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

Background:: Schistosomiasis, a neglected tropical parasitic disease, threatens the lives of over 250 million people worldwide. In schistosomiasis prevention, high-transmission areas that do not respond to treatments, known as hotspots, pose extreme challenges to the elimination of the disease. Accurate and early identification of such hotspots is crucial for timely intervention, but this is hindered by the limited availability of effective prediction methods. Methods:: Based on the Schistosomiasis Consortium for Operational Research and Evaluation (SCORE) project over a 5-year period, this study developed prediction methods for the first (baseline) year to identify hotspots. Three key aspects were considered: (i) collecting secondary data from public sources to complement baseline schistosomiasis infection data and constructing spatially weighted predictors to incorporate neighboring information; (ii) categorizing predictors to mitigate overfitting and quantifying the importance of each category in hotspot predictions; and (iii) investigating the hotspot imbalance distribution and addressing the imbalance with a sampling-based technique to improve prediction performance. Results:: Compared to the approach using only baseline infection data, the spatially weighted data fusion method achieved relative improvements (RIs) in hotspot prediction accuracy by fusing baseline infection data with each predictor category: 10% with biology, 8.6% with geography, 6.6% with society, 3.5% with baseline infection data around villages, 3.3% with environment, 1.8% with agriculture, and 7.2% with all predictors. Furthermore, across the same predictor combinations, applying the sampling-based technique with the proposed method yielded RIs of 6.5%-37.9%, compared to the approach that did not address the imbalance. Conclusion:: Spatially weighted data fusion using secondary data improved the early identification of schistosomiasis hotspots. Addressing the imbalance of hotspots can further improve the early identification of the hotspots. Author summary: 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.