State of the science and recommendations for using wearable technology in sleep and circadian research

SLEEP, Journal Year: 2023, Volume and Issue: 47(4)

Published: Dec. 24, 2023

Wearable sleep-tracking technology is of growing use in the sleep and circadian fields, including for applications across other disciplines, inclusive a variety disease states. Patients increasingly present data derived from their wearable devices to providers ever-increasing availability commercial new-generation research/clinical tools has led wide adoption wearables research, which become even more relevant given discontinuation Philips Respironics Actiwatch. Standards evaluating performance have been introduced available evidence suggests that consumer-grade exceed traditional actigraphy assessing as defined by polysomnogram. However, clear limitations exist, example, misclassification wakefulness during period, problems with tracking outside main bout or nighttime artifacts, unclear translation individuals certain characteristics comorbidities. This particular relevance when person-specific factors (like skin color obesity) negatively impact sensor potential downstream augmenting already existing healthcare disparities. holds great promise our field, features distinct such measurement autonomic parameters, estimation features, integrate self-reported, objective, passively recorded health indicators. Scientists face numerous decision points barriers incorporating actigraphy, multi-sensor devices, contemporary research/clinical-grade trackers into research. Considerations include device capabilities performance, target population goals study, outputs raw aggregate data, extraction, processing, analysis. Given difficulties implementation utilization real-world research clinical settings, following State Science review requested Sleep Research Society aims address questions. What can provide? How accurate are these data? should be taken account research? These outstanding questions surrounding considerations motivated this work, outlining practical recommendations using

Language: Английский

---

Electrocardiogram Monitoring Wearable Devices and Artificial-Intelligence-Enabled Diagnostic Capabilities: A Review

Sensors, Journal Year: 2023, Volume and Issue: 23(10), P. 4805 - 4805

Published: May 16, 2023

Worldwide, population aging and unhealthy lifestyles have increased the incidence of high-risk health conditions such as cardiovascular diseases, sleep apnea, other conditions. Recently, to facilitate early identification diagnosis, efforts been made in research development new wearable devices make them smaller, more comfortable, accurate, increasingly compatible with artificial intelligence technologies. These can pave way longer continuous monitoring different biosignals, including real-time detection thus providing timely accurate predictions events that drastically improve healthcare management patients. Most recent reviews focus on a specific category disease, use 12-lead electrocardiograms, or technology. However, we present advances electrocardiogram signals acquired from publicly available databases analysis methods detect predict diseases. As expected, most focuses heart emerging areas, mental stress. From methodological point view, although traditional statistical machine learning are still widely used, observe an increasing advanced deep methods, specifically architectures handle complexity biosignal data. typically include convolutional recurrent neural networks. Moreover, when proposing prevalent choice is rather than collecting

Language: Английский

---

Evaluating Accuracy in Five Commercial Sleep-Tracking Devices Compared to Research-Grade Actigraphy and Polysomnography

Sensors, Journal Year: 2024, Volume and Issue: 24(2), P. 635 - 635

Published: Jan. 19, 2024

The development of consumer sleep-tracking technologies has outpaced the scientific evaluation their accuracy. In this study, five devices, research-grade actigraphy, and polysomnography were used simultaneously to monitor overnight sleep fifty-three young adults in lab for one night. Biases limits agreement assessed determine how stage estimates each device actigraphy differed from polysomnography-derived measures. Every device, except Garmin Vivosmart, was able estimate total time comparably actigraphy. All devices overestimated nights with shorter wake times underestimated longer times. For light sleep, absolute bias low Fitbit Inspire Versa. Withings Mat Vivosmart sleep. Oura Ring any duration. deep while other REM all devices. Taken together, these results suggest that proportional patterns are prevalent could have important implications overall

Language: Английский

---

Consumer sleep technology for the screening of obstructive sleep apnea and snoring: current status and a protocol for a systematic review and meta‐analysis of diagnostic test accuracy

Journal of Sleep Research, Journal Year: 2023, Volume and Issue: 32(4)

Published: Feb. 17, 2023

There are concerns about the validation and accuracy of currently available consumer sleep technology for sleep-disordered breathing. The present report provides a background review existing technologies discloses methods procedures systematic meta-analysis diagnostic test these devices apps detection obstructive apnea snoring in comparison with polysomnography. search will be performed four databases (PubMed, Scopus, Web Science, Cochrane Library). Studies selected two steps, first by an analysis abstracts followed full-text analysis, independent reviewers perform both phases. Primary outcomes include apnea-hypopnea index, respiratory disturbance event oxygen desaturation duration index reference tests, as well number true positives, false negatives, negatives each threshold, epoch-by-epoch event-by-event results, which considered calculation surrogate measures (including sensitivity, specificity, accuracy). Diagnostic meta-analyses using Chu Cole bivariate binomial model. Mean difference continuous DerSimonian Laird random-effects Analyses independently outcome. Subgroup sensitivity analyses evaluate effects types (wearables, nearables, bed sensors, smartphone applications), (e.g., oximeter, microphone, arterial tonometry, accelerometer), role manufacturers, representativeness samples.

Language: Английский

---

A systematic review of the performance of actigraphy in measuring sleep stages

Journal of Sleep Research, Journal Year: 2024, Volume and Issue: 33(5)

Published: Feb. 21, 2024

The accuracy of actigraphy for sleep staging is assumed to be poor, but examination limited. This systematic review aimed assess the performance in stage classification adults. A search was performed using MEDLINE, Web Science, Google Scholar, and Embase databases. We identified eight studies that compared architecture estimates between wrist-worn polysomnography. Large heterogeneity found with respect how stages were grouped, choice metrics used evaluate performance. Quantitative synthesis not possible, so we a narrative literature. From limited number studies, actigraphy-based had some ability classify different

Language: Английский

---

Sleep characterization with smart wearable devices: a call for standardization and consensus recommendations

SLEEP, Journal Year: 2022, Volume and Issue: 45(12)

Published: Aug. 1, 2022

The general public increasingly adopts smart wearable devices to quantify sleep characteristics and dedicated for assessment. rapid evolution of technology has outpaced the ability implement validation approaches demonstrate relevant clinical applicability. There are untapped opportunities validate refine consumer in partnership with scientists academic institutions, patients, private sector allow effective integration into management pathways facilitate trust adoption once reliability validity have been demonstrated. We call formation a working group involving stakeholders from academia, care industry develop clear professional recommendations appropriate optimized utilization such technologies.

Language: Английский

---

Minimum number of nights for reliable estimation of habitual sleep using a consumer sleep tracker

SLEEP Advances, Journal Year: 2022, Volume and Issue: 3(1)

Published: Jan. 1, 2022

To determine the minimum number of nights required to reliably estimate weekly and monthly mean sleep duration variability measures from a consumer technology (CST) device (Fitbit).Data comprised 107 144 1041 working adults aged 21-40 years. Intraclass correlation (ICC) analyses were conducted on both time windows achieve ICC values 0.60 0.80, corresponding "good" "very good" reliability thresholds. These numbers then validated data collected 1-month 1-year later.Minimally, 3 5 obtain total (TST) estimates, while 10 for TST estimates. For weekday-only 2 sufficient 7 sufficed windows. Weekend-only estimates nights. 6 windows, 11 18 Weekday-only 4 9 14 Error made using later with these parameters comparable those associated original dataset.Studies should consider metric, measurement window interest, desired threshold decide assess habitual CST devices.

Language: Английский

---

Performance evaluation of Fitbit Charge 3 and actigraphy vs. polysomnography: Sensitivity, specificity, and reliability across participants and nights

Sleep Health, Journal Year: 2023, Volume and Issue: 9(4), P. 407 - 416

Published: June 1, 2023

Language: Английский

---

Belun Ring (Belun Sleep System BLS-100): Deep learning-facilitated wearable enables obstructive sleep apnea detection, apnea severity categorization, and sleep stage classification in patients suspected of obstructive sleep apnea

Sleep Health, Journal Year: 2023, Volume and Issue: 9(4), P. 430 - 440

Published: June 26, 2023

Our objective was to evaluate the performance of Belun Ring with second-generation deep learning algorithms in obstructive sleep apnea (OSA) detection, OSA severity categorization, and stage classification.Belun REFERENCE TECHNOLOGY: In-lab polysomnography (PSG) SAMPLE: Eighty-four subjects (M: F = 1:1) referred for an overnight study were eligible. Of these, 26% had PSG-AHI<5; 24% PSG-AHI 5-15; 23% 15-30; 27% ≥ 30.Rigorous evaluation by comparing concurrent in-lab PSG using 4% rule.Pearson's correlation coefficient, Student's paired t-test, diagnostic accuracy, sensitivity, specificity, positive predictive value, negative likelihood ratio, Cohen's kappa coefficient (kappa), Bland-Altman plots bias limits agreement, receiver operating characteristics curves area under curve, confusion matrix.The categorizing AHI 5 0.85, 0.92, 0.64, 0.58, respectively. The Kappa 15 0.89, 0.91, 0.88, 0.79, 30 0.83, 0.93, 0.76, BSP2 also achieved accuracy 0.88 detecting wake, 0.82 NREM, 0.90 REM sleep.Belun detected good demonstrated a moderate-to-substantial agreement classifying stages.

Language: Английский

---

Performance evaluation of portable respiratory polygraphy for assessing sleep bruxism in adults

Journal of Oral Rehabilitation, Journal Year: 2024, Volume and Issue: 51(9), P. 1862 - 1871

Published: May 15, 2024

Polysomnography (PSG) is the gold standard for sleep bruxism (SB) assessment, it expensive, not widely accessible, and time-consuming.

Language: Английский

---