Multicenter evaluation of the Waveband system for automated sleep assessment in patients with insomnia symptoms

This study (Octave-3) aimed to validate the performance of the Waveband dry-electroencephalography sensor device for automatic sleep staging and sleep parameter estimation as compared to gold-standard in-lab polysomnography (PSG).

Forty-five participants were enrolled, and 38 completed simultaneous PSG and Waveband recordings. PSG data were scored by six human technologists, while Waveband data were scored algorithmically. Agreement between sleep staging results and derived sleep parameters (total sleep time (TST), sleep efficiency (SE), sleep onset latency (SOL), latency to 10 minutes of persistent sleep (LPS), wake after sleep onset (WASO), and time spent in each sleep stage) was measured using the Intraclass Correlation Coefficient (ICC) and overall agreement (OA). Waveband OA was compared to each human rater using the leave-one-out consensus of the remaining five human experts.

Average OA between Waveband vs the leave one out consensuses was 87.3+/-5.4 per cent, equivalent to the average OA for individual human experts of 85.9+/-7.6 per cent (p > .1). Waveband and humans had better OA over the second half of the night, but Waveband had superior OA. ICCs for TST, SE, LPS, and WASO exceeded 0.9, indicating excellent agreement between automated Waveband and human PSG scoring. Lower agreement was found for time spent in N1, N3, and Rapid Eye Movement Sleep (REM), with ICCs ranging from 0.65 to 0.73.

Waveband provides accurate sleep staging and estimation of TST, SE, SOL, LPS, and WASO, with comparable performance to human expert staging of PSG. Its reduced form-factor and good performance should make it a valuable tool for automated assessment of sleep in patients with disturbed sleep. Clinical Trial Information Trial name: Octave-3.URL: https://www.clinicaltrials.gov/study/NCT05438017Registration: NCT05438017.