{ "background": "Public health surveillance systems are critical for early detection and response to disease outbreaks, yet robust methodological frameworks for quantifying their efficacy and attributable risk reduction are lacking, particularly in resource-limited settings.", "purpose and objectives": "This study aimed to develop and apply a novel Bayesian hierarchical model to evaluate the efficacy of a national surveillance framework and estimate the attributable reduction in disease risk conferred by its implementation.", "methodology": "We integrated national-level surveillance data with demographic and environmental covariates. The core model quantified the relationship between surveillance intensity and reported incidence: $\\log(\\lambda{it}) = \\alpha + \\beta S{it} + ui + vt + \\epsilon{it}$, where $\\lambda{it}$ is the incidence in region $i$ at time $t$, $S{it}$ is a standardised surveillance intensity score, $ui$ and $vt$ are structured spatial and temporal random effects, and $\\epsilon{it}$ is an unstructured error term. Posterior distributions were estimated using Markov chain Monte Carlo sampling.", "findings": "The model indicated a strong, negative association between enhanced surveillance and reported disease risk, with a posterior probability of 0.97 that the coefficient $\\beta$ was less than -0.15. A one-standard-deviation increase in the surveillance score was associated with an estimated 14% reduction in attributable risk (95% credible interval: 9% to 18%). Spatial random effects revealed significant residual heterogeneity in system performance.", "conclusion": "The Bayesian hierarchical model provides a robust, interpretable tool for quantifying surveillance system performance and its direct impact on population health risk. The analysis confirms the system's substantive role in mitigating disease burden while identifying priority regions for intervention.", "recommendations": "Health authorities should adopt similar model-based evaluations for routine system assessment and resource allocation. Investment should prioritise geographical areas with high residual spatial random effects to improve equity and overall national efficacy.", "key words": "Bayesian hierarchical model, public