Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning

doi:10.1016/j.bpsc.2020.12.007

	Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning
	Shi, Yachen 1; Wang, Zan 1; Chen, Pindong 3,4,6; Cheng, Piaoyue 1; Zhao, Kun3,4,7 ; Zhang, Hongxing 9,10; Shu, Hao 1; Gu, Lihua 1; Gao, Lijuan 1; Wang, Qing 1; Zhang, Haisan 10; Xie, Chunming 1; Liu, Yong 3,4,5,6,8; Zhang, Zhijun 1,2,9,10
发表期刊	BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING
ISSN	2451-9022
	2023-02-01
卷号	8 期号:2 页码:10
通讯作者	Liu, Yong(yongliu@bupt.edu.cn) ; Zhang, Zhijun(janemengzhang@vip.163.com)
摘要	BACKGROUND: Individualized and reliable biomarkers are crucial for diagnosing Alzheimer's disease (AD). However, lack of accessibility and neurobiological correlation are the main obstacles to their clinical application. Machine learning algorithms can effectively identify personalized biomarkers based on the prominent symptoms of AD. METHODS: Episodic memory-related magnetic resonance imaging (MRI) features of 143 patients with amnesic mild cognitive impairment (MCI) were identified using a multivariate relevance vector regression algorithm. The support vector machine classification model was constructed using these MRI features and verified in 2 independent datasets (N = 994). The neurobiological basis was also investigated based on cognitive assessments, neuropathologic biomarkers of cerebrospinal fluid, and positron emission tomography images of amyloid-b plaques. RESULTS: The combination of gray matter volume and amplitude of low-frequency fluctuation MRI features accurately predicted episodic memory impairment in individual patients with amnesic MCI (r = 0.638) when measured using an episodic memory assessment panel. The MRI features that contributed to episodic memory prediction were primarily distributed across the default mode network and limbic network. The classification model based on these features distinguished patients with AD from normal control subjects with more than 86% accuracy. Furthermore, most identified episodic memory-related regions showed significantly different amyloid-b positron emission tomography measurements among the AD, MCI, and normal control groups. Moreover, the classification outputs significantly correlated with cognitive assessment scores and cerebrospinal fluid pathological biomarkers' levels in the MCI and AD groups. CONCLUSIONS: Neuroimaging features can reflect individual episodic memory function and serve as potential diagnostic biomarkers of AD.
DOI	10.1016/j.bpsc.2020.12.007
关键词[WOS]	MILD COGNITIVE IMPAIRMENT ; DEFAULT NETWORK ; FUNCTIONAL CONNECTIVITY ; STRUCTURAL MRI ; DIFFERENTIAL-DIAGNOSIS ; BRAIN MRI ; STATE ; CLASSIFICATION ; RELEVANCE ; TEXTURE
收录类别	SCI
语种	英语
资助项目	National Key Projects for Research and Development Program of China[2016YFC1305800] ; National Key Projects for Research and Development Program of China[2016YFC1305802] ; National Natural Science Foundation of China[81671046] ; National Natural Science Foundation of China[81420108012] ; National Natural Science Foundation of China[81871438] ; National Natural Science Foundation of China[81801680] ; Jiangsu Provincial Medical Outstanding Talent[JCRCA2016006] ; Beijing Natural Science Funds for Distinguished Young Scholar[JQ200036] ; Science and Technology Program of Guangdong[2018B030334001] ; ADNI (National Institutes of Health)[U01 AG024904] ; Department of Defense ADNI[W81XWH-12-2-0012] ; National Institute on Aging ; National Institute of Biomedical Imaging and Bioengineering ; Canadian Institutes of Health Research
项目资助者	National Key Projects for Research and Development Program of China ; National Natural Science Foundation of China ; Jiangsu Provincial Medical Outstanding Talent ; Beijing Natural Science Funds for Distinguished Young Scholar ; Science and Technology Program of Guangdong ; ADNI (National Institutes of Health) ; Department of Defense ADNI ; National Institute on Aging ; National Institute of Biomedical Imaging and Bioengineering ; Canadian Institutes of Health Research
WOS研究方向	Neurosciences & Neurology
WOS类目	Neurosciences
WOS记录号	WOS:001019672400001
出版者	ELSEVIER
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53607
专题	脑图谱与类脑智能实验室_脑网络组研究
通讯作者	Liu, Yong; Zhang, Zhijun
作者单位	1.Southeast Univ, Affiliated ZhongDa Hosp, Inst Neuropsychiat, Sch Med,Dept Neurol, Nanjing, Peoples R China 2.Southeast Univ, Sch Life Sci & Technol, Key Lab Dev Genes & Human Dis, Nanjing, Peoples R China 3.Brainnetome Ctr, Beijing, Peoples R China 4.Natl Lab Pattern Recognit, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Automat, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China 6.Univ Chinese Acad Sci, Beijing, Peoples R China 7.Beihang Univ, Sch Biol Sci & Med Engn, Beijing, Peoples R China 8.Beijing Univ Posts & Tecommun, Sch Artificial Intelligence, Beijing, Peoples R China 9.Xinxiang Med Univ, Dept Psychol, Xinxiang, Peoples R China 10.Xinxiang Med Univ, Affiliated Hosp 2, Xinxiang, Peoples R China
通讯作者单位	模式识别国家重点实验室; 中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shi, Yachen,Wang, Zan,Chen, Pindong,et al. Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning[J]. BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING,2023,8(2):10.
APA	Shi, Yachen.,Wang, Zan.,Chen, Pindong.,Cheng, Piaoyue.,Zhao, Kun.,...&Zhang, Zhijun.(2023).Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning.BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING,8(2),10.
MLA	Shi, Yachen,et al."Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning".BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING 8.2(2023):10.