Efficient ECG-based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks

TL;DR

This paper introduces lightweight parameterised hypercomplex neural networks for ECG-based atrial fibrillation detection, enabling efficient and accurate analysis suitable for wearable devices with limited computing resources.

Contribution

It proposes a novel PH neural network architecture that reduces model complexity while maintaining high performance in AF detection from ECGs.

Findings

Comparable performance to real-valued CNNs on ECG datasets

Significantly fewer model parameters

Flexible operation on any number of ECG leads

Abstract

Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke. The use of wearable devices embedded with automatic and timely AF assessment from electrocardiograms (ECGs) has shown to be promising in preventing life-threatening situations. Although deep neural networks have demonstrated superiority in model performance, their use on wearable devices is limited by the trade-off between model performance and complexity. In this work, we propose to use lightweight convolutional neural networks (CNNs) with parameterised hypercomplex (PH) layers for AF detection based on ECGs. The proposed approach trains small-scale CNNs, thus overcoming the limited computing resources on wearable devices. We show comparable performance to corresponding real-valued CNNs on two publicly available ECG datasets using significantly fewer model parameters. PH models are more flexible than other hypercomplex neural networks and can operate on any number of input ECG leads.