Machine learning suggests polygenic contribution to cognitive dysfunction in amyotrophic lateral sclerosis

Abstract

Amyotrophic lateral sclerosis (ALS) is a multi-system disease characterized primarily by progressive muscle weakness. Cognitive dysfunction is commonly observed in patients, however factors influencing risk for cognitive dysfunction remain elusive. Using sparse canonical correlation analysis (sCCA), an unsupervised machine-learning technique, we observed that single nucleotide polymorphisms collectively associate with baseline cognitive performance in a large ALS patient cohort from the multicenter Clinical Research in ALS and Related Disorders for Therapeutic Development (CReATe) Consortium (N=327). We demonstrate that a polygenic risk score derived using sCCA relates to longitudinal cognitive decline in the same cohort, and also to in vivo cortical thinning in the orbital frontal cortex, anterior cingulate cortex, lateral temporal cortex, premotor cortex, and hippocampus (N=114) as well as post mortem motor cortical neuronal loss (N=88) in independent ALS cohorts from the University of Pennsylvania Integrated Neurodegenerative Disease Biobank. Our findings suggest that common genetic polymorphisms may exert a polygenic contribution to the risk of cortical disease vulnerability and cognitive dysfunction in ALS.

Social and Leisure Activity Contribute to the Attenuation of Decline in Behavioral Variant Frontotemporal Degeneration

“…For example, follow-up time and number of datapoints collected can vary due to reasons such as illness, death, unwillingness to participate due to disease progression, and transportation issues. Therefore, to ensure each subject was represented in longitudinal models equally, we chose to perform linear mixed effects modeling to extract individualized slopes of decline and relate this metric to late-life LEQ, similar to previous work (Placek et al, 2020). However, such a method has the potential to be biased by shrinkage towards the mean.…”