There is an increasing interest in using classification and
regression trees to predict outcomes in the medical literature.
Conventional classification and regression trees use binary
recursive partitioning of the independent variables to
either classify subjects or to determine predicted values
of the dependent variable for each subject [1,2]. Advocates
for classification and regression trees have suggested that
these methods allow for the construction of easily interpretable
decision rules, are adept at identifying important interactions
in the data [3] and at identifying clinical subgroups
of subjects at very high or very low risk of adverse outcomes