This work presents a paradigm for predicting changes in pathology, supporting diagnosis and providing a potential biomarker for Parkinson’s disease. This is achieved by creating a high-dimensional support vector machine (SVM) based classifier that learns the underlying pattern of pathology using numerous atlas-based regional features extracted from Diffusion Tensor Imaging (DTI) data. For the dataset of 72 controls and 73 PD patients, we achieve a 10-fold cross validation accuracy of 72.8% and a testing accuracy of 78.5%. The top discriminative features included widespread patterns of mean diffusivity changes in PD.
This abstract and the presentation materials are available to members only; a login is required.