Table 2.

Predictive performance of various models in the training, test and external validation sets

Classifiers	AUC	ACC	Sensitivity	Specificity
Training set
KNN	0.774	0.704	0.5	0.898
SVM	0.871	0.765	0.891	0.695
Lasso	0.941	0.861	0.982	0.780
DNN	0.927	0.870	0.911	0.864
Test set
KNN	0.669	0.655	0.538	0.75
SVM	0.688	0.621	0.769	0.563
Lasso	0.745	0.655	0.769	0.813
DNN	0.837	0.759	0.923	0.688
External validation set
KNN	0.615	0.536	0.857	0.357
SVM	0.712	0.679	0.786	0.714
Lasso	0.663	0.679	0.929	0.500
DNN	0.796	0.714	0.714	0.857

KNN, k-nearest neighbor; SVM, support vector machine; Lasso, the least absolute shrinkage and selection operator; DNN, deep neural networks; AUC, the area under the receiver operating characteristic curve; ACC, accuracy. Bold represents the highest values of AUC, ACC, sensitivity, and specificity in different data sets