Research Article

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

Table 5

Validation performances of the SVM classifier after performing the RFE feature selection.

ā€‰ Accuracy Sensitivity Specificity PPV NPV ROC

EV 0.818 0.750 1.000 1.000 0.600 0.875
2x 10-fold CV 0.713 0.625 0.775 0.740 0.767 0.778

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.