A Systematic Review of Machine Learning Models for Predicting Malaria Transmission Dynamics

Abstract

Malaria remains a major public health challenge, especially in endemic regions such as sub-Saharan Africa and Southeast Asia. Traditional epidemiological models often fail to capture the complex relationships between climatic, environmental, and socio-economic factors influencing malaria transmission. This study systematically reviews machine learning (ML) applications in malaria prediction, analyzing models such as Random Forest, Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Deep Learning approaches. Findings reveal that ML models outperform traditional methods, with predictive accuracies often exceeding 85%, and hybrid models enhancing reliability. However, challenges such as data limitations, computational constraints, and model interpretability hinder large-scale implementation. Explainable AI (XAI) techniques are crucial in improving model transparency and trust. Future research should focus on improving data quality, standardizing ML frameworks, and integrating real-time data sources for enhanced prediction accuracy. ML-driven malaria prediction presents a promising tool for strengthening early warning systems and guiding targeted public health interventions.