Performance of the Verily Study Watch for measuring sleep compared to polysomnography

Performance of the Verily Study Watch for measuring sleep compared to polysomnography

IntroductionThis study evaluated the performance of a wrist-worn wearable, Verily Study Watch (VSW), in detecting key sleep measures against polysomnography (PSG).MethodsWe collected data from 41 adults without obstructive sleep apnea or insomnia during a single overnight laboratory visit. We evalua...

Full description

Saved in:
Bibliographic Details
Main Authors: Sohrab Saeb, Benjamin W. Nelson, Poulami Barman, Nishant Verma, Hannah Allen, Massimiliano de Zambotti, Fiona C. Baker, Nicole Arra, Niranjan Sridhar, Shannon S. Sullivan, Scooter Plowman, Erin Rainaldi, Ritu Kapur, Sooyoon Shin
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Sleep
Subjects:
sleep-wake detection
sleep stage
digital health measures
polysomnography
free-living
sleep detection accuracy
Online Access:https://www.frontiersin.org/articles/10.3389/frsle.2024.1481878/full
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:IntroductionThis study evaluated the performance of a wrist-worn wearable, Verily Study Watch (VSW), in detecting key sleep measures against polysomnography (PSG).MethodsWe collected data from 41 adults without obstructive sleep apnea or insomnia during a single overnight laboratory visit. We evaluated epoch-by-epoch performance for sleep vs. wake classification, sleep stage classification and duration, total sleep time (TST), wake after sleep onset (WASO), sleep onset latency (SOL), sleep efficiency (SE), and number of awakenings (NAWK). Performance metrics included sensitivity, specificity, Cohen's kappa, and Bland-Altman analyses.ResultsSensitivity and specificity (95% CIs) of sleep vs. wake classification were 0.97 (0.96, 0.98) and 0.70 (0.66, 0.74), respectively. Cohen's kappa (95% CI) for 4-class stage detection was 0.64 (0.18, 0.82). Most VSW sleep measures had proportional bias. The mean bias values (95% CI) were 14.0 min (5.55, 23.20) for TST, −13.1 min (−21.33, −6.21) for WASO, 2.97% (1.25, 4.84) for SE, −1.34 min (−7.29, 4.81) for SOL, 1.91 min (−8.28, 11.98) for light sleep duration, 5.24 min (−3.35, 14.13) for deep sleep duration, and 6.39 min (−0.68, 13.18) for REM sleep duration. Mean and median NAWK count differences (95% CI) were 0.05 (−0.42, 0.53) and 0.0 (0.0, 0.0), respectively.DiscussionResults support applying the VSW to track overnight sleep measures in free-living settings. Registered at clinicaltrials.gov (NCT05276362).
ISSN:2813-2890

Similar Items