Local late gadolinium enhancement features to identify the electrophysiological substrate of post-infarction ventricular tachycardia: a machine learning approach

Tab1e 1 Classification performance scores using sample uncertainty weights

Area under the curves	Patient 1		Patient 2		Patient 3
	PR	ROC	PR	ROC	PR	ROC
No confidence weighting	0.79	0.80	0.88	0.89	0.75	0.92
Project distance weighting	0.85	0.85	0.94	0.94	0.96	0.99
Temporal displacement weighting	0.86	0.87	0.95	0.95	0.95	0.99
Combined uncertainty weighting	0.84	0.87	0.94	0.94	0.94	0.99

ISSN: 1532-429X