Self-Supervised Pre-Training with Joint-Embedding Predictive Architecture Boosts ECG Classification Performance

TL;DR

This paper introduces a novel self-supervised learning architecture called JEPA for ECG classification, which outperforms existing methods by learning high-quality representations without relying on data augmentation or reconstruction.

Contribution

The study presents JEPA, a joint-embedding predictive architecture for ECG data, demonstrating superior performance over existing self-supervised methods in ECG classification tasks.

Findings

JEPA achieves an AUC of 0.945 on PTB-XL dataset.

JEPA outperforms invariance-based and generative approaches.

JEPA learns high-quality representations even without additional data.

Abstract

Accurate diagnosis of heart arrhythmias requires the interpretation of electrocardiograms (ECG), which capture the electrical activity of the heart. Automating this process through machine learning is challenging due to the need for large annotated datasets, which are difficult and costly to collect. To address this issue, transfer learning is often employed, where models are pre-trained on large datasets and fine-tuned for specific ECG classification tasks with limited labeled data. Self-supervised learning has become a widely adopted pre-training method, enabling models to learn meaningful representations from unlabeled datasets. In this work, we explore the joint-embedding predictive architecture (JEPA) for self-supervised learning from ECG data. Unlike invariance-based methods, JEPA does not rely on hand-crafted data augmentations, and unlike generative methods, it predicts latent features rather than reconstructing input data. We create a large unsupervised pre-training dataset by combining ten public ECG databases, amounting to over one million records. We pre-train Vision Transformers using JEPA on this dataset and fine-tune them on various PTB-XL benchmarks. Our results show that JEPA outperforms existing invariance-based and generative approaches, achieving an AUC of 0.945 on the PTB-XL all statements task. JEPA consistently learns the highest quality representations, as demonstrated in linear evaluations, and proves advantageous for pre-training even in the absence of additional data.