Parkinson's disease (PD) is a highly heterogeneous condition with symptoms spanning motor and non-motor domains. Clinical scales like the Movement Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) are standard in clinical trials where disease progression is monitored. They rely on summing item values, assuming uniform item importance and score increments. Here, we propose a novel data-driven approach to optimize weights for such scales-so that total scores better reflect the underlying disease severity. In a retrospective observational analysis of longitudinal cohort data from the Parkinson's Progression Markers Initiative (PPMI), our methods identified which items (and value increments) most strongly indicate PD progression, down-weighting or excluding less informative items. The learned weights substantially improve the monotonic relationship between total scores and clinical progression. We validated our weights using both held-out PPMI data and an independent dataset (BeaT-PD), demonstrating their robustness. Applying such weights in clinical trials may increase power and reduce the required sample size1.
Motor dysfunction in Parkinson's disease (PD) has been linked to widespread oscillatory changes within the basal ganglia-thalamic-cortical network, particularly in the beta frequency range. However, the evolution of cortical neurophysiological alterations and their relationship to clinical progression remain poorly understood. We conducted a longitudinal resting-state magnetoencephalography (MEG) study in 27 persons with PD and 30 healthy individuals with a mean follow-up time of 4 years. Source-reconstructed MEG data were parcellated into cortical regions, from which power spectra were parameterized to separate oscillatory peaks from the aperiodic component. An increase in the aperiodic exponent in the left postcentral region was associated with progression of rigidity. Peak beta power in parieto-temporo-occipital regions was elevated at baseline, correlating with less severe bradykinesia. This negative relationship weakened over time in patients with progressive symptoms, suggesting an association with compensatory mechanisms. Using partial least squares regression to predict future disease course from baseline neurophysiological features, 19.5% of the variability in motor progression was explained in an independent validation cohort. Our results emphasize the importance of separating aperiodic neural activity from periodic oscillations as a progressive alteration of the aperiodic component represented the most prominent PD-related neurophysiological change. Further, our findings highlight the potential predictive value of resting-state neurophysiology for future disease progression.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：