Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration

Hypertension, a primary risk factor for various cardiovascular diseases, is a global health concern. Early identification and effective management of hypertensive individuals are vital for reducing associated health risks. This study explores the potential of deep learning (DL) techniques, specifica...

Descripción completa

Detalles Bibliográficos
Autores: Cano, J, Bertomeu-González, V, Fácila, L, Hornero, F, Alcaraz, R, Rieta, JJ
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:INCLIVA
Repositorio:r-INCLIVA. Repositorio Institucional de Producción Científica de INCLIVA
OAI Identifier:oai:incliva.fundanetsuite.com:p18002
Acceso en línea:https://incliva.portalinvestigacion.com/publicaciones/18002
Access Level:acceso abierto
Palabra clave:blood pressure
hypertension
photoplethysmography
calibration
deep learning
id ES_bcc18b3012a6aedc31723350d4cacd73
oai_identifier_str oai:incliva.fundanetsuite.com:p18002
network_acronym_str ES
network_name_str España
repository_id_str
spelling Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and CalibrationCano, JBertomeu-González, VFácila, LHornero, FAlcaraz, RRieta, JJblood pressurehypertensionphotoplethysmographycalibrationdeep learningHypertension, a primary risk factor for various cardiovascular diseases, is a global health concern. Early identification and effective management of hypertensive individuals are vital for reducing associated health risks. This study explores the potential of deep learning (DL) techniques, specifically GoogLeNet, ResNet-18, and ResNet-50, for discriminating between normotensive (NTS) and hypertensive (HTS) individuals using photoplethysmographic (PPG) recordings. The research assesses the impact of calibration at different time intervals between measurements, considering intervals less than 1 h, 1-6 h, 6-24 h, and over 24 h. Results indicate that calibration is most effective when measurements are closely spaced, with an accuracy exceeding 90% in all the DL strategies tested. For calibration intervals below 1 h, ResNet-18 achieved the highest accuracy (93.32%), sensitivity (84.09%), specificity (97.30%), and F1-score (88.36%). As the time interval between calibration and test measurements increased, classification performance gradually declined. For intervals exceeding 6 h, accuracy dropped below 81% but with all models maintaining accuracy above 71% even for intervals above 24 h. This study provides valuable insights into the feasibility of using DL for hypertension risk assessment, particularly through PPG recordings. It demonstrates that closely spaced calibration measurements can lead to highly accurate classification, emphasizing the potential for real-time applications. These findings may pave the way for advanced, non-invasive, and continuous blood pressure monitoring methods that are both efficient and reliable.MDPI2023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://incliva.portalinvestigacion.com/publicaciones/18002Bioengineering-BaselISSN: 23065354reponame:r-INCLIVA. Repositorio Institucional de Producción Científica de INCLIVAinstname:INCLIVAInglésinfo:eu-repo/semantics/openAccessoai:incliva.fundanetsuite.com:p180022026-06-07T16:35:31Z
dc.title.none.fl_str_mv Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
title Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
spellingShingle Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
Cano, J
blood pressure
hypertension
photoplethysmography
calibration
deep learning
title_short Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
title_full Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
title_fullStr Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
title_full_unstemmed Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
title_sort Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
dc.creator.none.fl_str_mv Cano, J
Bertomeu-González, V
Fácila, L
Hornero, F
Alcaraz, R
Rieta, JJ
author Cano, J
author_facet Cano, J
Bertomeu-González, V
Fácila, L
Hornero, F
Alcaraz, R
Rieta, JJ
author_role author
author2 Bertomeu-González, V
Fácila, L
Hornero, F
Alcaraz, R
Rieta, JJ
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv blood pressure
hypertension
photoplethysmography
calibration
deep learning
topic blood pressure
hypertension
photoplethysmography
calibration
deep learning
description Hypertension, a primary risk factor for various cardiovascular diseases, is a global health concern. Early identification and effective management of hypertensive individuals are vital for reducing associated health risks. This study explores the potential of deep learning (DL) techniques, specifically GoogLeNet, ResNet-18, and ResNet-50, for discriminating between normotensive (NTS) and hypertensive (HTS) individuals using photoplethysmographic (PPG) recordings. The research assesses the impact of calibration at different time intervals between measurements, considering intervals less than 1 h, 1-6 h, 6-24 h, and over 24 h. Results indicate that calibration is most effective when measurements are closely spaced, with an accuracy exceeding 90% in all the DL strategies tested. For calibration intervals below 1 h, ResNet-18 achieved the highest accuracy (93.32%), sensitivity (84.09%), specificity (97.30%), and F1-score (88.36%). As the time interval between calibration and test measurements increased, classification performance gradually declined. For intervals exceeding 6 h, accuracy dropped below 81% but with all models maintaining accuracy above 71% even for intervals above 24 h. This study provides valuable insights into the feasibility of using DL for hypertension risk assessment, particularly through PPG recordings. It demonstrates that closely spaced calibration measurements can lead to highly accurate classification, emphasizing the potential for real-time applications. These findings may pave the way for advanced, non-invasive, and continuous blood pressure monitoring methods that are both efficient and reliable.
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://incliva.portalinvestigacion.com/publicaciones/18002
url https://incliva.portalinvestigacion.com/publicaciones/18002
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv Bioengineering-Basel
ISSN: 23065354
reponame:r-INCLIVA. Repositorio Institucional de Producción Científica de INCLIVA
instname:INCLIVA
instname_str INCLIVA
reponame_str r-INCLIVA. Repositorio Institucional de Producción Científica de INCLIVA
collection r-INCLIVA. Repositorio Institucional de Producción Científica de INCLIVA
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418142429609984
score 15,198674

Similares en LA Referencia