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:
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!
_version_ 1850247711703433216
author Sohrab Saeb
Benjamin W. Nelson
Benjamin W. Nelson
Poulami Barman
Nishant Verma
Hannah Allen
Massimiliano de Zambotti
Fiona C. Baker
Nicole Arra
Niranjan Sridhar
Shannon S. Sullivan
Shannon S. Sullivan
Scooter Plowman
Erin Rainaldi
Ritu Kapur
Ritu Kapur
Sooyoon Shin
author_facet Sohrab Saeb
Benjamin W. Nelson
Benjamin W. Nelson
Poulami Barman
Nishant Verma
Hannah Allen
Massimiliano de Zambotti
Fiona C. Baker
Nicole Arra
Niranjan Sridhar
Shannon S. Sullivan
Shannon S. Sullivan
Scooter Plowman
Erin Rainaldi
Ritu Kapur
Ritu Kapur
Sooyoon Shin
author_sort Sohrab Saeb
collection DOAJ
description 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).
format Article
id doaj-art-727a2eefd01e4a2bb88d0daf1e002ecb
institution OA Journals
issn 2813-2890
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Sleep
spelling doaj-art-727a2eefd01e4a2bb88d0daf1e002ecb2025-08-20T01:58:52ZengFrontiers Media S.A.Frontiers in Sleep2813-28902024-12-01310.3389/frsle.2024.14818781481878Performance of the Verily Study Watch for measuring sleep compared to polysomnographySohrab Saeb0Benjamin W. Nelson1Benjamin W. Nelson2Poulami Barman3Nishant Verma4Hannah Allen5Massimiliano de Zambotti6Fiona C. Baker7Nicole Arra8Niranjan Sridhar9Shannon S. Sullivan10Shannon S. Sullivan11Scooter Plowman12Erin Rainaldi13Ritu Kapur14Ritu Kapur15Sooyoon Shin16Verily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesDivision of Digital Psychiatry, Department of Psychiatry, Harvard Medical School and Beth Israel Deaconess Medical Center, Boston, MA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesCenter for Health Sciences, Stanford Research Institute (SRI), Menlo Park, CA, United StatesCenter for Health Sciences, Stanford Research Institute (SRI), Menlo Park, CA, United StatesCenter for Health Sciences, Stanford Research Institute (SRI), Menlo Park, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesDivision of Pulmonary, Asthma, and Sleep Medicine, Department of Pediatrics, Stanford University School of Medicine, Palo Alto, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesVerily Life Sciences, South San Francisco, CA, United StatesDepartment of Neurology, Radboud University Medical Center, Nijmegen, NetherlandsVerily Life Sciences, South San Francisco, CA, United StatesIntroductionThis 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).https://www.frontiersin.org/articles/10.3389/frsle.2024.1481878/fullsleep-wake detectionsleep stagedigital health measurespolysomnographyfree-livingsleep detection accuracy
spellingShingle Sohrab Saeb
Benjamin W. Nelson
Benjamin W. Nelson
Poulami Barman
Nishant Verma
Hannah Allen
Massimiliano de Zambotti
Fiona C. Baker
Nicole Arra
Niranjan Sridhar
Shannon S. Sullivan
Shannon S. Sullivan
Scooter Plowman
Erin Rainaldi
Ritu Kapur
Ritu Kapur
Sooyoon Shin
Performance of the Verily Study Watch for measuring sleep compared to polysomnography
Frontiers in Sleep
sleep-wake detection
sleep stage
digital health measures
polysomnography
free-living
sleep detection accuracy
title Performance of the Verily Study Watch for measuring sleep compared to polysomnography
title_full Performance of the Verily Study Watch for measuring sleep compared to polysomnography
title_fullStr Performance of the Verily Study Watch for measuring sleep compared to polysomnography
title_full_unstemmed Performance of the Verily Study Watch for measuring sleep compared to polysomnography
title_short Performance of the Verily Study Watch for measuring sleep compared to polysomnography
title_sort performance of the verily study watch for measuring sleep compared to polysomnography
topic sleep-wake detection
sleep stage
digital health measures
polysomnography
free-living
sleep detection accuracy
url https://www.frontiersin.org/articles/10.3389/frsle.2024.1481878/full
work_keys_str_mv AT sohrabsaeb performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT benjaminwnelson performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT benjaminwnelson performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT poulamibarman performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT nishantverma performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT hannahallen performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT massimilianodezambotti performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT fionacbaker performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT nicolearra performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT niranjansridhar performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT shannonssullivan performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT shannonssullivan performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT scooterplowman performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT erinrainaldi performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT ritukapur performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT ritukapur performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography
AT sooyoonshin performanceoftheverilystudywatchformeasuringsleepcomparedtopolysomnography