A Support Vector Machine Classification of Thyroid Bioptic Specimens Using MALDI-MSI Data

Table 3

Validation performances of the SVM classifier without performing feature selection.

	Accuracy	Sensitivity	Specificity	PPV	NPV	ROC
EV	0.273	0.000	1.000	0.000	0.273	0.500
2x 10-fold CV	0.567	0.000	1.000	0.000	0.567	0.500

In our case, the performances indicate the ability of the algorithm to correctly detect the benignity when the case is filed as THY3.
EV: external validation; CV: cross-validation; PPV: positive predicted value; NPV: negative predictive value.