Semi automatic quantification of REM sleep without atonia in natural sleep environment

Abstract

Polysomnography, the gold standard diagnostic tool in sleep medicine, is performed in an artificial environment. This might alter sleep and may not accurately reflect typical sleep patterns. While macro-structures are sensitive to environmental effects, micro-structures remain more stable. In this study we applied semi-automated algorithms to capture REM sleep without atonia (RSWA) and sleep spindles, comparing lab and home measurements. We analyzed 107 full-night recordings from 55 subjects: 24 healthy adults, 28 Parkinson's disease patients (15 RBD), and three with isolated Rem sleep behavior disorder (RBD). Sessions were manually scored. An automatic algorithm for quantifying RSWA was developed and tested against manual scoring. RSWAi showed a 60% correlation between home and lab. RBD detection achieved 83% sensitivity, 79% specificity, and 81% balanced accuracy. The algorithm accurately quantified RSWA, enabling the detection of RBD patients. These findings could facilitate more accessible sleep testing, and provide a possible alternative for screening RBD.

Fig. 1. Soft electrode array and the wireless data acquisition unit.

The electrode array is designed to accommodate EEG recordings from the forehead region, EOG from below the right eye, and EMG recordings from the chin. A reference electrode is positioned on the right mastoid. Data were used to quantify sleep macrostructures, spindles, and RSWA.

Fig. 2. Macro structures at the lab and at home using wearable data and derived from manual sleep staging.

a Hypnogram captured at the lab of PD patient with RBD (female, 67 years old). b Hypnogram captured at home from the same subject. REM and wake stages are marked in blue and grey, correspondingly. c–f Correlation plots comparing hypnogram parameters between home and lab (N = 52). The Grey dashed line represents y = x.

Fig. 3. Spindles stability.

a 8 s recorded simultaneously from 60-year-old PD female H%Y = 1 with both systems showing two spindles captured (light blue) in the electroencephalogram (EEG) signals. b PSG sleep spindle density versus data collected using the wearable system, with Pearson’s correlation of 0.86. c PSG spindle median frequency versus wearable, with Pearson’s correlation of 0.48. d Home versus lab wearable-based spindle density, with Pearson’s correlation of 0.88. e Home versus lab wearable-based spindle median frequency, with Pearson’s correlation of 0.90. The Grey dashed line represents y = x.

Fig. 4. Automated detection of RSWA from a subgroup of 18 subjects (HC = 9; PD non-RBD = 3; PD RBD = 5; and iRBD = 1).

a An example of a 30 s REM epoch featuring differential EMG chin data from PSG (top) and wearable device (bottom) with automated EMG detection (green) and manual annotation (blue). b manual scoring of RSWAi derived from PSG data versus manual scoring of RSWAi derived from the wearable data. c Automated RSWAi derived from the wearable data versus RSWAi derived manually from the PSG data. d RSWAi value distribution of different subject groups at home versus in the lab (semi-automatic detection using data from the wearable system). e ROC curve analysis for binary classification including the identification of the optimal threshold of 6.269 (black dot), and AUC of 0.801 (light grey area) based on the train set. f Confusion matrix achieved from testing set data (N = 40) for binary classification of RBD versus Non-RBD.