Predicting Infection Positivity, Risk Estimation, and Disease Prognosis in Dengue Infected Patients by ML Expert System

Abstract

Dengue fever has earned the title of a rapidly growing global epidemic since the disease-causing mosquito has adapted to colder countries, breaking the notion of dengue being a tropical/subtropical disease only. This infectious time bomb demands timely and proper treatment as it affects vital body functions, often resulting in multiple organ failures once thrombocytopenia and internal bleeding manifest in the patients, adding to morbidity and mortality. In this paper, a tool is used for data collection and analysis for predicting dengue infection presence and estimating risk levels to identify which group of dengue infections the patient suffers from, using a machine-learning-based tertiary classification technique. Based on symptomatic and clinical investigations, the system performs real-time diagnosis. It uses warning indicators to alert the patient of possible internal hemorrhage, warning them to seek medical assistance in case of this disease-related emergency. The proposed model predicts infection levels in a patient based on the classification provided by the World Health Organization, i.e., dengue fever, dengue hemorrhagic fever, and dengue shock syndrome, acquiring considerably high accuracy of over 90% along with high sensitivity and specificity values. The experimental evaluation of the proposed model acknowledges performance efficiency and utilization through statistical approaches.