A SYSTEMATIC REVIEW OF MACHINE LEARNING ALGORITHMS FOR DISEASE OUTBREAK PREDICTION IN PUBLIC HEALTH

Abstract

In this digital age, because of the speedily increasing advances in science and technology, vast amounts of health care data are produced from health care applications with varying technologies such as embedded systems, intelligent health devices, and computers. Machine learning algorithms are being considered effective technologies in the health care sector, which can be employed effectively in the early detection of disease by extracting significant patterns from the data. Over the past few years, the problem of chronic disease has become a worldwide challenge. It requires hours for a doctor to detect a chronic disease effectively. Machine learning algorithms can be integrated with feature selection algorithms to avoid these limitations. An effective integration of machine learning and feature selection-based models can assist doctors in predicting the risk of chronic diseases at an early stage. The chapter deals with the various problems which still haunt traditional methods and the motivational goals towards overcoming these problems by way of the suggested research work