Identifying Depression in Parkinson's Disease by Using Combined Diffusion Tensor Imaging and Support Vector Machine

Objective: To investigate white matter microstructural alterations in Parkinson's disease (PD) patients with depression using the whole-brain diffusion tensor imaging (DTI) method and to explore the DTI-based machine learning model in identifying depressed PD (dPD). Methods: The DTI data were collected from 37 patients with dPD and 35 patients with non-depressed PD (ndPD), and 25 healthy control (HC) subjects were collected as the reference. An atlas-based analysis method was used to compare fractional anisotropy (FA) and mean diffusivity (MD) among the three groups. A support vector machine (SVM) was trained to examine the probability of discriminating between dPD and ndPD. Results: As compared with ndPD, dPD group exhibited significantly decreased FA in the bilateral corticospinal tract, right cingulum (cingulate gyrus), left cingulum hippocampus, bilateral inferior longitudinal fasciculus, and bilateral superior longitudinal fasciculus, and increased MD in the right cingulum (cingulate gyrus) and left superior longitudinal fasciculus-temporal part. For discriminating between dPD and ndPD, the SVM model with DTI features exhibited an accuracy of 0.70 in the training set [area under the receiver operating characteristic curve (ROC) was 0.78] and an accuracy of 0.73 in the test set (area under the ROC was 0.71). Conclusion: Depression in PD is associated with white matter microstructural alterations. The SVM machine learning model based on DTI parameters could be valuable for the individualized diagnosis of dPD.

Automated summary

This study investigates white matter microstructural alterations in Parkinson's disease patients with depression using the whole-brain diffusion tensor imaging (DTI) method and explores the potential of a DTI-based machine learning model in identifying depressed Parkinson's disease. The results imply that depression in Parkinson's disease is associated with changes in white matter microstructure, and the machine learning model using DTI parameters shows promise in individualized diagnosis of depressive Parkinson's disease.