Automatic analysis of single-channel sleep EEG in a large spectrum of sleep disorders

Laure Peter-Derex, Christian Berthomier,Jacques Taillard, Pierre Berthomier, Romain Bouet, Jérémie Mattout, Marie Brandewinder, Hélène Bastuji
Journal of Clinical Sleep Medicine. 2020-10-22; :
DOI: 10.5664/jcsm.8864

Lire sur PubMed

Peter-Derex L(1)(2)(3), Berthomier C(4), Taillard J(5), Berthomier P(4), Bouet R(2), Mattout J(2), Brandewinder M(4), Bastuji H(1)(2)(6).

Author information:
(1)Center for Sleep Medicine and Respiratory Diseases, Croix-Rousse Hospital, Lyon, France.
(2)Lyon Neuroscience Research Center, CNRS 5292 INSERM U1028, Lyon, France.
(3)Lyon 1 University, Lyon, France.
(4)Physip, Paris, France.
(5)CNRS, Bordeaux University, USR 3413 SANPSY Sleep, Addiction and NeuroPSYchiatry, Bordeaux, France.
(6)Functional Neurology and Epilepsy Unit, Neurological Hospital, Hospices Civils de Lyon, Bron, France.

STUDY OBJECTIVES: To assess the performance of the single channel automatic sleep
stage scoring (AS) software ASEEGA in adult patients suffering from various sleep
METHODS: Sleep recordings of 95 patients (38 women, 40.5±13.7 years) were
included: insomnia (N=23), idiopathic hypersomnia (N=24), narcolepsy (N=24) and
obstructive sleep apnea (OSA) (N=24). Visual staging (VS) was performed by two
experts (VS1 and VS2) according to the AASM rules. AS was based on the analysis
of a single EEG channel (CzPz), without any information from EOG nor EMG. The
epoch-by-epoch agreement (concordance and Conger’s kappa coefficient) was
compared pairwise (VS1-VS2, AS-VS1, AS-VS2) and between AS and consensual VS.
Sleep parameters were also compared.
RESULTS: The pairwise agreements were, between AS and VS1: 78.6% (kappa=0.70), AS
and VS2: 75.0% (0.65), VS1 and VS2: 79.5% (0.72). Agreement between AS and
consensual VS was 85.6% (0.80), with the following distribution: insomnia 85.5%
(0.80), narcolepsy 83.8% (0.78), idiopathic hypersomnia 86.1% (0.68), OSA 87.2%
(0.82). A significant low amplitude scorer effect was observed for most sleep
parameters, not always driven by the same scorer. Hypnograms obtained with AS and
VS exhibited very close sleep organization, except for 80 % of REM Sleep Onset
(SOREM) in the narcoleptic group missed by AS.
CONCLUSIONS: Agreement between AS and VS in sleep disorders is comparable to that
reported in healthy subjects and to inter-expert agreement in patients. ASEEGA
could therefore be considered as a complementary sleep stage scoring tool in
clinical practice, after improvement of SOREM detection.

© 2020 American Academy of Sleep Medicine.


Auteurs Bordeaux Neurocampus