Variable selection algorithm. This algorithm creates 500 data subsets for subsequent analysis. Each subset combines 29 patients with MACE and 29 randomly selected patients without MACE. Then, the algorithm runs random forest on each subset to pick 8 top-ranked variables. Having 500 sets of top-ranked variables, the algorithm sorts them according to their corresponding occurrence in the ensemble and chooses 8 variables with the highest appearance. The selection is refined by means of the statistical significance of each individual variable.