby providing monitoring capabilities that are often unavailable due to the requirement for specialized expertise and time-consuming professional annotations.