Fig. 6From: A comprehensive tool for creating and evaluating privacy-preserving biomedical prediction modelsROC performance in the case study using k-anonymous data for training random forests on the acute inflammation dataset. The False Positive Rates (FPR) and True Positive Rates (TPR) are plotted against the x-axes and y-axes, respectively. It can be seen that data anonymization had a negative impact on the performance of the resulting prediction models only for k≥15Back to article page