Advancing Malaria Prediction in Uganda through AI and Geospatial Analysis Models

Abstract

This study explores how integrating Gregor's Type IV theory with Geographic Information Systems (GIS) improves understanding of malaria transmission patterns in Uganda. Combining data-driven algorithms, artificial intelligence, and geospatial analysis, the research determined the most reliable predictors of malaria incident rates. Among Linear Regression, K-Nearest Neighbor, Neural Network, and Random Forest models, Random Forest outperformed the others (R² ≈ 0.88, MSE 0.0534). Antimalarial treatment was the most influential factor, mosquito net access was associated with significant reductions in incident rates, and higher temperatures correlated with increased rates.