Table 2.

Performance metrics of candidate models

Model	AUROC(95% CI)	AUPRC(95% CI)	Brier score(95% CI)
Extreme Gradient Boosting	0.870(0.786–0.938)	0.404(0.219–0.589)	0.024(0.016–0.032)
Gradient Boosting Machine	0.862(0.781–0.928)	0.287(0.133–0.431)	0.030(0.024–0.037)
Random forest	0.888(0.804–0.951)	0.305(0.151–0.481)	0.065(0.060–0.072)
Support vector machine	0.856(0.769–0.929)	0.247(0.111–0.414)	0.024(0.016–0.032)
Elastic Net logistic regression	0.857(0.775–0.925)	0.298(0.139–0.482)	0.105(0.079–0.139)

Performance metrics of models trained by extreme Gradient Boosting, Gradient Boosting Machine, random forest, support vector machine, and Elastic Net logistic regression. Abbreviations: AUROC Area under the receiver operating characteristic curve, CI Confidence interval, AUPRC Area under the precision-recall curve