European Journal of Biomedical and Pharmaceutical Sciences

AUTOMATIC DETECTION OF COVID-19 USING DIAGNOSTIC AND PROGNOSTIC INDICATORS

B. Suganthi*, A. Janani, B. Manimozhi, P. Dharanya and L. Kayalvizhi

ABSTRACT

Technology advancements have a rapid effect on every field of life, be it medical or any other field. Naive Bayes algorithm has shown promising results in health care through its decision-making process by analyzing the data. COVID-19 has affected more than 100 countries in a matter of no time. People all over the world are vulnerable to its consequences in future. It is imperative to develop a system that will detect the corona virus efficiently. One of the solutions to control the current havoc can be the diagnosis of the disease with the help of various tools. In this paper, we classified textual clinical reports such as RT-PCR, and CT scan, which are then ensembled through data mining algorithms. These features were supplied to traditional and ensembled data mining classifiers. Logistic regression and Multinomial Naive Bayes algorithm showed better results than other DM algorithms by producing a testing accuracy of about 96.2%.

Keywords: Naive Bayes algorithm, RT-PCR, CT scan, Data Mining algorithms, Data Mining classifiers, Logistic regression.