Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: A feasibility study

An artificial neural network (ANN) based on the Multi-Layer Perceptron (MLP) architecture is used for detecting sleep spindles in band-pass filtered electroencephalograms (EEG), without feature extraction. Following optimum classification schemes, the sensitivity of the network ranges from 79.2% to 87.5%, while the false positive rate ranges from 3.8% to 15.5%. Furthermore, due to the operation of the ANN on time-domain EEG data, there is agreement with visual assessment concerning temporal resolution. Specifically, the total inter-spindle interval duration and the total duration of spindles are calculated with 99% and 92% accuracy, respectively. Therefore, the present method may be suitable for investigations of the dynamics among successive inter-spindle intervals, which could provide information on the role of spindles in the sleep process, and for studies of pharmacological effects on sleep structure, as revealed by the modification of total spindle duration.

[1]  K. Blinowska,et al.  High resolution study of sleep spindles , 1999, Clinical Neurophysiology.

[2]  M Hirshkowitz,et al.  Sleep spindles: pharmacological effects in humans. , 1982, Sleep.

[3]  Y. -L. Hao,et al.  Improved procedure of complex demodulation and an application to frequency analysis of sleep spindles in EEG , 1992, Medical and Biological Engineering and Computing.

[4]  G. Pfurtscheller.  Handbook of electroencephalography and clinical neurophysiology , 1978 .

[5]  A. Rechtschaffen,et al.  A manual of standardized terminology, technique and scoring system for sleep stages of human subjects , 1968 .

[6]  T. Penzel,et al.  Computer based sleep recording and analysis. , 2000, Sleep medicine reviews.

[7]  M. Ferrara,et al.  Sleep spindles: an overview. , 2003, Sleep medicine reviews.

[8]  Eduardo D. Sontag,et al.  Feedback Stabilization Using Two-Hidden-Layer Nets , 1991, 1991 American Control Conference.

[9]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[10]  H. Schulz,et al.  Topographical analysis of sleep spindle activity. , 1992, Neuropsychobiology.

[11]  M. Lehtokangas,et al.  Optimization of sigma amplitude threshold in sleep spindle detection , 2000, Journal of sleep research.

[12]  P Y Ktonas,et al.  Sleep spindle incidence dynamics: a pilot study based on a Markovian analysis. , 2000, Sleep.

[13]  Tsuyoshi Shiina,et al.  Detection of characteristic waves of sleep EEG by neural network analysis , 2000, IEEE Transactions on Biomedical Engineering.

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

[15]  W. Herrmann,et al.  The future of computer-assisted investigation of the polysomnogram: sleep microstructure. , 1996, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[16]  P. Anderer,et al.  Topographic distribution of sleep spindles in young healthy subjects , 1997, Journal of sleep research.

[17]  V de Maertelaer,et al.  Sleep spindle activity changes in patients with affective disorders. , 1987, Sleep.

[18]  A Kumar,et al.  Human and automatic validation of a phase-locked loop spindle detection system. , 1980, Electroencephalography and clinical neurophysiology.

[19]  K. Watanabe,et al.  Spindle evolution in normal and mentally retarded children: a review. , 1982, Sleep.

[20]  Ktonas Py.  Computer-based recognition of EEG patterns. , 1996 .

[21]  H. Schulz,et al.  Pattern recognition by matched filtering: an analysis of sleep spindle and K-complex density under the influence of lormetazepam and zopiclone. , 1992, Neuropsychobiology.

[22]  Jean Gotman,et al.  Digital Tools in Polysomnography , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[23]  R Baumgart-Schmitt,et al.  On the use of neural network techniques to analyse sleep EEG data. First communication: application of evolutionary and genetic algorithms to reduce the feature space and to develop classification rules. , 1997, Neuropsychobiology.

[24]  Mary A. Carskadon,et al.  Chapter 116 – Monitoring and Staging Human Sleep , 2005 .

[25]  Günther J. L. Gerhardt,et al.  Characteristics of human EEG sleep spindles assessed by Gabor transform , 2003 .

[26]  Thomas J. Morrow,et al.  A microprocessor device for the real-time detection of synchronized alpha and spindle activity in the EEG , 1986, Brain Research Bulletin.

[27]  R. Godbout,et al.  Sleep architecture and its clinical correlates in first episode and neuroleptic-naive patients with schizophrenia , 2003, Schizophrenia Research.

[28]  M. Kryger,et al.  Principles and Practice of Sleep Medicine , 1989 .

[29]  Derk-Jan Dijk,et al.  EEG slow waves and sleep spindles: windows on the sleeping brain , 1995, Behavioural Brain Research.

[30]  M. Lehtokangas,et al.  Autoassociative MLP in Sleep Spindle Detection , 2004, Journal of Medical Systems.

[31]  A. Muzet,et al.  Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients. , 1996, Sleep.