Wearable Electro-Phonocardiography Device for Cardiovascular Disease Monitoring

Abstract

In this paper, we present a new wearable multichannel phonocardiography (PCG) and electrocardiography (ECG) device for cardiovascular disease (CVD) pre-screening and monitoring developed recently by researchers at Curtin University in collaboration with Ticking Heart, a health-tech start-up. An iterative Wiener filter based noise cancelation algorithm is proposed to improve the integrity of heart sound signals. We show that compared with an existing approach, the proposed algorithm has a better performance in suppressing the noise at 200-300 Hz. A convolutional neural network based classifier is implemented which exploits both the ECG and PCG signals to improve the pre-screening accuracy of CVD.