Results of the classifiers evaluated by leave-one-out cross-validation.

The table shows the results of the six classifiers evaluated by leave-one-out cross-validation on three different subsets of features (A, B and C): (i) linear regression considering the reactivity values; (ii) linear regression considering the binary classes 0-negative and 1-positive as continuous values; (iii) logistic regression; (iv) Naïve Bayes; (v) decision tree; (vi) rules learner. The second column displays the name of the tested classifiers. Columns 3–7 report the results reached by each classifier in terms of mean accuracy (Acc), sensitivity (Sens), specificity (Spec), precision (Prec) and F-measure ((2*Sens*Prec)/(Sens+Prec)). The two models with highest F-measure are highlighted in bold.