Comparison of the prediction models
The performance of the models was tested and compared using the AUROC. Accuracy was not used as performance measure, since the database is unbalanced (ratio between re-intervention and no re-intervention 1:8 (53:446)) (43). It was chosen to use the performance measures (AUC) as used in the previous study of Stevens et al. (1). In this way a good comparison can be made.