Performance of the frequency domain indices with respect to sleep staging

Terry B J Kuo, C. Y. Chen, Ya Chuan Hsu, Cheryl C H Yang

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)


Objective: To compare computerized staging using spectral analyses of various electrophysiological signals with manual sleep staging. Methods: Sleep recordings from 21 normal subjects were scored by an experienced rater and by a dichotomous algorithm. The performance of the spectral indices was assessed by the largest kappa value (LKV). Results: Theta/beta power ratio of the electroencephalogram, high frequency power (8-58. Hz) of the electromyogram (PEMG), mean R-R interval, and total power (0-16. Hz) of the body acceleration (PACCE) had high (>0.5) LKVs when differentiating between waking and sleep. To differentiate sleep with (stage 2 and slow wave sleep) and without (rapid eye movement and stage 1 sleep) spindles, sigma/beta power ratio had high LKVs. PEMG had a medium (>0.25) LKV to separate rapid eye movement from stage 1 sleep whereas delta/beta power ratio had a high LKV to separate stage 2 and slow wave sleep. Conclusion: The frequency components of electroencephalogram perform well in identifying sleep, sleep with spindles, and slow wave sleep. Electromyogram, heart rate, and body acceleration offer high agreement only when differentiating between wakefulness and sleep. Significance: The human-machine agreement is acceptable with spectral parameters, but heart rate and body acceleration still cannot substitute for electroencephalogram.

Original languageEnglish
Pages (from-to)1338-1345
Number of pages8
JournalClinical Neurophysiology
Issue number7
Publication statusPublished - Jul 2012
Externally publishedYes


  • Acceleration
  • Computer scoring
  • Frequency domain analysis
  • Heart rate variability
  • Sleep staging

ASJC Scopus subject areas

  • Clinical Neurology
  • Neurology
  • Physiology (medical)
  • Sensory Systems


Dive into the research topics of 'Performance of the frequency domain indices with respect to sleep staging'. Together they form a unique fingerprint.

Cite this