Fig. 2
From: The roles of predictors in cardiovascular risk models - a question of modeling culture?
Brier Score, discrimination slope, AUROC and AUPRC of the models (SLLN-LR (red), GAM (rose), MMLN (violet), XGBoost (blue)) fitted at full data availability, data availability of N/10 and N/100, evaluated in the test set. Abbreviations: GAM, generalized additive models; MLNN, multi-layer neural networks; SLNN-LR, single-layer neural network/logistic regression; XGBoost, extreme gradient boosted trees