Brain signatures for neuropsychological and everyday memory achieve high replicability and explanatory power in two data cohorts

BackgroundThe "brain signature of cognition" concept has garnered interest as a data-driven, exploratory approach to better understand key brain regions involved in specific cognitive functions, with the potential to maximally characterize brain substrates of clinical outcomes. However, to be a robust brain phenotype, the signature approach requires a statistical foundation showing that model performance replicates across a variety of cohorts. Here, we outline a procedure that provides this foundation for a signature models of two memory-related behavioral domains. MethodIn each of two independent data cohorts, we derived regional brain gray matter thickness associations for neuropsychological and everyday cognition memory, testing for replicability. In each cohort we computed regional association to outcome in 40 randomly selected "discovery subsets" of size N = 400; we generated spatial overlap frequency maps and selected high-frequency regions as "consensus" signature masks for each cohort. We tested replicability by comparing cohort-based consensus model fits in all discovery sets. We tested explanatory power in each full cohort, compare signature model fits with competing "standard" models of each outcome. ResultSpatial replications produced strongly convergent consensus signature regions derived from UCD and ADNI. Consensus model fits were highly correlated in 40 random subsets of each cohort indicating high replicability. In comparisons over each full cohort, signature models outperformed other models with one exception. ConclusionMultiple random model generations, followed by consensus selection of regional brain substrates, produced signature models that replicated model fits to outcome and outperformed other commonly used measures. Robust biomarkers of cognition and everyday function may be achievable by this method. FundingThis project was funded by R01 AG052132 (NIH/NIA)