Screening for REM Sleep Behaviour Disorder with Minimal Sensors

TL;DR

This study develops a cost-effective, minimally invasive method using only EOG and EMG sensors for automated screening of REM Sleep Behaviour Disorder, achieving high accuracy and practicality for early diagnosis.

Contribution

It introduces a novel minimal sensor setup combining EOG and EMG for effective automated RBD screening, reducing reliance on complex EEG sensors.

Findings

EOG and EMG combination achieved 0.57 kappa in sleep staging and 0.90 RBD detection accuracy.

Single ECG sensor provided lower performance with 0.28 kappa and 0.62 accuracy.

Proposed two-sensor system is practical and effective for RBD screening.

Abstract

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 investigates a minimal set of sensors to achieve effective screening for RBD in the population, integrating automated sleep staging (three state) followed by RBD detection without the need for cumbersome electroencephalogram (EEG) sensors. Polysomnography signals from 50 participants with RBD and 50 age-matched healthy controls were used to evaluate this study. Three stage sleep classification was achieved using a Random Forest (RF) classifier and features derived from a combination of cost-effective and easy to use sensors, namely electrocardiogram (ECG), electrooculogram (EOG), and electromyogram (EMG) channels. Subsequently, RBD detection was achieved using established and new metrics derived from ECG and EMG metrics. The EOG and EMG combination provided the best minimalist fully automated performance, achieving $0.57\pm0.19$ kappa (3 stage) for sleep staging and an RBD detection accuracy of $0.90\pm0.11$, (sensitivity, and specificity $0.88\pm0.13$, and $0.92\pm0.098$). A single ECG sensor allowed three state sleep staging with $0.28\pm0.06$ kappa and RBD detection accuracy of $0.62\pm0.10$. This study demonstrated the feasibility of using signals from a single EOG and EMG sensor to detect RBD using fully-automated techniques. This study proposes a cost-effective, practical, and simple RBD identification support tool using only two sensors (EMG and EOG), ideal for screening purposes.