Developing an Apnea/Hypopnea Diagnostic Model Using SVM

Introduction: Among sleep-related disorders, Sleep apnea has been under more attention and it’s the most common respiratory disorder in which respiration ceases frequently which can lead to serious health disorders and even mortality. Polysomnography is the standard method for diagnosing this disease at the moment which is costly and time-consuming. The present study aimed at analyzing vital signals to diagnose Sleep apnea using machine learning algorithms.Material and Methods: This analytical–descriptive was conducted on ۵۰ patients (۱۱ normal, ۱۳ mild, ۱۷ moderate and ۹ severe patients) in the sleep clinic of Imam Khomeini hospital. Initially, data pre-processing was carried out in two steps (noise elimination and moving average algorithm). Next, using the singular value decomposition method, ۱۲ features were extracted for airflow. Finally, to classify data, SVM with quadratic, polynomial and RBF kernels were trained and tested.Results: After applying different kernel functions on SVM, the RBF kernel showed the most efficient performance. After ۱۰ fold cross validation method for evaluation, the mean accuracy obtained for normal, apnea, and hypopnea modes were ۹۲.۷۴%, ۹۱.۷۰%, ۹۳.۲۶%.Conclusion: The results show that in online applications or applications where the volume and time of calculations and at the same time the accuracy of the result is very important, The disease can be diagnosed with acceptable accuracy using machine learning algorithms.

Keywords:

Sleep Apnea , SVM Algorithm , Polysomnography , Airflow