Investigating the relationship between malaria incidence and public health infrastructure in sub-Saharan Africa

Malaria remains a major public health challenge in sub-Saharan Africa, and its burden may be influenced by access to clean water, sanitation, and childhood vitamin A supplementation. Understanding how these indicators relate to malaria incidence can help inform targeted prevention strategies.

Country-level data from global health databases were analyzed using nonparametric statistical tests and machine learning models. The Kruskal-Wallis test and Dunn's post hoc comparisons were used to assess differences in malaria incidence across categories of water and sanitation access. Cliff's delta was used to measure effect sizes. Tree-based machine learning models and logistic regression were trained to evaluate the predictive strength of the three indicators.

Significant differences in malaria incidence were found across water and sanitation access groups, with the lowest access groups consistently exhibiting the highest incidence. Cliff's delta indicated large effect sizes, particularly between low and high access categories. Vitamin A supplementation showed statistically significant group differences, though effect sizes were generally small. Tree-based machine learning models showed moderate predictive performance and outperformed logistic regression in classification accuracy and recall.

Access to clean water and adequate sanitation are strongly associated with lower malaria incidence, underscoring their importance in malaria control efforts. While vitamin A supplementation shows weaker associations, it may still interact with broader health conditions. These findings highlight the essential role of basic infrastructure in reducing malaria burden and demonstrate the potential of predictive modeling to support future global health research.