Dengue Hemorrhagic Fever (DHF) is an endemic disease whose transmission is influenced by spatial and environmental factors, including population density, altitude, household sanitation, and clean and healthy living behaviors. In 2022, the city of Bandung reported a high incidence of DHF cases, highlighting the need for spatial modeling to capture interdependencies among geographic regions. This study aims to examine the impact of different parameter settings in hyperprior distributions on the Besag-York-Mollie conditional autoregressive (BYM CAR) model, estimate the relative risk (RR) of DHF, and map district-level risk to support the identification of priority areas for targeted prevention. The BYM CAR model was employed within a Bayesian framework, and the posterior distributions were obtained using Markov Chain Monte Carlo (MCMC) with the Gibbs sampling algorithm. Five hyperprior scenarios based on the Inverse-Gamma distribution were compared to evaluate their influence on model performance. The results show that hyperprior selection substantially affects model outcomes, with the best model obtained when the prior for the structured spatial component was specified as Inverse-Gamma(0.1, 0.1), and the unstructured spatial component as Inverse-Gamma(1, 0.01). Gedebage, Arcamanik, and Rancasari districts were identifies as high-risk areas, while Babakan Ciparay and Bandung Kulon exhibited the lowest RR estimates. This spatial risk mapping offers insights for policymakers in formulating more targeted and efficient DHF prevention strategies.