Table 3.

The descriptive statistics for best feature set for each classifier using cross-validation (CV) and independent validation set (IV) and features used in best classifiers.

Type of classifier	AUC, CV	PPV, CV	AUC, IV	PPV, IV	features
Naïve Bayes	0.966	0.972	0.928	0.913	mzmax, S, NnoID
ANN	0.970	0.965	0.923	0.903	n, σ, mzmax, Itot,, S, NnoID, IyIons,, INL
Logistic regression	0.968	0.964	0.922	0.907	n, mzImax, mzmax, Itot, Ibal, S, NnoID, IyIons, NNL, NoIDnL
Random forest	0.978	0.965	0.880	0.887	n, σ, mzImax, mzmax, Itot, Ibal, S, NnoID, IbIons, NNL
Decision tree	0.938	0.961	0.855	0.884	n, S, NnoID