基于多尺度熵特征优化算法的MCI早期诊断及敏感脑区分析

doi:10.3969/j.issn.0258-8021.2023.03.003

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1086 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Mild cognitive impairment (MCI) is an important stage of early diagnosis and timely treatment in the course of Alzheimer's disease. Therefore, early detection and early intervention are urgently needed. Aiming at the problems of early diagnosis of MCI, especially the location of sensitive brain areas in early diagnosis, an optimization algorithm of EEG feature extraction based on multi-scale entropy, namely multi-scale entropy feature optimization algorithm, was proposed. The algorithm was able to mine detailed information to the greatest extent by constructing multi-scale sequences and fully considering the contribution of each sequence. During the experiment, we collected the clinical EEG data of 49 subjects, including 28 in the experimental group (MCI group) and 21 in the normal control group. The entropy values of 16 channel multi-scale entropy feature optimization algorithm in MCI group were lower than those in the control group, and there were significant differences in the prefrontal lobe, anterior temporal lobe and middle temporal lobe brain regions (P<0.01). Only this feature was used as the input feature of the classifier to analyze the three brain regions of prefrontal lobe, anterior temporal lobe and middle temporal lobe, and the recognition rates of the brain region diagnosis test set were 83.33%, 86.67% and 73.33% respectively. Further, the AUC values of the two channels of the anterior temporal lobe with the highest recognition rate were calculated to be 0.753 and 0.733, respectively. The results showed that the entropy feature of the multi-scale entropy feature optimization algorithm could fully reflect the changes of EEG signals and could be used as a potential biomarker for the early diagnosis of MCI. The anterior temporal lobe brain region can provide research support for the sensitive brain region to evaluate the state of brain cognitive function in patients with MCI.

Key words： multi-scale entropy feature optimization algorithm early diagnosis localization of sensitive brain areas mild cognitive impairment (MCI)

Received: 08 October 2021

PACS:

R318

Corresponding Authors: ^* E-mail: yddylixin@ysu.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yang Changjie
	Li Xin
	Hou Yongjie
	Wang Yulin
	Liu Qinshuang
	Su Rui

Cite this article:

Yang Changjie,Li Xin,Hou Yongjie, et al. Early Diagnosis of MCI and Analysis of Sensitive Brain Regions Based on Multi-Scale Entropy Feature Optimization Algorithm[J]. Chinese Journal of Biomedical Engineering, 2023, 42(3): 274-280.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2023.03.003 OR http://cjbme.csbme.org/EN/Y2023/V42/I3/274

[1] 赵慧,沈逸. 阿尔茨海默病生物标志物研究进展 [J]. 生命科学, 2021, 33(05): 611-620.
[2] 安兴伟,周宇涛,狄洋,等. 功能性磁共振成像在轻度认知障碍检测诊断的研究综述 [J]. 中国生物医学工程学报, 2022, 41(1): 100-107.
[3] 吴越,赵进法,杨宏宇,等. 老年人快速认知筛查量表在社区人群应用的效度研究 [J]. 中华行为医学与脑科学杂志, 2019, 28(9): 854-859.
[4] Lombardi G, Crescioli G, Cavedo E, et al. Structural magnetic resonance imaging for the early diagnosis of dementia due to Alzheimer's disease in people with mild cognitive impairment [J]. Cochrane Database Syst Rev, 2020, 3(3): CD009628.
[5] El-Gamal FEA, Elmogy M, Mahmoud A, et al. A personalized computer-aided diagnosis system for mild cognitive impairment (MCI) using structural MRI (sMRI) [J]. Sensors (Basel), 2021, 21(16): 5416.
[6] 闫拓,薛青,魏玲,等. 老年人轻度认知障碍脑电的Lempel-Ziv复杂度分析 [J]. 生物医学工程学杂志, 2013, 30(5): 972-975.
[7] Garn H, Waser M, Deistler M, et al. Quantitative EEG markers relate to Alzheimer's disease severity in the Prospective Dementia Registry Austria (PRODEM) [J]. Clinical Neurophysiology, 2015, 126(3): 505-513.
[8] McBride JC, Zhao X, Munro NB, et al. Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease[J]. Computer Methods & Programs in Biomedicine, 2014, 114(2):153-163.
[9] Delorme A, Makeig S. EEGLAB: an open-source toolbox for analysis of single-trial EEG dynamics including independent component analysis [J]. Journal of Neuroscience Methods, 2004, 134(1): 9-21.
[10] Wu SD, Wu CW, Lee KY, et al. Modified multiscale entropy for short-term time series analysis [J]. Physica A: Statistical Mechanics and its Applications, 2013, 392(23): 5865-5873.
[11] Busa MA, van Emmerik REA. Multiscale entropy: A tool for understanding the complexity of postural control [J]. Journal of Sport and Health Science, 2016, 5(1): 44-51.
[12] 李昕,安占周,李秋月,等. 加权多重多尺度熵及其在孤独症儿童脑电信号分析中的应用 [J]. 生物医学工程学杂志, 2019, 36(1): 33-39, 49.
[13] Zhao Miaoying, Xu Gang. Feature extraction of power transformer vibration signals based on empirical wavelet transform and multiscale entropy [J]. IET Science Measurement & Technology, 2018, 12(1): 63-71.
[14] Su Rui, Li Xin, Li Zhenyang, et al. Constructing biomarker for early diagnosis of aMCI based on combination of multiscale fuzzy entropy and functional brain connectivity [J]. Biomedical Signal Processing and Control, 2021, 70(103000): 1746-8094.
[15] Li Xin, Yang Changjie, Xie Ping, et al. The diagnosis of amnestic mild cognitive impairment by combining the characteristics of brain functional network and support vector machine classifier [J]. Journal of Neuroscience Methods, 2021, 363(109334): 0165-0270.
[16] 蒋帅. 基于AUC的分类器性能评估问题研究 [D]. 长春: 吉林大学, 2016.
[17] 纪道文,张静,陶华英. 轻度认知功能障碍在脑活动状态下的脑电研究 [J]. 中华老年心脑血管病杂志, 2018, 20(5): 512-516.
[18] 马际童. 轻度认知障碍脑电事件相关电位熵与一致性研究 [D]. 秦皇岛: 燕山大学, 2019.
[19] 崔会芳. 基于格兰杰因果分析的MCI脑网络分类研究 [D]. 太原: 太原理工大学, 2019.
[20] 王鑫,高原,王彬,等. 多模态网络融合在轻度认知障碍分类中的应用 [J]. 计算机应用, 2019, 39(12): 3703-3708.
[21] 胡慧玲. AD、MCI患者脑区体积改变与认知相关性研究 [D]. 长春: 吉林大学, 2018.