Fig. 1From: The Brier score does not evaluate the clinical utility of diagnostic tests or prediction modelsCalibration plot for various continuous prediction models of differing degrees of miscalibration. All prediction models have an AUC of 0.75 for predicting an event with prevalence 20%. The prediction models include the following: a well-calibrated prediction model, a model that is miscalibrated such that it overestimates risk, a prediction model that underestimates risk, and a prediction model that more severely underestimates riskBack to article page