TABLE 3.

Classification model performance (calculated with LOO cross-validation) for models trained with features from Feature Set 1.

	MARS		RFs		GPR
	FS1-MARS	FS1-PCA	FS1-RF	FS1-PCA	FS1-GPR	FS1-PCA
Accuracy	0.74	0.64	0.90	0.74	0.87	0.67
Precision	0.81	0.66	0.90	0.74	0.89	0.67
Recall	0.93	0.96	0.96	0.93	0.96	1.0
MCC	0.55	−0.11	0.78	0.36	0.74	0

Bold values indicate performance metrics for recommended, best-performing models.