Alzheimer’s disease, mild cognitive impairment, and normal aging distinguished by multi-modal parcellation and machine learning

A novel classification approach is proposed to accurately identify different stages toward AD by integrating the JHCPMMP with the logistic regression-recursive feature elimination (LR-RFE), which is named as JMMP-LRR. This method is applied to complete the entire experiment. Firstly, the sparse network is obtained by using JHCPMMP¹⁰. The process of this step is to process the fMRI data, project it to CIFTI Space, and obtain the sparse network through MMP. Secondly, we calculate the 9 attributes of brain networks, including strength, betweenness centrality, local efficiency etc, and obtain 3,240 candidate features of each subject. Subsequently, we apply LR-RFE to select the 30 features of each subject. Finally, the classifier of OVR-SVM is applied to classify the extracted features of HC, MCI and AD for classification. The process of the three-class classification in this paper is…