ECG signals classification using overlapping variables to detect atrial fibrillation

Autores
Ziccardi, I. G.; Rey, A. A.; Legnani, W. E.
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In the present work a method for the detection of the cardiac pathology known as atrial fibrillation is proposed by calculating different information, statistics and other nonlinear measures over ECG signals. The original database contains records corresponding to patients who are diagnosed with this disease as well as healthy subjects. To formulate the dataset the R´enyi permutation entropy, Fisher information measure, statistical complexity, Lyapunov exponent and fractal dimension were calculated, in order to determine how to combine this features to optimize the identification of the signals coming from ECG with the above mentioned cardiac pathology. With the aim to improve the results obtained in previous studies, a classification method based upon decision trees algorithms is implemented. Later a Montecarlo simulation of one thousand trials is performed with a seventy percent randomly selected from the dataset dedicated to train the classifier and the remaining thirty percent reserved to test in every trial. The quality of the classification is assessed through the computation of the area under the receiver operation characteristic curve (ROC), the F1-score and other classical performance metrics, such as the balanced accuracy, sensitivity, specificity, positive and negative predicted values. The results show that the incorporation of all these features to the dataset when are employed to train the classifier in the training task produces the best classification, in such a way that the largest quality parameter is achieved.
UTN FRBA
Fil: Ziccardi, I. G. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Fil: Rey, A. A. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Fil: Legnani, W. E. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Peer Reviewed
Fuente
Trends in Computational and Applied Mathematics 23(3), 569-581. (2022)
Materia
Renyi entropy
statistical complexity
Fisher information
Lyapunov exponent
fractal dimension
atrial fibrillation
decision trees
Nivel de accesibilidad
acceso abierto
Condiciones de uso
2024-03-19T20:27:11Z
Repositorio
Repositorio Institucional Abierto (UTN)
Institución
Universidad Tecnológica Nacional
OAI Identificador
oai:ria.utn.edu.ar:20.500.12272/9929
Acceder
id RIAUTN_78b7a71b6f42bef5a88f076100d21226
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/9929
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling ECG signals classification using overlapping variables to detect atrial fibrillationZiccardi, I. G.Rey, A. A.Legnani, W. E.Renyi entropystatistical complexityFisher informationLyapunov exponentfractal dimensionatrial fibrillationdecision treesIn the present work a method for the detection of the cardiac pathology known as atrial fibrillation is proposed by calculating different information, statistics and other nonlinear measures over ECG signals. The original database contains records corresponding to patients who are diagnosed with this disease as well as healthy subjects. To formulate the dataset the R´enyi permutation entropy, Fisher information measure, statistical complexity, Lyapunov exponent and fractal dimension were calculated, in order to determine how to combine this features to optimize the identification of the signals coming from ECG with the above mentioned cardiac pathology. With the aim to improve the results obtained in previous studies, a classification method based upon decision trees algorithms is implemented. Later a Montecarlo simulation of one thousand trials is performed with a seventy percent randomly selected from the dataset dedicated to train the classifier and the remaining thirty percent reserved to test in every trial. The quality of the classification is assessed through the computation of the area under the receiver operation characteristic curve (ROC), the F1-score and other classical performance metrics, such as the balanced accuracy, sensitivity, specificity, positive and negative predicted values. The results show that the incorporation of all these features to the dataset when are employed to train the classifier in the training task produces the best classification, in such a way that the largest quality parameter is achieved.UTN FRBAFil: Ziccardi, I. G. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.Fil: Rey, A. A. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.Fil: Legnani, W. E. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.Peer Reviewed2024-03-19T20:27:11Z2024-03-19T20:27:11Z2022-03-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articulopdfapplication/pdfTrends in Computational and Applied Mathematics, 23.http://hdl.handle.net/20.500.12272/992910.5540/tcam.2022.023.03.00569Trends in Computational and Applied Mathematics 23(3), 569-581. (2022)reponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacionalenginfo:eu-repo/semantics/openAccess2024-03-19T20:27:11Zhttp://creativecommons.org/licenses/by-nc-sa/4.0/Atribución-NoComercial-CompartirIgual 4.0 InternacionalI. G. Ziccardi, A. A. Rey, W. E. LegnaniLicencia Creative Commons Atribución- No Comercial2026-09-24T12:45:05Zoai:ria.utn.edu.ar:20.500.12272/9929instacron:UTNInstitucionalhttp://ria.utn.edu.ar/Universidad públicaNo correspondehttp://ria.utn.edu.ar/oaigestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:a2026-09-24 12:45:06.546Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv ECG signals classification using overlapping variables to detect atrial fibrillation
title ECG signals classification using overlapping variables to detect atrial fibrillation
spellingShingle ECG signals classification using overlapping variables to detect atrial fibrillation
Ziccardi, I. G.
Renyi entropy
statistical complexity
Fisher information
Lyapunov exponent
fractal dimension
atrial fibrillation
decision trees
title_short ECG signals classification using overlapping variables to detect atrial fibrillation
title_full ECG signals classification using overlapping variables to detect atrial fibrillation
title_fullStr ECG signals classification using overlapping variables to detect atrial fibrillation
title_full_unstemmed ECG signals classification using overlapping variables to detect atrial fibrillation
title_sort ECG signals classification using overlapping variables to detect atrial fibrillation
dc.creator.none.fl_str_mv Ziccardi, I. G.
Rey, A. A.
Legnani, W. E.
author Ziccardi, I. G.
author_facet Ziccardi, I. G.
Rey, A. A.
Legnani, W. E.
author_role author
author2 Rey, A. A.
Legnani, W. E.
author2_role author
author
dc.subject.none.fl_str_mv Renyi entropy
statistical complexity
Fisher information
Lyapunov exponent
fractal dimension
atrial fibrillation
decision trees
topic Renyi entropy
statistical complexity
Fisher information
Lyapunov exponent
fractal dimension
atrial fibrillation
decision trees
dc.description.none.fl_txt_mv In the present work a method for the detection of the cardiac pathology known as atrial fibrillation is proposed by calculating different information, statistics and other nonlinear measures over ECG signals. The original database contains records corresponding to patients who are diagnosed with this disease as well as healthy subjects. To formulate the dataset the R´enyi permutation entropy, Fisher information measure, statistical complexity, Lyapunov exponent and fractal dimension were calculated, in order to determine how to combine this features to optimize the identification of the signals coming from ECG with the above mentioned cardiac pathology. With the aim to improve the results obtained in previous studies, a classification method based upon decision trees algorithms is implemented. Later a Montecarlo simulation of one thousand trials is performed with a seventy percent randomly selected from the dataset dedicated to train the classifier and the remaining thirty percent reserved to test in every trial. The quality of the classification is assessed through the computation of the area under the receiver operation characteristic curve (ROC), the F1-score and other classical performance metrics, such as the balanced accuracy, sensitivity, specificity, positive and negative predicted values. The results show that the incorporation of all these features to the dataset when are employed to train the classifier in the training task produces the best classification, in such a way that the largest quality parameter is achieved.
UTN FRBA
Fil: Ziccardi, I. G. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Fil: Rey, A. A. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Fil: Legnani, W. E. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Centro de Procesamiento de Señales e Imágenes (CPSI); Argentina.
Peer Reviewed
description In the present work a method for the detection of the cardiac pathology known as atrial fibrillation is proposed by calculating different information, statistics and other nonlinear measures over ECG signals. The original database contains records corresponding to patients who are diagnosed with this disease as well as healthy subjects. To formulate the dataset the R´enyi permutation entropy, Fisher information measure, statistical complexity, Lyapunov exponent and fractal dimension were calculated, in order to determine how to combine this features to optimize the identification of the signals coming from ECG with the above mentioned cardiac pathology. With the aim to improve the results obtained in previous studies, a classification method based upon decision trees algorithms is implemented. Later a Montecarlo simulation of one thousand trials is performed with a seventy percent randomly selected from the dataset dedicated to train the classifier and the remaining thirty percent reserved to test in every trial. The quality of the classification is assessed through the computation of the area under the receiver operation characteristic curve (ROC), the F1-score and other classical performance metrics, such as the balanced accuracy, sensitivity, specificity, positive and negative predicted values. The results show that the incorporation of all these features to the dataset when are employed to train the classifier in the training task produces the best classification, in such a way that the largest quality parameter is achieved.
publishDate 2022
dc.date.none.fl_str_mv 2022-03-01
2024-03-19T20:27:11Z
2024-03-19T20:27:11Z
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv Trends in Computational and Applied Mathematics, 23.
http://hdl.handle.net/20.500.12272/9929
10.5540/tcam.2022.023.03.00569
identifier_str_mv Trends in Computational and Applied Mathematics, 23.
10.5540/tcam.2022.023.03.00569
url http://hdl.handle.net/20.500.12272/9929
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
2024-03-19T20:27:11Z
http://creativecommons.org/licenses/by-nc-sa/4.0/
Atribución-NoComercial-CompartirIgual 4.0 Internacional
I. G. Ziccardi, A. A. Rey, W. E. Legnani
Licencia Creative Commons Atribución- No Comercial
eu_rights_str_mv openAccess
rights_invalid_str_mv 2024-03-19T20:27:11Z
http://creativecommons.org/licenses/by-nc-sa/4.0/
Atribución-NoComercial-CompartirIgual 4.0 Internacional
I. G. Ziccardi, A. A. Rey, W. E. Legnani
Licencia Creative Commons Atribución- No Comercial
dc.format.none.fl_str_mv pdf
application/pdf
dc.source.none.fl_str_mv Trends in Computational and Applied Mathematics 23(3), 569-581. (2022)
reponame:Repositorio Institucional Abierto (UTN)
instname:Universidad Tecnológica Nacional
reponame_str Repositorio Institucional Abierto (UTN)
collection Repositorio Institucional Abierto (UTN)
instname_str Universidad Tecnológica Nacional
repository.name.fl_str_mv Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacional
repository.mail.fl_str_mv gestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.ar
_version_ 1877230893949517824
score 13.265058

Publicaciones similares