Towards cross-cohort estimation of cognitive decline in neurodegenerative diseases

Heterogeneity of cohorts, in terms of inclusion criteria, design of follow-up visits and batteries of cognitive assessments, hinders any thorough comparisons between them. For that reason, we build a cross-cohort model of cognitive decline that can be personalized to any patient, allowing to impute partially or totally missing scores. This enables to compare at an individual level disease progression of subjects from different cohorts, with a temporal realignment and regarding a broader set of biomarkers.