Support vector machine prediction of obstructive sleep apnea in a large-scale Chinese clinical sample

• Published in: Sleep (New York, N.Y.) Vol. 43; no. 7; p. 1
• Main Authors: Huang, Wen-Chi, Lee, Pei-Lin, Liu, Yu-Ting, Chiang, Ambrose A, Lai, Feipei
• Format: Journal Article
• Language: English
• Published: US Oxford University Press 01.07.2020
• Subjects: Aged; Big Data Approaches to Sleep and Circadian Science; China - epidemiology; Editor's Choice; Female; Humans; Machine learning; Male; Medical care; Polysomnography; Quality management; Sensitivity and Specificity; Sleep apnea; Sleep apnea syndromes; Sleep Apnea, Obstructive - diagnosis; Sleep Apnea, Obstructive - epidemiology; Support Vector Machine; Support vector machines; Surveys and Questionnaires; China; Taiwan; prediction; modeling; obstructive; polysomnography; machine learning; sleep apnea
• ISSN: 0161-8105; 1550-9109; 1550-9109
• DOI: 10.1093/sleep/zsz295

Abstract Study Objectives Polysomnography is the gold standard for diagnosis of obstructive sleep apnea (OSA) but it is costly and access is often limited. The aim of this study is to develop a clinically useful support vector machine (SVM)-based prediction model to identify patients with high probability of OSA for nonsleep specialist physician in clinical practice. Methods The SVM model was developed using the features routinely collected at the clinical evaluation from 6,875 Chinese patients referred to sleep clinics for suspected OSA. Three apnea-hypopnea index (AHI) cutoffs, ≥5/h, ≥15/h, and ≥30/h were used to define the severity of OSA. The continuous and categorized features were selected separately and were further selected through stepwise forward feature selection. The modeling was achieved through fivefold cross-validation. The model discriminative ability was evaluated for the whole data set and four subgroups categorized with gender and age (<65 versus ≥65 years old [y/o]). Results Two features were selected to predict AHI cutoff ≥5/h with six features selected for ≥15/h, and six features selected for ≥30/h, respectively, to reach Area under the Receiver Operating Characteristic (AUROC) 0.82, 0.80, and 0.78, respectively. The sensitivity was 74.14%, 75.18%, and 70.26%, while the specificity was 74.71%, 68.73%, and 70.30%, respectively. Compared to logistic regression, Berlin questionnaire, NoSAS Score, and Supersparse Linear Integer Model (SLIM) scoring system, the SVM model performs better with a more balanced sensitivity and specificity. The discriminative ability was best for male <65 y/o and modest for female ≥65 y/o. Conclusion Our model provides a simple and accurate modality for early identification of patients with OSA and may potentially help prioritize them for sleep study.