Prediction of COVID-19 with Computed Tomography Images using Hybrid Learning Techniques

Table 11

Confusion matrix and classification report for proposed work, VGG-16 for feature extraction, and different machine learning models for classification.

Confusion matrix						Classification report
Models	Category	COVID-19	CAP	Normal	Total	Category	Precision	Recall	F1Score	Specificity
VGG-16+SVM	COVID-19	105	2	4	111	COVID-19	0.95	0.95	0.95	0.97
	CAP	3	105	3	111	CAP	0.94	0.95	0.94	0.97
	Normal	2	4	105	111	Normal	0.94	0.95	0.94	0.97
	Total	110	111	112	333	Average	0.94	0.94	0.94	0.97
VGG-16+Random Forest	COVID-19	106	2	3	111	COVID-19	0.95	0.95	0.96	0.97
	CAP	3	106	2	111	CAP	0.95	0.95	0.95	0.97
	Normal	3	3	105	111	Normal	0.94	0.95	0.94	0.97
	Total	112	111	110	333	Average	0.95	0.95	0.95	0.97
VGG-16+Decision Tree	COVID-19	104	4	3	111	COVID-19	0.94	0.94	0.94	0.96
	CAP	3	103	4	111	CAP	0.93	0.94	0.93	0.96
	Normal	3	4	104	111	Normal	0.94	0.93	0.93	0.96
	Total	111	110	112	333	Average	0.94	0.94	0.93	0.96
VGG-16+Naive Bayes	COVID-19	94	7	10	111	COVID-19	0.85	0.86	0.86	0.93
	CAP	7	94	10	111	CAP	0.85	0.85	0.85	0.92
	Normal	8	9	94	111	Normal	0.85	0.82	0.84	0.93
	Total	109	110	114	333	Average	0.85	0.84	0.85	0.92
VGG-16+KNN	COVID-19	103	4	4	111	COVID-19	0.93	0.94	0.93	0.96
	CAP	3	103	4111	333	CAP	0.94	0.93	0.93	0.96
	Normal	4	4	103	111	Normal	0.93	0.94	0.93	0.96
	Total	110	112	110	333	Average	0.93	0.94	0.93	0.96