Classification of sleep apnea types using EEG synchronization criteria

Abstract

In this study, to obtain high quality signal features in discriminating the Central Sleep Apnea (CSA) and Obstructive Sleep Apnea (OSA) from controls, both linear and nonlinear EEG synchronization methods so called Coherence Function (CF) and Mutual Information (MI) are performed. For this purpose, sleep EEG series data collected from patients and healthy volunteers are classified by using a well known and widely used Feed-Forward Neural Network (FFNN) with respect to synchronic activities between C3 and C4 recordings. The results show that the degree of central EEG synchronization during night sleep is closely linked to sleep disorders like CSA and OSA. The MI and CF provide information in meaningful collaboration to support the clinical findings. These three groups were defined with a medical expert and can be very successfully classified by using the FFNN having two hidden layers with the average area of CF curves ranged form 0 Hz to 10 Hz and the average MI values are assigned as two features. This study is a preliminary study for classifying types of sleep apnea.