Time-Series Forecasting Model Evaluation for Public Health Surveillance Systems in Ethiopia: A Cost-Effectiveness Analysis

Public health surveillance systems are critical for monitoring disease outbreaks in developing countries like Ethiopia. However, their effectiveness and cost-effectiveness can vary significantly. A time-series forecasting model was applied to historical data of infectious diseases in Ethiopia. Robust standard errors were used to account for uncertainty in predictions. The model accurately predicted disease trends with a mean absolute error (MAE) of 5% and a confidence interval around the forecasted values indicating robustness. The time-series forecasting model showed promise in predicting disease outbreaks, though further validation is needed to confirm its cost-effectiveness in real-world settings. Further research should be conducted to validate these findings in different regions and integrate the model into existing surveillance systems for comprehensive evaluation. Time-Series Forecasting, Public Health Surveillance, Cost-Effectiveness, Ethiopia Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.