A machine learning approach for modeling the occurrence of the major intermediate hosts for schistosomiasis in East Africa

Abstract

Abstract Schistosomiasis, a prevalent water-borne disease second only to malaria, significantly impacts impoverished rural communities, primarily in Sub-Saharan Africa where over 90% of the severely affected population resides. The disease, majorly caused by Schistosoma mansoni and S. haematobium parasites, relies on freshwater snails, specifically Biomphalaria and Bulinus species, as crucial intermediate host (IH) snails. Targeted snail control is advisable, however, there is still limited knowledge about the community structure of the two genera especially in East Africa. Utilizing a machine learning approach, we employed random forest to identify key features influencing the distribution of both IH snails in this region. Our results reveal geography and climate as primary factors for Biomphalaria, while Bulinus occurrence is additionally influenced by soil clay content and nitrogen concentration. Favorable climate conditions indicate a high prevalence of IHs in East Africa, while the intricate connection with geography might signify either dispersal limitations or environmental filtering. Predicted probabilities demonstrate non-linear patterns, with Bulinus being more likely to occur than Biomphalaria in the region. This study provides foundational framework insights for targeted schistosomiasis prevention and control strategies in the region, assisting health workers and policymakers in their efforts.

Keywords

• Freshwater snails
• Schistosomiasis
• Predictor features
• Random forest
• Sub-Saharan Africa