Table 3.

Performance of our method.

Algorithm	Selection	AUC	Accuracy	Sensitivity	Specificity
Merged	TestCath	0.78	0.79	0.84	0.61
	TestNoCath	-	0.86	-	-
Classification	TestCath	0.68	0.55	0.53	0.61
	TestNoCath	-	0.90	-	-
Regression	TestCath	0.83	0.89	0.95	0.67
	TestNoCath	-	0.59	-	-

The table lists the obtained AUC, accuracy, sensitivity and specificity. Rows correspond to the classification, regression and merged outputs. To obtain binary predictions, for probabilities a threshold of 0.5 was used and for regressed FFR values a threshold of 0.8.