A common problem in medical diagnosis is to combine information from several tests or patient characteristics into a decision rule to distinguish diseased from healthy patients. Among the statistical procedures proposed to solve this problem, recursive partitioning is appealing for the easily-used and intuitive nature of the rules it produces. The rules have the form of classification trees, in which each node of the tree represents a simple question about one of the predictor variables, and the branch taken depends on the answer. The authors consider the role of misclassification costs in developing classification trees. By varying the ratio of costs assigned to false negatives and false positives, a series of classification trees are generated, each optimal for some range of cost ratios, and each with a different sensitivity and specificity. The set of sensitivity-specificity combinations define a curve that can be used like an ROC curve.