PREDICTION OF DENGUE DISEASE USING MACHINE LEARNING

Abstract

A vector-borne flavivirus, the dengue virus (DENV) infects approximately 390 million people annually, with 2.5 billion at risk. In order to receive appropriate treatment and prevent further infections, it is essential to have access to testing. NS1-based antigen testing, IgM/IgG antibody testing, and polymerase chain reaction (PCR) testing are just a few of the conventional methods currently available for DENV testing. In addition, new approaches that can speed up the process and save money are emerging. In low-income and rural areas all over the world, such strategies may be successful. The structural evolution of the virus is the topic of this paper, which is followed by an in-depth look at the most recent developments in dengue detection technology that are either being developed or put on the market. We also go over the most recent biosensing technologies, evaluate how well they work, and offer suggestions for dealing with the disease's obstacles. In addition, we provide recommendations for how diagnostic tools should be used more effectively in future DENV outbreaks or recurrences. The aim of this study is to perform Dengue detection by use of machine-learning on the symptoms of Dengue.