Table 4.

Summary of the conventional machine learning techniques applied on X-ray and/or CT images

Image Type	Authors	Dataset	Classifiers used	Accuracy (%)
X-ray	Hussain et al. [139]	Github repository “covid-chest X-Ray dataset” Kaggle repository—pault imothymooney/chest-X-Rray pneumonia	KNN, NB, XGB-Tree, CART, XGB	96.34
	Mahdy et al. [140]	Montgomery County X-ray Set, covid-chest X-Ray-dataset-master	SVM	98.81
	Farhat et al. [142]	Kaggle repository, GitHub (Dr. Joseph Cohen)	LBP + SVM, HOG + SVM and GLCM + SVM	98.66
	Kumar et al. [143]	public dataset from Italy	LR, NN, DT, RF, AdaBoost, NB, XGBoost	97.77
	Pereira et al. [144]	RYDLS-20, NIH dataset	KNN, SVM, MLP, DT, RF	89.0
	Tuncer et al. [149]	Github, Kaggle	DT, LD, KNN, SVM, SD	100.0
	Saha et al. [153]	Github repository developed by Cohen et al. [154]	RF, DT, SVM, AB	98.91
	Rasheed et al. [155]	Kaggle dataset	LR	97.97
	Gilanie et al. [156]	Data collected four medical center in Israel	KNN	90.3
	Mijwil [157]	Kaggle [158, 159]	RF, NB, SVM, LR	97.7
	imad et al. [160]	Kaggle	SVM, DT, NB, KNN, RF	96.0
	Samsir et al. [161]	Kaggle	SVM, KNN	98.0
CT	Shi et al. [138]	Huazhong University of Science and Technology [138]	LR, SVM, NN	87.9
	Liu et al. [151]	National Health Commission of the People’s Republic of China [151]	SVM, LR, DT, KNN	94.16
	Perumal et al. [162]	Data used from three sources Kaggle, Radiopedia and Zenodo	SVM, RF, DT, KNN, NB	96.96
	Feng et al. [163]	Seven Hospital in China	LR, SVM, RF, XGBoost	94.6
X-ray, CT	Hosseinzadeh et al. [164]	X-ray from Kaggle dataset and CT from RSNA Pneumonia Detection	LightGBM, Bagging, Adaboost, R, XGBoost, DT	99
	Muhammad et al. [165]	Kaggle databases	KNN, SVM, LR, NB, (AB)	95.94

SVM support vector machine, LR logistic regression, CART classification and regression tree, DT decision tree, KNN K-nearest neighbor, MLP multilayer perceptron, NB naive Bayes, AB AdaBoost