Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets

TL;DR

Beat-SSL introduces a novel contrastive learning framework for ECG analysis that captures both rhythm and heartbeat features using soft targets, improving representation learning for classification and segmentation tasks.

Contribution

It proposes a dual-context contrastive learning approach with soft targets specifically tailored for ECG signals, enhancing feature representation over existing methods.

Findings

Achieved 93% performance of a foundation model in multilabel classification.

Surpassed all other methods in ECG segmentation by 4%.

Demonstrated effective transfer learning with limited labelled ECG data.

Abstract

Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL frameworks either focus solely on global context or fail to exploit ECG-specific characteristics. Furthermore, these methods rely on hard contrastive targets, which may not adequately capture the continuous nature of feature similarity in ECG signals. In this paper, we propose Beat-SSL, a contrastive learning framework that performs dual-context learning through both rhythm-level and heartbeat-level contrasting with soft targets. We evaluated our pretrained model on two downstream tasks: 1) multilabel classification for global rhythm assessment, and 2) ECG segmentation to assess its capacity to learn representations across both contexts. We conducted an ablation study and compared the best configuration with three other methods, including one ECG foundation model. Despite the foundation model's broader pretraining, Beat-SSL reached 93% of its performance in multilabel classification task and surpassed all other methods in the segmentation task by 4%.