A novel approach to classification of ECG arrhythmia types with latent ODEs

TL;DR

This paper introduces a novel end-to-end ECG classification method using latent ODEs that maintains high accuracy across different sampling frequencies, facilitating long-term wearable monitoring of arrhythmias.

Contribution

It develops a latent ODE-based feature extraction pipeline that is robust to sampling frequency variations, enabling effective arrhythmia classification from low-frequency wearable ECGs.

Findings

High classification accuracy with AUC-ROC above 0.97 at all tested frequencies.

Robustness of features across sampling frequencies demonstrated.

Potential for smaller, energy-efficient wearable ECG devices.

Abstract

12-lead ECGs with high sampling frequency are the clinical gold standard for arrhythmia detection, but their short-term, spot-check nature often misses intermittent events. Wearable ECGs enable long-term monitoring but suffer from irregular, lower sampling frequencies due to battery constraints, making morphology analysis challenging. We present an end-to-end classification pipeline to address these issues. We train a latent ODE to model continuous ECG waveforms and create robust feature vectors from high-frequency single-channel signals. We construct three latent vectors per waveform via downsampling the initial 360 Hz ECG to 90 Hz and 45 Hz. We then use a gradient boosted tree to classify these vectors and test robustness across frequencies. Performance shows minimal degradation, with macro-averaged AUC-ROC values of 0.984, 0.978, and 0.976 at 360 Hz, 90 Hz, and 45 Hz, respectively, suggesting a way to sidestep the trade-off between signal fidelity and battery life. This enables smaller wearables, promoting long-term monitoring of cardiac health.