Proof of concept: Screening for REM sleep behaviour disorder with a minimal set of sensors

Rapid-Eye-Movement (REM) sleep behaviour disorder (RBD) is an early predictor of Parkinson’s disease, dementia with Lewy bodies, and multiple system atrophy. This study investigated the use a minimal set sensors to achieve effective screening for RBD in population, integrating automated staging (three state) followed by detection without need cumbersome electroencephalogram (EEG) sensors. Polysomnography signals from 50 participants age-matched healthy controls were used evaluate this study. Three stage classification was achieved using random forest classifier features derived combination cost-effective easy sensors, namely electrocardiogram (ECG), electrooculogram (EOG), electromyogram (EMG) channels. Subsequently, established new metrics ECG EMG The EOG provided optimal minimalist fully-automated performance, achieving 0.57 ± 0.19 kappa (3 stage) accuracy 0.90 0.11, (sensitivity specificity 0.88 0.13 0.92 0.098, respectively). A single sensor three state 0.28 0.06 0.62 0.10. demonstrates feasibility detect techniques. proposes cost-effective, practical, simple identification support tool only two (EMG EOG); ideal purposes.