Table 3.

Comparison about previous works on COVID-19 classification techniques.

Used technique	Description	Advantages	Disadvantages
DarkCovidNet model [21]	DarkCovidNet model is an automated COVID-19 detection model that was introduced as a new detection method based on using chest X-ray images. It represented a development of deep learning technique to be able to perform binary and multi-class classification.	DarkCovidNet can be used in remote places in countries affected by COVID-19 to overcome a shortage of radiologists. Also, it can be used to diagnose other chest-related diseases including tuberculosis and pneumonia.	A limitation of this model is the use of a limited number of COVID-19 X-ray images.
Group Method of Data Handling (GMDH) model [22]	GMDH model was used as binary classification model. It is a type of artificial neural networks that used to predict the number of confirmed COVID-19 cases in Hubei province.	GMDH has the ability to work with inadequate knowledge and it have fault tolerance.	Unexplained behavior of the network represents the most problem of GMDH.
KNN Variant (KNNV) algorithm [23]	KNNV algorithm was introduced to accurately and efficiently classify COVID-19 patients using incomplete and heterogeneous COVID-19 data. It inherited the merits of KNN in which different K values were calculated for each unknown patient independently and efficient computations for the distances between patients were implemented	KNNV is a simple technique that used the merits of KNN method to classify COVID-19 patients.	KNNV is a lazy learning method that has a high computational time.
Automated Detection and Patient Monitoring (ADPM) algorithm [24]	ADPM was proposed for the detection, quantification, and tracking of COVID-19 patients. It depended on using a deep learning model to classify COVID-19 from CT images	ADPM could distinguish COVID-19 patients from other patients in which it efficient to classify positive cases.	ADPM cannot provide the optimal accuracy.
Proposed Convolutional Neural Network (CNN) [25]	CNN was proposed to accurately detect COVID-19 patients using EfficientNet architecture. CNN was used to perform binary and multi-class classification using X-ray images	CNN can accurately detect COVID-19 patients.	More complex
Corona Patients Detection Strategy (CPDS) [26]	CPDS was proposed to detect COVID-19 patients using enhanced KNN classifier based on the most effective and significant features. these features were selected using Hybrid Feature Selection Methodology (HFSM).	CPDS can accurately detect infected patients with minimum time penalty.	KNN is a lazy learner.