Automatic Classification of Sleep Apnea Type and Severity using EEG Signals

Sleep apnea is a potentially fatal disorder that causes frequent breathing pauses during sleep. Prior research has shown that monitoring of EEG signals during sleep can contribute to automatic detection of apnea events. However, a more comprehensive classification of specific apnea types and their severity is required for accurate clinical diagnosis and real-time detection of critical apnea episodes. In this study, we employed annotated EEG signals from 25 apnea patients and constructed two distinct classifiers using EEG frequency domain and non-linear features for binary classification of apnea severity and multiclass classification of apnea types. In both classification problems, three models i.e. Support Vector Machine (SVM), Linear Discriminant analysis (LDA) and Naive Bayes (NB) were evaluated and compared. Results showed that SVM model performed the best in both classification problems reaching accuracy higher than the baseline level. The SVM performance in the binary classification of apnea severity was acceptable (76% mean accuracy) however in the case of multiclass classification of apnea types, the SVM classifier did not reach acceptable performance for all apnea types (48% mean accuracy). Our findings illustrate that in addition to the detection of apnea episodes, EEG signals can be used in classification of apnea severity, which could lead to development of accurate diagnostic systems for automatic assessment and management of sleep disorders.