Predicting Cardiovascular Disorders Through Stethoscope Audio Using Convolutional Neural Network

Abstract

Cardiovascular disorders pose a significant global health challenge, resulting in a substantial number of annual deaths. Early and accurate prediction of heart disorders is crucial to mitigate their impact on individuals and healthcare systems. In this study, we explore the potential of Convolutional Neural Network in automating heart disease prediction using spectrogram data. The dataset comprises audio recordings collected from the general public via an iPhone app and a clinical trial using a digital stethoscope. We preprocess the data to obtain spectrograms and design a Convolutional Neural Network architecture to classify heart sounds into distinct categories. The Convolutional Neural Network exhibits promising performance, achieving an accuracy of approximately 77%. Our research highlights the opportunity to leverage Convolutional Neural Network in this context, paving the way for advanced automated cardiac diagnostics.

Keywords: Cardiovascular disorders, Convolutional neural network

DOI: 10.7176/RHSS/13-14-02

Publication date:August 31^st 2023