Table 1.

Comparison of classification performance across models using the internal validation dataset.

Algorithms	AUROCa (95% CI)	Accuracy	Recall	Specificity	Precision	NPVb	F1-score
RFc	0.922 (0.869-0.962)	0.835	0.759	0.922	0.917	0.770	0.831
XGBoostd	0.911 (0.855-0.955)	0.798	0.741	0.863	0.860	0.746	0.796
SVMe	0.905 (0.846-0.958)	0.780	0.690	0.882	0.870	0.714	0.770
KNNf	0.879 (0.817-0.934)	0.771	0.724	0.824	0.824	0.724	0.771
LRg	0.933 (0.883-0.972)	0.872	0.810	0.941	0.940	0.814	0.870

^aAUROC: area under the receiver operating characteristic curve.

^bNPV: negative predictive value.

^cRF: random forest.

^dXGBoost: extreme gradient boosting.

^eSVM: support vector machine.

^fKNN: k-nearest neighbors.

^gLR: logistic regression.