Publication:
Machine learning applications on covid-19 pandemic: A systematic literature review

No Thumbnail Available

Date

2022-12-10

Journal Title

Journal ISSN

Volume Title

Publisher

Research Projects

Organizational Units

Journal Issue

Abstract

Covid-19 is an infectious disease caused by the Sars-Cov-2 virus, which emerged on December 19, 2019 and was declared as a pandemic by the World Health Organization (WHO) on March 11, 2020. This disease, which causes infection in the lungs and upper respiratory tract, has been seen in more than 243 million people worldwide and spread to 192 countries/territories and 26 cruise/naval ships since the day it first appeared. Studies are carried out in many different areas to combat the increase in the number of infected patients. Computer-aided systems, —one of these areas— are used together with technologies such as data science, machine learning and artificial intelligence, and they provide great benefits in predictive diagnosis processes in the fight against Covid-19. In this study, machine learning methods used for the detection and diagnosis of Covid-19 are investigated by systematic literature method. 49 empirical studies in which machine learning is applied with a model and methodology suitable for the purpose determined as content were examined. In this study, the purposes and performances of using machine learning methods in the field of Covid-19 were examined. The articles between 2019-2021 from two different sources, IEEE and Science Direct, were obtained using five search queries. Using the exclusion and selection strategy among 49 out of a total of 532 studies were examined. Within the scope of the study, it was seen that the most used of the 3 data types, namely time series, image and clinical, was the time series. It has been concluded that among the 3 usage purposes determined for machine learning in the articles, Covid-19 diagnosis is the most studied problem type. While the most used machine learning method for Curve Fitting problems was Regression, it was concluded that Random Forest (RF) and Support Vector Machines (SVM) methods were frequently used in the diagnosis of Covid-19.

Description

Keywords

Machine Learning, Covid-19, Sars-Cov-2, Systematic Literature Review, PRISMA

Citation

KÖKSAL K., DOĞAN B., ALTIKARDEŞ Z. A., \"Machine Learning Applications on Covid-19 Pandemic: A Systematic Literature Review \", International Congress on Multidisciplinary Natural Sciences and Engineering, Ankara, Türkiye, 01 Aralık 2022, ss.63

Collections