Wearable Artificial Intelligence for Sleep Disorders: Scoping Review (Preprint) DOI
Sarah Aziz, A. Ali, Hania Aslam

et al.

Published: Aug. 11, 2024

BACKGROUND Worldwide, 30%-45% of adults have sleep disorders, which are linked to major health issues such as diabetes and cardiovascular disease. Long-term monitoring with traditional in-lab testing is impractical due high costs. Wearable artificial intelligence (AI)–powered solutions offer accessible, scalable, continuous monitoring, improving the identification treatment problems. OBJECTIVE This scoping review aims provide an overview AI-powered wearable devices used for focusing on study characteristics, technology features, AI methodologies detection analysis. METHODS Seven electronic databases (MEDLINE, PsycINFO, Embase, IEEE Xplore, ACM Digital Library, Google Scholar, Scopus) were searched peer-reviewed literature published before March 2024. Keywords selected based 3 domains: AI, devices. The primary selection criterion was inclusion studies that utilized algorithms detect or predict various disorders using data from Study conducted in 2 steps: first, by reviewing titles abstracts, followed full-text screening. Two reviewers independently extraction, resolving discrepancies consensus. extracted synthesized a narrative approach. RESULTS initial search yielded 615 articles, 46 met eligibility criteria included final majority focused apnea. widely deployed diagnosing screening disorders; however, none it treatment. Commercial most commonly type technology, appearing 30 out (65%) studies. Among these, brands rather than single large, well-known brand; 19 (41%) wrist-worn Respiratory 25 (54%) model development, heart rate (22/46, 48%) body movement (17/46, 37%). popular algorithm convolutional neural network, adopted 17 (37%) studies, random forest (14/46, 30%) support vector machines (12/46, 26%). CONCLUSIONS offers promising disorders. These can be diagnosis; research other apnea remains limited. To statistically synthesize performance efficacy results, more reviews needed. Technology companies should prioritize advancements deep learning invest treating given its potential. Further necessary validate machine techniques clinical develop useful analytics collection, prediction, classification, recommendation context

Language: Английский

Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice DOI Creative Commons
Huijun Yue, Zhuqi Chen, Wenbin Guo

et al.

Sleep Medicine Reviews, Journal Year: 2024, Volume and Issue: 74, P. 101897 - 101897

Published: Jan. 11, 2024

Over the past few decades, researchers have attempted to simplify and accelerate process of sleep stage classification through various approaches; however, only a such approaches gained widespread acceptance. Artificial intelligence technology, particularly deep learning, is promising for earning trust medicine community in automated sleep-staging systems, thus facilitating its application clinical practice integration into daily life. We aimed comprehensively review latest methods that are applying learning enhancing staging efficiency accuracy. Starting from requisite "data" constructing algorithms, we elucidated current landscape this domain summarized fundamental modeling process, encompassing signal selection, data pre-processing, model architecture, tasks, performance metrics. Furthermore, reviewed applications scenarios as sleep-disorder screening, diagnostic procedures, health monitoring management. Finally, conducted an in-depth analysis discussion challenges future intelligent staging, focusing on large-scale datasets, interdisciplinary collaborations, human-computer interactions.

Language: Английский

Citations

17
Detection of Sleep Apnea Using Wearable AI: Systematic Review and Meta-Analysis DOI Creative Commons
Alaa Abd‐Alrazaq, Hania Aslam, Rawan AlSaad

et al.

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e58187 - e58187

Published: Sept. 10, 2024

Early detection of sleep apnea, the health condition where airflow either ceases or decreases episodically during sleep, is crucial to initiate timely interventions and avoid complications. Wearable artificial intelligence (AI), integration AI algorithms into wearable devices collect analyze data offer various functionalities insights, can efficiently detect apnea due its convenience, accessibility, affordability, objectivity, real-time monitoring capabilities, thereby addressing limitations traditional approaches such as polysomnography.

Language: Английский

Citations

9
Diagnostic Modalities in Sleep Disordered Breathing: Current and Emerging Technology and Its Potential to Transform Diagnostics DOI Creative Commons
Lucía Pinilla, Ching Li Chai‐Coetzer, Danny J. Eckert

et al.

Respirology, Journal Year: 2025, Volume and Issue: unknown

Published: March 3, 2025

ABSTRACT Underpinned by rigorous clinical trial data, the use of existing home sleep apnoea testing is now commonly employed for disordered breathing diagnostics in most centres globally. This has been a welcome addition field given considerable burden disease, cost, and access limitations with in‐laboratory polysomnography testing. However, approaches predominantly aim to replicate elements conventional different forms focus on estimation apnoea‐hypopnoea index. New, simplified technology screening, detection/diagnosis, or monitoring expanded exponentially recent years. Emerging innovations go beyond simple single‐night replication varying numbers signals setting. These novel have potential provide important new insights overcome many transform disease diagnosis management improve outcomes patients. Accordingly, current review summarises evidence study people suspected sleep‐related disorders, discusses emerging technologies according three key categories: (1) wearables (e.g., body‐worn sensors including wrist finger sensors), (2) nearables bed‐embedded bedside (3) airables audio video recordings), outlines their disruptive role care.

Language: Английский

Citations

1
Novel Wearable Devices for Screening Obstructive Sleep Apnea DOI Creative Commons
Kaustav Kundu, Lokesh Kumar Saini

Sleep and Vigilance, Journal Year: 2024, Volume and Issue: 8(1), P. 1 - 2

Published: June 13, 2024

Language: Английский

Citations

4
OSA diagnosis goes wearable: are the latest devices ready to shine? DOI
Ambrose Chiang,

Evin Jerkins,

Steven Holfinger

et al.

Journal of Clinical Sleep Medicine, Journal Year: 2024, Volume and Issue: 20(11), P. 1823 - 1838

Published: Aug. 12, 2024

From 2019-2023, the United States Food and Drug Administration has cleared 9 novel obstructive sleep apnea-detecting wearables for home apnea testing, with many now commercially available clinicians to integrate into their clinical practices. To help comprehend these devices functionalities, we meticulously reviewed operating mechanisms, sensors, algorithms, data output, related performance evaluation literature.

Language: Английский

Citations

4
OSASformer: A transformer-based model for OSAS screening via multi-source representation fusion DOI
Yuanyuan Hou, Bin Wang, Chengxi Zhang

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113365 - 113365

Published: March 1, 2025

Language: Английский

Citations

0
Exploring nightly variability and clinical influences on sleep measures: insights from a digital brain health platform DOI
Huitong Ding,

Sanskruti Madan,

Edward Searls

et al.

Sleep Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 106532 - 106532

Published: April 1, 2025

Language: Английский

Citations

0
Wearable Sensors and Artificial Intelligence for Sleep Apnea Detection: A Systematic Review DOI Creative Commons
Ainhoa Osa-Sanchez,

Javier Ramos-Martinez-de-Soria,

Amaia Méndez Zorrilla

et al.

Journal of Medical Systems, Journal Year: 2025, Volume and Issue: 49(1)

Published: May 19, 2025

Language: Английский

Citations

0
Wearable Artificial Intelligence for Sleep Disorders: Scoping Review DOI Creative Commons
Sarah Aziz, A. Ali, Hania Aslam

et al.

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e65272 - e65272

Published: May 6, 2025

Background Worldwide, 30%-45% of adults have sleep disorders, which are linked to major health issues such as diabetes and cardiovascular disease. Long-term monitoring with traditional in-lab testing is impractical due high costs. Wearable artificial intelligence (AI)–powered solutions offer accessible, scalable, continuous monitoring, improving the identification treatment problems. Objective This scoping review aims provide an overview AI-powered wearable devices used for focusing on study characteristics, technology features, AI methodologies detection analysis. Methods Seven electronic databases (MEDLINE, PsycINFO, Embase, IEEE Xplore, ACM Digital Library, Google Scholar, Scopus) were searched peer-reviewed literature published before March 2024. Keywords selected based 3 domains: AI, devices. The primary selection criterion was inclusion studies that utilized algorithms detect or predict various disorders using data from Study conducted in 2 steps: first, by reviewing titles abstracts, followed full-text screening. Two reviewers independently extraction, resolving discrepancies consensus. extracted synthesized a narrative approach. Results initial search yielded 615 articles, 46 met eligibility criteria included final majority focused apnea. widely deployed diagnosing screening disorders; however, none it treatment. Commercial most commonly type technology, appearing 30 out (65%) studies. Among these, brands rather than single large, well-known brand; 19 (41%) wrist-worn Respiratory 25 (54%) model development, heart rate (22/46, 48%) body movement (17/46, 37%). popular algorithm convolutional neural network, adopted 17 (37%) studies, random forest (14/46, 30%) support vector machines (12/46, 26%). Conclusions offers promising disorders. These can be diagnosis; research other apnea remains limited. To statistically synthesize performance efficacy results, more reviews needed. Technology companies should prioritize advancements deep learning invest treating given its potential. Further necessary validate machine techniques clinical develop useful analytics collection, prediction, classification, recommendation context

Language: Английский

Citations

0
Enhancing artificial intelligence‐driven sleep apnea diagnosis: The critical importance of input signal proficiency with a focus on mandibular jaw movements DOI Open Access
Jean‐Benoît Martinot,

Nhat‐Nam Le‐Dong,

Atul Malhotra

et al.

Journal of Prosthodontics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 15, 2024

This review aims to highlight the pivotal role of mandibular jaw movement (MJM) signal in advancing artificial intelligence (AI)-powered technologies for diagnosing obstructive sleep apnea (OSA).

Language: Английский

Citations

1