Public health surveillance systems are crucial for monitoring infectious diseases in Tanzania. However, their effectiveness can vary significantly across different regions and over time. A time-series forecasting model was applied to historical data from multiple regions in Tanzania. The model considered seasonal patterns and external factors affecting disease incidence. Robust standard errors were used for inference, ensuring the robustness of the findings. The time-series analysis revealed a significant downward trend in cholera cases over the past five years, with a forecast suggesting an 8% reduction in future cases if preventive measures are maintained. This study provides evidence that time-series forecasting can be effectively used to evaluate and optimise public health surveillance systems in Tanzania. The findings suggest improvements in disease control strategies. Public health authorities should consider expanding surveillance networks and implementing targeted interventions based on the forecasted trends. public health, surveillance system, cost-effectiveness, time-series forecasting, infectious diseases, cholera Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.