Predicting mild cognitive impairment progression to Alzheimer's disease based on machine learning analysis of cortical morphological features

作者全名："Wang, Wei; Peng, Jiaxuan; Hou, Jie; Yuan, Zhongyu; Xie, Wutao; Mao, Guohe; Pan, Yaling; Shao, Yuan; Shu, Zhenyu"

作者地址："[Wang, Wei; Peng, Jiaxuan; Hou, Jie; Yuan, Zhongyu] Jinzhou Med Univ, Zhejiang Prov Peoples Hosp, Peoples Hosp Hangzhou Med Coll, Postgrad Educ Base, Hangzhou, Zhejiang, Peoples R China; [Wang, Wei; Xie, Wutao] Chongqing Med & Pharmaceut Coll, First Affiliated Hosp, Dept Radiol, Chongqing, Peoples R China; [Mao, Guohe] Chongqing Med Univ, Banan Hosp, Chongqing, Peoples R China; [Pan, Yaling; Shao, Yuan; Shu, Zhenyu] Zhejiang Prov Peoples Hosp, Ctr Rehabilitat Med, Affiliated Peoples Hosp, Hangzhou Med Coll, 158 Shangtang Rd, Hangzhou, Zhejiang, Peoples R China"

通信作者："Shu, ZY (通讯作者)，Zhejiang Prov Peoples Hosp, Ctr Rehabilitat Med, Affiliated Peoples Hosp, Hangzhou Med Coll, 158 Shangtang Rd, Hangzhou, Zhejiang, Peoples R China."

来源：AGING CLINICAL AND EXPERIMENTAL RESEARCH

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001023767700001

JCR分区：Q2

影响因子：3.4

年份：2023

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：Mild cognitive impairment; Alzheimer's disease; White matter; Cortical morphology; Machine learning

摘要："Purpose To establish a model for predicting mild cognitive impairment (MCI) progression to Alzheimer's disease (AD) using morphological features extracted from a joint analysis of voxel-based morphometry (VBM) and surface-based morphometry (SBM). Methods We analyzed data from 121 MCI patients from the Alzheimer's Disease Neuroimaging Initiative, 32 of whom progressed to AD during a 4-year follow-up period and were classified as the progression group, while the remaining 89 were classified as the non-progression group. Patients were divided into a training set (n = 84) and a testing set (n = 37). Morphological features measured by VBM and SBM were extracted from the cortex of the training set and dimensionally reduced to construct morphological biomarkers using machine learning methods, which were combined with clinical data to build a multimodal combinatorial model. The model's performance was evaluated using receiver operating characteristic curves on the testing set. Results The Alzheimer's Disease Assessment Scale (ADAS) score, apolipoprotein E (APOE4), and morphological biomarkers were independent predictors of MCI progression to AD. The combinatorial model based on the independent predictors had an area under the curve (AUC) of 0.866 in the training set and 0.828 in the testing set, with sensitivities of 0.773 and 0.900 and specificities of 0.903 and 0.747, respectively. The number of MCI patients classified as high-risk for progression to AD was significantly different from those classified as low-risk in the training set, testing set, and entire dataset, according to the combinatorial model (P < 0.05). Conclusion The combinatorial model based on cortical morphological features can identify high-risk MCI patients likely to progress to AD, potentially providing an effective tool for clinical screening."

基金机构：National Natural Science Foundation of China [82101983]

基金资助正文："This work was funded by National Natural Science Foundation of China, 82101983, Yuan Shao."