A Diagnostic Analysis Workflow to Optimal Multiple Tumor Markers to Predict the Nonmetastatic Breast Cancer from Breast Lumps

Table 4

Calculation of accuracy, sensitivity, specificity, and AUC after 10-fold cross-validation for different classifiers.

	Accuracy (%)	Sensitivity	Specificity	AUC
Logistic regression	71.316	0.713	0.632	0.789
Decision tree	65.466	0.683	0.619	0.703
Support vector machine	70.9	0.697	0.597	0.684
Random forest	71.699	0.721	0.666	0.772
Gradient boosting machine	68.4	0.68	0.614	0.679