Table 5 Evaluation metrics of various models used for predicting viability in each coronary territory.

	Model	AUC	Accuracy	Balanced accuracy	Recall	Precision	F1 score
LAD	Random Forest	0.87	0.74	0.75	0.75	0.78	0.74
	Neural Network	0.78	0.74	0.74	0.72	0.79	0.74
	KNN	0.82	0.75	0.75	0.65	0.84	0.70
	Logistic Regression	0.83	0.78	0.77	0.74	0.83	0.77
	SVM	0.79	0.72	0.72	0.70	0.77	0.70
	Gradient Boosting	0.73	0.70	0.71	0.62	0.82	0.65
	Decision Tree	0.72	0.71	0.72	0.73	0.73	0.69
RCA	Random Forest	0.90	0.79	0.79	0.77	0.81	0.78
	Neural Network	0.84	0.81	0.81	0.69	0.92	0.77
	KNN	0.80	0.70	0.70	0.54	0.81	0.62
	Logistic Regression	0.76	0.73	0.73	0.64	0.79	0.69
	SVM	0.74	0.72	0.72	0.59	0.82	0.66
	Gradient Boosting	0.74	0.66	0.67	0.65	0.72	0.65
	Decision Tree	0.72	0.71	0.72	0.65	0.78	0.67
LCX	Random Forest	0.92	0.83	0.83	0.79	0.87	0.81
	Neural Network	0.92	0.87	0.87	0.83	0.90	0.86
	KNN	0.87	0.74	0.74	0.62	0.84	0.69
	Logistic Regression	0.91	0.84	0.84	0.79	0.89	0.83
	SVM	0.89	0.83	0.83	0.78	0.88	0.82
	Gradient Boosting	0.76	0.69	0.69	0.65	0.71	0.66
	Decision Tree	0.74	0.74	0.74	0.70	0.76	0.71

AUC Area Under the Curve, KNN K-Nearest Neighbors, SVM Support Vector Machine.

Quick links

Search