A review on deep learning methods for heart sound signal analysis

IntroductionApplication of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic...

Full description

Saved in:
Bibliographic Details
Main Authors: Elaheh Partovi, Ankica Babic, Arash Gharehbaghi
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-11-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2024.1434022/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850191407129559040
author Elaheh Partovi
Ankica Babic
Ankica Babic
Arash Gharehbaghi
author_facet Elaheh Partovi
Ankica Babic
Ankica Babic
Arash Gharehbaghi
author_sort Elaheh Partovi
collection DOAJ
description IntroductionApplication of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic picture of the methodological performance from the reported methods.MethodsThis survey paper provides the results of a broad retrospective study on the recent advances in heart sound analysis using DL methods. Representation of the results is performed according to both methodological and applicative taxonomies. The study method covers a wide span of related keywords using well-known search engines. Implementation of the observed methods along with the related results is pervasively represented and compared.Results and discussionIt is observed that convolutional neural networks and recurrent neural networks are the most commonly used ones for discriminating abnormal heart sounds and localization of heart sounds with 67.97% and 33.33% of the related papers, respectively. The convolutional neural network and the autoencoder network show a perfect accuracy of 100% in the case studies on the classification of abnormal from normal heart sounds. Nevertheless, this superiority against other methods with lower accuracy is not conclusive due to the inconsistency in evaluation.
format Article
id doaj-art-4cacabae5ebe4a519b7d87783cb5b687
institution OA Journals
issn 2624-8212
language English
publishDate 2024-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-4cacabae5ebe4a519b7d87783cb5b6872025-08-20T02:14:56ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122024-11-01710.3389/frai.2024.14340221434022A review on deep learning methods for heart sound signal analysisElaheh Partovi0Ankica Babic1Ankica Babic2Arash Gharehbaghi3Department of Electrical Engineering, Amirkabir University of Technology, Tehran, IranDepartment of Biomedical Engineering, Linköping University, Linköping, SwedenDepartment of Information Science and Media Studies, University of Bergen, Bergen, NorwayDepartment of Biomedical Engineering, Linköping University, Linköping, SwedenIntroductionApplication of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic picture of the methodological performance from the reported methods.MethodsThis survey paper provides the results of a broad retrospective study on the recent advances in heart sound analysis using DL methods. Representation of the results is performed according to both methodological and applicative taxonomies. The study method covers a wide span of related keywords using well-known search engines. Implementation of the observed methods along with the related results is pervasively represented and compared.Results and discussionIt is observed that convolutional neural networks and recurrent neural networks are the most commonly used ones for discriminating abnormal heart sounds and localization of heart sounds with 67.97% and 33.33% of the related papers, respectively. The convolutional neural network and the autoencoder network show a perfect accuracy of 100% in the case studies on the classification of abnormal from normal heart sounds. Nevertheless, this superiority against other methods with lower accuracy is not conclusive due to the inconsistency in evaluation.https://www.frontiersin.org/articles/10.3389/frai.2024.1434022/fullphonocardiogramintelligent phonocardiographydeep learningheart soundheart sound segmentationheart disease
spellingShingle Elaheh Partovi
Ankica Babic
Ankica Babic
Arash Gharehbaghi
A review on deep learning methods for heart sound signal analysis
Frontiers in Artificial Intelligence
phonocardiogram
intelligent phonocardiography
deep learning
heart sound
heart sound segmentation
heart disease
title A review on deep learning methods for heart sound signal analysis
title_full A review on deep learning methods for heart sound signal analysis
title_fullStr A review on deep learning methods for heart sound signal analysis
title_full_unstemmed A review on deep learning methods for heart sound signal analysis
title_short A review on deep learning methods for heart sound signal analysis
title_sort review on deep learning methods for heart sound signal analysis
topic phonocardiogram
intelligent phonocardiography
deep learning
heart sound
heart sound segmentation
heart disease
url https://www.frontiersin.org/articles/10.3389/frai.2024.1434022/full
work_keys_str_mv AT elahehpartovi areviewondeeplearningmethodsforheartsoundsignalanalysis
AT ankicababic areviewondeeplearningmethodsforheartsoundsignalanalysis
AT ankicababic areviewondeeplearningmethodsforheartsoundsignalanalysis
AT arashgharehbaghi areviewondeeplearningmethodsforheartsoundsignalanalysis
AT elahehpartovi reviewondeeplearningmethodsforheartsoundsignalanalysis
AT ankicababic reviewondeeplearningmethodsforheartsoundsignalanalysis
AT ankicababic reviewondeeplearningmethodsforheartsoundsignalanalysis
AT arashgharehbaghi reviewondeeplearningmethodsforheartsoundsignalanalysis