MRI-based multivariate gray matter volumetric distance for predicting motor symptom progression in Parkinson's disease

Abstract

Abstract While Parkinson's disease (PD)-related neurodegeneration is associated with structural changes in the brain, conventional magnetic resonance imaging (MRI) has proven less effective for clinical diagnosis due to its inability to reliably identify subtle changes early in the disease course. In this study, we aimed to develop a structural MRI-based biomarker to predict the rate of progression of motor symptoms in the early stages of PD. The study included 88 patients with PD and 120 healthy controls from the Parkinson's Progression Markers Initiative database; MRI at baseline and motor symptom scores assessed using the MDS-UPDRS-III at two time points (baseline and 48 months) were selected. Group-level volumetric analyses at baseline were not associated with the decline in motor functioning. Then, we developed a patient-specific multivariate gray matter volumetric distance and demonstrated that it could significantly predict changes in motor symptom scores (P < 0.05). Further, we classified patients as relatively slower and faster progressors with 89% accuracy using a support vector machine classifier. Thus, we identified a promising structural MRI-based biomarker for predicting the rate of progression of motor symptoms and classifying patients based on motor symptom severity.