Fig. 11
From: A comprehensive tool for creating and evaluating privacy-preserving biomedical prediction models
Impact of data anonymization on prediction performance in the contraceptive methods case study. The False Positive Rates (FPR) and True Positive Rates (TPR) are plotted against the x-axes and y-axes, respectively. As can be seen, data anonymization using the game-theoretic model had only a very minor impact on prediction accuracy