Background. Differentiating nonwear time from sleep and wake times is essential forthe estimation of sleep duration based on actigraphy data. To efficiently analyze large-scale data sets, an automatic method of identifying these three different states is re-quired. Therefore, we developed a classification algorithm to determine nonwear, sleepand wake periods from accelerometer data. Our work aimed to (I) develop a new patternrecognition algorithm for identifying nonwear periods from actigraphy data based onthe influence of respiration rate on the power spectrum of the acceleration signal andimplement it in an automatic classification algorithm for nonwear/sleep/wake states;(II) address motion artifacts that occur during nonwear periods and are known to causemisclassification of these periods; (III) adjust the algorithm depending on the sensorposition (wrist, chest); and (IV) validate the algorithm on both healthy individuals andpatients with sleep disorders.
Methods. The study involved 98 participants who wore wrist and chest accelerationsensors for one day of measurements. They spent one night in the sleep laboratoryand continued to wear the sensors outside of the laboratory for the remainder of theday. ... mehrThe results of the classification algorithm were compared to those of the referencesource: polysomnography for wake/sleep and manual annotations for nonwear/wearclassification.
Results. The median kappa values for the two locations were 0.83 (wrist) and 0.84(chest). The level of agreement did not vary significantly by sleep health (good sleepersvs. subjects with sleep disorders) (p=0.348,p=0.118) or by sex (p=0.442,p=0.456).The intraclass correlation coefficients of nonwear total time between the referenceand the algorithm were 0.92 and 0.97 with the outliers and 0.95 and 0.98 after theoutliers were removed for the wrist and chest, respectively. There was no evidence of anassociation between the mean difference (and 95% limits of agreement) and the meanof the two methods for either sensor position (wrist p=0.110, chest p=0.164), and themean differences (algorithm minus reference) were 5.11 [95% LoA−15.4–25.7] and1.32 [95% LoA−9.59–12.24] min/day, respectively, after the outliers were removed.
Discussion. We studied the influence of the respiration wave on the power spectrum ofthe acceleration signal for the differentiation of nonwear periods from sleep and wakeperiods. The algorithm combined both spectral analysis of the acceleration signal and rescoring. Based on the Bland-Altman analysis, the chest-worn accelerometer showed better results than the wrist-worn accelerometer.