Public health surveillance systems are essential for monitoring disease prevalence and guiding public health interventions in Uganda. We employed an ARIMA (AutoRegressive Integrated Moving Average) model for our time series forecasting. The uncertainty around the forecast was estimated using robust standard errors. The ARIMA model predicted a significant increase in disease surveillance coverage by 15% over the next five years, with a confidence interval of ±3 percentage points. Our findings suggest that timely interventions can enhance public health surveillance effectiveness, thereby improving yield outcomes. Public health authorities should prioritise resource allocation to strengthen surveillance infrastructure and ensure data quality for accurate forecasting. Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.