A Comparative Study of COVID-19 Detection Using Deep and Machine Learning Methods

Coronavirus disease 2019 (COVID-19) is a global pandemic that causes a very significant health risk. This pandemic has attracted the attention of artificial intelligence engineers and big data analysts. The sensitivity of the diagnostic test of COVID19 is limited because of irregularities in handling specimens in addition to other factors. Finding other methods of detecting the COVID-19 virus is very essential. Using the current advancement in computer technology is a way to achieve this goal. Using classification algorithms to detect the disease is a promising solution. Classifying computed tomography (CT) chest images into infected or normal requires gathering intensive amounts of data in addition to an innovative architecture of AI modules. In this paper, we evaluate and apply the deep learning method using the convolutional neural networks (CNN), in comparison with using a number of traditional machine learning algorithms such as SVM, KNN, and Random Forest for the same purpose. The results of the paper include the performance of each method, and compare their outcome, in order to find out the best method to be used in real cases detection. Our work represents a potential computeraided diagnosis method for COVID19 in clinical practice. The results indicate that deep learning offers improved performance of precision, recall, and accuracy.