Abstract
A robust, automated pattern recognition system for polysomnography data targeted to the sleep-waking state and stage identification is presented. Five patterns were searched for: slow-delta and theta wave predominance in the background electro-encephalogram (EEG) activity; presence of sleep spindles in the EEG; presence of rapid eye movements in an electro-oculogram; and presence of muscle tone in an electromyogram. The performance of the automated system was measured indirectly by evaluating sleep staging, based on the experts' accepted methodology, to relate the detected patterns in infants over four months of post-term age. The set of sleep-waking classes included wakefulness, REM sleep and non-REM sleep stages I, II, and III–IV. Several noise and artifact rejection methods were implemented, including filters, fuzzy quality indices, windows of variable sizes and detectors of limb movements and wakefulness. Eleven polysomnographic recordings of healthy infants were studied. The ages of the subjects ranged from 6 to 13 months old. Six recordings counting 2665 epochs were included in the training set. Results on a test set (2369 epochs from five recordings) show an overall agreement of 87.7% (kappa 0.840) between the automated system and the human expert. These results show significant improvements compared with previous work.
Similar content being viewed by others
References
Anders, T., Emde, R., andParmelee, A. (Eds) (1971): ‘A manual of standardized terminology, techniques and criteria for scoring of states of sleep and wakefulness in newborn infants’ (UCLA Brain Information Service, NINDS, Neurological Information Network, Los Angeles, USA, 1971)
Bankman, I. N., Sigillito, V. G., Wise, R. A., andSmith, P. L. (1992): ‘Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks’,IEEE Trans. Biomed. Eng.,39, pp. 1305–1310
Besset, A. (1998): ‘L'analyse automatique du sommeil’, inBilliard, M. (Ed.): ‘Le sommeil normal et pathologique, 2nd edn’, (Masson, Paris, France, 1998), pp. 126–133
Collura, T. F., Jacobs, E. C., Braun, D. S., andBurgess, R. C. (1993): ‘EVIEW—A workstation-based viewer for intensive clinical electroencephalography’,IEEE Trans. Biomed. Eng.,40, pp. 736–744
Cook, R. J. (1998): ‘Kappa’, inArmitage, P., andColton, T. (Eds): ‘The encyclopedia of biostatistics’ (Wiley, New York, USA, 1998) pp. 2160–2166
Crowell, D., Brooks, L. J., Colton, T., Corwin, M. J., Hoppenbrouwers, T., Hunt, C. E., Kapuniai, L. E., Lister, G., Neuman, M. R., Peucker, M., Davidson Ward, S. L., Weese-Mayer, D. E., Willinger, M., andCollaborative Home Infant Monitoring Evaluation (CHIME) Steering Committee (1997): ‘Infant polysomnography: reliability’,Sleep,20, pp. 553–560
Curzi-Dascalova, L., andMirmiran, M. (1996): ‘Manual of methods of recording and analyzing sleep-wakefulness states in premature and full-term infants’ (INSERM Publ., Paris, France, 1996)
Estévez, P. A., Fernández, M. E., Held, C. M., Holzmann, C. A., Perez, C. A., andPérez, J. P. (2000): ‘Classification of sleep-waking states using modular neural networks’. IEEE International Conference on Systems, Man and Cybernetics, Nashville, Tennessee, USA, 2580–2585
Ferber, R., andKryger, M. (1995): ‘Principles and practice of sleep medicine in the child’ (Saunders, Philadelphia, USA, 1995)
Fleiss, J. (1981): ‘Statistical methods for rates and proportions, 2nd edn’ (John Wiley, New York, USA, 1981)
Goldman, L. R. (1992): ‘The kappa statistic — in reply’,JAMA,268, pp. 2513–2514
Guilleminault, C., andSouquet, M. (1979): ‘Sleep states and related pathology’ inKorobkin, R., andGuilleminault, C. (Eds): ‘Advances in perinatal neurology, Vol. 1’, (Spectrum, New York, USA, 1979)
Guilleminault, C. (1998): ‘Le sommeil normal de l'homme’, inBilliard, M. (Ed): ‘Le sommeil normal et pathologique, 2nd edn’ (Masson, Paris, France, 1998) pp. 3–11
Harper, R. M., Schechtman, V. L., andKluge, K. A. (1987): ‘Machine classification of infant sleep state using cardiorespiratory measures’,Electroenceph. Clin. Neurophysiol.,67, pp. 379–387
Holzmann, C. A., Perez, J. P., Held, C. M., San Martín, M., Pizarro, F., Pérez, J. P., Garrido, M., andPeirano, P. (1999): ‘Expert-system classification of sleep-waking states in infants’,Med. Biol. Eng. Comput.,37, pp. 466–476
Huupponen, E., Värri, A., Himanen, S. L., Hasan, J., Lehtokangas, M., andSaarinen, J. (2000): ‘Optimization of sigma amplitude threshold in sleep spindle detection’,J. Sleep Res.,9, pp. 327–334
Jankel, W. R., andNiedermeyer, E. (1985): ‘Sleep spindles’,J. Clin. Neurophysiol.,2, pp. 1–35
Jansen, B. H., andDawant, B. M. (1989): ‘Knowledge-based approach to sleep EEG analysis—A feasibility study’,IEEE Trans. Biomed. Eng.,36, pp. 510–518
Klösch, G., Kemp, B., Penzel, T., Schlögl, A., Rappelsberger, P., Trenker, E., Gruber, G., Zeitlhofer, J., Saletu, B., Herrmann, W. M., Himanen, S. L., Kunz, D., Barbanoj, M. J., Röschke, J., Värri, A., andDorffner, G. (2001): ‘The SIESTA project polygraphic and clinical database’IEEE Eng. Med. Biol. Mag.,20, pp. 51–57
Kubicki, St., Höller, L., Berg, I., Pastelak-Price, C., andDorow, R. (1989): ‘Sleep EEG evaluation: A comparison of results by visual scoring and automatic analysis with the Oxford sleep stager’,Sleep,12, pp. 140–149
Martin-baranera, M., Sancho, J. J., andSanz, F. (2000): ‘Controlling for chance agreement in the validation of medical expert systems with no gold standard: PNEUMON-IA and RENOIR revisited’,Comput. Biomed. Res.,33, pp. 380–397
Ohayon, M. M., Guilleminault, C., Zulley, J., Palombini, L., andRaab, H. (1999): ‘Validation of the sleep-EVAL system against clinical assessments of sleep disorders and polysomnographic data’,Sleep,22, pp. 925–930
Park, S., Principe, J. C., Smith, J. R., andReid, S. A. (1990): ‘TDAT — Time domain analysis tool for EEG analysis’,IEEE Trans. Biomed. Eng.,37, pp. 803–811
Park, H. J., Oh, J. S., Jeong, D. U., andPark, K. S. (2000): ‘Automated sleep stage scoring using hybrid rule- and case-based reasoning’,Comput. Biomed. Res.,33, pp. 330–349
Peirano, P., Curzi-Dascalova, L., andKorn, G. (1986): ‘Influence of sleep state and age on body motility in normal premature and full-term neonates’,Neuropediatrics,17, pp. 186–190
Peirano, P., Fagioli, I., Singh, B. B., andSalzarulo, P. (1989): ‘Effect of early human malnutrition on waking and sleep organization’,Early Hum. Dev.,20, pp. 67–76
Peirano, P., andCurzi-Dascalova, L. (1995): ‘Motor activity patterns modulation and sleep states in low-risk prematurely born infants reaching normal term: A comparison with full-term new-borns’,Neuropediatrics,26, pp. 8–13
Principe, J. C., Gala, S. K., andChang, T. G. (1989): ‘Sleep staging automaton based on the theory of evidence’,IEEE Trans. Biomed. Eng.,36, pp. 503–509
Proakis, J. G., andManolakis, D. G. (1996): ‘Digital signal processing: principles, algorithms and applications, 3rd edn’ (Prentice Hall, New Jersey, USA, 1996)
Rechtschaffen, A., andKales, A. (1968): ‘A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects’ (UCLA, Brain Research Institute/ Brain Information Service, Los Angeles, USA, 1968)
Roberts, S., andTarassenko, L. (1992): ‘Analysis of the sleep EEG using a multilayer network with spatial organization’,IEE Proc. F,139, pp. 420–425
Scher, M. S. (1997): ‘Computer classification of state in healthy preterm neonates’,Sleep,20, pp. 132–141
Shimada, T., Shina, T., andSaito, Y. (2000): ‘Detection of characteristic waves of sleep EEG by neural network analysis’,IEEE Trans. Biomed. Eng.,47, pp. 369–378
Smith, J. R. (1986): ‘Automated analysis of sleep EEG data’, inLopes De Silva, F. H., Storm van Leeuwen, W., andRémond, A. (Eds): ‘Handbook of electroencephalography and clinical neurophysiology, Vol. 2’ (Elsevier Publ., 1986) pp. 131–147
Tafti, M. (1998): ‘Analyse numèrique du sommeil’, inBilliard, M. (Ed.): ‘Le sommeil normal et pathologique, 2nd edn’ (Masson, Paris, France, 1998)
White, D. P., andGibb, T. J. (1998): ‘Evaluation of a computarized polysomnographic system’,Sleep,21, pp. 188–196
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Estévez, P.A., Held, C.M., Holzmann, C.A. et al. Polysomnographic pattern recognition for automated classification of sleep-waking states in infants. Med. Biol. Eng. Comput. 40, 105–113 (2002). https://doi.org/10.1007/BF02347703
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02347703