Table 6.

Performance metrics of machine learning models on the test set for RCC risk prediction.

Genetic model	Model	Accuracy	Sensitivity	Specificity	Precision	Recall	F 1
Codominant	Logistic regression	0.7000	0.8000	0.6000	0.6667	0.8000	0.7273
	Elastic net	0.8000	0.6000	1.0000	1.0000	0.6000	0.7500
	C5.0 Decision Tree	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Random Forests	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Radial kernel SVM	0.4000	0.6000	0.2000	0.4286	0.6000	0.5000
Dominant	Logistic regression	0.8000	0.8000	0.8000	0.8000	0.8000	0.8000
	Elastic net	0.8000	1.0000	0.6000	0.7143	1.0000	0.8333
	C5.0 Decision Tree	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Random Forests	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Radial kernel SVM	0.7000	0.4000	1.0000	1.0000	0.4000	0.5714
Recessive	Logistic regression	0.8000	0.6000	1.0000	1.0000	0.6000	0.7500
	Elastic net	0.8000	0.6000	1.0000	1.0000	0.6000	0.7500
	C5.0 Decision Tree	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Random Forests	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Radial kernel SVM	0.7000	0.6000	0.8000	0.7500	0.6000	0.6667