The Virtual Sleep Lab—A Novel Method for Accurate Four-Class Sleep Staging Using Heart-Rate Variability from Low-Cost Wearables DOI Creative Commons
Pavlos Topalidis, Dominik Philip Johannes Heib, Sebastian Baron

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(5), P. 2390 - 2390

Published: Feb. 21, 2023

Sleep staging based on polysomnography (PSG) performed by human experts is the de facto “gold standard” for objective measurement of sleep. PSG and manual sleep is, however, personnel-intensive time-consuming it thus impractical to monitor a person’s architecture over extended periods. Here, we present novel, low-cost, automatized, deep learning alternative that provides reliable epoch-by-epoch four-class approach (Wake, Light [N1 + N2], Deep, REM) solely inter-beat-interval (IBI) data. Having trained multi-resolution convolutional neural network (MCNN) IBIs 8898 full-night manually sleep-staged recordings, tested MCNN classification using two low-cost (<EUR 100) consumer wearables: an optical heart rate sensor (VS) breast belt (H10), both produced POLAR®. The overall accuracy reached levels comparable expert inter-rater reliability devices (VS: 81%, κ = 0.69; H10: 80.3%, 0.69). In addition, used H10 recorded daily ECG data from 49 participants with complaints course digital CBT-I-based training program implemented in App NUKKUAA™. As proof principle, classified extracted captured sleep-related changes. At end program, reported significant improvements subjective quality onset latency. Similarly, latency showed trend toward improvement. Weekly latency, wake time during sleep, total also correlated significantly reports. combination state-of-the-art machine suitable wearables allows continuous accurate monitoring naturalistic settings profound implications answering basic clinical research questions.

Language: Английский

The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring DOI Creative Commons
Marco Altini, Hannu Kinnunen

Sensors, Journal Year: 2021, Volume and Issue: 21(13), P. 4302 - 4302

Published: June 23, 2021

Consumer-grade sleep trackers represent a promising tool for large scale studies and health management. However, the potential limitations of these devices remain less well quantified. Addressing this issue, we aim at providing comprehensive analysis impact accelerometer, autonomic nervous system (ANS)-mediated peripheral signals, circadian features stage detection on dataset. Four hundred forty nights from 106 individuals, total 3444 h combined polysomnography (PSG) physiological data wearable ring, were acquired. Features extracted to investigate relative different streams 2-stage (sleep wake) 4-stage classification accuracy (light NREM sleep, deep REM wake). Machine learning models evaluated using 5-fold cross-validation standardized framework assessment. Accuracy (sleep, was 94% simple accelerometer-based model 96% full that included ANS-derived features. 57% 79% when including Combining compact form factor finger multidimensional biometric sensory streams, machine learning, high wake-sleep staging can be accomplished.

Language: Английский

Citations

131
Wearable Devices for Physical Monitoring of Heart: A Review DOI Creative Commons
Guillermo Prieto-Avalos, Nancy Aracely Cruz-Ramos, Giner Alor‐Hernández

et al.

Biosensors, Journal Year: 2022, Volume and Issue: 12(5), P. 292 - 292

Published: May 2, 2022

Cardiovascular diseases (CVDs) are the leading cause of death globally. An effective strategy to mitigate burden CVDs has been monitor patients' biomedical variables during daily activities with wearable technology. Nowadays, technological advance contributed wearables technology by reducing size devices, improving accuracy sensing be devices relatively low energy consumption that can manage security and privacy patient's medical information, have adaptability any data storage system, reasonable costs regard traditional scheme where patient must go a hospital for an electrocardiogram, thus contributing serious option in diagnosis treatment CVDs. In this work, we review commercial noncommercial used CVD variables. Our main findings revealed usually include smart wristbands, patches, smartwatches, they generally such as heart rate, blood oxygen saturation, electrocardiogram data. Noncommercial focus on monitoring photoplethysmography data, mostly accelerometers smartwatches detecting atrial fibrillation failure. However, using without healthy personal habits will disappointing results health.

Language: Английский

Citations

117
Multifunctional wearable humidity and pressure sensors based on biocompatible graphene/bacterial cellulose bioaerogel for wireless monitoring and early warning of sleep apnea syndrome DOI
Jingyao Sun,

Kunhao Xiu,

Ziying Wang

et al.

Nano Energy, Journal Year: 2023, Volume and Issue: 108, P. 108215 - 108215

Published: Jan. 25, 2023

Language: Английский

Citations

91
Automatic sleep staging of EEG signals: recent development, challenges, and future directions DOI Creative Commons
Huy Phan, Kaare B. Mikkelsen

Physiological Measurement, Journal Year: 2022, Volume and Issue: 43(4), P. 04TR01 - 04TR01

Published: March 23, 2022

Modern deep learning holds a great potential to transform clinical studies of human sleep. Teaching machine carry out routine tasks would be tremendous reduction in workload for clinicians. Sleep staging, fundamental step sleep practice, is suitable task this and will the focus article. Recently, automatic sleep-staging systems have been trained mimic manual scoring, leading similar performance experts, at least on scoring healthy subjects. Despite progress, we not seen adopted widely environments. This review aims provide shared view authors most recent state-of-the-art developments challenges that still need addressed, future directions needed achieve value.

Language: Английский

Citations

81
Evaluating Accuracy in Five Commercial Sleep-Tracking Devices Compared to Research-Grade Actigraphy and Polysomnography DOI Creative Commons
Kyle A. Kainec,

Jamie Caccavaro,

Morgan Barnes

et al.

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

Citations

22
Skin-inspired wearable self-powered electronic skin with tunable sensitivity for real-time monitoring of sleep quality DOI

Ouyang Yue,

Xuechuan Wang,

Mengdi Hou

et al.

Nano Energy, Journal Year: 2021, Volume and Issue: 91, P. 106682 - 106682

Published: Nov. 6, 2021

Language: Английский

Citations

61
SleepContextNet: A temporal context network for automatic sleep staging based single-channel EEG DOI
Caihong Zhao, Jinbao Li,

Yahong Guo

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2022, Volume and Issue: 220, P. 106806 - 106806

Published: April 12, 2022

Language: Английский

Citations

45
Sleep assessment using EEG-based wearables – A systematic review DOI Creative Commons
C.J. de Gans, P. C. Burger, Eva S. van den Ende

et al.

Sleep Medicine Reviews, Journal Year: 2024, Volume and Issue: 76, P. 101951 - 101951

Published: May 7, 2024

Polysomnography (PSG) is the reference standard of sleep measurement, but burdensome for participant and labor intensive. Affordable electroencephalography (EEG)-based wearables are easy to use gaining popularity, yet selecting most suitable device a challenge clinicians researchers. In this systematic review, we aim provide comprehensive overview available EEG-based measure human sleep. For each wearable, an will be provided regarding validated population reported measurement properties. A search was conducted in databases OVID MEDLINE, Embase.com CINAHL. machine learning algorithm (ASReview) utilized screen titles abstracts eligibility. total, 60 papers were selected, covering 34 unique wearables. Feasibility studies indicated good tolerance, high compliance, success rates. The 42 included validation across diverse populations showed consistently accuracy staging detection. Therefore, recent advancements show great promise as alternative PSG at-home monitoring. Users should consider factors like user-friendliness, comfort, costs, these devices vary features pricing, impacting their suitability individual needs.

Language: Английский

Citations

13
Artificial intelligence and sleep: Advancing sleep medicine DOI
Nathaniel F. Watson, Christopher R. Fernandez

Sleep Medicine Reviews, Journal Year: 2021, Volume and Issue: 59, P. 101512 - 101512

Published: June 2, 2021

Language: Английский

Citations

51
Methodologies and Wearable Devices to Monitor Biophysical Parameters Related to Sleep Dysfunctions: An Overview DOI Creative Commons
Roberto De Fazio, Veronica Mattei, Bassam Al‐Naami

et al.

Micromachines, Journal Year: 2022, Volume and Issue: 13(8), P. 1335 - 1335

Published: Aug. 17, 2022

Sleep is crucial for human health from metabolic, mental, emotional, and social points of view; obtaining good sleep in terms quality duration fundamental maintaining a life quality. Over the years, several systems have been proposed scientific literature on market to derive metrics used quantify as well detect disturbances disorders. In this field, wearable an important role discreet, accurate, long-term detection biophysical markers useful determine This paper presents current state-of-the-art software tools staging detecting disorders dysfunctions. At first, discusses sleep's functions importance monitoring eventual disturbance Afterward, overview prototype commercial headband-like devices monitor presented, both reported market, allowing unobtrusive accurate markers. Furthermore, survey works related effect COVID-19 pandemic functions, attributable infection lifestyle changes. addition, algorithms introduced based analysis single or multiple biosignals (EEG-electroencephalography, ECG-electrocardiography, EMG-electromyography, EOG-electrooculography, etc.). Lastly, comparative analyses insights are provided future trends systems.

Language: Английский

Citations

35