基于脑网络的阿尔茨海默病临床变量值预测

he brain functional connectivity networks have been widely used in the diagnosis of brain diseases. However, the traditional brain network based classification methods cannot assess the stage and predict the development of the disease. Recent works show that the value of the brain disease clinical variables can effectively help to evaluate the disease. In this paper, a novel brain connectivity network based method is proposed to estimate the value of Alzheimer's disease clinical variables. First, the functional connectivity network is extracted from the brain images. Then LASSO is adopted for feature selection eliminating redundant features and the clustering coefficients and edge weights of the network are fused as features. Finally, support vector regression machine (SVR) is involved to predict the value of the clinical variables. The proposed method is validated on ADNI dataset and the experimental results show that the proposed method can accurately predict the value of disease clinical variables and verify the effectiveness of the fusion of multiple features.