Efficient ECG-based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks
This work addresses the need for efficient AF detection on resource-constrained wearable devices, representing an incremental improvement in model efficiency.
The paper tackles the problem of atrial fibrillation detection from ECG signals on wearable devices by proposing lightweight convolutional neural networks with parameterized hypercomplex layers, achieving comparable performance to real-valued CNNs with significantly fewer parameters on two public datasets.
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.