Artificial Neural Network-Based Deep Learning Model for COVID-19 Patient Detection Using X-Ray Chest Images

Table 3

Classification results for ResNet50V2, VGG-16, and InceptionV3 on the holdout test dataset.

Model	Accuracy	Precision	Sensitivity	Specificity	F1-score	AUC
ResNet50V2	95.49	96.85	99.19	98.27	98.00	95.94
VGG-16	92.70	97.50	94.35	98.69	95.89	95.73
InceptionV3	92.97	97.60	98.39	98.67	97.99	94.72