Can nonlinear dynamics measures applied to EEG data accurately discriminate between different sleep stages?
Nonlinear dynamics measures, particularly the third order cumulant of higher order spectra, can effectively discriminate between sleep stages using EEG data, offering potential utility for sleep disorder diagnosis and monitoring.
The characteristic ranges of these features are reported for the five different sleep stages. All nonlinear measures produce clinically significant results, that is, they can discriminate the individual sleep stages. Feature ranking based on the statistical F-value, however, shows that the third order cumulant of higher order spectra yields the most discriminative result. The distinct value ranges for each sleep stage and the discriminative power of the features can be used for sleep disorder diagnosis, treatment monitoring, and drug efficacy assessment.
Acharya et al. (Thu,) studied this question.