Download PDF
Methods Inf Med 1997; 36(04/05): 41-46
DOI: 10.1055/s-0038-1636853
Original Article
Schattauer GmbH

Causal Probabilistic Network and Power Spectral Estimation Used in Sleep Stage Classification

K. D. Nielsen
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
A. Kjaer
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
W. Jensen
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
T. Dyrby
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
L. Andreasen
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
J. Andersen
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
,
S. Andreassen
1   Department of Medical Informatics and Image Analysis, Aalborg University, Denmark
› Author Affiliations
Further Information

Publication History

Publication Date:
19 February 2018 (online)

    Permissions and Reprints

Abstract.

A new method for sleep-stage classification using a causal probabilistic network as automatic classifier has been implemented and validated. The system uses features from the primary sleep signals from the brain (EEG) and the eyes (AOG) as input. From the EEG, features are derived containing spectral information which is used to classify power in the classical spectral bands, sleep spindles and K-complexes. From AOG, information on rapid eye movements is derived. Features are extracted every 2 seconds. The CPN-based sleep classifier was implemented using the HUGIN system, an application tool to handle causal probabilistic networks. The results obtained using different training approaches show agreements ranging from 68.7 to 70.7% between the system and the two experts when a pooled agreement is computed over the six subjects. As a comparison, the interrater agreement between the two experts was found to be 71.4%, measured also over the six subjects.

Keywords:

Causal Probabilistic Network - Sleep - EEG-spectraIntroduction
 

  • REFERENCES

  • 1 Nielsen KD. Computer Assisted Sleep Analysis. (Ph.D thesis). Department of Medical Informatics, Aalborg University; 1993
    Google Scholar
  • 2 Rechtschaffen A, Kales A. A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. Brain Information Service/ Brain Research Institute, UCLA; Los Angeles: 1968
    Google Scholar
  • 3 Kemp B, Värri A, Rosa AC, Nielsen KD, Gade J. A simple format for exchange of digitized polygraphic recordings. Electroenc Clin Neurophysiol 1992; 82: 391-3.
    CrossrefPubMedGoogle Scholar
  • 4 Nielsen KD, Drewes AM, Svendsen L, Bjerregård K, Taagholt S. Ambulatory recording and power spectral analysis by autoregressive modelling of polygraphic sleep signals in patients suffering from chronic pain. Meth Inform Med 1994; 33: 76-9.
    PubMedGoogle Scholar
  • 5 Lacroix B. Optimal Bayesian recursive filter applied to on-line scoring of polygraphic sleep recordings. Universite Libre de Bruxelles, laboratoire d’automatique. MELECON ‘85, Volume 1: Bioengineering, IEEE 1985; 01: 5-8.
    PubMedGoogle Scholar
  • 6 Kemp B, Kamphuisen HAC. Model-Based Sleep Analysis. In: Sleep and Health Risk. Heidelberg: Springer-Verlag; 1991: 50-7.
    Google Scholar
  • 7 Andreassen S. Model-based biosignal interpretation. Meth Inform Med 1994; 33: 103-10.
    PubMedGoogle Scholar