人工智能应用于老年人睡眠障碍的诊断与干预：基于ICF的Scoping综述

doi:10.3969/j.issn.1006-9771.2024.08.007

Abstract

Abstract:

Objective To review the application of artificial intelligence (AI) in the identification, monitoring and intervention of sleep disorders in the elderly and the effect.

Methods A scoping review was conducted by searching relevant literature ahout the application of AI in the field of sleep disorders among the elderly from databases including PubMed, Web of Science, CNKI, and Wanfang data, covering literatures from the establishment to June, 2024.

Results A total of ten articles were included, originating from seven countries and involving 36 344 elderly participants. The publication dates ranged from 2020 to 2024. The study types included six cross-sectional studies, one prospective study, one self-controlled study and two randomized controlled trials. The articles mainly came from the fields of clinical medicine, sleep research, rehabilitation medicine and information engineering. AI was primarily used for monitoring the entire sleep process of the elderly, predicting and identifying sleep disorders, and interventions such as biofeedback, online consultations and cognitive-behavioral therapy based on mobile platforms.

Conclusions AI not only improves the accuracy of diagnosing sleep disorders, but also provides robust data support for clinical intervention. Online sleep interventions based on big data and intelligent algorithms can offer effective health management for the elderly.

Key words: elderly, sleep disorder, artificial intelligence, scoping review

CLC Number:

R749.7

JIANG Changhao, JIANG Xianxin, HUANG Chen, ZHONG Xiaoke. Application of artificial intelligence in diagnosis and intervention in sleep disorder for older adults: a scoping review using ICF[J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(8): 922-929.

Figures/Tables 4

Table 1

Figure 1

Table 2

Table 3

Basic characteristics of included literatures"

纳入文献	国家	样本特征	方法与工具	识别/干预方式	结局指标	人工智能模型	结果
Matsushima等^[18](2024)	日本	实验组： iRBD患者(n = 55)；平均年龄69.6岁对照组：健康老年人(n = 97)	横断面研究：比较iRBD患者和健康老年人静息态fMRI大脑功能连接	识别iRBD患者	准确度： LR 0.649±0.004 SVM 0.651±0.004	RF LR SVM	机器学习分类器可以识别健康老年人和iRBD患者
Ramasubbu等^[19](2020)	印度	OSA患者中年组(n = 9)：年龄30~50岁老年组(n = 9)：年龄50~70岁	横断面研究：从数据库中提取18例被试SpO₂和ECG数据	识别OSA效果	准确度：老年组(SpO₂+ECG) KNN 94.76% RF 94.76% LR 93.76% AB 95.76%	KNN RF LR AB 决策树	人工智能分类方法能有效识别睡眠呼吸暂停综合征
Vyas等^[20] (2021)	美国	睡眠障碍老年人(n = 5) 平均年龄66.2岁	横断面研究：通过提取液压床传感器信号数据，对睡眠障碍老年人睡眠阶段进行分类	识别睡眠障碍老年人睡眠阶段	准确度： 70-30分割方法 75% 留一法交叉验证 75.6%	CNN LSTM	深度学习方法能够对睡眠障碍老年人睡眠阶段进行分类
Banerjee等^[21] (2022)	印度	老年人人数：未提及平均年龄≥ 65岁	横断面研究：通过内置传感器的健身带对老年人进行远程实时监测	监测老年人睡眠质量	实时反馈准确率： 97%	CNN LSTM NLP	机器学习模型能够为老年人提供准确的健康监测和实时反馈
Cho等^[22] (2023)	韩国	老年痴呆患者训练集(n = 187) 平均年龄80.4岁测试集(n = 35) 平均年龄80.7岁	前瞻性研究：被试佩戴腕式活动记录仪记录睡眠和活动水平，连续2周	预测痴呆老年人睡眠障碍发生的概率	准确度： LR 77.7% RF 90.6% GBM 91.8% SVM 77.0%	LR RF GBM SVM	机器学习能够有效预测痴呆症患者睡眠障碍的发生
Gauld等^[23] (2024)	法国	被试分为18~30岁、31~45岁、46~55岁、> 55岁4个年龄段 (n = 35808) 平均年龄42.7岁	横断面研究：通过症状网络分析方法，对比不同年龄被试睡眠健康状况	揭示不同年龄组之间的睡眠差异	非恢复性睡眠：0.54过度白天嗜睡：0.40慢性睡眠剥夺：0.68慢性昼夜节律失调：0.36 腿部感觉不适：0.33清醒满意度：0.39	症状网络分析、中心性分析、网络比较、稳健性分析	老年人组睡眠质量相较其他年龄组更差
Hammour等^[24] (2024)	英国	老年人(n = 17) 平均年龄71.8岁	横断面研究：采用顶叶和耳部EEG记录老年人睡眠时的脑电信号	识别老年人睡眠阶段	准确度：初始准确度70.1% 微调后准确度73.7%	lightGBM	基于lightGBM的迁移学习能提高耳部EEG信号在睡眠阶段分类中的正确率
Laborda-Sánchez等^[25] (2020)	墨西哥	老年女性(n = 14) 平均年龄77.42岁	随机对照试验：实验组接受神经反馈训练，对照组接受常规护理干预	神经反馈训练，每次40 min，每周5次，持续6周	PSQI评分 α波频率	BioGraph Infiniti软件	实验组PSQI评分显著降低，α波频率显著增加，睡眠质量改善
Tang等^[26] (2015)	美国	睡眠障碍老年人(n = 8) 平均年龄88岁	治疗前后比较研究：神经反馈训练，每次30 min，每天1次，持续30 d	通过视觉及声音进行神经反馈	ISI PSQI PHQ-9	Procyon by MindPlace软件	被试失眠从重度转向轻度，63%的被试不再符合失眠标准
Lee等^[27] (2024)	韩国	睡眠障碍老年人(n = 100) 年龄≥ 65岁	随机对照试验：实验组采用ICT应用程序，进行线上睡眠咨询并提供睡眠改善建议	睡眠习惯改进睡眠辅助实时咨询	ISI	Smart Sleep信息和通信技术程序	干预后被试ISI得分显著降低，失眠症状有所改善

Table 3

References 35

[1]	World Health Organization. China country assessment report on ageing and health[EB/OL]. (2015-02-16) [2024-01-14]. https://www.who.int/publications/i/item/9789241509312 .
[2]	SMALL S A, STERN Y, TANG M, et al. Selective decline in memory function among healthy elderly[J]. Neurology, 1999, 52(7): 1392-1396. doi: 10.1212/wnl.52.7.1392 pmid: 10227623
[3]	CHEN J, CHEN X, MAO R, et al. Hypertension, sleep quality, depression, and cognitive function in elderly: a cross-sectional study[J]. Front Aging Neurosci, 2023, 15: 1051298.
[4]	CLEMENTE L, GASPARRE D, ALFEO F, et al. Theory of mind and executive functions in individuals with mild cognitive impairment or healthy aging[J]. Brain Sci, 2023, 13(10): 1356.
[5]	温娜娜, 张芯慧, 龙清, 等. 步态和平衡功能对上海社区老年人衰弱的预测效能[J]. 中国康复理论与实践, 2024, 30(6): 731-736. doi: 10.3969/j.issn.1006-9771.2024.06.014
	WEN N N, ZHANG X H, LONG Q, et al. Predictive value of gait and balance on frailty in community-dwelling older adults in Shanghai, China[J]. Chin J Rehabil Theory Pract, 2024, 30(6): 731-736.
[6]	CULLINAN T. Visual disability in the elderly[M]. Taylor Francis, 2024.
[7]	NAZERI A R, LOTFI Y, MOOSAVI A, et al. Auditory processing disorders in elderly people[J]. Sci J Rehabil Med, 2014, 3(1): 58-66.
[8]	FOLEY D J, MONJAN A A, BROWN S L, et al. Sleep complaints among elderly persons: an epidemiologic study of three communities[J]. Sleep, 1995, 18(6): 425-432. doi: 10.1093/sleep/18.6.425 pmid: 7481413
[9]	FULDA S, SCHULZ H. Cognitive dysfunction in sleep disorders[J]. Sleep Med Rev, 2001, 5(6): 423-445. doi: 10.1053/smrv.2001.0157 pmid: 12531152
[10]	BOMBOIS S, DERAMBURE P, PASQUIER F, et al. Sleep disorders in aging and dementia[J]. J Nutr Health Aging, 2010, 14: 212-217. pmid: 20191256
[11]	ANAFI R C, KAYSER M S, RAIZEN D M. Exploring phylogeny to find the function of sleep[J]. Nat Rev Neurosci, 2019, 20(2): 109-116. doi: 10.1038/s41583-018-0098-9 pmid: 30573905
[12]	SALVEMINI A, D'ONOFRIO G, CICCONE F, et al. Insomnia and information and communication technologies (ICT) in elderly people: a systematic review[J]. Med Sci, 2019, 7(6): 70.
[13]	MALWADE S, ABDUL S S, UDDIN M, et al. Mobile and wearable technologies in healthcare for the ageing population[J]. Comput Methods Programs Biomed, 2018, 161: 233-237.
[14]	World Heath Oranization. International Classification of Diseases 11th Revision[EB/OL]. (2019-10-17) [2024-01-16]. https:// int/browse11/1-m/en .
[15]	世界卫生组织. 国际功能、残疾和健康分类(国际中文增补版)[M]. 邱卓英,译. 日内瓦: 世界卫生组织, 2015.
	World Health Organization. International Classification ofFunctioning, Disability and Health-International Chinese Supplement[M]. QIU Z Y, trans trans. Geneva: World Health Organization, 2015.
[16]	周英风, 顾莺, 胡雁, 等. JBI循证卫生保健中心对关于不同类型研究的质量评价工具:患病率及分析性横断面研究的质量评价[J]. 护士进修杂志, 2018, 33(3): 219-221.
	ZHOU Y F, GU Y, HU Y, et al. The Joanna Briggs Institutecritical appraisal tools for use in systematic review: prevalence study and analytical cross sectional study[J]. J Nur Train, 2018, 33(3): 219-221.
[17]	AROMATARIS E, MUNN Z. JBI manual for evidence synthesis[M]. Adelaide, Australia: JBI, 2020.
[18]	MATSUSHIMA T, YOSHINAGA K, WAKASUGI N, et al. Functional connectivity-based classification of rapid eye movement sleep behavior disorder[J]. Sleep Med, 2024, 115: 5-13. doi: 10.1016/j.sleep.2024.01.019 pmid: 38295625
[19]	RAMASUBBU S, LAKSHMI R V, PRIYA S L, et al. Analysis of sleep apnea considering biosignals from peripheral capillary oxygen saturation level and electrocardiogram data[C]. Proceedings of International Conference on Intelligent Computing, Information and Control Systems, 2020.
[20]	VYAS N, RYOO K, TESFAYE H, et al. Sleep stage classification using non-invasive bed sensing and deep learning[C]. 2021 IEEE International Conference on Bioinformatics and Biomedicine, 2021.
[21]	BANERJEE A, MAJI D, DATTA R, et al. SHUBHCHINTAK: an efficient remote health monitoring approach for elderly people[J]. Multimed Tools Appl, 2022, 81(26): 37137-37163.
[22]	CHO E, KIM S, HEO S J, et al. Machine learning-based predictive models for the occurrence of behavioral and psychological symptoms of dementia: model development and validation[J]. Sci Rep, 2023, 13(1): 8073. doi: 10.1038/s41598-023-35194-5 pmid: 37202454
[23]	GAULD C, HARTLEY S, MICOULAUD-FRANCHI J A, et al. Sleep health analysis through sleep symptoms in 35,808 individuals across age and sex differences: comparative symptom network study[J]. JMIR Public Health Surveill, 2024, 10: e51585.
[24]	HAMMOUR G, DAVIES H, ATZORI G, et al. From scalp to ear-EEG: a generalisable transfer learning model for automatic sleep scoring in older people[J]. IEEE J Transl Eng Health Med, 2024, 17(12): 448-456.
[25]	LABORDA-SÁNCHEZ F, HERNÁNDEZ-REYES K M. The effect of neurofeedback on sleep quality amongst elderly women in nursing homes[J]. Psicología Iberoamericana, 2020, 28(1): 1-22.
[26]	TANG H Y, VITIELLO M V, PERLIS M, et al. Open-loop neurofeedback audiovisual stimulation: a pilot study of its potential for sleep induction in older adults[J]. Appl Psychophysiol Biofeedback, 2015, 40(3): 183-188.
[27]	LEE Y, KIM I, LEE S, et al. Information and communication technology-based application for cognitive behavioral therapy among community-dwelling older adults with insomnia: development and validation study[J]. Healthcare, 2024, 12(1): 106.
[28]	LEE S, YU S. Effectiveness of information and communication technology (ICT) interventions in elderly's sleep disturbances: a systematic review and meta-analysis[J]. Sensors, 2021, 21(18): 6003
[29]	VAN ERUM J, VAN DAM D, DE DEYN P P. Alzheimer's disease: neurotransmitters of the sleep-wake cycle[J]. Neurosci Biobehav Rev, 2019, 105: 72-80. doi: S0149-7634(19)30015-6 pmid: 31377219
[30]	BRZECKA A, LESZEK J, ASHRAF G M, et al. Sleep disorders associated with Alzheimer's disease: a perspective[J]. Front Neurosci, 2018, 12: 324683.
[31]	FAN Y, XU P, JIN H, et al. Vital sign measurement in telemedicine rehabilitation based on intelligent wearable medical devices[J]. IEEE Access, 2019, 7: 54819-54823.
[32]	LIU M, ZHU H, TANG J, et al. Overview of a sleep monitoring protocol for a large natural population[J]. Phenomics, 2023, 3(4): 421-438.
[33]	AL-SHAQI R, MOURSHED M, REZGUI Y. Progress in ambient assisted systems for independent living by the elderly[J]. SpringerPlus, 2016, 14(5): 1-20.
[34]	NUO M, FANG H, WANG T, et al. Understanding the research on tracking, diagnosing, and intervening in sleep disorders using mHealth APPs: bibliometric analysis and systematic reviews[J]. Digital Health, 2023, 9: 20552076231165967.
[35]	吕美玲, 王洁, 曾维斯, 等. 虚拟现实技术对帕金森病患者认知功能和生活质量影响的Meta分析[J]. 中国康复理论与实践, 2024, 30(6): 648-656. doi: 10.3969/j.issn.1006-9771.2024.06.004
	LÜ M L, WANG J, ZENG W S, et al. Effect of virtual reality on cognitive function and quality of life in patients with Parkinson's disease: a meta-analysis[J]. Chin J Rehabil Theory Pract, 2024, 30(6): 648-656.

人群(Population)		人工智能分类/ 干预方法(Intervention)	比较 (Comparison)	结局 (Outcome)
健康状况	ICD-11编码	人工智能分类/ 干预方法(Intervention)	比较 (Comparison)	结局 (Outcome)
睡眠障碍患者年龄≥ 60岁	7A0Z 未特指的失眠 7A4Z 未特指的睡眠相关呼吸障碍 7A6Z 未特指的睡眠-觉醒昼夜节律障碍 7A8Z 未特指的睡眠相关运动障碍	训练数据来源临床数据数据库数据可穿戴设备数据人工智能技术类型卷积神经网络长短期记忆网络自然语言处理模型种类特征选择分类方法支持向量机症状网络分析干预类型神经反馈干预认知行为疗法	识别效果监测效果干预效果	识别效果分类准确性敏感性特异性监测效果实时反馈准确度干预效果 b134睡眠功能 b1340睡眠量 b1341睡眠开始 b1342睡眠维持 b1343睡眠质量 b1344涉及睡眠周期的功能

纳入文献	样本纳入标准	研究对象和研究场所	暴露因素测量方法	疾病或健康问题的界定	混杂因素识别	混杂因素控制	结局指标测量方法	资料分析方法	总分
Matsushima等^[18](2024)	√	√	√	√			√	√	6
Ramasubbu等^[19](2020)	√	√	√				√	√	5
Vyas等^[20](2021)	√	√	√	√			√	√	6
Banerjee等^[21](2022)	√	√	√	√			√	√	6
Cho等^[22](2023)	√	√	√	√			√	√	6
Gauld等^[23](2024)	√	√	√		√	√	√	√	7
Hammour等^[24](2024)	√	√	√	√	√	√	√	√	8
Laborda-Sánchez等^[25](2020)	√	√	√		√	√	√	√	7
Tang等^[26](2015)	√	√	√	√			√	√	6
Lee等^[27](2024)	√	√	√	√	√	√	√	√	8

Application of artificial intelligence in diagnosis and intervention in sleep disorder for older adults: a scoping review using ICF

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 4

References 35

Related Articles 15

Metrics

Comments

Recommended 0

[1]	JING Qi, CAI Weiqin, GAO Qianqian, JI Lihong, DONG Zhiwei, XING Yang, LI Wei, ZHANG Jianhua. Analysis of framework and strategies of community-based health-related rehabilitation service for older adults based on ICF [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(7): 804-810.
[2]	DONG Ping, KAN Chaojie, GUO Chuan, ZHUANG Ren, WANG Qinglei, QIAN Xue. Characteristics of cortical activation in balance control under different sensory strategies in the elderly [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(7): 848-853.
[3]	CAO Yaping, LI Ju, HUANG Minghao, LI Zhongcheng, LANG Jian. Risk factors, health and rehabilitation intervention strategies for low back pain in adult golfers: a scoping review [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(6): 657-664.
[4]	SU Rufeng, ZHONG Xiaoke, GAO Xiaoyan, JIANG Changhao. Application of artificial intelligence in anxiety and depression among children and adolescents: a scoping review [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(5): 513-519.
[5]	WANG Zhenzhou, ZHANG Yang. International researches on artificial intelligence enabled diagnosis and intervention for children with disabilities in the past two decades: a visualized analysis [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(4): 404-415.
[6]	WU Jinlong, REN Zhanbing, YI Zizhen, PENG Li. Characteristics of interbrain synchrony during interactions among individuals with autism spectrum disorder: a scoping review [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(2): 168-175.
[7]	SHAO Weiting, LEI Jianghua. Effect of response interruption and redirection as a behavioral intervention on vocal stereotypy in children with autism spectrum disorder: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2024, 30(1): 10-20.
[8]	YANG Ya'nan, MU Liping, XING Fengmei, XUE Xinhong, WANG Xiaoguang, TAO Yangyu, SUN Zhumei, ZHANG Xiaoli. Effect of intervention based on theory of planned behavior on muscle attenuation and balance of the elderly with sarcopenia [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(8): 869-874.
[9]	JIANG Changhao, HUANG Chen, GAO Xiaoyan, DAI Yuanfu, ZHAO Guoming. Effect of neurofeedback training on cognitive function in the elderly: a systematic review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(8): 903-909.
[10]	ZHANG Yuan, YANG Jian. School health services and effectiveness based on World Health Organization health-promoting school framework: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(7): 791-799.
[11]	YUAN Yuan, YANG Jian. Health benefits of integrating physical activity with chronic disease management in community-dwelling older adults: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(5): 541-550.
[12]	CAO Yuhan, LI Jin, HE Min, WANG Dan, CHEN Wei. Telerehabilitation for patients with coronary heart disease based on ICF: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(4): 433-442.
[13]	HUANG Kaiqi, XIN Rong, LING Gengqiang, WANG Pu. Repetitive transcranial magnetic stimulation for lower limb dysfunction post stroke: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(3): 286-293.
[14]	SONG Beibei, LIU Hui, BAI Kaixiang. Content and psychological measurement index of ICF-CY-based motor function evaluation scale for children and adolescents with disabilities: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(2): 182-192.
[15]	CHENG Siman, XIN Rong, ZHAO Yan, LIU Qingyu, XIE Jiale, LIU Peng, WANG Pu. Functional magnetic resonance imaging study about repetitive transcranial magnetic stimulation for dysfunction after stroke: a scoping review [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(2): 193-204.