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

Abstract

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.

Figure 1

Diagram of the 3-step procedure for automatic sleep scoring based on a single EEG CzPz channel. The 3 steps are preprocessing, analysis, and classification.

Figure 2

Representative 5-state hypnograms obtained using ASEEGA (bottom) and manual scoring (scorer 1, top panel; and scorer 2, middle panel). For this subject, agreement between M1 and M2 was 79% (κ = 0.70), 73% between M1 and A (κ = 0.62), and 77% between M2 and A (κ = 0.66). M1 and M2 scores differed in 198 epochs. Finally, agreement between A and M1∩M2 was 83%.

Figure 3

Bland-Altman plots of sleep parameters showing the differences between ASEEGA scoring and manual scoring by scorer 1 versus the corresponding mean, calculated for sleep latency (min), wake after sleep onset (WASO, min), REM sleep (%), slow wave sleep (SWS, min) and number of stage shifts. The mean difference and the limits of agreement (± 1.96 SD) are represented as dotted lines. A similar figure could be drawn with the results from scorer 2.