Investigating the relationship between the SNCA gene and cognitive abilities in idiopathic Parkinson’s disease using machine learning

Abstract

Cognitive impairments are prevalent in Parkinson’s disease (PD), but the underlying mechanisms of their development are unknown. In this study, we aimed to predict global cognition (GC) in PD with machine learning (ML) using structural neuroimaging, genetics and clinical and demographic characteristics. As a post-hoc analysis, we aimed to explore the connection between novel selected features and GC more precisely and to investigate whether this relationship is specific to GC or is driven by specific cognitive domains. 101 idiopathic PD patients had a cognitive assessment, structural MRI and blood draw. ML was performed on 102 input features including demographics, cortical thickness and subcortical measures, and several genetic variants (APOE, MAPT, SNCA, etc.). Using the combination of RRELIEFF and Support Vector Regression, 11 features were found to be predictive of GC including sex, rs894280, Edinburgh Handedness Inventory, UPDRS-III, education, five cortical thickness measures (R-parahippocampal, L-entorhinal, R-rostral anterior cingulate, L-middle temporal, and R-transverse temporal), and R-caudate volume. The rs894280 of SNCA gene was selected as the most novel finding of ML. Post-hoc analysis revealed a robust association between rs894280 and GC, attention, and visuospatial abilities. This variant indicates a potential role for the SNCA gene in cognitive impairments of idiopathic PD.

Internetwork Connectivity Predicts Cognitive Decline in Parkinson’s and Is Altered by Genetic Variants

“…In our study, SNCA did not mediate baseline or longitudinal changes in cognition, consistent with some studies ( Mata et al, 2014 ; Huertas et al, 2017 ), but not others ( Campelo et al, 2017 ; Luo et al, 2019 ). Yet another SNCA risk variant (rs894280) predicted poorer attention and visuospatial processing ( Ramezani et al, 2021 ). Correspondingly, higher baseline CSF α-synuclein levels also predicted faster longitudinal deterioration in visuospatial working memory and verbal memory ( Stewart et al, 2014 ) and processing speed ( Hall et al, 2015 ).…”

“…Cognitive decline is common in early stages of Parkinson’s disease (PD), but diversity exists in the domains affected suggesting that patterns of neurodegeneration differ amongst people. The pathophysiological underpinnings of cognitive changes are complex, involving multiple neurotransmitter systems ( Gratwicke et al, 2015 ) and large-scale brain networks ( Tessitore et al, 2019 ), which may be vulnerable to genetic variants that carry different risks for neurocognitive progression including α-synuclein (SNCA) ( Sampedro et al, 2018a ; Ramezani et al, 2021 ) and microtubule-associated protein tau (MAPT) ( Williams-Gray et al, 2009 ; Morley et al, 2012 ; Sampedro et al, 2018b ). Knowledge about the pathophysiology behind cognitive changes in PD is largely based on people who already show mild cognitive impairment (MCI).…”

Motor symptoms in Parkinson’s disease are related to the interplay between cortical curvature and thickness

“…Inclusion criteria for the present study were as follows: (1) a T1-weighted MRI scan at baseline, (2) availability of demographic data and scores for all tests used in this study (for all participants: age, sex, years of education, and scores for Montreal Cognitive Assessment; for the PD group specifically: additional scores for MDS-UPDRS part III). To assess the effects of PD diagnosis in a cohort with a longer disease duration, we combined four different databases that had both PD patients and healthy controls, which included a dataset acquired at the Movement Disorders Clinic of the University of Alberta ( Acharya et al, 2007 ), a dataset acquired at the Unité de Neuroimagie Fonctionnelle of the Centre de Recherche de l’Institut Universitaire de Gériatrie de Montréal ( Hanganu et al, 2013 ), a dataset acquired at the Seaman Family Imaging Centre at the University of Calgary ( Ramezani et al, 2021 ), and the Tao Wu dataset ( Badea et al, 2017 ; https://fcon_1000.projects.nitrc.org/indi/retro/parkinsons.html ). Inclusion criteria for this database were as follows: (1) a T1-weighted MRI scan, (2) availability of the following variables: disease duration (for PD only), age, and sex.…”

The Impact of SNCA Variations and Its Product Alpha-Synuclein on Non-Motor Features of Parkinson’s Disease

“…Finally, a robust association between rs894280 and cognitive decline, particularly affecting attention and visuospatial functions, was detected in a group of 101 PD patients from Canada. Intriguingly, the authors used a computer-based approach, consisting of an informatics algorithm combining imaging, genetic and clinical features to identify the determinants of global cognition [ 55 ].…”