Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis

Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia, as its prevalence increases with age, and its initial stage is paroxysmal atrial fibrillation (PAF). This pathology usually triggers hemodynamic disorders that can generate cerebrovascular accidents (CVA), causing morbidity and ev...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Henry Castro, Juan D. Garcia-Racines, Alvaro Bernal-Norena
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	HRV PAF prediction Paroxysmal atrial fibrillation Recursive feature elimination Machine learning Science (General) Q1-390 Social sciences (General) H1-99
Acceso en línea:	https://doaj.org/article/7f804b680ed04ac0928827fef0db8da8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7f804b680ed04ac0928827fef0db8da8
record_format	dspace
spelling	oai:doaj.org-article:7f804b680ed04ac0928827fef0db8da82021-12-02T05:02:16ZMethodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis2405-844010.1016/j.heliyon.2021.e08244https://doaj.org/article/7f804b680ed04ac0928827fef0db8da82021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2405844021023471https://doaj.org/toc/2405-8440Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia, as its prevalence increases with age, and its initial stage is paroxysmal atrial fibrillation (PAF). This pathology usually triggers hemodynamic disorders that can generate cerebrovascular accidents (CVA), causing morbidity and even death. The aim of this study is to predict the occurrence of PAF episodes in order to take precautions to prevent PAF episodes. The PhysioNet AFPDB prediction database was used to extract 77 heart rate variability (HRV) features using time domain, geometrical analysis, Poincaré plot, nonlinear analysis, detrended fluctuation analysis, autoregressive modeling, fast Fourier transform (FFT), Lomb-Scargle periodogram, wavelet packet transform (WPT) and bispectrum measurements. The number of features was reduced using the near-zero value, correlation, and recursive feature elimination (RFE) methods for time windows of 1, 2, 5, 10, and 30 min. Feature selection was performed using backwards selection, genetic algorithm, analysis of variance (ANOVA), and non-dominated sorting genetic algorithm (NSGA-III) methods, and then random forest, conditional random forest, k-nearest neighbor (KNN), and support vector machine (SVM) classification algorithms were applied and evaluated using 10-fold cross-validation. The proposed method achieved a precision of 93.24% with a 5-minute window and 89.21% with a 2-minute window, improving performance in predicting PAF when compared with similar studies in the literature.Henry CastroJuan D. Garcia-RacinesAlvaro Bernal-NorenaElsevierarticleHRVPAF predictionParoxysmal atrial fibrillationRecursive feature eliminationMachine learningScience (General)Q1-390Social sciences (General)H1-99ENHeliyon, Vol 7, Iss 11, Pp e08244- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	HRV PAF prediction Paroxysmal atrial fibrillation Recursive feature elimination Machine learning Science (General) Q1-390 Social sciences (General) H1-99
spellingShingle	HRV PAF prediction Paroxysmal atrial fibrillation Recursive feature elimination Machine learning Science (General) Q1-390 Social sciences (General) H1-99 Henry Castro Juan D. Garcia-Racines Alvaro Bernal-Norena Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
description	Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia, as its prevalence increases with age, and its initial stage is paroxysmal atrial fibrillation (PAF). This pathology usually triggers hemodynamic disorders that can generate cerebrovascular accidents (CVA), causing morbidity and even death. The aim of this study is to predict the occurrence of PAF episodes in order to take precautions to prevent PAF episodes. The PhysioNet AFPDB prediction database was used to extract 77 heart rate variability (HRV) features using time domain, geometrical analysis, Poincaré plot, nonlinear analysis, detrended fluctuation analysis, autoregressive modeling, fast Fourier transform (FFT), Lomb-Scargle periodogram, wavelet packet transform (WPT) and bispectrum measurements. The number of features was reduced using the near-zero value, correlation, and recursive feature elimination (RFE) methods for time windows of 1, 2, 5, 10, and 30 min. Feature selection was performed using backwards selection, genetic algorithm, analysis of variance (ANOVA), and non-dominated sorting genetic algorithm (NSGA-III) methods, and then random forest, conditional random forest, k-nearest neighbor (KNN), and support vector machine (SVM) classification algorithms were applied and evaluated using 10-fold cross-validation. The proposed method achieved a precision of 93.24% with a 5-minute window and 89.21% with a 2-minute window, improving performance in predicting PAF when compared with similar studies in the literature.
format	article
author	Henry Castro Juan D. Garcia-Racines Alvaro Bernal-Norena
author_facet	Henry Castro Juan D. Garcia-Racines Alvaro Bernal-Norena
author_sort	Henry Castro
title	Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
title_short	Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
title_full	Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
title_fullStr	Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
title_full_unstemmed	Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
title_sort	methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/7f804b680ed04ac0928827fef0db8da8
work_keys_str_mv	AT henrycastro methodologyforthepredictionofparoxysmalatrialfibrillationbasedonheartratevariabilityfeatureanalysis AT juandgarciaracines methodologyforthepredictionofparoxysmalatrialfibrillationbasedonheartratevariabilityfeatureanalysis AT alvarobernalnorena methodologyforthepredictionofparoxysmalatrialfibrillationbasedonheartratevariabilityfeatureanalysis
_version_	1718400774089736192

Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis

Ejemplares similares