Identifying key aspects to enhance predictive modeling for early identification of schistosomiasis hotspots to guide mass drug administration

Schistosomiasis infection is a major public health problem. The related study shows that mass drug administration (MDA), a widely used method for achieving preventive chemotherapy with praziquantel (PZQ), does not prevent reinfection and the formation of high-risk areas (i.e., hotspots) between MDA rounds. Especially in endemic regions, multiple rounds of MDA are typically required for the elimination of schistosomiasis. This study aims to develop prediction methods that identify hotspots before the first MDA round (i.e., early identification) to guide subsequent treatment efforts. Accurate and early identification of hotspots, however, faces challenges due to a lack of sufficient infection data. Furthermore, the ratio of hotspots to non-hotspots is often highly imbalanced, making it even more difficult to extract useful information from the available baseline infection data to identify these hotspots. To overcome these challenges, we collected secondary data from public sources, applied spatial weighting techniques to construct predictors, and employed synthetic sampling-based methods to mitigate hotspots imbalance. We then developed statistical and machine learning models for hotspot prediction. Our method supports MDA efforts, contributes to schistosomiasis elimination, and improves public health.

Recommended citation: Chen Y, Luo F, Martinez L, Jiang S, and Shen Y. (2025). "Identifying key aspects to enhance predictive modeling for early identification of schistosomiasis hotspots to guide mass drug administration." PLOS Neglected Tropical Diseases. 19(7): e0013315.
Download Paper | Download Slides | Download Bibtex