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, Год журнала: 2024, Номер 115, С. 251 - 263

Опубликована: Янв. 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

Язык: Английский

---

COVID-19-related mobility reduction: heterogenous effects on sleep and physical activity rhythms

SLEEP, Год журнала: 2020, Номер 44(2)

Опубликована: Сен. 11, 2020

Mobility restrictions imposed to suppress transmission of COVID-19 can alter physical activity (PA) and sleep patterns that are important for health well-being. Characterization response heterogeneity their underlying associations may assist in stratifying the impact pandemic.We obtained wearable data covering baseline, incremental mobility restriction, lockdown periods from 1,824 city-dwelling, working adults aged 21-40 years, incorporating 206,381 nights 334,038 days PA. Distinct rest-activity rhythm (RAR) profiles were identified using k-means clustering, indicating participants' temporal distribution step counts over day. Hierarchical clustering proportion spent each these RAR revealed four groups who expressed different mixtures before during lockdown.Time bed increased by 20 min without loss efficiency, while social jetlag measures decreased 15 min. Resting heart rate declined ~2 bpm. PA dropped an average 42%. Four with compositions found. Three better able maintain weekday/weekend differentiation lockdown. The least active group comprising ~51% sample, younger predominantly singles. Habitually less already, this showed greatest reduction little differences.In early aftermath appears be more severely affected than sleep. evaluation uncovered responses could associate outcomes should resolution protracted.

Язык: Английский

---

Sleep Tracking of a Commercially Available Smart Ring and Smartwatch Against Medical-Grade Actigraphy in Everyday Settings: Instrument Validation Study

JMIR mhealth and uhealth, Год журнала: 2020, Номер 8(10), С. e20465 - e20465

Опубликована: Сен. 23, 2020

Background Assessment of sleep quality is essential to address poor and understand changes. Owing the advances in Internet Things wearable technologies, monitoring under free-living conditions has become feasible practicable. Smart rings smartwatches can be employed perform mid- or long-term home-based monitoring. However, validity such wearables should investigated terms parameters. Sleep validation studies are mostly limited short-term laboratory tests; there a need for study assess attributes everyday settings, where users engage their daily routines. Objective This aims evaluate parameters Oura ring along with Samsung Gear Sport watch comparison medically approved actigraphy device midterm setting, Methods We conducted which 45 healthy individuals (23 women 22 men) were tracked 7 days. Total time (TST), efficiency (SE), wake after onset (WASO) assessed using paired t tests, Bland-Altman plots, Pearson correlation. The also considering gender participants as dependent variable. Results found significant correlations between ring’s actigraphy’s TST (r=0.86; P<.001), WASO (r=0.41; SE (r=0.47; P<.001). Comparing showed correlation (r=0.59; mean differences TST, WASO, within satisfactory ranges, although (P<.001); ranges watch, was slightly higher than range (31.27, SD 35.15). considerably those ring. difference (P<.001) female male groups. Conclusions In sample population adults, both have acceptable indicate actigraphy, but outperforms nonstaging

Язык: Английский

---

A standardized framework for testing the performance of sleep-tracking technology: step-by-step guidelines and open-source code

SLEEP, Год журнала: 2020, Номер 44(2)

Опубликована: Сен. 3, 2020

Abstract Sleep-tracking devices, particularly within the consumer sleep technology (CST) space, are increasingly used in both research and clinical settings, providing new opportunities for large-scale data collection highly ecological conditions. Due to fast pace of CST industry combined with lack a standardized framework evaluate performance trackers, their accuracy reliability measuring remains largely unknown. Here, we provide step-by-step analytical evaluating trackers (including standard actigraphy), as compared gold-standard polysomnography (PSG) or other reference methods. The guidelines based on recent recommendations using from our group others (de Zambotti colleagues; Depner colleagues), include raw organization well critical procedures, including discrepancy analysis, Bland–Altman plots, epoch-by-epoch analysis. Analytical steps accompanied by open-source R functions (depicted at https://sri-human-sleep.github.io/sleep-trackers-performance/AnalyticalPipeline_v1.0.0.html). In addition, an empirical sample dataset is describe discuss main outcomes proposed pipeline. accompanying aimed standardizing testing CSTs performance, not only increase replicability validation studies, but also ready-to-use tools researchers clinicians. All all, this work can help efficiency, interpretation, quality improve informed adoption settings.

Язык: Английский

---

Agent architecture of an intelligent medical system based on federated learning and blockchain technology

Journal of Information Security and Applications, Год журнала: 2021, Номер 58, С. 102748 - 102748

Опубликована: Фев. 3, 2021

Язык: Английский

---

Relationship Between Major Depression Symptom Severity and Sleep Collected Using a Wristband Wearable Device: Multicenter Longitudinal Observational Study

JMIR mhealth and uhealth, Год журнала: 2021, Номер 9(4), С. e24604 - e24604

Опубликована: Фев. 3, 2021

Research in mental health has implicated sleep pathologies with depression. However, the gold standard for assessment, polysomnography, is not suitable long-term, continuous, monitoring of daily sleep, and methods such as diaries rely on subjective recall, which qualitative inaccurate. Wearable devices, other hand, provide a low-cost convenient means to monitor home settings. The main aim this study was devise extract features, from data collected using wearable device, analyse their correlation depressive symptom severity quality, measured by self-assessed Patient Health Questionnaire 8-item. Daily were passively Fitbit wristband self-reported every two weeks PHQ-8. used paper included 2,812 PHQ-8 records 368 participants recruited three sites Netherlands, Spain, UK.We extracted 21 features describe following five aspects: architecture, stability, insomnia, hypersomnia. Linear mixed regression models explore associations between severity. z-test evaluate significance coefficient each feature. We tested our entire dataset individually different sites. identified 16 that significantly correlated score dataset. Associations varied across sites, possibly due difference populations.

Язык: Английский

---

Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling

JMIR mhealth and uhealth, Год журнала: 2021, Номер 9(10), С. e24872 - e24872

Опубликована: Июль 15, 2021

Background Depression is a prevalent mental disorder that undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior physiology users (ie, digital biomarkers), which could be used for timely, unobtrusive, scalable depression screening. Objective The aim this study was to examine predictive ability biomarkers, based on from consumer-grade wearables, detect risk working population. Methods This cross-sectional 290 healthy adults. Participants wore Fitbit Charge 2 devices 14 consecutive days completed health survey, including screening depressive symptoms using 9-item Patient Health Questionnaire (PHQ-9), at baseline weeks later. We extracted range known novel biomarkers physical activity, sleep patterns, circadian rhythms wearables steps, heart rate, energy expenditure, data. Associations between severity were examined with Spearman correlation multiple regression analyses adjusted potential confounders, sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective loneliness. Supervised machine learning statistically selected predict symptom status). varying cutoff scores an acceptable PHQ-9 score define group different subsamples classification, while set remained same. For performance evaluation, we k-fold cross-validation obtained accuracy measures holdout folds. Results A total 267 participants included analysis. mean age 33 (SD 8.6, 21-64) years. Out participants, there mild female bias displayed (n=170, 63.7%). majority Chinese (n=211, 79.0%), single (n=163, 61.0%), had university degree (n=238, 89.1%). found greater robustly associated variation nighttime rate AM 4 6 AM; it also lower regularity weekday steps estimated nonparametric interdaily stability autocorrelation as well fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited whole sample However, balanced contrasted comprised depressed no or minimal symptoms), model achieved 80%, sensitivity 82%, specificity 78% detecting subjects high depression. Conclusions Digital have been discovered are behavioral physiological consumer increased assist screening, yet current shows ability. Machine models combining these discriminate individuals risk.

Язык: Английский

---

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

npj Digital Medicine, Год журнала: 2021, Номер 4(1)

Опубликована: Сен. 15, 2021

Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better disorder screening and health monitoring. However, PPG is rarely included in large studies with gold-standard annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks challenging. In this work a recurrent network first trained data set electrocardiogram (ECG) (292 participants, 584 recordings) to perform 4-class stage classification (wake, rapid-eye-movement, N1/N2, N3). A small part of its weights adapted smaller, newer (60 healthy 101 through three variations transfer learning. Best results (Cohen's kappa 0.65 ± 0.11, accuracy 76.36 7.57%) were achieved domain decision combined learning strategy, significantly outperforming PPG-trained ECG-trained baselines. This performance PPG-based unprecedented literature, bringing closer clinical use. The demonstrates merit developing reliable methods new sensor technologies by reusing similar, older non-wearable sets. Further study should evaluate our approach patients disorders such as insomnia apnoea.

Язык: Английский

---

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

Nature and Science of Sleep, Год журнала: 2021, Номер Volume 13, С. 177 - 190

Опубликована: Фев. 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.

Язык: Английский

---

Effect of virtual reality meditation on sleep quality of intensive care unit patients: A randomised controlled trial

Intensive and Critical Care Nursing, Год журнала: 2020, Номер 59, С. 102849 - 102849

Опубликована: Март 31, 2020

Язык: Английский

---