Cortical connectivity predicts cognition across time in Parkinson's disease

Abstract

Cognitive symptoms are common in Parkinson's disease (PD), yet the underlying brain mechanisms remain poorly understood. To address this gap, we investigated the relationship between functional connectivity and cognition at multiple time points using longitudinal functional MRI (fMRI) and cognitive assessments from the Parkinson's Progression Marker Initiative (PPMI). We calculated resting-state functional connectivity within and between three key cortical brain networks that have been linked with cognitive function in PD: the frontoparietal network (FPN); the salience network (SAL); and the default mode network (DMN). Cognitive function was assessed with the Montreal Cognitive Assessment (MoCA). Linear mixed-effects modeling revealed that decreased FPN-DMN functional connectivity is associated with lower MoCA scores over time. This finding suggests that cortical connectivity is associated with and may contribute to the progression of cognitive symptoms in PD. Our findings advance knowledge about cognitive changes in PD and emphasize the importance of functional brain network architecture.

Figure 1.

In patients with PD in our PPMI dataset, MoCA scores from Visit 1 to Visit 3 (an average of ~3 years) did not significantly change. Black bars represent mean MoCA scores. Gray lines connect data from individual participants across visits.

Figure 2.

FPN-DMN inter-network functional connectivity (N = 27). A) 3D-rendered display of FPN-DMN regions of interest (ROIs) from the superior view of the brain. B) Differences in FPN-DMN inter-network functional connectivity across Visits 1–3 for each participant, over a total of ~3 years on average. FPN-DMN functional connectivity did not significantly differ across Visits 1–3 (p = 0.36). C) Scatterplot showing the relationship between FPN-DMN functional connectivity (Fisher R-to-Z values) and MoCA scores for each participant across Visits 1–3. Data for each participant are plotted individually. The colors of the datapoints (pink, red, and maroon) represent Visits 1, 2, and 3, respectively; a thin gray line connects the datapoints for each participant. The black line represents our overall linear regression model regressing MoCA scores on FPN-DMN functional connectivity, with adjustments for time, age, education, MDS-UPDRS-III, LEDD, and a random intercept by participant. Gray bands denote the 95% confidence interval. LPFC = lateral prefrontal cortex, PPC = posterior parietal cortex, MPFC = medial prefrontal cortex, PCC = posterior cingulate cortex, LP = lateral parietal cortex.