Periodicity analysis of sleep EEG in the second and minute ranges--example of application in different alpha activities in sleep

Abstract

To investigate the temporal organization of EEG sleep activity in the second and minute ranges we developed a method which, based on Fourier transformation, allows the presentation of periodic oscillations of spectral power and coherence. The application of this method is demonstrated in 3 subjects with different types of alpha activity during sleep: (a) alpha-sleep pattern (a physiological variant of NREM sleep activity); (b) abnormally increased arousal alpha activity. The results show that differences in the temporal organization of these alpha activities can be determined with the following parameters: period length, duration of sequences with periodic activity, number and rate of these sequences, and proportion of periodicities generated simultaneously in the left and right hemispheres. The physiologically modulated periodicities of the alpha-sleep pattern are contrary to a stereotyped 40-60 sec periodicity of abnormal arousal alpha activity. Such abnormal periodicity corresponds to periodicities occurring in association with other sleep disturbances, such as sleep apnea or periodic movements in sleep. Periodicity analysis gives additional criteria for a more refined evaluation of normal as well as abnormal sleep structure.