Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling

Abstract Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced cli...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jou-Kou Wang, Yun-Fan Chang, Kun-Hsi Tsai, Wei-Chien Wang, Chang-Yen Tsai, Chui-Hsuan Cheng, Yu Tsao
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/841663a1c2db4fc1994bfe542fea94ad
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:841663a1c2db4fc1994bfe542fea94ad
record_format	dspace
spelling	oai:doaj.org-article:841663a1c2db4fc1994bfe542fea94ad2021-12-02T15:11:50ZAutomatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling10.1038/s41598-020-77994-z2045-2322https://doaj.org/article/841663a1c2db4fc1994bfe542fea94ad2020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77994-zhttps://doaj.org/toc/2045-2322Abstract Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.Jou-Kou WangYun-Fan ChangKun-Hsi TsaiWei-Chien WangChang-Yen TsaiChui-Hsuan ChengYu TsaoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-10 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jou-Kou Wang Yun-Fan Chang Kun-Hsi Tsai Wei-Chien Wang Chang-Yen Tsai Chui-Hsuan Cheng Yu Tsao Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
description	Abstract Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.
format	article
author	Jou-Kou Wang Yun-Fan Chang Kun-Hsi Tsai Wei-Chien Wang Chang-Yen Tsai Chui-Hsuan Cheng Yu Tsao
author_facet	Jou-Kou Wang Yun-Fan Chang Kun-Hsi Tsai Wei-Chien Wang Chang-Yen Tsai Chui-Hsuan Cheng Yu Tsao
author_sort	Jou-Kou Wang
title	Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
title_short	Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
title_full	Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
title_fullStr	Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
title_full_unstemmed	Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
title_sort	automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/841663a1c2db4fc1994bfe542fea94ad
work_keys_str_mv	AT joukouwang automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT yunfanchang automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT kunhsitsai automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT weichienwang automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT changyentsai automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT chuihsuancheng automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling AT yutsao automaticrecognitionofmurmursofventricularseptaldefectusingconvolutionalrecurrentneuralnetworkswithtemporalattentivepooling
_version_	1718387642084622336

Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling

Ejemplares similares