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.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 2, 2024

Abstract Sleep apnea, a prevalent disorder affecting millions of people worldwide, has attracted increasing attention in recent years due to its significant impact on public health and quality life. The integration wearable devices artificial intelligence technologies revolutionized the treatment diagnosis sleep apnea. Leveraging portability sensors devices, coupled with AI algorithms, enabled real-time monitoring accurate analysis patterns, facilitating early detection personalized interventions for suffering from This review articles presents systematic current state art identifying latest techniques, data types, preprocessing methods employed Four databases were used results before screening report 249 studies published between 2020 2024. After screening, 28 met inclusion criteria. reveals trend where methodologies involving patches, clocks rings have been increasingly integrated convolutional neural networks, producing promising results, particularly when combined transfer learning techniques. We observed that outcomes various algorithms their combinations also rely quantity type utilized training. findings suggest employing multiple different networks layers contributes development more precise system

Language: Английский

A review of automated sleep stage based on EEG signals DOI

Xiaoli Zhang,

Xizhen Zhang, Qiong Huang

et al.

Journal of Applied Biomedicine, Journal Year: 2024, Volume and Issue: 44(3), P. 651 - 673

Published: June 29, 2024

Language: Английский

Citations

9
Hypnogram and Hypnodensity Analysis of REM Sleep Behaviour Disorder Using Both EEG and HRV‐Based Sleep Staging Models DOI Creative Commons
Jaap F. van der Aar, Merel M. van Gilst, Daan van den Ende

et al.

Journal of Sleep Research, Journal Year: 2025, Volume and Issue: unknown

Published: March 12, 2025

ABSTRACT Rapid‐eye‐movement (REM) sleep behaviour disorder (RBD) is a primary strongly associated with Parkinson's disease. Assessing structure in RBD important for understanding the underlying pathophysiology and developing diagnostic methods. However, performance of automated stage classification (ASSC) models considered suboptimal RBD, both utilising neurological signals (“ExG”: EEG, EOG, chin EMG) heart rate variability combined body movements (HRVm). Here, we explore this underperformance through categorical representation macrostructure (i.e., hypnogram) that leverages probability distribution ASSCs hypnodensity). By comparing population ( n = 36) to sex‐ age‐matched group OSA patients chosen their anticipated similarly decreased stability, confirm lower 4‐stage ExG‐based ASSC (RBD: κ 0.74, OSA: 0.80) HRVm‐based 0.50, 0.63). Stages showing agreement namely, N1 + N2 REM sleep, exhibited elevated ambiguity hypnodensity, indicating more ambiguous distributions. Limited differences bout durations between suggested instability not necessarily driving RBD. transitions showed abrupt changes distribution, while had continuous profile, possibly complicating classification. Although staging remain challenging, hypnodensity analysis informative characterisation can capture potential drivers disagreement.

Language: Английский

Citations

0
About Digitalisation and AI, Data Protection, Data Exchange, Data Mining—Legal Constraints/Challenges Concerning Sleep Medicine DOI Creative Commons
Bernd Feige, Fee Benz, Raphael J. Dressle

et al.

Journal of Sleep Research, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

ABSTRACT The revolution of artificial intelligence (AI) methods in the scope last years has inspired a deluge use cases but also caused uncertainty about actual utility and boundaries these methods. In this overview, we briefly introduce their main characteristics before focusing on sleep medicine, discriminating four areas: Measuring state, advancing diagnostics, research general advances. We then outline current European legal framework AI related topic data sharing.

Language: Английский

Citations

0
Single-channel EOG sleep staging on a heterogeneous cohort of subjects with sleep disorders DOI Creative Commons
Hans van Gorp, Merel M. van Gilst, Sebastiaan Overeem

et al.

Physiological Measurement, Journal Year: 2024, Volume and Issue: 45(5), P. 055007 - 055007

Published: April 23, 2024

Sleep staging based on full polysomnography is the gold standard in diagnosis of many sleep disorders. It however costly, complex, and obtrusive due to use multiple electrodes. Automatic single-channel electro-oculography (EOG) a promising alternative, requiring fewer electrodes which could be self-applied below hairline. EOG algorithms are yet validated clinical populations with

Language: Английский

Citations

2
Refining sleep staging accuracy: transfer learning coupled with scorability models DOI
Wolfgang Ganglberger, Samaneh Nasiri, Haoqi Sun

et al.

SLEEP, Journal Year: 2024, Volume and Issue: 47(11)

Published: Aug. 31, 2024

Abstract Study Objectives This study aimed to (1) improve sleep staging accuracy through transfer learning (TL), achieve or exceed human inter-expert agreement and (2) introduce a scorability model assess the quality trustworthiness of automated staging. Methods A deep neural network (base model) was trained on large multi-site polysomnography (PSG) dataset from United States. TL used calibrate reduced montage limited samples Korean Genome Epidemiology (KoGES) dataset. Model performance compared reliability among three experts. assessment developed predict between Results Initial by base showed lower with experts (κ = 0.55) 0.62). Calibration 324 randomly sampled training cases matched expert levels. Further targeted sampling improved performance, models exceeding 0.70). The assessment, combining biosignal confidence features, predicted model-expert moderately well (R² 0.42). Recordings higher scores demonstrated greater than agreement. Even scores, comparable Conclusions Fine-tuning pretrained significantly enhances for an atypical montage, achieving surpassing introduction provides robust measure reliability, ensuring control enhancing practical application system before deployment. approach marks important advancement in analysis, demonstrating potential AI clinical settings.

Language: Английский

Citations

2
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.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 2, 2024

Abstract Sleep apnea, a prevalent disorder affecting millions of people worldwide, has attracted increasing attention in recent years due to its significant impact on public health and quality life. The integration wearable devices artificial intelligence technologies revolutionized the treatment diagnosis sleep apnea. Leveraging portability sensors devices, coupled with AI algorithms, enabled real-time monitoring accurate analysis patterns, facilitating early detection personalized interventions for suffering from This review articles presents systematic current state art identifying latest techniques, data types, preprocessing methods employed Four databases were used results before screening report 249 studies published between 2020 2024. After screening, 28 met inclusion criteria. reveals trend where methodologies involving patches, clocks rings have been increasingly integrated convolutional neural networks, producing promising results, particularly when combined transfer learning techniques. We observed that outcomes various algorithms their combinations also rely quantity type utilized training. findings suggest employing multiple different networks layers contributes development more precise system

Language: Английский

Citations

0