Sleep for Sale: Can Commercial Wearable Sleep Technology Measure up Clinically?

August 5, 2025

Class Act Clinical Questions Pulmonary/Critical Care 5 min read

By Emily Lock

Peer Reviewed

Sleep is a currency of wellness. Increased sleep duration has been associated with enhanced cognitive performance and decreased risk of dementia, while decreased sleep predicts reduced gray matter volume and impaired clearance of neuronal metabolites such as beta-amyloid.1 Yet, more is not always better; compared to optimal sleepers getting 7-9 hours per night, both short and long duration of sleep have been correlated with higher BMI and greater incidence of stroke and myocardial infarction.2 Further, not all sleep is equal. Differences in sleep architecture, such as suppression of rapid eye movement (REM) or slow-wave sleep phases, can predict metabolic disturbances like insulin resistance.3

The prevalence of sleep disorders has increased over the last decade, with an estimated 16% prevalence of insomnia disorder in American adults.4 The rise in insomnia is related to elements of modern lifestyle, including increased screen time, chronic stress exacerbated by media, and increased rates of anxiety and depression.5 Obstructive sleep apnea (OSA), a disorder characterized by nocturnal pauses in ventilation and strongly correlated with obesity, also has a rising incidence paralleling the rise in average BMI.6 Fortunately, sleep is largely considered to be a modifiable risk factor, giving people hope to climb out of their “sleep debt.”

Public conceptualization of sleep as a commodity to be acquired and monitored, akin to money invested in an index fund, spurred the integration of sleep monitoring capabilities into consumer technology, like smartwatches and rings. According to a 2023 study conducted by the American Academy of Sleep Medicine, one-third of Americans track their sleep using an electronic device.7 These tools use various sensors, including accelerometers, heart rate monitors, photoplethysmography (PPG), skin thermometers, and oxygen saturation (SpO2) detectors to estimate sleep stages, duration, and quality. Reported metrics include sleep latency and disruptions, sleep efficiency (percentage of time asleep relative to total time in bed), time spent in various sleep stages, and periodic vital signs.

When compared with polysomnography (PSG), the gold standard for sleep assessment, wearables tend to overestimate sleep efficiency and have inconsistent sleep stage classification, with poorer performance on nights with more disruptions or greater sleep latency.8-9 Many devices incorporate these variables into a composite “sleep score.” While research indicates that high scores can be energizing and low scores can serve as motivation for lifestyle change,10 lack of transparency in calculation methods makes these scores less useful in clinical practice.

Devices with SpO2 sensors can detect oxygen desaturation events, which are common in OSA, introducing the possibility of screening for this underdiagnosed condition in the general public. Wearable technology monitoring is also attractive in its ability to provide long-term, repeated analysis to gather more longitudinal trends without major disruption to the sleep environment. Integration of AI into commercial wearable devices has been shown to have sensitivity and specificity of 0.79 and 0.95, respectively, in detecting apnea events, but inconsistent performance in determining sleep apnea severity.11 Greater agreement is found between PSG and commercial wearables in individuals with severe OSA,12 raising concern that milder cases may not be properly detected.

Beyond the detection of sleep disorders, commercial sleep-detecting technology has the potential to supplement standard insomnia treatment. Cognitive behavioral therapy for insomnia (CBT-I) requires patients to keep a sleep diary with subjective reporting of metrics like sleep duration and latency. The use of automated measurements via wearable technology to complete sleep diaries is reasonable, with only a 5 percent deviation from manually recorded values,13 especially if it can increase therapy adherence due to decreased cognitive and time burden.

Awareness is a double-edged sword. Receiving feedback with objective numerical metrics, such as heart rate variability and sleep time, can motivate lifestyle changes, guided by illuminated patterns between variables like caffeine consumption or exercise and sleep quality. On the other hand, engagement with sleep data can be detrimental, especially when users draw definitive conclusions about their health without accounting for the limitations of the data. “Orthosomnia” is an unhealthy preoccupation with achieving “ideal” sleep, frequently driven by wearable devices reporting poor sleep statistics. Paradoxically, this fixation often exacerbates insomnia symptoms due to increased anxiety.14, 15 The primary value of commercial sleep trackers lies in their use as adjunctive, rather than definitive, tools to improve sleep hygiene through increased awareness.

Several improvements to commercial wearable technology could translate well into the clinical setting. Increased transparency and standardization of the sleep scores reported by commercial devices could enhance the clinical utility of data that are already collected and readily available on a mass scale. Standardization of sleep score calculations could allow for more cost-effective, robust research with a validated metric. Refining and expanding the development of AI models to predict adverse outcomes can improve early detection and prompt more timely presentation for medical evaluation. Finally, sleep data should be used as an educational opportunity, with additional integration of facts and recommendations for sleep hygiene. While we may not be able to buy our way to perfect slumber, investment in sleep tools can increase mindfulness around practices and reliably provide generalized feedback as to how we are resting.

Emily Lock is a Class of 2027 medical student at NYU Grossman School of Medicine

Reviewed by Michael Tanner, MD, Executive Editor, Clinical Correlations

Image courtesy of  Wikimedia Commons: Sanjay ach, CC BY-SA 3.0 <http://creativecommons.org/licenses/by-sa/3.0/>, via Wikimedia Commons
ensors.webp

References

  1. Sexton CE, Sykara K, Karageorgiou E, et al. Connections Between Insomnia and Cognitive Aging. Neurosci Bull. 2020;36(1):77-84. doi:https://doi.org/10.1007/s12264-019-00401-9
  2. Krittanawong C, Kumar A, Wang Z, et al. Sleep Duration and Cardiovascular Health in a Representative Community Population (from NHANES, 2005 to 2016). Am J Cardiol. 2020;127:149-155. doi:https://doi.org/10.1016/j.amjcard.2020.04.012
  3. Dutil C, Chaput J-P. Inadequate sleep as a contributor to type 2 diabetes in children and adolescents. Nutr Diabetes. 2017;7(5):e266-e266. doi:https://doi.org/10.1038/nutd.2017.19
  4. Benjafield A, Kuniyoshi FS, Malhotra A, et al. 0404 Americas Prevalence of Insomnia Disorder in Adults: Estimation Using Currently Available Data. Sleep. 2024;47(Supplement_1):A173-A174. doi:https://doi.org/10.1093/sleep/zsae067.0404
  5. Gradisar M, Wolfson AR, Harvey AG, Hale L, Rosenberg R, Czeisler CA. The sleep and technology use of Americans: findings from the National Sleep Foundation’s 2011 Sleep in America poll. J Clin Sleep Med. 2013;9(12):1291-1299. doi:https://doi.org/10.5664/jcsm.3272
  6. Surani S, Taweesedt P. Obstructive Sleep Apnea: New Perspective. Medicina (Kaunas). 2022;59(1):75. doi:https://doi.org/10.3390/medicina59010075
  7. Celmer L. One in three Americans have used electronic sleep trackers. American Academy of Sleep Medicine. https://aasm.org/one-in-three-americans-have-used-electronic-sleep-trackers-leading-to-changed-behavior-for-many/ Published November 15, 2023. Accessed October 3, 2024.
  8. Lee T, Cho Y, Cha KS, et al. Accuracy of 11 Wearable, Nearable, and Airable Consumer Sleep Trackers: Prospective and Multicenter Validation Study. JMIR Mhealth Uhealth. 2023;11:e50983-e50983. doi:https://doi.org/10.2196/50983
  9. Chinoy ED, Cuellar JA, Huwa KE, et al. Performance of seven consumer sleep-tracking devices compared with polysomnography. Sleep. 2020;44(5):zssa291. doi:https://doi.org/10.1093/sleep/zsaa291
  10. Nagele AN, Hough J. “The sleep data looks way better than I feel.” An autoethnographic account and diffractive reading of sleep-tracking. Front Comput Sci. 2024;6. doi:https://doi.org/10.3389/fcomp.2024.1258289
  11. Bilge PC, Fatma EK, Cansu S, et al. Scanning of obstructive sleep apnea syndrome using smartwatch: A comparison of smartwatch and polysomnography. J Clin Neurosci. 2024;119:212-219. doi:https://doi.org/10.1016/j.jocn.2023.12.009
  12. Abd-Alrazaq A, Aslam H, AlSaad R, et al. Detection of Sleep Apnea Using Wearable AI: Systematic Review and Meta-Analysis. J Med Internet Res. 2024;26:e58187-e58187. doi:https://doi.org/10.2196/58187
  13. Gaiduk M, Seepold R, Madrid NM, Orcioni S, Conti M, Ortega JA. Initial evaluation of substituting a sleep diary by smartwatch measurement. Procedia Computer Science. 2022;207(12):3376-3383. doi:https://doi.org/10.1016/j.procs.2022.09.396
  14. Jahrami H, Trabelsi K, Vitiello MV, BaHammam AS. The Tale of Orthosomnia: I Am so Good at Sleeping that I Can Do It with My Eyes Closed and My Fitness Tracker on Me. Nature and Science of Sleep. 2023;15:13-15. doi:https://doi.org/10.2147/nss.s402694
  15. Baron KG, Abbott S, Jao N, Manalo N, Mullen R. Orthosomnia: Are Some Patients Taking the Quantified Self Too Far? J Clin Sleep Med. 2017;13(2):351-354. doi:https://doi.org/10.5664/jcsm.6472

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *