A reliable probabilistic sleep stager based on a single EEG signal

OBJECTIVE We developed a probabilistic continuous sleep stager based on Hidden Markov models using only a single EEG signal. It offers the advantage of being objective by not relying on human scorers, having much finer temporal resolution (1s instead of 30s), and being based on solid probabilistic principles rather than a predefined set of rules (Rechtschaffen & Kales) METHODS AND MATERIAL Sixty-eight whole night sleep recordings from two different sleep labs are analysed using Gaussian observation Hidden Markov models. RESULTS Our unsupervised approach detects the cornerstones of human sleep (wakefulness, deep and REM sleep) with around 80% accuracy based on data from a single EEG channel. There are some difficulties in generalizing results across sleep labs. CONCLUSION Using data from a single electrode is sufficient for reliable continuous sleep staging. Sleep recordings from different sleep labs are not directly comparable. Training of separate models for the sleep labs is necessary.

[1]  Georg Dorffner,et al.  Improvements on continuous unsupervised sleep staging , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[2]  S. Ancoli-Israel,et al.  Characteristics of insomnia in the United States: results of the 1991 National Sleep Foundation Survey. I. , 1999, Sleep.

[3]  E. Reilly,et al.  Reliability of Rapid Clinical Staging of All Night Sleep EEG , 1985, Clinical EEG.

[4]  Georg Dorffner,et al.  Continuous Unsupervised Sleep Staging Based on a Single EEG Signal , 2002, ICANN.

[5]  A. Rechtschaffen.  A manual of standardized terminology, techniques and scoring system for sleep of human subjects , 1968 .

[6]  L. Tarassenko,et al.  New method of automated sleep quantification , 1992, Medical and Biological Engineering and Computing.

[7]  Irena Koprinska,et al.  Sleep classification in infants by decision tree-based neural networks , 1996, Artif. Intell. Medicine.

[8]  E. Wolpert.  A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[9]  Stephen J. Roberts,et al.  A Probabilistic Approach to High-Resolution Sleep Analysis , 2001, ICANN.

[10]  William D. Penny,et al.  Gaussian Observation Hidden Markov models for EEG analysis , 1998 .

[11]  A. Varri,et al.  The SIESTA project polygraphic and clinical database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[12]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[13]  S. Kubicki,et al.  Sleep EEG evaluation: a comparison of results obtained by visual scoring and automatic analysis with the Oxford sleep stager. , 1989, Sleep.

[14]  B. Kemp,et al.  A proposal for computer‐based sleep/wake analysis , 1993, Journal of sleep research.

[15]  J Röschke,et al.  The automatic recognition of REM sleep: a challenge and some answers. , 2002, Methods and findings in experimental and clinical pharmacology.

[16]  E. Rodin,et al.  Epilepsy, sleep, and sleep deprivation , 1991 .

[17]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[18]  A. Schlögl,et al.  Interrater reliability between scorers from eight European sleep laboratories in subjects with different sleep disorders , 2004, Journal of sleep research.

[19]  Georg Dorffner,et al.  An automatic, continuous and probabilistic sleep stager based on a hidden markov model , 2002, Appl. Artif. Intell..

[20]  T Penzel,et al.  Integrated sleep analysis, with emphasis on automatic methods. , 1991, Epilepsy research. Supplement.