AUTHOR=Lama Ramesh Kumar , Kwon Goo-Rak TITLE=Diagnosis of Alzheimer’s Disease Using Brain Network JOURNAL=Frontiers in Neuroscience VOLUME=Volume 15 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2021.605115 DOI=10.3389/fnins.2021.605115 ISSN=1662-453X ABSTRACT=Recent studies suggest the brain functional connectivity impairment is the early event occurred in Alzheimer’s disease (AD) and its prodromal stage mild cognitive impairment (MCI). In general these impairments can be studied comprehensively by modeling brain as a graph based network. In this paper, we present a new diagnosis approach using graph based features from functional magnetic resonance (fMR) images to discriminate AD, MCI, and healthy control (HC) subjects using a support vector machine (SVM), and regularized extreme learning machine (RELM). We compare the performance of these classifiers for brain network data from Alzheimer’s disease neuroimaging initiative (ADNI) datasets with different feature selection methods. Node2vec graph embedding approach is employed to convert graph features to feature vectors. Experiments on the ADNI datasets showed that SVM with the feature selection approach can significantly improve classification accuracy of AD from MCI and HC subjects.