An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals

Deep-learning (DL) approaches have been developed using pulse rate (PR) and blood oxygen saturation (SpO2) recordings from pulse oximetry to streamline sleep staging, particularly for obstructive sleep apnea (OSA) patients. However, lack of interpretability and validation across patients from a wide...

Descripción completa

Detalles Bibliográficos
Autores: Vaquerizo Villar, Fernando, Gutiérrez Tobal, Gonzalo César, Álvarez González, Daniel, Martín Montero, Adrián, Gozal, David, Hornero Sánchez, Roberto
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/39017
Acceso en línea:https://hdl.handle.net/10902/39017
Access Level:acceso abierto
Palabra clave:Age subgroups
Deep learning
Explainable artificial intelligence
Pulse oximetry
Obstructive sleep apnea
Sleep stages
id ES_a0d6da509878021986eadbb6df48fdcb
oai_identifier_str oai:repositorio.unican.es:10902/39017
network_acronym_str ES
network_name_str España
repository_id_str
spelling An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signalsVaquerizo Villar, FernandoGutiérrez Tobal, Gonzalo CésarÁlvarez González, DanielMartín Montero, AdriánGozal, DavidHornero Sánchez, RobertoAge subgroupsDeep learningExplainable artificial intelligencePulse oximetryObstructive sleep apneaSleep stagesDeep-learning (DL) approaches have been developed using pulse rate (PR) and blood oxygen saturation (SpO2) recordings from pulse oximetry to streamline sleep staging, particularly for obstructive sleep apnea (OSA) patients. However, lack of interpretability and validation across patients from a wide range of ages (children, adolescents, adults, and elderly OSA individuals) are two major concerns. In this study, a DL model based on the U-Net framework (POxi-SleepNet) was tailored to accurately perform 4-class sleep staging (wake, light sleep, deep sleep, and rapid-eye movement sleep) in OSA patients across all age subgroups using PR and SpO2 signals. An explainable artificial intelligence (XAI) methodology based on semantic segmentation via gradient-weighted class activation mapping (Seg-Grad-CAM) was also applied to quantitatively interpret the time and frequency characteristics of pulse oximetry recordings that influence sleep stage classification. Overnight PR and SpO2 signals from 17303 sleep studies from six datasets encompassing children, adolescents, adults, and elderly OSA individuals were used. POxi-SleepNet showed high performance for sleep staging in the six databases, with accuracies between 81.5 % and 84.5 % and Cohen's kappa values from 0.726 to 0.779. It also demonstrated greater generalizability than previous studies. XAI analysis showed the key contributions of mean and variability in PR and SpO2 amplitude, as well as changes in their spectral content across specific frequency bands (0.004-0.020 Hz, 0.020-0.100 Hz, and 0.180-0.400 Hz), for sleep stage classification. These findings indicate that POxi-SleepNet could effectively automate sleep staging and assist in diagnosing OSA across all age groups in clinical settings.This work is part of the projects PID2023-148895OB-I00, PID2020- 115468RB-I00, and CPP2022-009735, funded by MCIN/AEI/10.13039/ 501100011033, the ‘Fondo Social Europeo Plus (FSE+)’, and the European Union “NextGenerationEU”/PRTR. This research was also co- funded by the European Union through the Interreg VI-A Spain- Portugal Program (POCTEP) 2021–2027 (0043_NET4SLEEP_2_E), and by “Consorcio Centro de Investigaci´on Biom´edica en Red (CIBER) en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN)” (CB19/01/ 00012) through “Instituto de Salud Carlos III (ISCIII)”, co-funded with European Regional Development Fund.Elsevier LimitedUniversidad de Cantabria20252025-12-22journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articlehttps://hdl.handle.net/10902/39017Engineering Applications of Artificial Intelligence, 2025, 162 (Part C), 112562reponame:UCrea Repositorio Abierto de la Universidad de Cantabriainstname:Universidad de Cantabria (UC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:repositorio.unican.es:10902/390172026-06-02T12:39:31Z
dc.title.none.fl_str_mv An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
title An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
spellingShingle An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
Vaquerizo Villar, Fernando
Age subgroups
Deep learning
Explainable artificial intelligence
Pulse oximetry
Obstructive sleep apnea
Sleep stages
title_short An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
title_full An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
title_fullStr An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
title_full_unstemmed An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
title_sort An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals
dc.creator.none.fl_str_mv Vaquerizo Villar, Fernando
Gutiérrez Tobal, Gonzalo César
Álvarez González, Daniel
Martín Montero, Adrián
Gozal, David
Hornero Sánchez, Roberto
author Vaquerizo Villar, Fernando
author_facet Vaquerizo Villar, Fernando
Gutiérrez Tobal, Gonzalo César
Álvarez González, Daniel
Martín Montero, Adrián
Gozal, David
Hornero Sánchez, Roberto
author_role author
author2 Gutiérrez Tobal, Gonzalo César
Álvarez González, Daniel
Martín Montero, Adrián
Gozal, David
Hornero Sánchez, Roberto
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidad de Cantabria
dc.subject.none.fl_str_mv Age subgroups
Deep learning
Explainable artificial intelligence
Pulse oximetry
Obstructive sleep apnea
Sleep stages
topic Age subgroups
Deep learning
Explainable artificial intelligence
Pulse oximetry
Obstructive sleep apnea
Sleep stages
description Deep-learning (DL) approaches have been developed using pulse rate (PR) and blood oxygen saturation (SpO2) recordings from pulse oximetry to streamline sleep staging, particularly for obstructive sleep apnea (OSA) patients. However, lack of interpretability and validation across patients from a wide range of ages (children, adolescents, adults, and elderly OSA individuals) are two major concerns. In this study, a DL model based on the U-Net framework (POxi-SleepNet) was tailored to accurately perform 4-class sleep staging (wake, light sleep, deep sleep, and rapid-eye movement sleep) in OSA patients across all age subgroups using PR and SpO2 signals. An explainable artificial intelligence (XAI) methodology based on semantic segmentation via gradient-weighted class activation mapping (Seg-Grad-CAM) was also applied to quantitatively interpret the time and frequency characteristics of pulse oximetry recordings that influence sleep stage classification. Overnight PR and SpO2 signals from 17303 sleep studies from six datasets encompassing children, adolescents, adults, and elderly OSA individuals were used. POxi-SleepNet showed high performance for sleep staging in the six databases, with accuracies between 81.5 % and 84.5 % and Cohen's kappa values from 0.726 to 0.779. It also demonstrated greater generalizability than previous studies. XAI analysis showed the key contributions of mean and variability in PR and SpO2 amplitude, as well as changes in their spectral content across specific frequency bands (0.004-0.020 Hz, 0.020-0.100 Hz, and 0.180-0.400 Hz), for sleep stage classification. These findings indicate that POxi-SleepNet could effectively automate sleep staging and assist in diagnosing OSA across all age groups in clinical settings.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-12-22
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10902/39017
url https://hdl.handle.net/10902/39017
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier Limited
publisher.none.fl_str_mv Elsevier Limited
dc.source.none.fl_str_mv Engineering Applications of Artificial Intelligence, 2025, 162 (Part C), 112562
reponame:UCrea Repositorio Abierto de la Universidad de Cantabria
instname:Universidad de Cantabria (UC)
instname_str Universidad de Cantabria (UC)
reponame_str UCrea Repositorio Abierto de la Universidad de Cantabria
collection UCrea Repositorio Abierto de la Universidad de Cantabria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415061368340480
score 15.812429

Similares en LA Referencia