| Home | E-Submission | Sitemap | Contact Us |  
J Sleep Med > Volume 17(2); 2020 > Article
J Sleep Med. 2020;17(2):128-137.         doi: https://doi.org/10.13078/jsm.200022
Diagnostic Accuracy of Different Machine Learning Algorithms for Obstructive Sleep Apnea
Hyun-Woo Kim1 , Euihwan Park2 , Dae Jin Kim3 , Sue Jean Mun4 , Jiyoung Kim5 , Gha-Hyun Lee5 , Jae Wook Cho1
1Department of Neurology, Pusan National University Yangsan Hospital, Yangsan, Korea
2Department of Economics, Hannam University, Daejeon, Korea
3Department of Biomedical Laboratory Science, Kyungbok University, Porcheon, Korea
4Department of Otorhinolaryngology, Pusan National University Yangsan Hospital, Yangsan, Korea
5Department of Neurology, Pusan National University Hospital, Busan, Korea
Corresponding Author: Jae Wook Cho ,Tel: +82-55-360-2122, Fax: +82-55-360-2152, Email: sleepcho@pusan.ac.kr
Received: October 22, 2020   Revised: November 12, 2020   Accepted: November 17, 2020   Published online: December 31, 2020
Share :  
Objectives: The objective of this study was to develop models for predicting obstructive sleep apnea (OSA) based on easily obtainable clinical information of patients using various machine learning techniques.
Methods: We used a data set that included the records of 1,368 patients, in which 1,074 patients were male (78.5 %), and 294 patients were female (21.5 %). We randomly divided the data into a training set (1,000) and test set (368). Five machine learning methods, i.e., support vector machine model, lasso logit model, naïve bayes, discriminant analysis, and K-nearest neighbor (KNN), with a 10-cross fold technique were used with the proposed model to predict OSA. We evaluated the accuracy, sensitivity, specificity, and precision of each model for three thresholds [Apnea-Hypopnea Index (AHI)≥5, AHI≥15, and AHI≥30].
Results: Among the machine learning techniques, KNN showed the best results compared to the other techniques. The accuracy, sensitivity, specificity, and precision of OSA prediction were 87.0%, 91.0%, 74.4%, and 91.9%, respectively, based on AHI≥5. When the threshold of OSA was AHI≥15 or AHI≥30, KNN provided lower accuracy (79.6% each) and precision (79.0% and 68.7%), which were still higher than those of the other techniques.
Conclusions: The model derived from the KNN technique exhibited the best performance based on its highest level of accuracy. We demonstrate that this model is a useful tool for predicting OSA.
Keywords: Obstructive sleep apnea | Apnea | Machine learning | Algorithm
Editorial Office
Joong-Ang Bldg., 18-8, Wonhyo-ro 89 Gil, Yonsan-gu, Seoul 04314, Republic of Korea
Tel: +82-2-717-5545   Fax: +82-2-717-5515   E-mail: jsleepmed@gmail.com

Copyright© Korean Sleep Research Society. All rights reserved.               powerd by M2community
About |  Browse Articles |  Current Issue |  For Authors and Reviewers