Targeted dengue interventions require reliable estimates of transmission intensity and population immunity at the local level. The force of infection (FOI) provides an objective measure of transmission intensity, but its estimation traditionally relies on resource-intensive seroprevalence surveys. We developed a hierarchical extension of existing catalytic models to estimate FOI using routine age-stratified surveillance data, allowing partial pooling of information across districts within provinces. We applied this approach to dengue surveillance data from Jakarta and West Java provinces, Indonesia, and compared it with non-hierarchical implementations. Both hierarchical and non-hierarchical approaches produced FOI estimates consistent with 2014 seroprevalence data. The hierarchical framework provided more robust estimates through partial pooling under varied data availability scenarios but showed sensitivity to age-stratification choices and could miss district-specific patterns when local epidemiology differed from regional trends. Model comparison using expected log pointwise predictive density showed that accounting for overdispersion through negative binomial likelihood improved model performance regardless of hierarchical structure. Our analysis showed distinct patterns in reporting parameters between provinces, with Jakarta showing higher reporting rates despite lower FOI estimates than West Java. Implementation of the hierarchical framework requires understanding of local dengue epidemiology, as clustering districts with different epidemiological profiles could produce inaccurate estimates.

Dengue virus (DENV) infection is a significant public health concern in Indonesia, with increasing cases and severity posing challenges to the country’s healthcare systems. This study aims to develop and validate a machine learning-based prediction model for assessing dengue infection cases and their severity. The model incorporates epidemiological, clinical, and environmental factors to enhance early detection and resource allocation. Additionally, the model can be utilized to support logistics planning, such as the distribution of diagnostic kits and the preparation of health facilities in each region across Indonesia, ensuring timely and targeted responses to potential outbreaks. We applied various machine learning algorithms, including logistic regression, random forest, XGBoost, and SVM models, and evaluated them to determine the most effective predictive model. The results demonstrate the model’s efficacy in predicting dengue cases and severity, which can support public health interventions and clinical decision-making. Geospatial clustering and correlation matrices were generated to visualize risk patterns and support predictions. The XGBoost model demonstrated the highest performance, achieving an accuracy of 85%. Our findings suggest that integrating clinical and environmental data through machine learning (ML) techniques can significantly improve early detection and inform resource allocation strategies. The model offers a promising approach for public health surveillance and targeted interventions in dengue-endemic regions.