As an outlook, a third method is compared to RF and LR: RF tuned using the package tuneRanger [4] with all arguments set to the defaults (in particular, tuning is performed by optimizing the Brier score by using the out-of-bag observations). To keep computational time reasonable, in this additional study CV is performed only once (and not repeated 10 times as in the main study), and we focus on the 67 datasets from biosciences/medicine. The results are displayed in Additional file 4 in the same format as the previously described figures.
