Predictive Modeling for Multifaceted Diseases: A Comprehensive Review

Abstract

Electronic data has accumulated due to the rising incidence of chronic illnesses, the complexity of the relationships between various diseases, and also the widespread use of computer-based technologies in sector of health care. Doctors are encountering challenges in accurately diagnosing illnesses and analysing symptoms due to extensive volumes of data. In many of the reviews of the present medical service frameworks, the focus was on considering one disease at a time. The majority of severe articles focus on a certain illness. These days, the inability to identify the precise infection has led to an increase in mortality. Indeed, a previously recovered patient might experience reinfection with another illness. Algorithms in machine learning (ML) have demonstrated substantial capability in outperforming traditional systems for diagnosing diseases, playing a pivotal role in assisting medical professionals in the early identification of elevated-risk diseases. In this literature, the intention is to identify patterns across different types of supervised and unsupervised ML models in disease detection by assessing performance metrics.