Table 4.

Comparison of model performance for maximum sensitivity criterion and maximum BCR criterion.

Model	Training Set						Test Set
	Accuracy	SN	SP	BCR	Precision	F1 Score	Accuracy	SN	SP	BCR	Precision	F1 Score
For maximum sensitivity criterion
DAC	0.70	0.58	0.73	0.65	0.35	0.44	0.70	0.59	0.73	0.65	0.37	0.45
KNNC	1	1	1	1	1	1	0.72	0.34	0.82	0.53	0.34	0.34
NBC	0.62	0.73	0.60	0.66	0.31	0.44	0.63	0.73	0.60	0.66	0.33	0.45
SVMC	0.53	0.48	0.54	0.51	0.21	0.29	0.52	0.48	0.54	0.51	0.22	0.30
DTC	0.80	0.10	0.97	0.31	0.52	0.17	0.78	0.08	0.97	0.28	0.49	0.14
RFC	0.78	0.88	0.75	0.81	0.47	0.61	0.68	0.66	0.69	0.67	0.36	0.47
For maximum BCR criterion
DAC	0.70	0.58	0.73	0.65	0.35	0.44	0.70	0.59	0.73	0.65	0.37	0.45
KNNC	1.00	1.00	1.00	1.00	1.00	1.00	0.72	0.34	0.82	0.53	0.34	0.34
NBC	0.62	0.73	0.60	0.66	0.31	0.44	0.63	0.73	0.60	0.66	0.33	0.45
SVMC	0.53	0.48	0.54	0.51	0.21	0.29	0.52	0.48	0.54	0.51	0.22	0.30
DTC	0.80	0.10	0.97	0.31	0.52	0.17	0.78	0.08	0.97	0.28	0.49	0.14
RFC	0.73	0.71	0.73	0.72	0.40	0.51	0.70	0.64	0.71	0.68	0.37	0.47

SN: sensitivity; SP: specificity; BCR: balanced classification rate; DAC: discriminant analysis classification; KNNC: K-nearest neighbor classification; NBC: naïve Bayes classification; SVMC: support vector machine classification; DTC: decision tree classification; and RFC: random forest classification.