Table 2.

Model performance indicators.

Model	AUROC	95% confidence interval	Sensitivity	Specificity	p-values
					vs. LR	vs. RF	vs. DNN
XGB	0.765	0.742–0.788	0.805	0.613	0.485	0.049	0.010
LR	0.762	0.739–0.784	0.788	0.621	—	0.487	0.021
RF	0.757	0.733–0.779	0.815	0.591		—	0.197
DNN	0.748	0.724–0.770	0.853	0.571			—

AUROC = area under the receiver operating characteristic curve; LR = logistic regression; RF = random forest; DNN = deep neural networks; XGB = scalable tree boosting system.