Predicating risk habitats of Oncomelania hupensis, the intermediate host of schistosoma japonicum under multiple environmental drivers

Abstract

Background: Oncomelania hupensis (O. hupensis), the unique intermediate host for Schistosoma japonicum, exerts a substantial influence on the risk of schistosomiasis. Being amphibious freshwater snails, the growth, development, and reproductive distribution of O. hupensis are intricately tied to climatic environmental variables. This study aims to predict O. hupensis habitat risks along the Yangtze River in China, considering multiple environmental factors. Methods: Data pertaining to the distribution of O. hupensis, including both presence and absence records, with the Jiangsu section of the Yangtze River basin for the period 2017–2021, were retrieved from the Jiangsu Schistosomiasis Control Information Platform. Ten machine learning algorithms and an ensemble model were used to explore environmental drivers. Three datasets (Snail_CLIM, Snail_TOPO, and Snail_ALL) incorporating climatic and topographic variables were examined for their impact on model accuracy. We conducted validation using the AUC and TSS metrics. Moreover, we utilized the data from the 2022 snail field survey for model external validation. Results: The findings demonstrate that snail_ALL, which incorporates both climatic and topographic variables, exhibits superior performance (ensemble model: sensitivity = 98.000, specificity = 95.960, AUC = 0.994). Among the ten model algorithms, Random Forest (RF) exhibited the highest degree of accuracy and stability (Snail_ALL: AUC = 1.000 ± 0.000, TSS = 0.985 ± 0.005). The key environmental factors affecting snail distribution included the distance to the nearest river, elevation, annual precipitation, and annual average pressure. High-risk areas manifested as two distinct concentrations: downstream of the Luhe District in Nanjing and at the confluence of Zhenjiang and Yangzhou. The results of 2022 field validation showed that over 90 % of the data points for snail breeding sites are concentrated in medium to high-risk areas. Conclusion: By selecting pertinent environmental variables and employing ensemble modeling techniques, we can accurately predict O. hupensis habitats. The resulting risk distribution map for snail habitats not only provides valuable insights but also serves as a guiding tool for targeted monitoring and control measures. The holds particular significance within the contest of the Yangtze River protection and restoration projects.

Keywords

• Oncomelania hupensis
• Schistosomiasis
• Ecological niche modeling
• Machine learning
• Yangtze River