Automatic analysis of single-channel sleep EEG:: Validation in healthy individuals

被引:210
作者
Berthomier, Christian
Drouot, Xavier
Herman-Stoieca, Maria
Berthomier, Pierre
Prado, Jacques
Bokar-Thire, Djibril
Benoit, Odile
Mattout, Jeremie
d'Ortho, Marie-Pia
机构
[1] PHYSIP SA, F-75013 Paris, France
[2] Grp Hosp Henri Mondor Albert Chenevier, AP HP, Serv Physiol Explorat Fonctionnelles, Creteil, France
[3] Hop Henri Mondor, INSERM, Unite U841, F-94010 Creteil, France
[4] Univ Paris 12, Fac Med, Inst Mondor Med Mol IFR 10, Creteil, France
[5] Ecole Natl Super Telecommun Bretagne, Dept Traitement Signal & Images, Paris, France
[6] INSERM, Unite Dynam Cerebrale & Cognit, F-69008 Lyon, France
关键词
automatic sleep scoring; single channel; EEG; clinical validation; healthy subjects;
D O I
10.1093/sleep/30.11.1587
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
Study Objective: To assess the performance of automatic sleep scoring software (ASEEGA) based on a single EEG channel comparatively with manual scoring (2 experts) of conventional full polysomnograms. Design: Polysomnograms from 15 healthy individuals were scored by 2 independent experts using conventional R&K rules. The results were compared to those of ASEEGA scoring on an epoch-by-epoch basis. Setting: Sleep laboratory in the physiology department of a teaching hospital. Participants: Fifteen healthy volunteers. Measurements and Results: The epoch-by-epoch comparison was based on classifying into 2 states (wake/sleep), 3 states (wake/REM/NREM), 4 states (wake/REM/stages 1-2/SWS), or 5 states (wake/REM/stage 1/stage 2/SWS). The obtained overall agreements, as quantified by the kappa coefficient, were 0.82, 0.81, 0.75, and 0.72, respectively. Furthermore, obtained agreements between ASEEGA and the expert consensual scoring were 96.0%, 92.1%, 84.9%, and 82.9%, respectively. Finally, when classifying into 5 states, the sensitivity and positive predictive value of ASEEGA regarding wakefulness were 82.5% and 89.7%, respectively. Similarly, sensitivity and positive predictive value regarding REM state were 83.0% and 89.1%. Conclusions: Our results establish the face validity and convergent validity of ASEEGA for single-channel sleep analysis in healthy individuals. ASEEGA appears as a good candidate for diagnostic aid and automatic ambulant scoring.
引用
收藏
页码:1587 / 1595
页数:9
相关论文
共 40 条
[1]   ALL-NIGHT DYNAMICS OF THE HUMAN SLEEP EEG [J].
AESCHBACH, D ;
BORBELY, AA .
JOURNAL OF SLEEP RESEARCH, 1993, 2 (02) :70-81
[2]   Computer-assisted sleep staging [J].
Agarwal, R ;
Gotman, J .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2001, 48 (12) :1412-1423
[3]   An E-health solution for automatic sleep classification according to Rechtschaffen and Kales:: Validation study of the Somnolyzer 24 x 7 utilizing the Siesta database [J].
Anderer, P ;
Gruber, G ;
Parapatics, S ;
Woertz, M ;
Miazhynskaia, T ;
Klösch, G ;
Saletu, B ;
Zeitlhofer, J ;
Barbanoj, MJ ;
Danker-Hopfe, H ;
Himanen, SL ;
Kemp, B ;
Penzel, T ;
Grözinger, M ;
Kunz, D ;
Rappelsberger, P ;
Schlögl, A ;
Dorffner, G .
NEUROPSYCHOBIOLOGY, 2005, 51 (03) :115-133
[4]  
[Anonymous], PRACTICAL STAT MED R
[5]   Slow (0.7-2 Hz) and fast (2-4 Hz) delta components are differently correlated to theta, alpha and beta frequency bands during NREM sleep [J].
Benoit, O ;
Daurat, A ;
Prado, J .
CLINICAL NEUROPHYSIOLOGY, 2000, 111 (12) :2103-2106
[6]   EFFECT OF A SINGLE-DOSE (10 MG) OF ZOLPIDEM ON VISUAL-ANALYSIS AND SPECTRAL-ANALYSIS OF SLEEP IN YOUNG POOR SLEEPERS [J].
BENOIT, O ;
BOUARD, G ;
PAYAN, C ;
BORDERIES, P ;
PRADO, J .
PSYCHOPHARMACOLOGY, 1994, 116 (03) :297-303
[7]  
Berthomier C, 1999, Biomed Sci Instrum, V35, P241
[8]  
BERTHOMIER C, 2005, SLEEP MED S2, V6, pS194
[9]   STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT [J].
BLAND, JM ;
ALTMAN, DG .
LANCET, 1986, 1 (8476) :307-310
[10]  
BOUARD G, 1986, TRAITEMENT SIGNAL EL, P531