Deep Learning Model for Predicting Rhythm Outcomes after Radiofrequency Catheter Ablation in Patients with Atrial Fibrillation

Table 3

Quantitative evaluation results of evaluated models.

	AUROC	F1 score	Sensitivity	Specificity	Accuracy
APPLE score	0.605	0.357	0.426	0.654	0.593
CHD-VASc score	0.595	0.397	0.489	0.646	0.605
Linear regression	0.541	0.412	0.574	0.562	0.565
Logistic regression	0.546	0.381	0.511	0.585	0.565
XGBoost	0.608	0.452	0.617	0.600	0.605
SVM	0.638	0.482	0.617	0.662	0.650
Proposed model	0.766	0.632	0.745	0.777	0.768

The best and second-best results are shown in boldface and italics, respectively.