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

Table 9

Confusion matrix and classification report for the proposed work, CNN for feature extraction, and various machine learning models for classification.

Confusion matrix						Classification report
Models	Category	COVID-19	CAP	Normal	Total	Category	Precision	Recall	F1Score	Specificity
CNN+SVM	COVID-19	104	4	3	111	COVID-19	0.93	0.93	0.93	0.97
	CAP	3	104	4	111	CAP	0.93	0.93	0.93	0.97
	Normal	4	3	104	111	Normal	0.93	0.93	0.93	0.97
	Total	111	113	109	333	Average	0.93	0.93	0.93	0.97
CNN+Random Forest	COVID-19	104	3	4	111	COVID-19	0.94	0.93	0.93	0.96
	CAP	3	103	5	111	CAP	0.93	0.93	0.93	0.96
	Normal	5	5	101	111	Normal	0.91	0.92	0.91	0.97
	Total	112`	111	110	333	Average	0.93	0.93	0.93	0.96
CNN+Decision Tree	COVID-19	101	4	6	111	COVID-19	0.91	0.92	0.92	0.95
	CAP	3	101	7	111	CAP	0.91	0.92	0.92	0.96
	Normal	5	5	101	111	Normal	0.91	0.89	0.90	0.96
	Total	109	110	114	333	Average	0.91	0.91	0.91	0.96
CNN+Naive Bayes	COVID-19	104	3	4	111	COVID-19	0.94	0.93	0.93	0.91
	CAP	3	103	5	111	CAP	0.93	0.93	0.93	0.92
	Normal	5	5	101	111	Normal	0.91	0.92	0.91	0.91
	Total	112	111	110	333	Average	0.93	0.93	0.93	0.91
CNN+KNN	COVID-19	102	5	4	111	COVID-19	0.92	0.91	0.91	0.95
	CAP	4	102	5	111	CAP	0.91	0.91	0.91	0.95
	Normal	5	4	102	111	Normal	0.91	0.91	0.91	0.96
	Total	111	111	110	333	Average	0.91	0.91	0.91	0.95