• español
  • English
  • français
  • Deutsch
  • português (Brasil)
  • italiano
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Navegar

    Todo o repositórioComunidadesPor data do documentoAutoresAssuntosTítulos

    Minha conta

    Entrar

    Estatística

    Ver as estatísticas de uso

    Compartir

    Ver item 
    •   Página inicial
    • PRODUÇÃO CIENTÍFICA
    • Grupos de Investigación
    • Grupo de Ingeniería Biomédica
    • GIB - Artículos de revista
    • Ver item
    •   Página inicial
    • PRODUÇÃO CIENTÍFICA
    • Grupos de Investigación
    • Grupo de Ingeniería Biomédica
    • GIB - Artículos de revista
    • Ver item
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano

    Exportar

    RISMendeleyRefworksZotero
    • edm
    • marc
    • xoai
    • qdc
    • ore
    • ese
    • dim
    • uketd_dc
    • oai_dc
    • etdms
    • rdf
    • mods
    • mets
    • didl
    • premis

    Citas

    Por favor, use este identificador para citar o enlazar este ítem:https://uvadoc.uva.es/handle/10324/55620

    Título
    A 2D convolutional neural network to detect sleep apnea in children using airflow and oximetry
    Autor
    Jimenez García, JorgeAutoridad UVA Orcid
    García Gadañón, MaríaAutoridad UVA Orcid
    Gutierrez Tobal, Gonzalo CésarAutoridad UVA Orcid
    Kheirandish Gozal, Leila
    Vaquerizo Villar, FernandoAutoridad UVA Orcid
    Álvarez González, DanielAutoridad UVA Orcid
    Campo Matias, Félix delAutoridad UVA Orcid
    Gozal, David
    Hornero Sánchez, RobertoAutoridad UVA Orcid
    Año del Documento
    2022
    Editorial
    Elsevier
    Descripción
    Producción Científica
    Documento Fuente
    Computers in Biology and Medicine, 2022, vol. 147, 105784
    Resumo
    The gold standard approach to diagnose obstructive sleep apnea (OSA) in children is overnight in-lab polysomnography (PSG), which is labor-intensive for clinicians and onerous to healthcare systems and families. Simplification of PSG should enhance availability and comfort, and reduce complexity and waitlists. Airflow (AF) and oximetry (SpO2) signals summarize most of the information needed to detect apneas and hypopneas, but automatic analysis of these signals using deep-learning algorithms has not been extensively investigated in the pediatric context. The aim of this study was to evaluate a convolutional neural network (CNN) architecture based on these two signals to estimate the severity of pediatric OSA. PSG-derived AF and SpO2 signals from the Childhood Adenotonsillectomy Trial (CHAT) database (1638 recordings), as well as from a clinical database (974 recordings), were analyzed. A 2D CNN fed with AF and SpO2 signals was implemented to estimate the number of apneic events, and the total apnea-hypopnea index (AHI) was estimated. A training-validation-test strategy was used to train the CNN, adjust the hyperparameters, and assess the diagnostic ability of the algorithm, respectively. Classification into four OSA severity levels (no OSA, mild, moderate, or severe) reached 4-class accuracy and Cohen's Kappa of 72.55% and 0.6011 in the CHAT test set, and 61.79% and 0.4469 in the clinical dataset, respectively. Binary classification accuracy using AHI cutoffs 1, 5 and 10 events/h ranged between 84.64% and 94.44% in CHAT, and 84.10%–90.26% in the clinical database. The proposed CNN-based architecture achieved high diagnostic ability in two independent databases, outperforming previous approaches that employed SpO2 signals alone, or other classical feature-engineering approaches. Therefore, analysis of AF and SpO2 signals using deep learning can be useful to deploy reliable computer-aided diagnostic tools for childhood OSA.
    Palabras Clave
    Obstructive sleep apnea
    Apnea obstructiva del sueño
    Airflow
    Flujo aéreo
    Oximetry
    Oximetría
    ISSN
    0010-4825
    Revisión por pares
    SI
    DOI
    10.1016/j.compbiomed.2022.105784
    Patrocinador
    Ministerio de Ciencia, Innovación y Universidades - Agencia Estatal de Investigación (project 10.13039/501100011033)
    Fondo Europeo de Desarrollo Regional - Unión Europea (projects PID2020-115468RB-I00 and PDC2021-120775-I00)
    Sociedad Española de Neumología y Cirugía Torácica (project 649/2018)
    Sociedad Española de Sueño (project Beca de Investigación SES 2019)
    Consorcio Centro de Investigación Biomédica en Red - Instituto de Salud Carlos III - Ministerio de Ciencia, Innovación y Universidades (project CB19/01/00012)
    National Institutes of Health (projects HL083075, HL083129, UL1-RR-024134 and UL1 RR024989)
    National Heart, Lung, and Blood Institute (projects R24 HL114473 and 75N92019R002)
    Ministerio de Educación, Cultura y Deporte (grant FPU16/02938)
    Ministerio de Ciencia, Innovación y Universidades - Agencia Estatal de Investigación - Fondo Social Europeo (grant RYC2019-028566-I)
    National Institutes of Health (grants HL130984, HL140548, and AG061824)
    Version del Editor
    https://www.sciencedirect.com/science/article/pii/S0010482522005510?via%3Dihub
    Propietario de los Derechos
    © 2022 The Authors
    Idioma
    eng
    URI
    https://uvadoc.uva.es/handle/10324/55620
    Tipo de versión
    info:eu-repo/semantics/publishedVersion
    Derechos
    openAccess
    Aparece en las colecciones
    • GIB - Artículos de revista [36]
    Mostrar registro completo
    Arquivos deste item
    Nombre:
    2D-convolutional-neural-network.pdf
    Tamaño:
    5.815Mb
    Formato:
    Adobe PDF
    Thumbnail
    Visualizar/Abrir
    Attribution-NonCommercial-NoDerivatives 4.0 InternacionalExceto quando indicado o contrário, a licença deste item é descrito como Attribution-NonCommercial-NoDerivatives 4.0 Internacional

    Universidad de Valladolid

    Powered by MIT's. DSpace software, Version 5.10