Automatic Assessment of Pediatric Sleep Apnea Severity Using Overnight Oximetry and Convolutional Neural Networks

In this study, we use the overnight blood oxygen saturation (SpO2) signal along with convolutional neural networks (CNN) for the automatic estimation of pediatric sleep apnea-hypopnea syndrome (SAHS) severity. The few preceding studies have focused on the application of conventional feature extraction methods to obtain information from the SpO2 signal, which may omit relevant data related to the illness. In contrast, deep learning techniques are able to automatically learn features from raw input signal. Thus, we propose to assess whether CNN, a deep learning algorithm, could automatically estimate the apnea-hypopnea index (AHÍ) from nocturnal oximetry to help establish pediatric SAHS presence and severity. A database of 746 SpO2 recordings is involved in the study. CNN was trained using 20-min segments from the SpO2 signal in the training set (400 subjects). Hyperparameters of the CNN architecture were tuned using a validation set (100 subjects). This model was applied to a test set (246 subjects), in which the final AHI of each patient was obtained as the average of the output of the CNN for all the segments of the corresponding SpO2 signal. The AHI estimated by the CNN showed a promising diagnostic performance, with 74.8%, 90.7%, and 95.1% accuracies for the common AHI severity thresholds of 1, 5, and 10 events per hour (e/h), respectively. Furthermore, this model reached 28.6, 32.9, and 120.0 positive likelihood ratios for the above-mentioned AHI thresholds. This suggests that the information extracted from the oximetry signal by deep learning techniques may be useful to both establish pediatric SAHS and its severity.

[1]  G. C. Gutiérrez-Tobal,et al.  Nocturnal Oximetry‐based Evaluation of Habitually Snoring Children , 2017, American journal of respiratory and critical care medicine.

[2]  G. Church,et al.  The role of polysomnography in diagnosing and treating obstructive sleep apnea in pediatric patients. , 2012, Current problems in pediatric and adolescent health care.

[3]  Roberto Hornero,et al.  Detrended fluctuation analysis of the oximetry signal to assist in paediatric sleep apnoea–hypopnoea syndrome diagnosis , 2018, Physiological measurement.

[4]  A. Halbower,et al.  Diagnosis and Management of Childhood Obstructive Sleep Apnea Syndrome , 2012, Pediatrics.

[5]  W. Karlen,et al.  Development of a Screening Tool for Sleep Disordered Breathing in Children Using the Phone Oximeter™ , 2014, PloS one.

[6]  Raanan Arens,et al.  A randomized trial of adenotonsillectomy for childhood sleep apnea. , 2013, The New England journal of medicine.

[7]  Bahareh Pourbabaee,et al.  SleepNet: automated sleep analysis via dense convolutional neural network using physiological time series , 2019, Physiological measurement.

[8]  G. C. Gutiérrez-Tobal,et al.  Automated Screening of Children With Obstructive Sleep Apnea Using Nocturnal Oximetry: An Alternative to Respiratory Polygraphy in Unattended Settings. , 2017, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.

[9]  Kwang Suk Park,et al.  Real-time apnea-hypopnea event detection during sleep by convolutional neural networks , 2018, Comput. Biol. Medicine.

[10]  Haoqi Sun,et al.  Expert-level sleep scoring with deep neural networks , 2018, J. Am. Medical Informatics Assoc..

[11]  Raanan Arens,et al.  The Childhood Adenotonsillectomy Trial (CHAT): rationale, design, and challenges of a randomized controlled trial evaluating a standard surgical procedure in a pediatric population. , 2011, Sleep.

[12]  M. Su,et al.  Usefulness of desaturation index for the assessment of obstructive sleep apnea syndrome in children. , 2013, International journal of pediatric otorhinolaryngology.

[13]  Daniel Álvarez,et al.  Convolutional Neural Networks to Detect Pediatric Apnea-Hypopnea Events from Oximetry , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[14]  Daniel Álvarez,et al.  Utility of bispectrum in the screening of pediatric sleep apnea-hypopnea syndrome using oximetry recordings , 2018, Comput. Methods Programs Biomed..

[15]  L. Kheirandish-Gozal What is "abnormal" in pediatric sleep? , 2010, Respiratory care.

[16]  K. Brown,et al.  Planning adenotonsillectomy in children with obstructive sleep apnea: the role of overnight oximetry. , 2004, Pediatrics.

[17]  A. Chesson,et al.  The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications , 2007 .

[18]  Timo Leppänen,et al.  Artificial neural network analysis of the oxygen saturation signal enables accurate diagnostics of sleep apnea , 2019, Scientific Reports.

[19]  A. Chesson,et al.  The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology, and Techinical Specifications , 2007 .

[20]  D. Altman,et al.  Diagnostic tests 4: likelihood ratios , 2004, BMJ : British Medical Journal.