Detecting REM sleep from the finger: an automatic REM sleep algorithm based on peripheral arterial tone (PAT) and actigraphy

Abstract

Scoring of REM sleep based on polysomnographic recordings is a laborious and time-consuming process. The growing number of ambulatory devices designed for cost-effective home-based diagnostic sleep recordings necessitates the development of a reliable automatic REM sleep detection algorithm that is not based on the traditional electroencephalographic, electrooccolographic and electromyographic recordings trio. This paper presents an automatic REM detection algorithm based on the peripheral arterial tone (PAT) signal and actigraphy which are recorded with an ambulatory wrist-worn device (Watch-PAT100). The PAT signal is a measure of the pulsatile volume changes at the finger tip reflecting sympathetic tone variations. The algorithm was developed using a training set of 30 patients recorded simultaneously with polysomnography and Watch-PAT100. Sleep records were divided into 5 min intervals and two time series were constructed from the PAT amplitudes and PAT-derived inter-pulse periods in each interval. A prediction function based on 16 features extracted from the above time series that determines the likelihood of detecting a REM epoch was developed. The coefficients of the prediction function were determined using a genetic algorithm (GA) optimizing process tuned to maximize a price function depending on the sensitivity, specificity and agreement of the algorithm in comparison with the gold standard of polysomnographic manual scoring. Based on a separate validation set of 30 patients overall sensitivity, specificity and agreement of the automatic algorithm to identify standard 30 s epochs of REM sleep were 78%, 92%, 89%, respectively. Deploying this REM detection algorithm in a wrist worn device could be very useful for unattended ambulatory sleep monitoring. The innovative method of optimization using a genetic algorithm has been proven to yield robust results in the validation set.

Sleep Staging Based on Autonomic Signals: A Multi-Center Validation Study

“…5 It has been shown to accurately detect OSA (in laboratory and ambulatory settings), [5][6][7][8] autonomic arousals, 9 and sleep/wake status. 10 The validity of using PAT and actigraphy signals derived from the PAT recorder to detect REM 11 and light/deep 12 sleep has also been demonstrated in two small studies. In the current study, we aimed to validate the sleep staging algorithm of the PAT recorder device in a large population including normal subjects and patients with suspected OSA.…”

“…Then, the NREM sleep epochs were further categorized as either light (mirror sleep stage 1 and 2) or deep (mirror sleep stage 3 and 4) sleep. The detailed algorithms of sleep/wake detection from actigraphy signal 10 and sleep staging from the PAT signal 11,12 have previously been described.…”

“…While most portable devices do not assess sleep or sleep stages, detect wakefulness, light sleep, deep sleep, and REM sleep. While separate components of the sleep stage algorithm have been assessed previously, [10][11][12] this is the first PSG-based validation study using a complete software package (zzzPAT) for sleep staging in normal subjects and patients with different degree of OSA severity.…”

Study Looking at End Expiratory Pressure for Altitude Illness Decrease (SLEEP-AID)

“…It performs physiologic sleep monitoring by gathering sleep data using a pulse oximeter, decibel meter, positional gyroscope, and finger plethysmograph-which computes peripheral arterial tonometry (PAT). This device analyzes continuous oxygen saturation, oxygen desaturation events, pulse, sleep time, and stages (awake, light, deep, and REM sleep) (Herscovici et al, 2007;Bresler et al, 2008). The PAT detects transient vasoconstriction and tachycardic events that correlate pulsatile finger blood flow patterns with standard apnea-hypopnea scoring (Schnall et al, 1999;Pillar et al, 2002) to analyze sleep architecture and accurately diagnose sleep conditions Dvir et al, 2002;Penzel et al, 2004).…”

Data mining techniques for detection of sleep arousals

“…Some articles describing sleep analysis and arousal detection are based on data recorded from the finger alone (Pillar et al, 2003;Pittman et al, 2000;Herscovici et al, 2007). These algorithms avoid the overload caused by recording electroencephalographic signals (EEG, EMG, etc.)…”