Revolutionizing Malaria Prediction Using Digital Twins and Advanced Gradient Boosting Techniques

Abstract

A persistent global health concern is malaria, a potentially fatal illness caused by Plasmodium parasites spread by Anopheles mosquitoes. The most severe instances are caused by Plasmodium falciparum, with common symptoms including fever, chills, headaches, and exhaustion. Machine learning has proven effective for forecasting malaria epidemics, particularly with sophisticated methods like gradient boosting. This study investigates the algorithm's effectiveness in predicting malaria prevalence using numerical datasets. The gradient boosting algorithm can reliably examine variables, including location, climate, and past incidence rates. With the use of numerical datasets, the gradient boosting technique produces remarkable results in 98.8% accuracy, 0.012 mean absolute error, and 0.10 root mean squared error for predicting the incidence of malaria. Gradient boosting demonstrates potential in tackling the worldwide health issue of malaria, confirming its accuracy and practical applicability for prompt epidemic responses.