Automatic sleep stage classification using ear-EEG

Abstract

Sleep assessment is of great importance in the diagnosis and treatment of sleep disorders. In clinical practice this is typically performed based on polysomnography recordings and manual sleep staging by experts. This procedure has the disadvantages that the measurements are cumbersome, may have a negative influence on the sleep, and the clinical assessment is labor intensive. Addressing the latter, there has recently been encouraging progress in the field of automatic sleep staging [1]. Furthermore, a minimally obtrusive method for recording EEG from electrodes in the ear (ear-EEG) has recently been proposed [2]. The objective of this study was to investigate the feasibility of automatic sleep stage classification based on ear-EEG. This paper presents a preliminary study based on recordings from a total of 18 subjects. Sleep scoring was performed by a clinical expert based on frontal, central and occipital region EEG, as well as EOG and EMG. 5 subjects were excluded from the study because of alpha wave contamination. In one subject the standard polysomnography was supplemented by ear-EEG. A single EEG channel sleep stage classifier was implemented using the same features and the same classifier as proposed in [1]. The performance of the single channel sleep classifier based on the scalp recordings showed an 85.7 % agreement with the manual expert scoring through 10-fold inter-subject cross validation, while the performance of the ear-EEG recordings was based on a 10-fold intra-subject cross validation and showed an 82 % agreement with the manual scoring. These results suggest that automatic sleep stage classification based on ear-EEG recordings may provide similar performance as compared to single channel scalp EEG sleep stage classification. Thereby ear-EEG may be a feasible technology for future minimal intrusive sleep stage classification.