A Novel COVID-19 Diagnosis Support System Using the Stacking Approach and Transfer Learning Technique on Chest X-Ray Images

Table 10

Models’ performance evaluation based on scoring metrics: loss, accuracy, precision, sensitivity, specificity, and NPV.

Model	Accuracy (%)	Loss (%)	Precision (%)	Sensitivity (%)	Specificity (%)	NPV (%)
ResNet152V2	98.55	5.06	98.56	98.22	99.5	99.52
ResNet101V2	98.55	5.99	98.32	98.44	99.52	99.51
MobileNetV2	98.36	5.18	98.4	97.99	99.45	99.46
VGG16	98.75	3.69	98.59	98.6	99.59	99.57
VGG19	99.13	5.51	99.27	98.66	99.69	99.73
Generated model by stacking technique	99.23	3.09	98.96	99.34	99.75	99.72