Detection of obstructive sleep apnea in pediatric subjects using surface lead electrocardiogram features

• Published in: Sleep (New York, N.Y.) N.Y.), 2004-06, Vol.27 (4), p.784-792
• Main Authors: SHOULDICE, Redmond B, O'BRIEN, Louise M, O'BRIEN, Ciara, DE CHAZAL, Philip, GOZAL, David, HENEGHAN, Conor
• Format: Article
• Language: English
• Subjects: Adult; Biological and medical sciences; Body Mass Index; Electrocardiography; Electrocardiography. Vectocardiography; Electrodiagnosis. Electric activity recording; Female; Humans; Investigative techniques, diagnostic techniques (general aspects); Male; Medical sciences; Non tumoral diseases; Observation; Otorhinolaryngology. Stomatology; Polysomnography; Retrospective Studies; Sleep Apnea, Obstructive - diagnosis; Upper respiratory tract, upper alimentary tract, paranasal sinuses, salivary glands: diseases, semeiology
• ISSN: 0161-8105; 1550-9109
• DOI: 10.1093/sleep/27.4.784

To investigate the feasibility of detecting obstructive sleep apnea (OSA) in children using an automated classification system based on analysis of overnight electrocardiogram (ECG) recordings. Retrospective observational study. A pediatric sleep clinic. Fifty children underwent full overnight polysomnography. N/A. Expert polysomnography scoring was performed. The datasets were divided into a training set of 25 subjects (11 normal, 14 with OSA) and a withheld test set of 25 subjects (11 normal, 14 with OSA). Features, calculated from the ECG of the 25 training datasets, were empirically chosen to train a modified quadratic discriminant analysis classification system. The selected configuration used a segment length of 60 seconds and processed mean, SD, power spectral density, and serial correlation measures to classify segments as apneic or normal. By combining per-segment classifications and using receiver-operator characteristic analysis, a per-subject classifier was obtained that had a sensitivity of 85.7%, specificity of 90.9%, and accuracy of 88% on the training datasets. The same decision threshold was applied to the withheld datasets and yielded a sensitivity of 85.7%, specificity of 81.8%, and accuracy of 84%. The positive and negative predictive values were 85.7% and 81.8%, respectively, on the test dataset. The ability to correctly identify 12 out of 14 cases of OSA (with the 2 false negatives arising from subjects with an apnea-hypopnea index less than 10) indicates that the automated apnea classification system outlined may have clinical utility in pediatric patients.