Widespread adoption of smartphones, smartwatches and fitness devices opens up new opportunities for monitoring sleep and physical activity. Because subjects are attached to many electrodes, sleep is disturbed by the recording, so that it is better at looking at qualitative abnormalities such as sleep apnea or narcolepsy. However, information-rich PSG is expensive, laborious and intrusive. During PSG, subjects spend a night in a dedicated sleep lab, hooked up to a range of devices to measure physiological signals. Polysomnography (PSG) is currently the gold standard method to monitor sleep. Without it, our body and mind function poorly, with consequences that include risk of obesity 1, diabetes 2 and cardiovascular disease 3. Good sleep is vital for our health and wellbeing. Further study is needed to assess longer-term performance in natural conditions, and against polysomnography in clinical settings. Conclusions: This study suggests that the Apple Watch could be an acceptable alternative to the Philips Actiwatch for sleep monitoring, paving the way for larger-scale sleep studies using Appleās consumer-grade mobile device and publicly available sleep classification algorithms. The performance of the Apple Watch compares favorably to the clinically validated Actiwatch in a normal environment. On average, the Apple Watch over-estimated total sleep time by 6.31 minutes and under-estimated Wake After Sleep Onset by 5.74 minutes. Over the 27 nights, total sleep time was strongly linearly correlated between the two devices (r=0.85). Results: The Apple Watch had high overall accuracy (97%) and sensitivity (99%) in detecting actigraphy-defined sleep, and adequate specificity (79%) in detecting actigraphy defined wakefulness. We used a range of analyses, including Bland-Altman plots and linear correlation, to visualize and assess the agreement between Actiwatch and Apple Watch. We extracted triaxial acceleration data (at 50 Hz) from the Apple Watch, calculated Euclidean norm minus one (ENMO) for the same epochs, and classified them using a similar algorithm. We extracted activity counts from the Actiwatch and classified 15-second epochs into sleep/wake using the Actiware Software. Methods: We recorded 27 nights of sleep from 14 healthy adults (9 male, 5 female). Background: We investigate the feasibility of using an Apple Watch for sleep monitoring by comparing its performance to the clinically validated Philips Actiwatch Spectrum Pro (the gold standard in this study), under free-living conditions.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |