The random forests classification analysis was performed using the R-packages “randomForest” [75], “caret” [76], and “randomForestExplainer” [77] to classify the memory vs. control groups using multi-domain predictors. The details of these predictors, which include 29 functional connectivity, 27 personality and life experience, 12 alcohol outcomes, and 4 PRS variables, are listed in the Materials and Methods Section of the Supplementary Materials. The random forests model, as implemented in the current study, is detailed in Section S1.9 of the Supplementary Materials.
