Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection

Autores
Franco, Lorena; Escobar Robledo, Luis; Bayés de Luna, Antoni; Massa, José
Año de publicación
2021
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Early-stage detection of Bayès Syndrome, a condition related to interatrial block, is of great interest due to its association with multiple medical conditions. For preventive purposes, this block can be detected by analysing the P-Wave morphology of ECG signals. Although few related works on ECG analysis for this syndrome detection and typically signal processing algorithms were used, it is interesting to explore clustering techniques as an alternative approach based on Machine Learning. In this work, two clustering techniques were applied: K-Means++ (two different implementations) and a novel clustering algorithm called FAUM (Fast Autonomous Unsupervised Multidimensional) with a fixed number of clusters. For each ECG signal sample, derivative and integrative variations on II, III and AVF leads, were calculated. A total of 2113 signals previously obtained by data augmentation techniques were used in this work with the mentioned clustering methods. Regarding the results, one of the K-Means++ implementations reached a value of 0.82 for the F1-Score metric. Also, integrative variation performance was better than derivative in detecting the P-Wave morphology.
Fil: Franco, Lorena. Universidad Tecnológica Nacional. Facultad Regional Delta; Argentina.
Fil: Escobar Robledo, Luis. Universidad CES. Facultad de Medicina; Colombia
Fil: Bayés de Luna, Antoni. Fundació d'Investigació Cardiovascular; España.
Fil: Massa, José. Universidad Nacional del Centro de Buenos Aires. INTIA. Facultad de Ciencias Exactas; Argentina.
Materia
Bayès Syndrome
ECG
Clustering
K-Means++
FAUM
Signal derivative
Signal integration
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Attribution-NonCommercial-NoDerivs 2.5 Argentina
Repositorio
Repositorio Institucional Abierto (UTN)
Institución
Universidad Tecnológica Nacional
OAI Identificador
oai:ria.utn.edu.ar:20.500.12272/15455
Acceder
id RIAUTN_b3dca1f2888838aa68b4a10dea327a08
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/15455
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling Clustering of derivative and integrative P-Wave features for Bayès Syndrome detectionFranco, LorenaEscobar Robledo, LuisBayés de Luna, AntoniMassa, JoséBayès SyndromeECGClusteringK-Means++FAUMSignal derivativeSignal integrationEarly-stage detection of Bayès Syndrome, a condition related to interatrial block, is of great interest due to its association with multiple medical conditions. For preventive purposes, this block can be detected by analysing the P-Wave morphology of ECG signals. Although few related works on ECG analysis for this syndrome detection and typically signal processing algorithms were used, it is interesting to explore clustering techniques as an alternative approach based on Machine Learning. In this work, two clustering techniques were applied: K-Means++ (two different implementations) and a novel clustering algorithm called FAUM (Fast Autonomous Unsupervised Multidimensional) with a fixed number of clusters. For each ECG signal sample, derivative and integrative variations on II, III and AVF leads, were calculated. A total of 2113 signals previously obtained by data augmentation techniques were used in this work with the mentioned clustering methods. Regarding the results, one of the K-Means++ implementations reached a value of 0.82 for the F1-Score metric. Also, integrative variation performance was better than derivative in detecting the P-Wave morphology.Fil: Franco, Lorena. Universidad Tecnológica Nacional. Facultad Regional Delta; Argentina.Fil: Escobar Robledo, Luis. Universidad CES. Facultad de Medicina; ColombiaFil: Bayés de Luna, Antoni. Fundació d'Investigació Cardiovascular; España.Fil: Massa, José. Universidad Nacional del Centro de Buenos Aires. INTIA. Facultad de Ciencias Exactas; Argentina.2026-09-01T20:19:41Z2021info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciapdfapplication/pdfhttps://hdl.handle.net/20.500.12272/15455enghttps://ria.utn.edu.ar/items/d99ce8b2-09b5-43a8-beed-422caf33cbf2info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivs 2.5 Argentinahttp://creativecommons.org/licenses/by-nc-nd/2.5/ar/Los autoresAtribución – No Comercial – Sin Obra Derivada (by-nc-nd)reponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacional2026-09-24T12:47:10Zoai:ria.utn.edu.ar:20.500.12272/15455instacron: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 12:47:12.063Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
title Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
spellingShingle Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
Franco, Lorena
Bayès Syndrome
ECG
Clustering
K-Means++
FAUM
Signal derivative
Signal integration
title_short Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
title_full Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
title_fullStr Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
title_full_unstemmed Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
title_sort Clustering of derivative and integrative P-Wave features for Bayès Syndrome detection
dc.creator.none.fl_str_mv Franco, Lorena
Escobar Robledo, Luis
Bayés de Luna, Antoni
Massa, José
author Franco, Lorena
author_facet Franco, Lorena
Escobar Robledo, Luis
Bayés de Luna, Antoni
Massa, José
author_role author
author2 Escobar Robledo, Luis
Bayés de Luna, Antoni
Massa, José
author2_role author
author
author
dc.subject.none.fl_str_mv Bayès Syndrome
ECG
Clustering
K-Means++
FAUM
Signal derivative
Signal integration
topic Bayès Syndrome
ECG
Clustering
K-Means++
FAUM
Signal derivative
Signal integration
dc.description.none.fl_txt_mv Early-stage detection of Bayès Syndrome, a condition related to interatrial block, is of great interest due to its association with multiple medical conditions. For preventive purposes, this block can be detected by analysing the P-Wave morphology of ECG signals. Although few related works on ECG analysis for this syndrome detection and typically signal processing algorithms were used, it is interesting to explore clustering techniques as an alternative approach based on Machine Learning. In this work, two clustering techniques were applied: K-Means++ (two different implementations) and a novel clustering algorithm called FAUM (Fast Autonomous Unsupervised Multidimensional) with a fixed number of clusters. For each ECG signal sample, derivative and integrative variations on II, III and AVF leads, were calculated. A total of 2113 signals previously obtained by data augmentation techniques were used in this work with the mentioned clustering methods. Regarding the results, one of the K-Means++ implementations reached a value of 0.82 for the F1-Score metric. Also, integrative variation performance was better than derivative in detecting the P-Wave morphology.
Fil: Franco, Lorena. Universidad Tecnológica Nacional. Facultad Regional Delta; Argentina.
Fil: Escobar Robledo, Luis. Universidad CES. Facultad de Medicina; Colombia
Fil: Bayés de Luna, Antoni. Fundació d'Investigació Cardiovascular; España.
Fil: Massa, José. Universidad Nacional del Centro de Buenos Aires. INTIA. Facultad de Ciencias Exactas; Argentina.
description Early-stage detection of Bayès Syndrome, a condition related to interatrial block, is of great interest due to its association with multiple medical conditions. For preventive purposes, this block can be detected by analysing the P-Wave morphology of ECG signals. Although few related works on ECG analysis for this syndrome detection and typically signal processing algorithms were used, it is interesting to explore clustering techniques as an alternative approach based on Machine Learning. In this work, two clustering techniques were applied: K-Means++ (two different implementations) and a novel clustering algorithm called FAUM (Fast Autonomous Unsupervised Multidimensional) with a fixed number of clusters. For each ECG signal sample, derivative and integrative variations on II, III and AVF leads, were calculated. A total of 2113 signals previously obtained by data augmentation techniques were used in this work with the mentioned clustering methods. Regarding the results, one of the K-Means++ implementations reached a value of 0.82 for the F1-Score metric. Also, integrative variation performance was better than derivative in detecting the P-Wave morphology.
publishDate 2021
dc.date.none.fl_str_mv 2021
2026-09-01T20:19:41Z
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.12272/15455
url https://hdl.handle.net/20.500.12272/15455
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://ria.utn.edu.ar/items/d99ce8b2-09b5-43a8-beed-422caf33cbf2
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
Attribution-NonCommercial-NoDerivs 2.5 Argentina
http://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Los autores
Atribución – No Comercial – Sin Obra Derivada (by-nc-nd)
eu_rights_str_mv openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivs 2.5 Argentina
http://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Los autores
Atribución – No Comercial – Sin Obra Derivada (by-nc-nd)
dc.format.none.fl_str_mv pdf
application/pdf
dc.source.none.fl_str_mv 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_ 1877230933650702336
score 13.265058

Publicaciones similares