Scaling Representation Learning from Ubiquitous ECG with State-Space Models

TL;DR

This paper introduces WildECG, a pre-trained state-space model trained on extensive in-the-wild ECG data, improving representation learning for health monitoring and stress estimation, especially in low-resource settings.

Contribution

The paper presents WildECG, a novel self-supervised, state-space model trained on large-scale wild ECG data, advancing representation learning for diverse health-related tasks.

Findings

Competitive performance on multiple downstream tasks

Effective in low-resource regimes

Robust backbone for ECG analysis

Abstract

Ubiquitous sensing from wearable devices in the wild holds promise for enhancing human well-being, from diagnosing clinical conditions and measuring stress to building adaptive health promoting scaffolds. But the large volumes of data therein across heterogeneous contexts pose challenges for conventional supervised learning approaches. Representation Learning from biological signals is an emerging realm catalyzed by the recent advances in computational modeling and the abundance of publicly shared databases. The electrocardiogram (ECG) is the primary researched modality in this context, with applications in health monitoring, stress and affect estimation. Yet, most studies are limited by small-scale controlled data collection and over-parameterized architecture choices. We introduce \textbf{WildECG}, a pre-trained state-space model for representation learning from ECG signals. We train this model in a self-supervised manner with 275,000 10s ECG recordings collected in the wild and evaluate it on a range of downstream tasks. The proposed model is a robust backbone for ECG analysis, providing competitive performance on most of the tasks considered, while demonstrating efficacy in low-resource regimes. The code and pre-trained weights are shared publicly at https://github.com/klean2050/tiles_ecg_model.