Skip to main content
Fig. 3 | BMC Medical Research Methodology

Fig. 3

From: The roles of predictors in cardiovascular risk models - a question of modeling culture?

Fig. 3

Calibration of the models (SLLN-LR, GAM, MLNN, XGBoost) fitted at full data availability, data availability of N/10 and N/100, evaluated in the test set. The visualization across the full range of predicted risk is found in Additional file 2: Appendix 6. Abbreviations: GAM, generalized additive models; MLNN, multi-layer neural networks; SLNN-LR, single-layer neural network/logistic regression; XGBoost, extreme gradient boosted trees

Back to article page