Nonlinear dynamics measures for automated EEG-based sleep stage detection

U. Rajendra Acharya, Shreya Bhat, Oliver Faust, Hojjat Adeli, Eric Chern Pin Chua, Wei Jie Eugene Lim, Joel En Wei Koh

Research output: Contribution to journalReview article

35 Citations (Scopus)

Abstract

Background: The brain's continuous neural activity during sleep can be monitored by electroencephalogram (EEG) signals. The EEG wave pattern and frequency vary during five stages of sleep. These subtle variations in sleep EEG signals cannot be easily detected through visual inspection. Summary: A range of time, frequency, time-frequency and nonlinear analysis methods can be applied to understand the complex physiological signals and their chaotic behavior. This paper presents a comprehensive comparative review and analysis of 29 nonlinear dynamics measures for EEG-based sleep stage detection. Key Messages: 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.

Original languageEnglish
Pages (from-to)268-287
Number of pages20
JournalEuropean Neurology
Volume74
Issue number5-6
DOIs
Publication statusPublished - 01-12-2015
Externally publishedYes

Fingerprint

Nonlinear Dynamics
Sleep Stages
Electroencephalography
Sleep
Drug Monitoring
Brain

All Science Journal Classification (ASJC) codes

  • Neurology
  • Clinical Neurology

Cite this

Acharya, U. R., Bhat, S., Faust, O., Adeli, H., Chua, E. C. P., Lim, W. J. E., & Koh, J. E. W. (2015). Nonlinear dynamics measures for automated EEG-based sleep stage detection. European Neurology, 74(5-6), 268-287. https://doi.org/10.1159/000441975
Acharya, U. Rajendra ; Bhat, Shreya ; Faust, Oliver ; Adeli, Hojjat ; Chua, Eric Chern Pin ; Lim, Wei Jie Eugene ; Koh, Joel En Wei. / Nonlinear dynamics measures for automated EEG-based sleep stage detection. In: European Neurology. 2015 ; Vol. 74, No. 5-6. pp. 268-287.
@article{b92006088532427da5bd97657ba273cf,
title = "Nonlinear dynamics measures for automated EEG-based sleep stage detection",
abstract = "Background: The brain's continuous neural activity during sleep can be monitored by electroencephalogram (EEG) signals. The EEG wave pattern and frequency vary during five stages of sleep. These subtle variations in sleep EEG signals cannot be easily detected through visual inspection. Summary: A range of time, frequency, time-frequency and nonlinear analysis methods can be applied to understand the complex physiological signals and their chaotic behavior. This paper presents a comprehensive comparative review and analysis of 29 nonlinear dynamics measures for EEG-based sleep stage detection. Key Messages: 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.",
author = "Acharya, {U. Rajendra} and Shreya Bhat and Oliver Faust and Hojjat Adeli and Chua, {Eric Chern Pin} and Lim, {Wei Jie Eugene} and Koh, {Joel En Wei}",
year = "2015",
month = "12",
day = "1",
doi = "10.1159/000441975",
language = "English",
volume = "74",
pages = "268--287",
journal = "European Neurology",
issn = "0014-3022",
publisher = "S. Karger AG",
number = "5-6",

}

Acharya, UR, Bhat, S, Faust, O, Adeli, H, Chua, ECP, Lim, WJE & Koh, JEW 2015, 'Nonlinear dynamics measures for automated EEG-based sleep stage detection', European Neurology, vol. 74, no. 5-6, pp. 268-287. https://doi.org/10.1159/000441975

Nonlinear dynamics measures for automated EEG-based sleep stage detection. / Acharya, U. Rajendra; Bhat, Shreya; Faust, Oliver; Adeli, Hojjat; Chua, Eric Chern Pin; Lim, Wei Jie Eugene; Koh, Joel En Wei.

In: European Neurology, Vol. 74, No. 5-6, 01.12.2015, p. 268-287.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Nonlinear dynamics measures for automated EEG-based sleep stage detection

AU - Acharya, U. Rajendra

AU - Bhat, Shreya

AU - Faust, Oliver

AU - Adeli, Hojjat

AU - Chua, Eric Chern Pin

AU - Lim, Wei Jie Eugene

AU - Koh, Joel En Wei

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Background: The brain's continuous neural activity during sleep can be monitored by electroencephalogram (EEG) signals. The EEG wave pattern and frequency vary during five stages of sleep. These subtle variations in sleep EEG signals cannot be easily detected through visual inspection. Summary: A range of time, frequency, time-frequency and nonlinear analysis methods can be applied to understand the complex physiological signals and their chaotic behavior. This paper presents a comprehensive comparative review and analysis of 29 nonlinear dynamics measures for EEG-based sleep stage detection. Key Messages: 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.

AB - Background: The brain's continuous neural activity during sleep can be monitored by electroencephalogram (EEG) signals. The EEG wave pattern and frequency vary during five stages of sleep. These subtle variations in sleep EEG signals cannot be easily detected through visual inspection. Summary: A range of time, frequency, time-frequency and nonlinear analysis methods can be applied to understand the complex physiological signals and their chaotic behavior. This paper presents a comprehensive comparative review and analysis of 29 nonlinear dynamics measures for EEG-based sleep stage detection. Key Messages: 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.

UR - http://www.scopus.com/inward/record.url?scp=84949563152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949563152&partnerID=8YFLogxK

U2 - 10.1159/000441975

DO - 10.1159/000441975

M3 - Review article

C2 - 26650683

AN - SCOPUS:84949563152

VL - 74

SP - 268

EP - 287

JO - European Neurology

JF - European Neurology

SN - 0014-3022

IS - 5-6

ER -

Acharya UR, Bhat S, Faust O, Adeli H, Chua ECP, Lim WJE et al. Nonlinear dynamics measures for automated EEG-based sleep stage detection. European Neurology. 2015 Dec 1;74(5-6):268-287. https://doi.org/10.1159/000441975