A Deep-Learning Approach to Heart Sound Classification Based on Combined Time-Frequency Representations
Open Access
- 7 April 2025
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 13 (4) , 147
Abstract
Worldwide, heart disease is the leading cause of mortality. Cardiac auscultation, when conducted by a trained professional, is a non-invasive, cost-effective, and readily available method for the initial assessment of cardiac health. Automated heart sound analysis offers a promising and accessible approach to supporting cardiac diagnosis. This work introduces a novel method for classifying heart sounds as normal or abnormal by leveraging time-frequency representations. Our approach combines three distinct time-frequency representations—short-time Fourier transform (STFT), mel-scale spectrogram, and wavelet synchrosqueezed transform (WSST)—to create images that enhance classification performance. These images are used to train five convolutional neural networks (CNNs): AlexNet, VGG-16, ResNet50, a CNN specialized in STFT images, and our proposed CNN model. The method was trained and tested using three public heart sound datasets: PhysioNet/CinC Challenge 2016, CirCor DigiScope Phonocardiogram Dataset 2022, and another open database. While individual representations achieve maximum accuracy of ≈85.9%, combining STFT, mel, and WSST boosts accuracy to ≈99%. By integrating complementary time-frequency features, our approach demonstrates robust heart sound analysis, achieving consistent classification performance across diverse CNN architectures, thus ensuring reliability and generalizability.Keywords
Funding Information
- Mexican National Council for Science and Technology (CONACYT) (994947)
This publication has 70 references indexed in Scilit:
- PCG classification through spectrogram using transfer learningBiomedical Signal Processing and Control, 2022
- Automated classification of valvular heart diseases using FBSE-EWT and PSR based geometrical featuresBiomedical Signal Processing and Control, 2022
- Detection of heart valve disorders from PCG signals using TQWT, FA-MVEMD, Shannon energy envelope and deterministic learningArtificial Intelligence Review, 2021
- Microscopic abnormality classification of cardiac murmurs using ANFIS and HMMMicroscopy Research and Technique, 2018
- Classification of heart sound signal using curve fitting and fractal dimensionBiomedical Signal Processing and Control, 2018
- Recent advances in heart sound analysisPhysiological Measurement, 2017
- DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart soundsPhysiological Measurement, 2017
- Deep learningNature, 2015
- A novel hybrid energy fraction and entropy-based approach for systolic heart murmurs identificationExpert Systems with Applications, 2015
- Cluster analysis and classification of heart soundsBiomedical Signal Processing and Control, 2009