Factors Controlling the Distribution of Intermediate Host Snails of Schistosoma in Crater Lakes in Uganda: A Machine Learning Approach

Abstract

Schistosomiasis affects over 700 million people globally. 90% of the infected live in sub-Saharan Africa, where the trematode species Schistosoma mansoni and S. haematobium transmitted by intermediate hosts (IH) of the gastropod genera Biomphalaria and Bulinus are the major cause of the human disease burden. Understanding the factors influencing the distribution of the IH is vital towards the control of human schistosomiasis. We explored the applicability of a machine learning algorithm, random forest, to determine significant predictors of IH distribution and their variation across different geographic scales in crater lakes in western Uganda. We found distinct variation in the potential controls of IH snail distribution among the two snail genera as well as across different geographic scales. On the larger scale, geography, diversity of the associated mollusk fauna and climate are important predictors for the presence of Biomphalaria, whereas mollusk diversity, water chemistry and geography mainly control the occurrence of Bulinus. Mollusk diversity and geography are relevant for the presence of both genera combined. On the scale of an individual crater lake field, Biomphalaria is solely controlled by geography, while mollusk diversity is most relevant for the presence of Bulinus. Our study demonstrates the importance of combining a comprehensive set of predictor variables, a method that allows for variable selection and a differentiated assessment of different host genera and geographic scale to reveal relevant predictors of distribution. The results of our study contribute to making realistic predictions of IH snail distribution and schistosomiasis prevalence and can help in supporting strategies towards controlling the disease.

Adapting Strategies for Effective Schistosomiasis Prevention: A Mathematical Modeling Approach

“…Our study examines whether molluscicides and/or mechanical control for snail management, combined with mass drug administration and/or health education, can eliminate schistosomiasis. In addition, we postulate that the temperature rise, as predicted by climate change models [22][23][24], will strongly influence the use of chemicals/molluscicides, and their performance against the target species [25,26] and the general transmission dynamics of the disease. As such, it is important to understand how temperature affects molluscicide usage for the control of schistosomiasis.…”

Ecosystem Links: Macrophytes, Snail Preferences, and Trematode Transmission in Man-Made Water Bodies

“…These findings align with a previous study by Mudavanhu et al (in press) conducted in the same water bodies. Most of these species are short-lived pulmonate snails, including planorbids (e.g., Bulinus and Biomphalaria ) and lymnaeids (i.e., Radix ), which are ecological generalists capable of dispersing easily with or without hydrographic connections (Tabo et al, 2022).…”

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

“…East Africa covers an extensive area of approximately 6667 Mio and is home to roughly 488 million people, making it the most densely populated sub-region in Africa 27 . This region is rich in freshwater sources, such as swamps, rivers, and (crater) lakes, but also man-made structures such as dams and irrigation schemes, serving as potential habitats for IH snails 14 , 28 , 29 . In addition, East Africa exhibits a diverse range of geographical, climatic, hydrological, and human-induced factors, all of which are highly relevant for the distribution of IH snails.…”

“…Nonetheless, targeting IH snails, demonstrated as effective 13 , holds promise. However, our understanding of various aspects related to snail hosts remains limited, with a scarcity of studies providing comprehensive prevalence data and identifying significant features influencing the distribution of Biomphalaria and/or Bulinus IH snails 14 , 15 . This knowledge gap is particularly pronounced in East Africa overall, with persistent schistosomiasis hotspots in Kenya and Tanzania 9 .…”

“…Machine learning techniques, particularly random forest (RF) 16 , have gained wide application in various scientific domains for classification and regression analyses pertaining identification of significant features 14 , 17 – 20 . In classification tasks, RF has demonstrated superior predictive accuracy compared to other methods, such as logistic regression 21 – 23 .…”