Table 2.

The performance of nine popular classifiers in test set

	LR	SVM	DT	RF	AdaB	GB	XGB	KNN	SGD
AUC (95% CI)	0.68 (0.56, 0.75)	0.73 (0.61, 0.79)	0.59 (0.50, 0.69)	0.68 (0.55, 0.72)	0.63 (0.54, 0.71)	0.66 (0.58,0.76)	0.65 (0.59, 0.74)	0.65 (0.54,0.71)	0.6 (0.55.0.71)
ACC	0.53	0.54	0.47	0.5	0.51	0.5	0.47	0.5	0.43
SEN	0.51	0.52	0.46	0.46	0.46	0.48	0.45	0.47	0.43
SPE	0.52	0.75	0.73	0.74	0.73	0.73	0.72	0.73	0.71

LR logistic regression, SVM support vector machine, DT decision tree, RF random forest, AdaB AdaBoost, GB gradient boosting, XGB XG boost, KNN K-nearest neighbors, SGD stochastic gradient descent, ROC receiver-operating characteristic, AUC area under the curve, ACC accuracy, SEN sensitivity, SPE specificity