Download PDF
Klinische Neurophysiologie 2015; 46(03): 128-135
DOI: 10.1055/s-0035-1559649
Originalia
© Georg Thieme Verlag KG Stuttgart · New York

Möglichkeiten der automatischen Schlafstadienklassifikation und ihre Grenzen

Automatic Sleep Stage Classification: Potential and Limitations
T. Penzel
1   CCM-CC11, Interdisziplinäres Schlafmedizinisches Zentrum, Charité-Universitätsmedizin Berlin
,
I. Fietze
1   CCM-CC11, Interdisziplinäres Schlafmedizinisches Zentrum, Charité-Universitätsmedizin Berlin
,
C. Veauthier
1   CCM-CC11, Interdisziplinäres Schlafmedizinisches Zentrum, Charité-Universitätsmedizin Berlin
› Author Affiliations
Further Information

Publication History

Publication Date:
13 August 2015 (online)

Also available at
    Permissions and Reprints

Zusammenfassung

Die Referenzuntersuchung im Schlaflabor ist die kardiorespiratorische Polysomnografie. Diese ist bezogen auf Signalkonfiguration, Aufnahmetechnik und Visualisierung gut standardisiert. Die Untersuchung erfordert einen hohen Zeitaufwand bei Aufzeichnung und visueller Auswertung. Eine computergestützte Auswertung kann den Zeitaufwand reduzieren und die Reliabilität der Auswertung verbessern. Eine computergestützte Auswertung ist bislang nicht akzeptiert, da diagnoserelevante Fehlklassifikationen befürchtet werden.

Die Prinzipien einer automatischen Schlafauswertung sind bekannt. Sie kann das Auftreten von Mustern quantitativ zusammenfassen und erleichtert Vergleiche, die aufgrund des Aufwands einer visuellen Analyse nicht zugänglich sind: Statistik, Zählen von Mustern, Arousal und Mikrostruktur des Schlafes. Klassische Frequenzanalysen und neue Auswertemethoden, auch unter Einsatz nichtlinearer Analysen, sind sehr hilfreich für die Beantwortung von Forschungsfragen und zur Charakterisierung von Schlaf EEG Abnormitäten.

Die computergestützte Auswertung von schlafbezogenen Atmungsstörungen und Bewegungsstörungen ist zuverlässig und wird auch eingesetzt, sofern man sich auf eine Sensortechnik geeinigt hat und die benutzten Amplituden Definitionen angibt.

Um mit den herkömmlichen Kennwerten der schlafmedizinischen Befunde (Schlafzeiten, Prozente Schlafstadien, Schlafeffizienz, Latenzen) kompatibel zu bleiben, ist eine visuelle Bearbeitung oder Überarbeitung der automatisch berechneten Schlafstadien weiterhin erforderlich.

Abstract

The reference method for sleep recording in a sleep medicine center is cardiorespiratory polysomnography. This method is well standardized in terms of signal choice, recording technology and visual presentation. A sleep study requires much time for recording and subsequent visual scoring. A computer-based scoring can reduce time and effort and improve reliability of the result. A computer-based scoring is not yet accepted because of potential misclassifications, which may lead to false diagnoses.

The principles of automatic sleep scoring are well known and documented. Automatic sleep scoring can summarize patterns quantitatively and enables a comparison of result, which is not possible by visual scoring alone: statistics, counting of patterns, arousal scoring, and sleep microstructure analysis. Classical methods such as frequency analysis and new methods, including nonlinear signal processing, can be of great help in answering research questions and for characterizing sleep EEG abnormalities.

The computer-supported scoring of sleep-related breathing disorders and sleep-related movement disorders is reliable and is widely used in clinical practice. It is reliable if applicants agree on the sensor technology applied and specify the amplitude criteria chosen.

In order to remain compatible with values from previous sleep study reports (sleep duration times, percent spent in each sleep stage, sleep efficiency, latencies), a visual scoring or a re-scoring of automated sleep analysis is indispensable.

Schlüsselwörter

Polysomnografie - Computer-gestützte Schlaf-Aufzeichnung - Cyclic alternating pattern - Schlaf-EEG - EOG - EMG

Key words

polysomnography - computer-assisted sleep recording - cyclic alternating pattern - sleep EEG - EOG - EMG
 

  • Literatur

  • 1 Schlack R, Hapke U, Maske U et al. Häufigkeit und Verteilung von Schlafproblemen und Insomnie in der deutschen Erwachsenenbevölkerung. Ergebnisse der Studie zur Gesundheit Erwachsener in Deutschland (DEGS1) Bundesgesundheitsblatt 2013; 56: 740-748
    PubMedGoogle Scholar
  • 2 Mayer G, Fietze I, Fischer J et al. S3-Leitlinie Nicht erholsamer Schlaf/Schlafstörungen. Somnologie 2009; 13: 4-160
    CrossrefPubMedGoogle Scholar
  • 3 Penzel T, Fietze I. Aktueller Stand der Polysomnografie. Klin Neurophysiol 2007; 38: 122-127
    Article in Thieme ConnectPubMedGoogle Scholar
  • 4 Rechtschaffen A, Kales A. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. NIH Publication No. 204 Washington DC: US Government Printing Office; 1968
    Google Scholar
  • 5 Iber C, Ancoli-Israel S, Chesson AL et al. The AASM manual for the scoring of sleep and associated events: rules, terminology, and technical specifications. 1st (ed.). Westchester, IL: American Academy of Sleep Medicine; 2007
    Google Scholar
  • 6 Rosenberg RS, Van Hout S. The American Academy of Sleep Medicine inter-scorer reliability program: sleep stage scoring. J Clin Sleep Med 2013; 9: 81-87
    PubMedGoogle Scholar
  • 7 Silber MH, Ancoli-Israel S, Bonnet MH et al. The visual scoring of sleep in adults. J Clin Sleep Med 2007; 3: 121-131
    PubMedGoogle Scholar
  • 8 Berry RB, Brooks R, Gamaldo CE et al. for the American Academy of Sleep Medicine . The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, Version 2.0. www.aasmnet.org Darien, Illinois: American Academy of Sleep Medicine; 2012
    Google Scholar
  • 9 Anderer P, Moreau A, Woertz M et al. Computer-Assisted Sleep Classification according to the Standard of the American Academy of Sleep Medicine: Validation Study of the AASM Version of the Somnolyzer 24×7. Neuropsychobiology 2010; 62: 250-264
    CrossrefPubMedGoogle Scholar
  • 10 Rappelsberger P, Trenker E, Rothmann C et al. Das Projekt SIESTA. Klin Neurophysiol 2001; 32: 76-88
    Article in Thieme ConnectPubMedGoogle Scholar
  • 11 Penzel T, Conradt R. Automatic Sleep Scoring. Sleep Medicine Reviews 2000; 4: 131-148
    CrossrefPubMedGoogle Scholar
  • 12 American Academy of Sleep Medicine . International Classification of Sleep Disorders. 3rd (ed.). Diagnostic and Coding Manual Darien, Ill: American Academy of Sleep Medicine; 2014
    Google Scholar
  • 13 Penzel T, Zhang X, Fietze I. Inter-scorer reliability between sleep centers can teach us what to improve in the scoring rules. J Clin Sleep Med 2013; 9: 89-91
    PubMedGoogle Scholar
  • 14 Koch H, Christensen JA, Frandsen R et al. Automatic sleep classification using a data-driven topic model reveals latent sleep states. J Neurosci Methods 2014; 235: 130-137
    CrossrefPubMedGoogle Scholar
  • 15 Danker-Hopfe H, Anderer P, Zeitlhofer J et al. Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard. J Sleep Res 2009; 18: 74-84
    CrossrefPubMedGoogle Scholar
  • 16 Stege G, Vos PJ, Dekhuijzen PN et al. Manual vs. automated analysis of polysomnographic recordings in patients with chronic obstructive pulmonary disease. Sleep Breath 2013; 17: 533-539
    CrossrefPubMedGoogle Scholar
  • 17 Punjabi NM, Shifa N, Dorffner G et al. Computer-Assisted Automated Scoring of Polysomnograms Using the Somnolyzer System. Sleep 2015; pii: sp-00224-14 (published online before press)
    PubMedGoogle Scholar
  • 18 Svetnik V, Ma J, Soper KA et al. Evaluation of automated and semi-automated scoring of polysomnographic recordings from a clinical trial using zolpidem in the treatment of insomnia. Sleep 2007; 30: 1562-1574
    PubMedGoogle Scholar
  • 19 Parrino L, Halasz P, Tassinari CA et al. epilepsy and motor events during sleep: the unifying role of arousal. Sleep Med Rev 2006; 10: 267-285
    CrossrefPubMedGoogle Scholar
  • 20 Terzano MG, Parrino L, Sherieri A et al. Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleep. Sleep Med 2001; 2: 537-553
    CrossrefPubMedGoogle Scholar
  • 21 Parrino L, Boselli M, Spaggiari MC et al. Cyclic alternating pattern (CAP) in normal sleep: polysomnographic parameters in different age groups. Electroencephalogr Clin Neurophysiol 1998; 107: 439-450
    CrossrefPubMedGoogle Scholar
  • 22 Bricolo A, Faccioli F, Turazzi S. EEG in post-traumatic coma. Diagnostic and prognostic value. Rev Electroencephalogr Neurophysiol Clin 1979; 9: 116-130
    CrossrefPubMedGoogle Scholar
  • 23 Parrino L, Boselli M, Buccino GP et al. The cyclic alternating pattern plays a gate-control on periodic limb movements during non-rapid eye movement sleep. J Clin Neurophysiol 1996; 13: 314-323
    CrossrefPubMedGoogle Scholar
  • 24 Hening W. The clinical neurophysiology of the restless legs syndrome and periodic limb movements. Part I: diagnosis, assessment, and characterization. Clin Neurophysiol 2004; 115: 1965-1974
    CrossrefPubMedGoogle Scholar
  • 25 Zucconi M, Ferini-Strambi L. NREM parasomnias: arousal disorders and differentiation from nocturnal frontal lobe epilepsy. Clin Neurophysiol 2000; 111 (Suppl. 02) 129-135
    CrossrefPubMedGoogle Scholar
  • 26 Terzano MG, Parrino L, Spaggiari MC et al. CAP variables and arousals as sleep electroencephalogram markers for primary insomnia. Clin Neurophysiol 2003; 114: 1715-1723
    CrossrefPubMedGoogle Scholar
  • 27 Ferri R, Bruni O, Miano S et al. Inter-rater reliability of sleep cyclic alternating pattern (CAP) scoring and validation of a new computer-assisted CAP scoring method. Clin Neurophysiol 2005; 116: 696-707
    CrossrefPubMedGoogle Scholar
  • 28 Koupparis AM, Kokkinos V, Kostopoulos GK. Semi-automatic sleep EEG scoring based on the hypnospectrogram. J Neurosci Methods 2014; 221: 189-195
    CrossrefPubMedGoogle Scholar
  • 29 Heinzer R, Vat S, Marques-Vidal P et al. Prevalence of sleep-disordered breathing in the general population: the HypnoLaus study. Lancet Respir Med 2015; 3: 310-318
    CrossrefPubMedGoogle Scholar
  • 30 Penzel T, Garcia C, Glos M et al. Herzfrequenz und EKG in der Polysomnographie. Somnologie 2015; 19 im Druck
    PubMedGoogle Scholar
  • 31 Task force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology . Heart rate variability. Standards of measurement, physiological interpretation, and clinical use. Circulation 1996; 93: 1043-1065
    CrossrefPubMedGoogle Scholar