Self-supervised representation learning from 12-lead ECG data

Abstract

Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity remains a central challenge in the field. Self-supervised learning represents a promising way to alleviate this issue. In this work, we put forward the first comprehensive assessment of self-supervised representation learning from clinical 12-lead ECG data. To this end, we adapt state-of-the-art self-supervised methods based on instance discrimination and latent forecasting to the ECG domain. In a first step, we learn contrastive representations and evaluate their quality based on linear evaluation performance on a recently established, comprehensive, clinical ECG classification task. In a second step, we analyze the impact of self-supervised pretraining on finetuned ECG classifiers as compared to purely supervised performance. For the best-performing method, an adaptation of contrastive predictive coding, we find a linear evaluation performance only 0.5% below supervised performance. For the finetuned models, we find improvements in downstream performance of roughly 1% compared to supervised performance, label efficiency, as well as robustness against physiological noise. This work clearly establishes the feasibility of extracting discriminative representations from ECG data via self-supervised learning and the numerous advantages when finetuning such representations on downstream tasks as compared to purely supervised training. As first comprehensive assessment of its kind in the ECG domain carried out exclusively on publicly available datasets, we hope to establish a first step towards reproducible progress in the rapidly evolving field of representation learning for biosignals.

15 pages, 12 figures, matches published version, code available under https://github.com/hhi-aml/ecg-selfsupervised

References in corpus (5)

• Bootstrap your own latent: A new approach to self-supervised Learning
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Subject-Aware Contrastive Learning for Biosignals
• A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• Analysis of Predictive Coding Models for Phonemic Representation Learning in Small Datasets

Cited by in corpus (11)

• From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology
• Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery
• Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks
• In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection
• MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations
• Deep learning based ECG segmentation for delineation of diverse arrhythmias
• Transfer Learning Application of Self-supervised Learning in ARPES
• 3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations
• Towards Hardware Supported Domain Generalization in DNN-Based Edge Computing Devices for Health Monitoring
• A Systematic Review of ECG Arrhythmia Classification: Adherence to Standards, Fair Evaluation, and Embedded Feasibility
• Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning