2026-07-22T10:41:31Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/615072025-02-20T11:39:39Zcom_10324_23459com_10324_954com_10324_894col_10324_23460

Vaquerizo Villar, Fernando Gutierrez Tobal, Gonzalo César Calvo, Eva Álvarez González, Daniel Kheirandish Gozal, Leila Campo Matias, Félix del Hornero Sánchez, Roberto 2023-09-11T12:54:50Z 2023-09-11T12:54:50Z 2023 Computers in Biology and Medicine, 2023, vol. 165, 107419 0010-4825 https://uvadoc.uva.es/handle/10324/61507 10.1016/j.compbiomed.2023.107419 107419 Computers in Biology and Medicine 165 Producción Científica Automatic deep-learning models used for sleep scoring in children with obstructive sleep apnea (OSA) are perceived as black boxes, limiting their implementation in clinical settings. Accordingly, we aimed to develop an accurate and interpretable deep-learning model for sleep staging in children using single-channel electroencephalogram (EEG) recordings. We used EEG signals from the Childhood Adenotonsillectomy Trial (CHAT) dataset (n = 1637) and a clinical sleep database (n = 980). Three distinct deep-learning architectures were explored to automatically classify sleep stages from a single-channel EEG data. Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable artificial intelligence (XAI) algorithm, was then applied to provide an interpretation of the singular EEG patterns contributing to each predicted sleep stage. Among the tested architectures, a standard convolutional neural network (CNN) demonstrated the highest performance for automated sleep stage detection in the CHAT test set (accuracy = 86.9% and five-class kappa = 0.827). Furthermore, the CNN-based estimation of total sleep time exhibited strong agreement in the clinical dataset (intra-class correlation coefficient = 0.772). Our XAI approach using Grad-CAM effectively highlighted the EEG features associated with each sleep stage, emphasizing their influence on the CNN's decision-making process in both datasets. Grad-CAM heatmaps also allowed to identify and analyze epochs within a recording with a highly likelihood to be misclassified, revealing mixed features from different sleep stages within these epochs. Finally, Grad-CAM heatmaps unveiled novel features contributing to sleep scoring using a single EEG channel. Consequently, integrating an explainable CNN-based deep-learning model in the clinical environment could enable automatic sleep staging in pediatric sleep apnea tests. Ministerio de Ciencia e Innovación- Agencia Estatal de Investigación- FEDER-EU y NextGenerationEU/PRTR (PID2020-115468RB-I00 y PDC2021-120775-I00) Sociedad Española de Neumología y Cirugía Torácica (SEPAR) (649/2018) CIBER -Consorcio Centro de Investigación Biomédica en Red- Instituto de Salud Carlos III (CB19/01/00012) Institutos Nacionales de Salud (HL083075, HL083129, UL1-RR-024134, UL1 RR024989) Instituto Nacional del Corazón, los Pulmones y la Sangre (R24 HL114473, 75N92019R002) Ministerio de Ciencia e Innovación - Agencia Estatal de Investigación- “Ramón y Cajal” grant (RYC2019-028566-I) application/pdf eng Elsevier info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-nd/4.0/ © 2023 The Authors Attribution-NonCommercial-NoDerivatives 4.0 Internacional Sueño, trastornos del Pediatría Deep learning Electroencephalogram (EEG) Pediatric obstructive sleep apnea (OSA) Aprendizaje profundo Electroencefalograma (EEG) Apnea obstructiva del sueño pediátrica (AOS) 3201.10 Pediatría An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://www.sciencedirect.com/science/article/pii/S0010482523008843?via%3Dihub SI