Machine Learning Approaches for Early Detection of Malaria in Rural Nigeria

Abstract

This study investigates the application of supervised machine learning algorithms—specifically Random Forest, Support Vector Machine, and Gradient Boosting—for early-stage malaria detection using clinical symptom datasets collected from rural health centres in Kwara State, Nigeria. The models were trained on 3,200 anonymised patient records. Random Forest achieved 94.2% accuracy, outperforming benchmark methods.

labelKeywords