<![CDATA[Tuberculosis (TB) remains a major public health problem in many parts of the world, including in West Java Province, Indonesia. By guiding targeted medication, an accurate assessment of TB risk factors can enhance overall efforts to control tuberculosis. This study introduces modelling by integrating Negative Binomial Mixed Models (NBMM) and Random Forest (RF) called the Negative binomial mixed model random forest (NBMMRF) model. This model is used to identify and assess risk factors associated with the incidence of tuberculosis. First, utilized NBMM to add fixed effects and random effects in the model and compensate for overdispersion. Modelling count data with overdispersion is a crucial problem in epidemiological studies, and the NBMM component in this model provides a flexible. Afterward, we include a Random Forest component in the model, which helps us detect relevant predictive features and change model weights accordingly. The resulting Negative Binomial Mixed Model Random Forest (NBMMRF) has a high accuracy value of up to 0.915. In contrast to simpler models, the NBMMRF model can capture complex and nonlinear interactions between predictors and outcomes.]]>
Copyrights © 2025
