The random forest classification model, as used in the current study, has been described in our previous work on rsFC of the default mode network (DMN) [63]. The predictor variables included in the model were 21 reward network connections identified by feature selection (Table A1), 13 neuropsychological scores consisting of 5 TOLT scores and 8 VST scores (see Section 2.2), and 3 BIS scores (see Section 2.3), while the group status (AUD and CTL) served as the outcome variable (see Table A1, Appendix A). Although age was significantly different between the groups, we did not include age as an input variable in the classification model for the following reasons: (i) as done in our previous publications on the same sample of subjects [63,85], we performed post hoc correlational analysis of age with the significant features of the random forest model, to see if any of the top variables had associations with age in the individual groups or in total sample (see Section 3.4); and (ii) since the age difference between the groups was highly significant, including age as a feature
