Sleep apnea detection based on universal wristband

doi:10.11772/j.issn.1001-9081.2024081234

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 3045-3056.DOI: 10.11772/j.issn.1001-9081.2024081234

• Frontier and comprehensive applications • Previous Articles

Sleep apnea detection based on universal wristband

Jinyang HUANG¹^,², Fengqi CUI²^,³^,⁴, Changxiu MA⁵, Wendong FAN¹, Meng LI¹(), Jingyu LI⁴, Xiao SUN¹^,²^,⁴, Linsheng HUANG⁶, Zhi LIU⁷

^1.School of Computer Science and Information Engineering，Hefei University of Technology，Hefei Anhui 230601，China
^2.Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine （Hefei University of Technology），Hefei Anhui 230601，China
^3.Institute of Advanced Technology，University of Science and Technology of China，Hefei Anhui 230031，China
^4.Institute of Artificial Intelligence Research，Hefei Comprehensive National Science Center （Anhui Artificial Intelligence Laboratory），Hefei Anhui 230088，China
^5.Department of Respiratory and Critical Care Medicine，The Second Hospital of Anhui Medical University，Hefei Anhui 230601，China
^6.School of Internet，Anhui University，Hefei Anhui 230039，China
^7.The University of Electro-Communications，Tokyo 182-8585，Japan

Received:2024-09-02 Revised:2024-11-14 Accepted:2024-11-19 Online:2024-11-25 Published:2025-09-10
Contact: Meng LI
About author:HUANG Jinyang， born in 1994， Ph. D.， lecturer. His research interests include multimodal human factor perception， artificial intelligence.
CUI Fengqi， born in 2001， M. S. candidate. His research interests include affective computing， artificial intelligence.
MA Changxiu， born in 1980， Ph. D.， chief physician. Her research interests include sleep apnea， respiratory rehabilitation.
FAN Wendong， born in 1998， M. S. His research interests include multimodal human factor perception， machine learning.
LI Jingyu， born in 1995， Ph. D.， associate research fellow. His research interests include artificial intelligence.
SUN Xiao， born in 1980， Ph. D.， professor. His research interests include multimodal human factor perception， natural language processing， face recognition.
HUANG Linsheng， born in 1977， Ph. D.， professor. His research interests include image processing， artificial intelligence.
LIU Zhi， born in 1986， Ph. D.， associate professor. His research interests include multimedia information processing.
Supported by:
National Natural Science Foundation of China(62302145);Major Scientific and Technological Project of Anhui Provincial Science and Technology Innovation Platform(202305a12020012)

基于通用手环的睡眠呼吸暂停检测

黄锦阳¹^,², 崔丰麒²^,³^,⁴, 马长秀⁵, 樊文东¹, 李萌¹(), 李经宇⁴, 孙晓¹^,²^,⁴, 黄林生⁶, 刘志⁷

^1.合肥工业大学计算机与信息学院，合肥 230601
^2.情感计算与先进智能机器安徽省重点实验室（合肥工业大学），合肥 230601
^3.中国科学技术大学先进技术研究院，合肥 230031
^4.合肥综合性国家科学中心人工智能研究院（安徽省人工智能实验室），合肥 230088
^5.安徽医科大学第二附属医院呼吸与危重症医学科，合肥 230601
^6.安徽大学互联网学院，合肥 230039
^7.电气通信大学，东京 182-8585，日本

通讯作者: 李萌
作者简介:黄锦阳（1994—），男，安徽安庆人，讲师，博士，CCF会员，主要研究方向：多模态人因感知、人工智能
崔丰麒（2001—），男，山东烟台人，硕士研究生，CCF会员，主要研究方向：情感计算、人工智能
马长秀（1980—），女，安徽蚌埠人，主任医师，博士，主要研究方向：睡眠呼吸暂停、呼吸康复
樊文东（1998—），男，山东德州人，硕士，主要研究方向：多模态人因感知、机器学习
李经宇（1995—），男，安徽淮北人，副研究员，博士，主要研究方向：人工智能
孙晓（1980—），男，山东烟台人，教授，博士，CCF会员，主要研究方向：多模态人因感知、自然语言处理、人脸识别
黄林生（1977—），男，安徽安庆人，教授，博士，CCF会员，主要研究方向：图像处理、人工智能
刘志（1986—），男，河北衡水人，副教授，博士，CCF会员，主要研究方向：多媒体信息处理。
基金资助:
国家自然科学基金资助项目(62302145);安徽省科技创新平台重大科技项目(202305a12020012)

Abstract

Abstract:

Sleep apnea affects quality of life and health seriously. PolySomnoGraphy （PSG） is the “gold standard” for diagnosis of sleep apnea， but it is expensive and inconvenient for long-term monitoring. Based on the above， a new method based on universal smart wristband was proposed to detect sleep apnea conveniently. In the method， by analyzing heart rate， blood oxygen saturation， and sleep state data collected by the wristband， an adaptive physiological data reconstruction method and a data interpolation method were used to achieve noise filtering； in feature engineering， continuous physiological variables and categorical variables were fused to extract sleep state features deeply； in the classification module， a lightweight Gated Recurrent Unit （GRU） model was used to simplify the training process and reduce the risk of overfitting. Experimental results show that the proposed method obtains 93.68% accuracy and 93.97% recall on a 23-person dataset. Correlation analysis shows that blood oxygen saturation， body mass index， and age are confirmed as key features for sleep apnea detection. Compared with PSG， the proposed method is more suitable for long-term monitoring in a home environment.

Key words: sleep apnea detection, universal wristband, multimodal data processing, long-term health monitoring, analysis of multi-factor impact indicators

摘要：

睡眠呼吸暂停严重影响生活质量和健康。多导睡眠图（PSG）是诊断睡眠呼吸暂停的“金标准”，然而它的成本高且不便长期监测。基于此，提出一种基于通用运动手环的新方法以便捷地检测睡眠呼吸暂停。该方法通过分析手环采集的心率、血氧饱和度和睡眠状态数据，采用自适应生理数据重构方法和数据插值方法滤除噪声；在特征工程中，融合连续生理变量和类别变量，以深度提取睡眠状态特征；而分类模块采用轻量级门控循环单元（GRU）模型，从而简化训练过程，并降低过拟合风险。实验结果表明，所提方法在23人数据集上获得了93.68%的准确率和93.97%的召回率。相关性分析表明，血氧饱和度、身体质量指数和年龄是判断睡眠呼吸暂停的关键特征。与PSG相比，所提方法更适用于家庭环境下的长期监测。

关键词: 睡眠呼吸暂停检测, 通用手环, 多模态数据处理, 长时健康监测, 多因素影响指标分析

CLC Number:

TP391

Jinyang HUANG, Fengqi CUI, Changxiu MA, Wendong FAN, Meng LI, Jingyu LI, Xiao SUN, Linsheng HUANG, Zhi LIU. Sleep apnea detection based on universal wristband[J]. Journal of Computer Applications, 2025, 45(9): 3045-3056.

黄锦阳, 崔丰麒, 马长秀, 樊文东, 李萌, 李经宇, 孙晓, 黄林生, 刘志. 基于通用手环的睡眠呼吸暂停检测[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 3045-3056.

Figures/Tables 11

References 28

[1]	吕建行，李玉榕，陈建国，等. 两步式自适应阈值法滤除心电信号中运动伪迹［J］. 电子学报， 2024， 52（10）： 3493-3506.
	LYU J H， LI Y R， CHEN J G， et al. ECG motion artifact filtering based on two-stage adaptive threshold rules ［J］. Acta Electronica Sinica， 2024， 52（10）： 3493-3506.
[2]	TYAGI P K， AGRAWAL D. Automatic detection of sleep apnea from a single-lead ECG signal based on spiking neural network model ［J］. Computers in Biology and Medicine， 2024， 179： No.108877.
[3]	赵津，宋文爱，邰隽，等. 儿童阻塞性睡眠呼吸暂停计算机人脸辅助诊断综述［J］. 计算机应用， 2021， 41（11）： 3394-3401.
	ZHAO J， SONG W A， TAI J， et al. Review of computer-aided face diagnosis for obstructive sleep apnea in children ［J］. Journal of Computer Applications， 2021， 41（11）： 3394-3401.
[4]	LIN Y， WU Y， LIN Q， et al. Objective sleep duration and all-cause mortality among people with obstructive sleep apnea ［J］. JAMA Network Open， 2023， 6（12）： No.e2346085.
[5]	GUPTA K， BAJAJ V， ANSARI I A. OSACN-Net： automated classification of sleep apnea using deep learning model and smoothed Gabor spectrograms of ECG signal ［J］. IEEE Transactions on Instrumentation and Measurement， 2022， 71： No.4002109.
[6]	AZIMI H， BOUCHARD M， GOUBRAN R， et al. Unobtrusive screening of central sleep apnea from pressure sensors measurements： a patient-specific longitudinal study ［J］. IEEE Transactions on Instrumentation and Measurement， 2020， 69（6）： 3282-3296.
[7]	THORNTON C S， TSAI W H， SANTANA M J， et al. Effects of wait times on treatment adherence and clinical outcomes in patients with severe sleep-disordered breathing： a secondary analysis of a noninferiority randomized clinical trial ［J］. JAMA Network Open， 2020， 3（4）： No.e203088.
[8]	BAHRAMI M， FOROUZANFAR M. Sleep apnea detection from single-lead ECG： a comprehensive analysis of machine learning and deep learning algorithms ［J］. IEEE Transactions on Instrumentation and Measurement， 2022， 71： No.4003011.
[9]	FENG K， QIN H， WU S， et al. A sleep apnea detection method based on unsupervised feature learning and single-lead electrocardiogram ［J］. IEEE Transactions on Instrumentation and Measurement， 2021， 70： No.4000912.
[10]	LEE P， CHANDEL N S， SIMON M C. Cellular adaptation to hypoxia through hypoxia inducible factors and beyond ［J］. Nature Reviews Molecular Cell Biology， 2020， 21（5）： 268-283.
[11]	WEN D， ZHANG X， LEI J. Consumers’ perceived attitudes to wearable devices in health monitoring in China： a survey study［J］. Computer Methods and Programs in Biomedicine， 2017， 140： 131-137.
[12]	ÁLVAREZ D， CEREZO-HERNÁNDEZ A， CRESPO A， et al. A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow ［J］. Scientific Reports， 2020， 10： No.5332.
[13]	YOOK S， KIM D， GUPTE C， et al. Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity ［J］. Sleep Medicine， 2024， 114： 211-219.
[14]	HU S， WANG Y， LIU J， et al. Semi-supervised learning for low-cost personalized obstructive sleep apnea detection using unsupervised deep learning and single-lead electrocardiogram ［J］. IEEE Journal of Biomedical and Health Informatics， 2023， 27（11）： 5281-5292.
[15]	YÜCELBAŞ Ş， YÜCELBAŞ C， TEZEL G， et al. Identification of full-night sleep parameters using morphological features of ECG signals： a practical alternative to EEG and EOG signals ［J］. Biomedical Signal Processing and Control， 2024， 88： No.105633.
[16]	VAQUERIZO-VILLAR F， GUTIÉRREZ-TOBAL G C， CALVO E， et al. An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea［J］. Computers in Biology and Medicine， 2023， 165： No.107419.
[17]	宋钰丹，王晶，王雪徽，等. 基于自适应多任务学习的睡眠生理时序分类方法［J］. 计算机应用， 2024， 44（2）： 654-662.
	SONG Y D， WANG J， WANG X H， et al. Sleep physiological time series classification method based on adaptive multi-task learning ［J］. Journal of Computer Applications， 2024， 44（2）： 654-662.
[18]	FURLOTTI G. Obstructive sleep apnea detection： exploring neural activity variations through statistical analysis and machine learning ［D］. Turin： Politecnico di Torino， 2023.
[19]	TRAN T D L， NGUYEN T H T， LIN S Y， et al. Late breaking abstract-detecting sleep apnea in advance using machine learning and ECG-deprived spectrogram during CPAP titration ［J］. European Respiratory Journal， 2023， 62（S67）： No.PA1288.
[20]	HUANG J， LIU B， MIAO C， et al. PhyFinAtt： an undetectable attack framework against PHY layer fingerprint-based WiFi authentication ［J］. IEEE Transactions on Mobile Computing， 2024， 23（7）： 7753-7770.
[21]	ABD-ALRAZAQ A， ASLAM H， ALSAAD R， et al. Detection of sleep apnea using wearable AI： systematic review and meta-analysis ［J］. Journal of Medical Internet Research， 2024， 26： No.e58187.
[22]	PILLAR G， BERALL M， BERRY R B， et al. Detection of common arrhythmias by the Watch-PAT： expression of electrical arrhythmias by pulse recording ［J］. Nature and Science of Sleep， 2022， 14： 751-763.
[23]	ZHANG Z， SOWHO M， OTVOS T， et al. A comparison of automated and manual sleep staging and respiratory event recognition in a portable sleep diagnostic device with in-lab sleep study ［J］. Journal of Clinical Sleep Medicine， 2020， 16（4）： 563-573.
[24]	BROWN J， YAZDI F T， JODARI-KARIMI M， et al. Obstructive sleep apnea and hypertension： updates to a critical relationship［J］. Current Hypertension Reports， 2022， 24（6）： 173-184.
[25]	CHEN Y， WANG W， GUO Y， et al. A single-center validation of the accuracy of a photoplethysmography-based smartwatch for screening obstructive sleep apnea ［J］. Nature and Science of Sleep， 2021： 1533-1544.
[26]	HUANG J， LIU B， MIAO C， et al. PhaseAnti： an anti-interference WiFi-based activity recognition system using interference-independent phase component ［J］. IEEE Transactions on Mobile Computing， 2023， 22（5）： 2938-2954.
[27]	PENZEL T， MOODY G B， MARK R G， et al. The apnea-ECG database ［C］// Proceedings of the Computers in Cardiology 2000. Piscataway： IEEE， 2000： 255-258.
[28]	O’REILLY C， GOSSELIN N， CARRIER J， et al. Montreal archive of sleep studies： an open-access resource for instrument benchmarking and exploratory research ［J］. Journal of Sleep Research， 2014， 23（6）： 628-635.

start_time	end_time	SPO₂	BPM	sleep_stage	PSG
1705413120	1705413180	95	72	a	0
1705413240	1705413300	94	75	b	0
1705413360	1705413420	92	78	a	1
1705413480	1705413540	90	82	c	2
1705413600	1705413660	94	74	a	0

start_time	end_time	SPO₂	BPM	sleep_stage	PSG
1705413120	1705413180	95	72	a	0
1705413240	1705413300	94	75	b	0
1705413360	1705413420	92	78	a	1
1705413480	1705413540	90	82	c	2
1705413600	1705413660	94	74	a	0

方法	准确率/%	精确率/%	召回率/%	F1/%	训练时间/min
MLR	75.38	81.37	71.02	75.88	3.9
KNN	84.73	82.92	77.59	80.11	4.1
RF	92.21	90.65	89.63	90.07	3.6
GRU	93.68	94.36	93.97	94.08	5.4
LSTM	90.33	89.21	90.54	89.74	13.4
DBN	87.43	88.12	87.44	87.99	15.2

方法	准确率/%	精确率/%	召回率/%	F1/%	训练时间/min
MLR	75.38	81.37	71.02	75.88	3.9
KNN	84.73	82.92	77.59	80.11	4.1
RF	92.21	90.65	89.63	90.07	3.6
GRU	93.68	94.36	93.97	94.08	5.4
LSTM	90.33	89.21	90.54	89.74	13.4
DBN	87.43	88.12	87.44	87.99	15.2

Sleep apnea detection based on universal wristband

基于通用手环的睡眠呼吸暂停检测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 28

Related Articles 15

Recommended Articles

Metrics

[1]	Chao SHI, Yuxin ZHOU, Qian FU, Wanyu TANG, Ling HE, Yuanyuan LI. Action recognition algorithm for ADHD patients using skeleton and 3D heatmap [J]. Journal of Computer Applications, 2025, 45(9): 3036-3044.
[2]	Zhixiong XU, Bo LI, Xiaoyong BIAN, Qiren HU. Adversarial sample embedded attention U-Net for 3D medical image segmentation [J]. Journal of Computer Applications, 2025, 45(9): 3011-3016.
[3]	Weigang LI, Jiale SHAO, Zhiqiang TIAN. Point cloud classification and segmentation network based on dual attention mechanism and multi-scale fusion [J]. Journal of Computer Applications, 2025, 45(9): 3003-3010.
[4]	Jiaxiang ZHANG, Xiaoming LI, Jiahui ZHANG. Few-shot object detection algorithm based on new category feature enhancement and metric mechanism [J]. Journal of Computer Applications, 2025, 45(9): 2984-2992.
[5]	Panfeng JING, Yudong LIANG, Chaowei LI, Junru GUO, Jinyu GUO. Semi-supervised image dehazing algorithm based on teacher-student learning [J]. Journal of Computer Applications, 2025, 45(9): 2975-2983.
[6]	Xuejin WANG, Leilei HUANG, Zhenhui ZHONG. Noise and semantic prior guided low-light image enhancement algorithm [J]. Journal of Computer Applications, 2025, 45(9): 2966-2974.
[7]	Jin LI, Liqun LIU. SAR and visible image fusion based on residual Swin Transformer [J]. Journal of Computer Applications, 2025, 45(9): 2949-2956.
[8]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[9]	Dengran REN, Shuying WANG. Nested named entity recognition model for wind power equipment based on differential boundary enhancement [J]. Journal of Computer Applications, 2025, 45(9): 2798-2805.
[10]	Li LI, Han SONG, Peihe LIU, Hanlin CHEN. Named entity recognition for sensitive information based on data augmentation and residual networks [J]. Journal of Computer Applications, 2025, 45(9): 2790-2797.
[11]	Binbin ZHANG, Yongbin QIN, Ruizhang HUANG, Yanping CHEN. Judgment document summarization method combining large language model and dynamic prompts [J]. Journal of Computer Applications, 2025, 45(9): 2783-2789.
[12]	Yiming LIANG, Jing FAN, Wenze CHAI. Multi-scale feature fusion sentiment classification based on bidirectional cross attention [J]. Journal of Computer Applications, 2025, 45(9): 2773-2782.
[13]	Bing YIN, Zhenhua LING, Yin LIN, Changfeng XI, Ying LIU. Emotion recognition method compatible with missing modal reasoning [J]. Journal of Computer Applications, 2025, 45(9): 2764-2772.
[14]	Penghuan QU, Wei WEI, Jing YAN, Feng WANG. Dual imputation based incomplete multi-view metric learning [J]. Journal of Computer Applications, 2025, 45(9): 2755-2763.
[15]	Wei ZHANG, Zhongwei GONG, Zhixin LI, Peihua LUO, Lingling SONG. Learning behavior boosted knowledge tracing model [J]. Journal of Computer Applications, 2025, 45(9): 2747-2754.