Table 2. Performance of all prediction models under consideration.

Model	AUC-ROC	Absolute AUC-ROC Change
Framingham Score	0.724 ± 0.004	Baseline model
Cox PH Model (7 core variables)	0.734 ± 0.005	+ 1.0%
Cox PH Model (all variables)	0.758 ± 0.005	+ 3.4%
Support Vector Machines	0.709 ± 0.061	- 1.5%
Random Forest	0.730 ± 0.004	+ 0.6%
Neural Networks	0.755 ± 0.005	+ 3.1%
AdaBoost	0.759 ± 0.004	+ 3.5%
Gradient Boosting	0.769 ± 0.005	+ 4.5%
AutoPrognosis (7 core variables)	0.744 ± 0.005	+ 2.0%
AutoPrognosis (369 non-lab. variables)	0.761 ± 0.005	+ 3.7%
AutoPrognosis (104 lab. variables)	0.735 ± 0.008	+ 1.1%
AutoPrognosis (all variables)	0.774 ± 0.005	+ 5.0%

The Framingham score is provided as the reference model for comparative purposes.