Table 8.

Comparison of experimental results of classification accuracy (%), sensitivity (%), specificity (%), and AUC (in terms of mean ± standard deviation) using the different classifiers for only our proposed feature set (FS7), where 𝛜 indicates 1.0 × 10⁻⁵.

Classifier	Validation	Accuracy	Sensitivity	Specificity	AUC
SVM	5-fold	85.18 ± 1.04	78.38 ± 1.44	91.03 ± 1.49	0.8471 ± 0.0103
	10-fold	87.63 ± 1.53	80.27 ± 2.11	93.95 ± 1.54	0.8711 ± 0.0155
	Leave-one-out	88.75 ± 𝛜	81.08 ± 𝛜	95.35 ± 𝛜	0.8821 ± 𝛜
RF	5-fold	84.86 ± 1.5	77.78 ± 2.47	90.96 ± 2.31	0.8437 ± 0.015
	10-fold	85.63 ± 1.53	77.67 ± 1.31	92.73 ± 2.44	0.8505 ± 0.0147
	Leave-one-out	86.25 ± 1.48	77.3 ± 1.32	93.95 ± 2.59	0.8564 ± 0.0141
DT	5-fold	81.46 ± 1.97	77.93 ± 2.88	84.50 ± 3.72	0.8121 ± 0.019
	10-fold	80.36 ± 1.1	80.31 ± 2.78	80.40 ± 2.44	0.8035 ± 0.0112
	Leave-one-out	83.75 ± 𝛜	83.78 ± 𝛜	83.72 ± 𝛜	0.8375 ± 𝛜
LDA	5-fold	83.00 ± 0.93	75.68 ± 𝛜	89.3 0± 1.54	0.8249 ± 0.0077
	10-fold	82.29 ± 0.47	75.68 ± 𝛜	87.98 ± 0.87	0.8183 ± 0.0043
	Leave-one-out	82.50 ± 𝛜	75.68 ± 𝛜	88.37 ± 𝛜	0.8202 ± 𝛜