Online Obstructive Sleep Apnea Detection Based on Hybrid Machine Learning And Classifier Combination For Home-based Applications

Automatic detection of obstructive sleep apnea (OSA) is in great demand. OSA is one of the most prevalent diseases of the current century and established comorbidity to Covid-19. OSA is characterized by complete or relative breathing pauses during sleep. According to medical observations, if OSA remained unrecognized and un-treated, it may lead to physical and mental complications. The gold standard of scoring OSA severity is the time-consuming and expensive method of polysomnography (PSG). The idea of online home-based surveillance of OSA is welcome. It serves as an effective way for spurred detection and reference of patients to sleep clinics. In addition, it can perform automatic control of the therapeutic/assistive devices. In this paper, several configurations for online OSA detection are proposed. The best configuration uses both ECG and SpO2 signals for feature extraction and MI analysis for feature reduction. Various methods of supervised machine learning are exploited for classification. Finally, to reach the best result, the most successful classifiers in sensitivity and specificity are combined in groups of three members with four different combination methods. The proposed method has advantages like limited use of biological signals, automatic detection, online working scheme, and uniform and acceptable performance (over 85%) in all the employed databases. These advantages have not been integrated in previous published methods.