Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders

Abstract Obstructive sleep apnea (OSA) and related hypoxia are well-established cardiovascular and neurocognitive risk factors. Current multi-sensor diagnostic approaches are intrusive and prone to misdiagnosis when simplified. This study introduces an enhanced single-sensor-based OSA screening meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoman Xing, Sizhi Ai, Jihui Zhang, Rui Huang, Yaping Liu, Dongming Quan, Jiacheng Ma, Guoli Wu, Jiangen Xu, Yuan Zhang, Hongliang Feng, Wen-fei Dong
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01430-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731831309533184
author Xiaoman Xing
Sizhi Ai
Jihui Zhang
Rui Huang
Yaping Liu
Dongming Quan
Jiacheng Ma
Guoli Wu
Jiangen Xu
Yuan Zhang
Hongliang Feng
Wen-fei Dong
author_facet Xiaoman Xing
Sizhi Ai
Jihui Zhang
Rui Huang
Yaping Liu
Dongming Quan
Jiacheng Ma
Guoli Wu
Jiangen Xu
Yuan Zhang
Hongliang Feng
Wen-fei Dong
author_sort Xiaoman Xing
collection DOAJ
description Abstract Obstructive sleep apnea (OSA) and related hypoxia are well-established cardiovascular and neurocognitive risk factors. Current multi-sensor diagnostic approaches are intrusive and prone to misdiagnosis when simplified. This study introduces an enhanced single-sensor-based OSA screening method, leveraging novel signal processing and machine learning to ensure accurate detection across diverse populations. Wrist actigraphy is a widely-used and energy-efficient tool for respiratory rate estimation. The main challenge in OSA pattern recognition is handling various disturbances in real-world applications. We developed a novel approach combining apex-centric tokenization with a Multi-Head Causal Attention (MHCA) mechanism. Apex-centric tokenization enhances sensitivity to OSA events, while MHCA refines predictions and increases specificity in detecting oxygen desaturation. Our study involved 58 participants, with overnight bilateral wrist actigraphy and concurrent polysomnography used as a reference for thorough analysis. By focusing on the physiological causal relationship of the events, the algorithm excelled in detecting moderate to severe oxygen desaturation, achieving a sensitivity of 85.7% and a specificity of 98.1%, even in the presence of disturbances such as restless leg movements and snoring. The estimated oxygen desaturation index correlated strongly with clinical standards (r = 0.89), and the correlation with the apnea-hypopnea index was 0.87. Both apex-centric tokenization and MHCA were crucial for this performance. Our approach shows potential for analyzing apnea patterns and related oxygen desaturation in a broader population using only wrist actigraphy, reducing measurement burdens and improving understanding of complex sleep disorders.
format Article
id doaj-art-dd5d0402f10e48b49c38d99a7f8ebf6e
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-dd5d0402f10e48b49c38d99a7f8ebf6e2025-08-20T03:08:25ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-01430-3Apnea detection using wrist actigraphy in patients with heterogeneous sleep disordersXiaoman Xing0Sizhi Ai1Jihui Zhang2Rui Huang3Yaping Liu4Dongming Quan5Jiacheng Ma6Guoli Wu7Jiangen Xu8Yuan Zhang9Hongliang Feng10Wen-fei Dong11Division of Life Sciences and Medicine, School of Biomedical Engineering (Suzhou), University of Science and Technology of ChinaCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversityCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversitySuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of SciencesCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversityGuangdong Mental Health Center, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical UniversityCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversityCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversitySuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of SciencesDepartment of Respiratory Medicine, Xiangya Hospital, Central South UniversityCenter for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical UniversitySuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of SciencesAbstract Obstructive sleep apnea (OSA) and related hypoxia are well-established cardiovascular and neurocognitive risk factors. Current multi-sensor diagnostic approaches are intrusive and prone to misdiagnosis when simplified. This study introduces an enhanced single-sensor-based OSA screening method, leveraging novel signal processing and machine learning to ensure accurate detection across diverse populations. Wrist actigraphy is a widely-used and energy-efficient tool for respiratory rate estimation. The main challenge in OSA pattern recognition is handling various disturbances in real-world applications. We developed a novel approach combining apex-centric tokenization with a Multi-Head Causal Attention (MHCA) mechanism. Apex-centric tokenization enhances sensitivity to OSA events, while MHCA refines predictions and increases specificity in detecting oxygen desaturation. Our study involved 58 participants, with overnight bilateral wrist actigraphy and concurrent polysomnography used as a reference for thorough analysis. By focusing on the physiological causal relationship of the events, the algorithm excelled in detecting moderate to severe oxygen desaturation, achieving a sensitivity of 85.7% and a specificity of 98.1%, even in the presence of disturbances such as restless leg movements and snoring. The estimated oxygen desaturation index correlated strongly with clinical standards (r = 0.89), and the correlation with the apnea-hypopnea index was 0.87. Both apex-centric tokenization and MHCA were crucial for this performance. Our approach shows potential for analyzing apnea patterns and related oxygen desaturation in a broader population using only wrist actigraphy, reducing measurement burdens and improving understanding of complex sleep disorders.https://doi.org/10.1038/s41598-025-01430-3Wrist actigraphyApneaOxygen desaturationTokenizationMulti-head causal attention
spellingShingle Xiaoman Xing
Sizhi Ai
Jihui Zhang
Rui Huang
Yaping Liu
Dongming Quan
Jiacheng Ma
Guoli Wu
Jiangen Xu
Yuan Zhang
Hongliang Feng
Wen-fei Dong
Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
Scientific Reports
Wrist actigraphy
Apnea
Oxygen desaturation
Tokenization
Multi-head causal attention
title Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
title_full Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
title_fullStr Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
title_full_unstemmed Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
title_short Apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
title_sort apnea detection using wrist actigraphy in patients with heterogeneous sleep disorders
topic Wrist actigraphy
Apnea
Oxygen desaturation
Tokenization
Multi-head causal attention
url https://doi.org/10.1038/s41598-025-01430-3
work_keys_str_mv AT xiaomanxing apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT sizhiai apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT jihuizhang apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT ruihuang apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT yapingliu apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT dongmingquan apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT jiachengma apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT guoliwu apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT jiangenxu apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT yuanzhang apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT hongliangfeng apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders
AT wenfeidong apneadetectionusingwristactigraphyinpatientswithheterogeneoussleepdisorders