A Systematic Review of Sensing Technologies for Wearable Sleep Staging

Sensors, Journal Year: 2021, Volume and Issue: 21(5), P. 1562 - 1562

Published: Feb. 24, 2021

Designing wearable systems for sleep detection and staging is extremely challenging due to the numerous constraints associated with sensing, usability, accuracy, regulatory requirements. Several researchers have explored use of signals from a subset sensors that are used in polysomnography (PSG), whereas others demonstrated feasibility using alternative sensing modalities. In this paper, systematic review different modalities been presented. Based on 90 papers, 13 identified. Each modality identify can be obtained it, stages reliably identified, classification accuracy methods modality, as well usability sensor system. It concludes two most common those based electroencephalography (EEG) photoplethysmography (PPG). EEG-based accurate, EEG being only capable identifying all sleep. PPG-based much simpler better suited monitoring but unable stages.

Language: Английский

---

Performance of Four Commercial Wearable Sleep-Tracking Devices Tested Under Unrestricted Conditions at Home in Healthy Young Adults

Nature and Science of Sleep, Journal Year: 2022, Volume and Issue: Volume 14, P. 493 - 516

Published: March 1, 2022

Commercial wearable sleep-tracking devices are growing in popularity and recent studies have performed well against gold standard sleep measurement techniques. However, most were conducted controlled laboratory conditions. We therefore aimed to test the performance of under naturalistic unrestricted home conditions.Healthy young adults (n = 21; 12 women, 9 men; 29.0 ± 5.0 years, mean SD) slept at conditions for 1 week using a set commercial completed daily diaries. Devices included Fatigue Science Readiband, Fitbit Inspire HR, Oura ring, Polar Vantage V Titan. Participants also wore research-grade actigraphy watch (Philips Respironics Actiwatch 2) comparison. To assess performance, all compared with high performing mobile electroencephalography headband device (Dreem 2). Analyses epoch-by-epoch summary agreement comparisons.Devices accurately tracked sleep-wake metrics (ie, time bed, total time, efficiency, latency, wake after onset) on nights but best higher efficiency. Epoch-by-epoch sensitivity (for sleep) specificity wake), respectively, as follows: (0.95, 0.35), (0.94, 0.40), (0.93, 0.45), 0.41), (0.96, 0.35). Sleep stage-tracking was mixed, variability.As previous studies, better detecting than wake, favorably detection. more consolidated patterns. Unrestricted TIB differences nights. High variability suggests that these devices, their current form, still utilized tracking outcomes not stages. Most wearables exhibited promising real-world conditions, further supporting consideration an alternative actigraphy.

Language: Английский

---

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

---

Validity and reliability of the Oura Ring Generation 3 (Gen3) with Oura sleep staging algorithm 2.0 (OSSA 2.0) when compared to multi-night ambulatory polysomnography: A validation study of 96 participants and 421,045 epochs

Sleep Medicine, Journal Year: 2024, Volume and Issue: 115, P. 251 - 263

Published: Jan. 26, 2024

. To evaluate the validity and reliability of Oura Ring Generation 3 (Gen3) with Sleep Staging Algorithm 2.0 (OSSA 2.0) through multi-night polysomnography (PSG). Participants were 96 generally healthy Japanese men women aged between 20 70 years contributing 421,045 30-s epochs. scoring was performed according to American Academy Medicine criteria. Each participant could contribute a maximum three (PSG) nights. Within-participant means created for each sleep measure paired t-tests used compare equivalent measures obtained from PSG Rings (non-dominant dominant hand). Agreement assessed using Bland-Altman plots. Interrater epoch accuracy determined by prevalence-adjusted bias-adjusted kappa (PABAK). The did not significantly differ time in bed, total time, onset latency, period wake after onset, spent light sleep, deep sleep. worn on non-dominant- dominant-hand underestimated efficiency 1.1 %–1.5 % REM 4.1–5.6 min. had sensitivity 94.4 %–94.5 %, specificity 73.0 %–74.6 predictive value 95.9 %–96.1 66.6 %–67.0 91.7 %–91.8 %. PABAK 0.83–0.84 94.8 staging ranged 75.5 (light sleep) 90.6 (REM sleep). Gen3 OSSA shows good agreement global

Language: Английский

---

Multi-Night Validation of a Sleep Tracking Ring in Adolescents Compared with a Research Actigraph and Polysomnography

Nature and Science of Sleep, Journal Year: 2021, Volume and Issue: Volume 13, P. 177 - 190

Published: Feb. 1, 2021

Wearable devices have tremendous potential for large-scale longitudinal measurement of sleep, but their accuracy needs to be validated. We compared the performance multisensor Oura ring (Oura Health Oy, Oulu, Finland) polysomnography (PSG) and a research actigraph in healthy adolescents.Fifty-three adolescents (28 females; aged 15-19 years) underwent overnight PSG monitoring while wearing both an Actiwatch 2 (Philips Respironics, USA). Measurements were made over multiple nights across three levels sleep opportunity (5 with either 6.5 or 8h, 3 9h). data at two sensitivity settings analyzed. Discrepancies estimated measures as well sleep-wake, stage agreements evaluated using Bland-Altman plots epoch-by-epoch (EBE) analyses.Compared PSG, consistently underestimated TST by average 32.8 47.3 minutes (Ps < 0.001) different TIB conditions; its default setting 25.8 33.9 minutes. significantly overestimated WASO 30.7 46.3 It was comparable 6.5, 8h conditions. Relative REM (12.8 19.5 minutes) light (51.1 81.2 N3 31.5 46.8 0.01). EBE analyses demonstrated excellent sleep-wake accuracies, specificities, sensitivities - between 0.88 0.89 all TIBs.The yielded grade actigraphy latter's settings. Sleep staging improvement. However, device appears adequate characterizing effect duration manipulation on adolescent macro-architecture.

Language: Английский

---

Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography

Scientific Reports, Journal Year: 2020, Volume and Issue: 10(1)

Published: Aug. 11, 2020

A large part of the worldwide population suffers from obstructive sleep apnea (OSA), a disorder impairing restorative function and constituting risk factor for several cardiovascular pathologies. The standard diagnostic metric to define OSA is apnea-hypopnea index (AHI), typically obtained by manually annotating polysomnographic recordings. However, this clinical procedure cannot be employed screening long-term monitoring due its obtrusiveness cost. Here, we propose an automatic unobtrusive AHI estimation method fully based on wrist-worn reflective photoplethysmography (rPPG), employing deep learning model exploiting cardiorespiratory information extracted rPPG signal trained with 250 We tested our independent set 188 heterogeneously disordered recordings found it estimates good agreement gold polysomnography reference (correlation = 0.61, error 3±10 events/h). estimated was shown reliably assess severity (weighted Cohen's kappa 0.51) screen (ROC-AUC 0.84/0.86/0.85 mild/moderate/severe OSA). These findings suggest that measurements can implemented in wearables such as smartwatches, have potential complement techniques allowing respiratory monitoring.

Language: Английский

---

Past, Present, and Future of Multisensory Wearable Technology to Monitor Sleep and Circadian Rhythms

Frontiers in Digital Health, Journal Year: 2021, Volume and Issue: 3

Published: Aug. 16, 2021

Movement-based sleep-wake detection devices (i.e., actigraphy devices) were first developed in the early 1970s and have repeatedly been validated against polysomnography, which is considered "gold-standard" of sleep measurement. Indeed, they become important tools for objectively inferring free-living conditions. Standard are rooted accelerometry to measure movement make predictions, via scoring algorithms, as whether wearer a state wakefulness or sleep. Two developments incorporated newer devices. First, additional sensors, including measures heart rate variability higher resolution sensing through triaxial accelerometers, introduced improve upon traditional, movement-based algorithms. Second, these transcended scientific utility now being manufactured distributed general public. This review will provide an overview of: (1) history actigraphic measurement, (2) physiological underpinnings measurement wearables, (3) refinement validation both standard newer, multisensory real-world detection, (4) practical applications actigraphy, (5) limitations lastly (6) future directions within field.

Language: Английский

---

Wearable Devices: Current Status and Opportunities in Pain Assessment and Management

Digital Biomarkers, Journal Year: 2021, Volume and Issue: 5(1), P. 89 - 102

Published: April 19, 2021

<b><i>Introduction:</i></b> We investigated the possibilities and opportunities for using wearable devices that measure physical activity physiometric signals in conjunction with ecological momentary assessment (EMA) data to improve treatment of pain. <b><i>Methods:</i></b> considered studies cross-sectional longitudinal designs as well interventional or observational correlating pain scores measures derived from devices. A search was also performed on among patients <b><i>Results:</i></b> Few have assessed possibility incorporating objective tools contextualizing function free-living environments. Of been conducted, most focus solely functional outcomes measured by a accelerometer. Several report promising correlations between devices, objectively activity, function. In addition, there is known association physiologic can be pain, though these associate them environments are limited. <b><i>Conclusion:</i></b> There exists great opportunity study complex interplay signals, function, real-time fashion The literature supports hypothesis used develop reproducible biosignals correlate combination EMA will likely lead development clinically meaningful endpoints transform how we understand treat patients.

Language: Английский

---

Rigorous performance evaluation (previously, “validation”) for informed use of new technologies for sleep health measurement

Sleep Health, Journal Year: 2022, Volume and Issue: 8(3), P. 263 - 269

Published: May 3, 2022

New sleep technologies have become pervasive in the consumer space, and are becoming highly common research clinical settings. The rapid, widespread use of largely unregulated unstandardized technology has enabled quantification many different facets health, driving scientific discovery. As scientists, it is our responsibility to inform principles practices for proper evaluation any new used settings, by consumers. A current lack standardized methods evaluating performance challenges rigor accurate representation health interest. This special article describes rationale priorities an interdisciplinary effort rigorous, standardized, rapid (previously, "validation") disorders related all kinds (eg, devices or algorithms), including associated template a initiative publication Sleep Health empirical studies systematically technologies. structured type should streamline manuscript development enable more writing, review, publication. goal promote rigorous dissemination technology, enhance integrity, standardize terminology Rigorous Performance Evaluation papers prevent misinterpretation while facilitating comparisons across

Language: Английский

---

Wearable devices: Cross benefits from healthcare to construction

Automation in Construction, Journal Year: 2022, Volume and Issue: 142, P. 104501 - 104501

Published: Aug. 5, 2022

Language: Английский

---