A Brain Network Based Multi-modal Method To Identify Alzheimer' Disease And Preclinical AD

Recently,effective and accurate diagnosis of Alzheimer's disease(AD),as well as its prodromal stage(i.e.,mild cognitive impairment(MCI)and Subjective cognitive decline(SCD)),has attracted more and more attention recently.So far,different feature selection methods have been used in multi-modality based classification of AD,MCI and SCD.However,most existing research focuses on only a single modality of biomarkers for diagnosis of AD and MCI,although recent studies have shown that different biomarkers may provide complementary information for the diagnosis of AD and MCI.In the meanwhile,there is a need for surrogate markers that are sensitive to changes in neuronal dysfunction during the prodromal phase.Although Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible.Accordingly,in this paper,we proposed multiple-kernel based support vector machine(SVM)algorithm to integrate anatomical and functional connectivity information extracted from diffusion tensor imaging(DTI)and resting-state functional magnetic resonance imaging(rs-fMRI).Then,a linear support vector machine(SVM)is adopted to evaluate the classification accuracy,using a 10-fold cross-validation.As a result,for classifying AD from healthy controls,The classification accuracy obtained by the proposed method is 98.4%,and only90.9% when using even the best individual modality of markers.Similarly,for classifying MCI from healthy controls,The classification accuracy yielded by the proposed method is 95.5%,and only90.89% even using the best individual modality of markers.for classifying SCD from healthy controls,The classification accuracy yielded by the proposed method is 83.17%,and only90.89% even using the best individual modality of markers.The multimodality classification approach shows considerably better performance,compared to the case of using an individual modality of markers.Our classification framework allows accurate early detection of brain abnormalities,which is of paramount importance for treatment management of potential AD patients.