定量脑电图在轻度认知障碍数字化筛查中的应用

doi:10.3969/j.issn.1006-9771.2025.11.008

《中国康复理论与实践》 ›› 2025, Vol. 31 ›› Issue (11): 1314-1321.doi: 10.3969/j.issn.1006-9771.2025.11.008

定量脑电图在轻度认知障碍数字化筛查中的应用

顾剑鹏¹, 宋玉磊¹, 殷海燕¹, 尹婷婷¹, 孙凤仪¹, 杨冰清¹, 赵鸣晖², 徐桂华¹, 柏亚妹¹()

1.南京中医药大学护理学院，江苏南京市 210023
2.东南大学仪器科学与工程学院，江苏南京市 210096

收稿日期:2025-07-14 修回日期:2025-10-07 出版日期:2025-11-25 发布日期:2025-11-26
通讯作者: 柏亚妹 E-mail:czbym@njucm.edu.cn
作者简介:顾剑鹏(2001-)，男，汉族，江苏泰州市人，硕士研究生，主要研究方向：老年护理。
基金资助:
1.国家重点研发项目(2023YFC3603600);2.国家自然科学基金面上项目(72174095);3.江苏省社会发展面上项目(BE2022802);4.江苏省研究生科研创新计划课题(YCX25_2388)

Application of quantitative electroencephalography in digital screening for mild cognitive impairment

GU Jianpeng¹, SONG Yulei¹, YIN Haiyan¹, YIN Tingting¹, SUN Fengyi¹, YANG Bingqing¹, ZHAO Minghui², XU Guihua¹, BAI Yamei¹()

1. School of Nursing, Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210023, China
2. School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu 210096, China

Received:2025-07-14 Revised:2025-10-07 Published:2025-11-25 Online:2025-11-26
Contact: BAI Yamei E-mail:czbym@njucm.edu.cn
Supported by:
National Key Research and Development Program of China(2023YFC3603600);National Natural Science Foundation of China (General)(72174095);Jiangsu Provincial Social Development Project (General)(BE2022802);Jiangsu Postgraduate Research & Practice Innovation Program(YCX25_2388)

摘要/Abstract

摘要：

目的探讨轻度认知障碍(MCI)患者在数字化认知筛查任务中前额叶定量脑电图(qEEG)特征，并分析其用于MCI患者筛查的应用价值。

方法选取2024年7月至8月江苏省南京市40个社区的592例MCI患者(MCI组)和317例正常认知老年人(对照组)。两组均接受蒙特利尔认知评估量表-北京版(MoCA-BJ)评估。采用便携式脑电仪采集前额叶脑电数据，通过快速傅里叶变换进行功率谱分析。采用XGBoost算法构建基于qEEG功率特征的MCI识别模型，采用受试者工作特征曲线(ROC)评估模型的识别性能。

结果与对照组相比，MCI组筛查任务中前额叶δ、α和β频段功率显著升高(P < 0.05)；δ频段功率与MoCA-BJ总分、视空间与执行能力、注意力和延迟回忆评分呈显著负相关(r = -0.269、-0.169、-0.133、-0.171, P < 0.001)；α频段功率与MoCA-BJ总分、注意力和延迟回忆评分呈负相关(r = -0.113、-0.075、-0.091, P < 0.05)。基于δ和α频段功率构建的XGBoost模型识别MCI，ROC曲线下面积为0.91，准确率为0.81，精准率为0.89，F1分数为0.84，召回率为0.80，特异性为0.81。

结论 MCI患者在数字化筛查任务中表现出前额叶δ和α频段功率升高，且与认知功能下降有关；基于qEEG功率特征构建XGBoost模型可以实现MCI的早期预测。

关键词: 老年人, 轻度认知障碍, 数字化筛查, 定量脑电图, XGBoost算法

Abstract:

Objective To explore the quantitative electroencephalography (qEEG) characteristics of the prefrontal cortex in patients with mild cognitive impairment (MCI) during digital screening tasks for MCI screening.

Methods A total of 592 MCI patients (MCI group) and 317 normal cognitively elderly individuals (control group) were recruited from 40 communities in Nanjing, Jiangsu Province, from July to August, 2024. All participants were assessed using Montreal Cognitive Assessment-Beijing Version (MoCA-BJ). Prefrontal EEG data were collected using a portable EEG device, and power spectral analysis was performed via Fast Fourier Transform. An XGBoost algorithm was employed to construct an MCI identification model based on qEEG power features, and the model's performance was evaluated using receiver operating characteristic (ROC) curve.

Results Compared with the control group, prefrontal δ, α, and β band power increased during screening tasks in MCI group (P < 0.05); δ power was negatively correlated with MoCA-BJ total scores, and visuospatial/executive function, attention and delayed recall scores (r = -0.269, -0.169, -0.133, -0.171, P < 0.001); α power was negatively correlated with MoCA-BJ total scores, attention and delayed recall scores (r = -0.113, -0.075, -0.091, P < 0.05). The XGBoost model based on δ and α power was excellent in MCI identification, with an area under the curve of 0.91, accuracy of 0.81, precision of 0.89, F1 score of 0.84, recall of 0.80, and specificity of 0.81.

Conclusion MCI patients exhibit increased power in the prefrontal δ and α frequency bands during digital screening tasks, which is associated with cognitive decline. An XGBoost model based on qEEG power features can enable early prediction of MCI.

Key words: elderly, mild cognitive impairment, digital screening, quantitative electroencephalography, XGBoost

中图分类号:

R749.1

顾剑鹏, 宋玉磊, 殷海燕, 尹婷婷, 孙凤仪, 杨冰清, 赵鸣晖, 徐桂华, 柏亚妹. 定量脑电图在轻度认知障碍数字化筛查中的应用[J]. 《中国康复理论与实践》, 2025, 31(11): 1314-1321.

GU Jianpeng, SONG Yulei, YIN Haiyan, YIN Tingting, SUN Fengyi, YANG Bingqing, ZHAO Minghui, XU Guihua, BAI Yamei. Application of quantitative electroencephalography in digital screening for mild cognitive impairment[J]. Chinese Journal of Rehabilitation Theory and Practice, 2025, 31(11): 1314-1321.

图/表 4

表1

表2

表3

图1

参考文献 33

[1]	PETERSEN R C, LOPEZ O, ARMSTRONG M J, et al. Practice guideline update summary: mild cognitive impairment: report of the guideline development, dissemination, and implementation subcommittee of the American Academy of Neurology[J]. Neurology, 2018, 90(3): 126-135. doi: 10.1212/WNL.0000000000004826 pmid: 29282327
[2]	JIA L, DU Y, CHU L, et al. Prevalence, risk factors, and management of dementia and mild cognitive impairment in adults aged 60 years or older in China: a cross-sectional study[J]. Lancet Public Health, 2020, 5(12): e661-e671. doi: 10.1016/S2468-2667(20)30185-7 pmid: 33271079
[3]	JIA J, NING Y, CHEN M, et al. Biomarker changes during 20 years preceding Alzheimer's disease[J]. N Engl J Med, 2024, 390(8): 712-722. doi: 10.1056/NEJMoa2310168
[4]	SOUCHET B, MICHAÏL A, HEUILLET M, et al. Multiomics blood-based biomarkers predict Alzheimer's predementia with high specificity in a multicentric cohort study[J]. J Prev Alzheimers Dis, 2024, 11(3): 567-581. doi: 10.14283/jpad.2024.34 pmid: 38706273
[5]	国家老年疾病临床医学研究中心华西, 老年认知障碍数字疗法联合实验室及社区轻度认知功能障碍数字化筛查中国专家共识工作组. 社区轻度认知功能障碍数字化筛查专家共识(2025版)[J]. 中华老年医学杂志, 2025, 44(3): 238-249.
	National Clinical Research Center for Geriatric Diseases West China Hospital, Joint Laboratory of Digital Therapy for Cognitive Impairment in the Elderly, Chinese Expert Consensus Working Group on Digital Screening for Mild Cognitive Impairment in Communities. Chinese expert consensus on digital screening for mild cognitive impairment in the community (2025 edition)[J]. Chin J Geriatr, 2025, 44(3): 238-249.
[6]	李晗, 李霞. 老年人认知障碍的智能化认知筛查工具研究进展[J]. 中国医学科学院学报, 2024, 46(1): 104-110. doi: 10.3881/j.issn.1000-503X.15519
	LI H, LI X. Research progress in intelligent screening tools for cognitive impairment in the elderly[J]. Acta Acad Med Sin, 2024, 46(1): 104-110. doi: 10.3881/j.issn.1000-503X.15519
[7]	WIJAYA A, SETIAWAN N A, AHMAD A H, et al. Electroencephalography and mild cognitive impairment research: a scoping review and bibliometric analysis (ScoRBA)[J]. AIMS Neurosci, 2023, 10(2): 154-171. doi: 10.3934/Neuroscience.2023012 pmid: 37426780
[8]	SIMFUKWE C, HAN S H, JEONG H T, et al. qEEG as biomarker for Alzheimer's disease: investigating relative PSD difference and coherence analysis[J]. Neuropsychiatr Dis Treat, 2023, 19: 2423-2437. doi: 10.2147/NDT.S433207
[9]	LIN Y, SHI X, MU J, et al. Uncovering stage-specific neural and molecular progression in Alzheimer's disease: implications for early screening[J]. Alzheimers Dement, 2025, 21(5): e70182. doi: 10.1002/alz.v21.5
[10]	YUAN Y, ZHAO Y. The role of quantitative EEG biomarkers in Alzheimer's disease and mild cognitive impairment: applications and insights[J]. Front Aging Neurosci, 2025, 17: 1522552. doi: 10.3389/fnagi.2025.1522552
[11]	HAN F, LEE J, CHEN X, et al. Global brain activity and its coupling with cerebrospinal fluid flow is related to tau pathology[J]. Alzheimers Dement, 2024, 20(12): 8541-8555. doi: 10.1002/alz.14296 pmid: 39508716
[12]	ILIADOU P, PALIOKAS I, ZYGOURIS S, et al. A comparison of traditional and serious game-based digital markers of cognition in older adults with mild cognitive impairment and healthy controls[J]. J Alzheimers Dis, 2021, 79(4): 1747-1759. doi: 10.3233/JAD-201300 pmid: 33459650
[13]	ALBERT M S, DEKOSKY S T, DICKSON D, et al. The diagnosis of mild cognitive impairment due to Alzheimer's disease: recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease[J]. Alzheimers Dement, 2011, 7(3): 270-279. doi: 10.1016/j.jalz.2011.03.008 pmid: 21514249
[14]	中国痴呆与认知障碍诊治指南写作组, 中国医师协会神经内科医师分会认知障碍疾病专业委员会. 2018中国痴呆与认知障碍诊治指南(五):轻度认知障碍的诊断与治疗[J]. 中华医学杂志, 2018, 98(17): 1294-1301.
	Writing Group of Chinese Guideline for the Diagnosis and Treatment of Dementia and Cognitive Impairment, Cognitive Impairment Disease Professional Committee of Chinese Medical Doctor Association. Guideline for the diagnosis and treatment of cognitive impairment in China (2018) (Fifth part): Diagnosis and treatment of mild cognitive impairment[J]. Natl Med J Chin, 2018, 98(17): 1294-1301.
[15]	夏安琪, 李军, 岳玲, 等. 蒙特利尔认知评估量表在中国社区老人中的应用[J]. 上海交通大学学报(医学版), 2021, 41(12): 1661-1667.
	XIA A Q, LI J, YUE L, et al. Application of Montreal Cognitive Assessment in the elderly in Chinese communities[J]. J Shanghai Jiaotong Univ (Med Sci), 2021, 41(12): 1661-1667.
[16]	SIDDI S, PRETI A, LARA E, et al. Comparison of the touch-screen and traditional versions of the Corsi block-tapping test in patients with psychosis and healthy controls[J]. BMC Psychiatry, 2020, 20(1): 329. doi: 10.1186/s12888-020-02716-8 pmid: 32576254
[17]	CONG Z, ZHAO M, LING L, et al. A temporal-spectral based single-lead electroencephalogram feature fusion network may provide potential clinical biomarker for cardiac arrest[C]. 2023 Computing in Cardiology, 2023, 50: 1-4.
[18]	ÖZBEK Y, YENER G G. Understanding effects of late-life depressive symptoms on event-related oscillations in cognitively unimpaired seniors and individuals with mild cognitive impairment[J]. [ahead of print]. J Geriatr Psychiatry Neurol, 2025. DOI: 10.1177/08919887251370398.
[19]	YENER G, HÜNERLI-GÜNDÜZ D, YILDIRIM E, et al. Treatment effects on event-related EEG potentials and oscillations in Alzheimer's disease[J]. Int J Psychophysiol, 2022, 177: 179-201. doi: 10.1016/j.ijpsycho.2022.05.008 pmid: 35588964
[20]	JIANG Y, GUO Z, JIAO R, et al. Abnormal resting-state EEG neural oscillations and functional connectivity in mild cognitive impairment[J]. Front Aging Neurosci, 2025, 17: 1640966. doi: 10.3389/fnagi.2025.1640966
[21]	HÜNERLI-GÜNDÜZ D, ÖZBEK İŞBITIREN Y, UZUNLAR H, et al. Reduced power and phase-locking values were accompanied by thalamus, putamen, and hippocampus atrophy in Parkinson's disease with mild cognitive impairment: an event-related oscillation study[J]. Neurobiol Aging, 2023, 121: 88-106. doi: 10.1016/j.neurobiolaging.2022.10.001
[22]	ZENG H, FANG X, ZHAO Y, et al. EMCI: a novel EEG-based mental workload assessment index of mild cognitive impairment[J]. IEEE Trans Biomed Circuits Syst, 2022, 16(5): 902-914. doi: 10.1109/TBCAS.2022.3198265
[23]	FODOR Z, SIRALY E, HORVATH A, et al. Decreased event-related beta synchronization during memory maintenance marks early cognitive decline in mild cognitive impairment[J]. J Alzheimers Dis, 2018, 63(2): 489-502. doi: 10.3233/JAD-171079 pmid: 29630552
[24]	CHOI J, KU B, DOAN D N T, et al. Prefrontal EEG slowing, synchronization, and ERP peak latency in association with predementia stages of Alzheimer's disease[J]. Front Aging Neurosci, 2023, 15: 1131857. doi: 10.3389/fnagi.2023.1131857
[25]	MEIRON O, EZRA TSUR E, FACTOR H, et al. Left-prefrontal alpha-dynamics predict executive working-memory functioning in elderly people[J]. Cogn Neurosci, 2022, 13(1): 15-25.
[26]	ERICSON J, IBÁÑEZ N R, LUNDQVIST M, et al. Low frequency oscillations-neural correlates of stability and flexibility in cognition[J]. Nat Commun, 2025, 16(1): 5381. doi: 10.1038/s41467-025-60821-2
[27]	KNIGHTS E, HENSON R N, MORCOM A M, et al. Neural evidence of functional compensation for fluid intelligence in healthy ageing[J]. eLife, 2024, 13: e93327.
[28]	JIANG Y, ZHANG X, GUO Z, et al. Optimizing electrode configurations for EEG mild cognitive impairment detection[J]. Sci Rep, 2025, 15(1): 578. doi: 10.1038/s41598-024-84277-4
[29]	SIULY S, ALÇIN Ö F, KABIR E, et al. A new framework for automatic detection of patients with mild cognitive impairment using resting-state EEG signals[J]. IEEE Trans Neural Syst Rehabil Eng, 2020, 28: 1966-1976. doi: 10.1109/TNSRE.7333
[30]	KHATUN S, MORSHED B I, BIDELMAN G M. A single-channel EEG-based approach to detect mild cognitive impairment via speech-evoked brain responses[J]. IEEE Trans Neural Syst Rehabil Eng, 2019, 27(5): 1063-1070. doi: 10.1109/TNSRE.7333
[31]	JIANG J, ZHANG J, LI C, et al. Development of a machine learning model to discriminate mild cognitive impairment subjects from normal controls in community screening[J]. Brain Sci, 2022, 12(9): 1149. doi: 10.3390/brainsci12091149
[32]	XAVIER A, NOBLE S, JOSEPH J, et al. Heart rate and its variability from short-term ECG recordings as potential biomarkers for detecting mild cognitive impairment[J]. Am J Alzheimers Dis Other Demen, 2024, 39: 15333175241309527.
[33]	GOENARJO R, BOSQUET L, BERRYMAN N, et al. Cerebral oxygenation reserve: the relationship between physical activity level and the cognitive load during a Stroop task in healthy young males[J]. Int J Environ Res Public Health, 2020, 17(4): 1406. doi: 10.3390/ijerph17041406

组别		对照组(n = 317)	MCI组 (n = 592)	χ²/Z值	P值
性别/n	男	115	179	3.443^a	0.064
性别/n	女	202	413	3.443^a	0.064
年龄/岁		68(63,75)	69(64,74)	-0.571^b	0.568
文化程度/n	小学及以下	40	191	81.808^a	< 0.001
	初中	118	265
	高中/中专	119	107
	大专及以上	40	29
婚姻状况/n	未婚	0	3	4.562^a	0.207
	已婚	264	466
	离婚	5	16
	丧偶	47	107

组别	n	δ	θ	α	β	γ
对照组	317	29.60(26.70, 33.70)	3.70(1.50, 10.00)	10.20(4.30, 21.70)	4.40(1.90, 7.80)	1.70(0.70, 5.90)
MCI组	592	45.10(25.80, 71.40)	4.10(1.70, 10.00)	14.10(5.60, 26.60)	4.90(2.10, 11.50)	2.00(0.80, 5.20)
Z值		-9.116	-0.879	-2.924	-2.278	-0.493
P值		< 0.001	0.379	< 0.001	0.023	0.622

项目	MoCA-BJ总分	视空间与执行能力	命名能力	注意力	语言能力	抽象能力	延迟回忆	定向能力
δ	-0.269^b	-0.169^b	-0.045	-0.133^b	-0.171	-0.114	-0.166^b	0.008
θ	-0.004	0.020	-0.023	-0.036	0.010	0.045	-0.037	0.060
α	-0.113^b	-0.038	-0.018	-0.075^a	-0.061	-0.059	-0.091^b	0.014
β	-0.038	0.008	-0.023	-0.036	-0.031	0.006	-0.043	0.038
γ	0.000	0.021	-0.025	-0.030	0.013	0.052	-0.043	0.052

定量脑电图在轻度认知障碍数字化筛查中的应用

Application of quantitative electroencephalography in digital screening for mild cognitive impairment

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 33

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	都丽露, 姚仁魁, 赵衍宇, 李孟轩, 邹敏, 张功法. 生命意义感和居住方式在日常生活活动能力对老年人抑郁影响中的效应[J]. 《中国康复理论与实践》, 2025, 31(8): 987-992.
[2]	段林茹, 郑洁皎, 郑拥军, 丁建伟. 老年人与青年人姿势控制能力的差异[J]. 《中国康复理论与实践》, 2025, 31(7): 846-852.
[3]	吴晓晖, 蒋雷, 朱静茹, 解利辉. 深度学习在老年人轻度认知障碍诊断中应用的Scoping综述[J]. 《中国康复理论与实践》, 2025, 31(6): 674-681.
[4]	陈俊利, 张晗, 石志学, 刘亚, 赵盈喆, 董志伟, 嵇丽红, 李海燕, 陈芳芳, 王春平, 马安宁, 井淇. 老年人轻度认知障碍社区识别-干预工具包的研制[J]. 《中国康复理论与实践》, 2025, 31(6): 692-702.
[5]	林利霞, 曾秋婵, 郭蕴源, 梁荣相, 吴昊, 邵玉萍. 睡眠时长模式对中老年日常生活活动能力的影响[J]. 《中国康复理论与实践》, 2025, 31(3): 331-338.
[6]	徐晓红, 钟晓珂, 孙思怡, 张祁, 程怀春. 轻度认知障碍老年人参与艺术治疗心理健康效益的系统综述[J]. 《中国康复理论与实践》, 2025, 31(2): 165-171.
[7]	蒋长好, 蒋现新, 黄辰, 钟晓珂. 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[J]. 《中国康复理论与实践》, 2024, 30(8): 922-929.
[8]	井淇, 蔡伟芹, 高倩倩, 嵇丽红, 董志伟, 邢洋, 李伟, 张建华. 基于ICF的社区老年人健康相关康复服务架构与策略探析[J]. 《中国康复理论与实践》, 2024, 30(7): 804-810.
[9]	董平, 阚超杰, 郭川, 庄任, 王庆雷, 钱雪. 不同感觉策略下老年人平衡控制的皮质激活特征[J]. 《中国康复理论与实践》, 2024, 30(7): 848-853.
[10]	温娜娜, 张芯慧, 龙清, 王雨豪, 余群萍, 张晗淳, 郑国华. 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.
[11]	粟昭隐, 康巍瀚, 刘亚涛, 吕媛, Michael NERLICH. 中国中老年人身体活动水平与脑卒中发生的相关性：基于CHARLS数据[J]. 《中国康复理论与实践》, 2024, 30(4): 449-453.
[12]	刘辉, 尹航, 胡承红, 贾绍辉, 封叶文哲, 胡庆奎. 基于ICF的老年肌少症功能测量工具的内容和心理测量特性比较[J]. 《中国康复理论与实践》, 2024, 30(3): 273-280.
[13]	马晓晨, 李淑璠, 贾舒祺, 刘聪, 张振宇, 韩东洋. 认知障碍老年人身体活动、认知功能与睡眠质量的关系：基于静息脑电的中介效应分析[J]. 《中国康复理论与实践》, 2024, 30(12): 1442-1451.
[14]	王航宇, 葛可可, 范永红, 都丽露, 邹敏, 封磊. 基于ICD-11和ICF主动式音乐疗法改善认知障碍老年人认知功能的系统综述[J]. 《中国康复理论与实践》, 2024, 30(1): 36-43.
[15]	葛可可, 范永红, 王航宇, 都丽露, 李长江, 邹敏. 失眠老年人正念干预健康效益的系统综述[J]. 《中国康复理论与实践》, 2024, 30(1): 54-60.