A 2D convolutional neural network to detect sleep apnea in children using airflow and oximetry. (August 2022)

• Record Type: Journal Article
• Authors: Jiménez-García, Jorge; García, María; Gutiérrez-Tobal, Gonzalo C.; Kheirandish-Gozal, Leila; Vaquerizo-Villar, Fernando; Álvarez, Daniel; del Campo, Félix; Gozal, David; Hornero, Roberto
• Is Part Of: Computers in biology and medicine. Volume 147(2022)
• Publication Date: 2022-08
• Subjects: Obstructive sleep apnea -- Children -- Airflow -- Oximetry -- Convolutional neural network -- Deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105784
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: 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. Highlights: A 2D convolutional neural network aimed at detecting pediatric obstructive sleep apnea. Airflow and oximetry signals were jointly used to train and evaluate the algorithm. Two large databases were employed, covering a total of 2612 pediatric subjects. Accurate estimation of the severity and enhanced identification of mild and moderate cases. The algorithm outperformed other feature-engineering or single-signal approaches.