Comparison between Five Classifiers for Automatic Scoring of Human Sleep Recordings

The aim of this work is to compare the performances of 5 classifiers (linear and quadratic classifiers, k nearest neighbors, Parzen kernels and neural network) to score a set of 8 biological features extracted from EEG and EMG, in six classes corresponding to different sleep stages as to automatically elaborate an hypnogram and help the physician diagnosticate sleep disorders. The data base is composed of 17265 epochs of 20 s recorded from 4 patients. Each epoch has been classified by an expert into one of the six sleep stages. In order to evaluate the classifiers, learning and testing sets of fixed size are randomly drawn and are used to train and test the classifiers. After several trials, an estimation of the misclassification percentage and its variability is obtained (optimistically and pessimistically). Data transformations toward normal distribution are explored as an approach to deal with extreme values. It is shown that these transformations improve significantly the results of the classifiers based on data proximity.

[1]  Alfred L. Loomis,et al.  DISTRIBUTION OF DISTURBANCE-PATTERNS IN THE HUMAN ELECTROENCEPHALOGRAM, WITH SPECIAL REFERENCE TO SLEEP , 1938 .

[2]  Eamonn J. Keogh,et al.  An online algorithm for segmenting time series , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

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

[4]  G. Avanzolini,et al.  Classification of postoperative cardiac patients: comparative evaluation of four algorithms. , 1991, International journal of bio-medical computing.

[5]  T. Gasser,et al.  Transformations towards the normal distribution of broad band spectral parameters of the EEG. , 1982, Electroencephalography and clinical neurophysiology.

[6]  R. Pigeau,et al.  Distinctive effects of modafinil and d-amphetamine on the homeostatic and circadian modulation of the human waking EEG , 2003, Psychopharmacology.

[7]  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.

[8]  N. Kleitman,et al.  Regularly occurring periods of eye motility, and concomitant phenomena, during sleep. , 1953, Science.

[9]  W. Dement,et al.  Cyclic variations in EEG during sleep and their relation to eye movements, body motility, and dreaming. , 1957, Electroencephalography and clinical neurophysiology.

[10]  B. Efron.  Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation , 1983 .

[11]  Sylvie Charbonnier,et al.  On-line segmentation algorithm for continuously monitored data in intensive care units , 2004, IEEE Transactions on Biomedical Engineering.

[12]  Klaus-Robert Müller,et al.  Identification of nonstationary dynamics in physiological recordings , 2000, Biological Cybernetics.

[13]  Antoine Cornuéjols,et al.  Apprentissage artificiel - Concepts et algorithmes , 2003 .

[14]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

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

[16]  M. Hirshkowitz.  Standing on the shoulders of giants: the Standardized Sleep Manual after 30 years , 2000 .

[17]  J D Frost,et al.  An automatic sleep analyzer. , 1970, Electroencephalography and clinical neurophysiology.

[18]  A. Loomis,et al.  Cerebral states during sleep, as studied by human brain potentials , 1937 .

[19]  L. Lebart,et al.  Statistique exploratoire multidimensionnelle , 1995 .

[20]  S. Himanen,et al.  Limitations of Rechtschaffen and Kales. , 2000, Sleep medicine reviews.

[21]  W. Dement,et al.  The occurrence of low voltage, fast, electroencephalogram patterns during behavioral sleep in the cat. , 1958, Electroencephalography and clinical neurophysiology.

[22]  A Limoge,et al.  Comparison between conventional and neural network classifiers for rat sleep-wake stage discrimination. , 1997, Neuropsychobiology.

[23]  J Möcks,et al.  How to select epochs of the EEG at rest for quantitative analysis. , 1984, Electroencephalography and clinical neurophysiology.

[24]  Katharina Morik,et al.  The Representation Race - Preprocessing for Handling Time Phenomena , 2000, ECML.

[25]  J R Smith,et al.  EEG sleep stage scoring by an automatic hybrid system. , 1971, Electroencephalography and clinical neurophysiology.

[26]  C. Robert,et al.  Automated sleep staging systems in rats , 1999, Journal of Neuroscience Methods.

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

[28]  Jack R. Smith,et al.  Automatic Analysis of Sleep Electroencephalograms by Hybrid Computation , 1969, IEEE Trans. Syst. Sci. Cybern..