Table 3.

Predictive performance of established models in validation cohort.

Models	Accuracy	Precision	Sensitivity	Specificity	AUC (95% CI)
XGB	0.84	0.29	1	0.83	0.94 (0.91, 0.96)
CNN	0.90	0.57	1	0.89	0.96 (0.93, 0.98)
XGB + CNN	0.97	0.86	1	0.96	0.97 (0.95, 0.99)

AUC, area under curve; XGB, extreme gradients boosting; CNN, convolutional neural network; CI, confidence interval.