Individual cases of Parkinson's disease can be robustly classified by cortical oscillatory activity from magnetoencephalography

Parkinsons disease (PD) is a progressive neurodegenerative disorder which causes debilitating symptoms in both the motor and cognitive domains. The neurophysiological markers of PD include oscillopathies such as diffuse neural oscillatory slowing, dysregulated beta band activity, and changes in interhemispheric functional connectivity; however, the relative importance of these markers as determinants of disease status is not clear. In this study, we used resting state magnetoencephalography data (n = 199 participants, 78 PD, 121 controls) from the open OMEGA repository to investigate changes in spectral power and functional networks in PD. Using a Contrast of Parameter Estimates (COPE) approach, we modelled the effects of PD while controlling for population-level confounds (age, sex, brain volume). Permutation testing revealed highly significant increases in theta (p=0.0001) and decreases in gamma band spectral power (p=0.0001). Building on the group contrast results, we investigated the ability of source-resolved MEG data to distinguish PD from healthy controls. Our approach uses a Partial Least Squares (PLS)-based classifier to find linear combinations of MEG features which independently predict PD. We found MEG-based predictions to be highly sensitive and specific, reaching an optimal AUC-ROC of 0.87 {+/-} 0.04 using a model including spectral power features with 4 independent PLS components, compared to 0.68 {+/-} 0.04 when using functional connectivity. Interpretation of the model weights suggests that oscillatory slowing can be separated into independent posterior theta and global diffuse delta components that can robustly identify individual cases of PD with a high degree of accuracy. This suggests MEG can reveal dissociable, complementary neural processes which contribute to PD.