A Study of Classification Model in Medical Health Applications

Abstract

Medical health sector is one the largest industry worldwide. Nowadays, the emergence of coronavirus (COVID-19) presents an important alert to the healthcare sector. This threatening virus is a concern because this virus is spreading fast and has caused many deaths. The goal of this study is to analyze the classification algorithms that have been utilized for various diseases in past research. This will be considered and explored further for future analysis of COVID-19 that could help researchers manage COVID-19 infections using the discussed data mining techniques. In this study, there are 60 studies have been included from a variety of sources such as iGATE’s, Elsevier, ResearchGate, Springer, BMC Public Health Journal, J. Health Engineering, International journal computing Technology and other etc. With data mining classification algorithms, the researcher can easily do the classification, prediction, clustering and data filtering from various data sources, especially in the healthcare system. The classification algorithms such as Naïve Bayes, support vector machine (SVM), multilayer perceptron (MLP), J48, K-nearest neighbor (KNN), decision tree, random forest and logistic regression were listed as the most applied algorithms in the past research. The naïve bayes, support vector machine (SVM), random forest, multilayer perceptron (MLP) and J48 algorithms were identified as the top five most utilized algorithms. Therefore, this study indicates that these classification algorithms are suitable for identifying, classifying and predicting COVID-19. In conclusion, this review paper will guide the researcher for future research and other research community as well on the upcoming development of machine learning for the medical health sector, especially COVID-19.