ECG data dependency for atrial fibrillation detection based on residual networks

Abstract Atrial fibrillation (AF) is an arrhythmia that can cause blood clot and may lead to stroke and heart failure. To detect AF, deep learning-based detection algorithms have recently been developed. However, deep learning models were often trained with limited datasets and were evaluated within...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyo-Chang Seo, Seok Oh, Hyunbin Kim, Segyeong Joo
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0da4d25ba9034d199e05998b2199c177
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0da4d25ba9034d199e05998b2199c177
record_format	dspace
spelling	oai:doaj.org-article:0da4d25ba9034d199e05998b2199c1772021-12-02T18:33:47ZECG data dependency for atrial fibrillation detection based on residual networks10.1038/s41598-021-97308-12045-2322https://doaj.org/article/0da4d25ba9034d199e05998b2199c1772021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97308-1https://doaj.org/toc/2045-2322Abstract Atrial fibrillation (AF) is an arrhythmia that can cause blood clot and may lead to stroke and heart failure. To detect AF, deep learning-based detection algorithms have recently been developed. However, deep learning models were often trained with limited datasets and were evaluated within the same datasets, which makes their performance generally drops on the external datasets, known as data dependency. For this study, three different databases from PhysioNet were used to investigate the data dependency of deep learning-based AF detection algorithm using the residual neural network (Resnet). Resnet 18, 34, 50 and 152 model were trained with raw electrocardiogram (ECG) signal extracted from independent database. The highest accuracy was about 98–99% which is evaluation results of test dataset from the own database. On the other hand, the lowest accuracy was about 53–92% which was evaluation results of the external dataset extracted from different source. There are data dependency according to the train dataset and the test dataset. However, the data dependency decreased as a large amount of train data.Hyo-Chang SeoSeok OhHyunbin KimSegyeong JooNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Hyo-Chang Seo Seok Oh Hyunbin Kim Segyeong Joo ECG data dependency for atrial fibrillation detection based on residual networks
description	Abstract Atrial fibrillation (AF) is an arrhythmia that can cause blood clot and may lead to stroke and heart failure. To detect AF, deep learning-based detection algorithms have recently been developed. However, deep learning models were often trained with limited datasets and were evaluated within the same datasets, which makes their performance generally drops on the external datasets, known as data dependency. For this study, three different databases from PhysioNet were used to investigate the data dependency of deep learning-based AF detection algorithm using the residual neural network (Resnet). Resnet 18, 34, 50 and 152 model were trained with raw electrocardiogram (ECG) signal extracted from independent database. The highest accuracy was about 98–99% which is evaluation results of test dataset from the own database. On the other hand, the lowest accuracy was about 53–92% which was evaluation results of the external dataset extracted from different source. There are data dependency according to the train dataset and the test dataset. However, the data dependency decreased as a large amount of train data.
format	article
author	Hyo-Chang Seo Seok Oh Hyunbin Kim Segyeong Joo
author_facet	Hyo-Chang Seo Seok Oh Hyunbin Kim Segyeong Joo
author_sort	Hyo-Chang Seo
title	ECG data dependency for atrial fibrillation detection based on residual networks
title_short	ECG data dependency for atrial fibrillation detection based on residual networks
title_full	ECG data dependency for atrial fibrillation detection based on residual networks
title_fullStr	ECG data dependency for atrial fibrillation detection based on residual networks
title_full_unstemmed	ECG data dependency for atrial fibrillation detection based on residual networks
title_sort	ecg data dependency for atrial fibrillation detection based on residual networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0da4d25ba9034d199e05998b2199c177
work_keys_str_mv	AT hyochangseo ecgdatadependencyforatrialfibrillationdetectionbasedonresidualnetworks AT seokoh ecgdatadependencyforatrialfibrillationdetectionbasedonresidualnetworks AT hyunbinkim ecgdatadependencyforatrialfibrillationdetectionbasedonresidualnetworks AT segyeongjoo ecgdatadependencyforatrialfibrillationdetectionbasedonresidualnetworks
_version_	1718377902129545216

ECG data dependency for atrial fibrillation detection based on residual networks

Ejemplares similares