This study evaluates the effectiveness of a time-series forecasting model in predicting health outcomes within Ethiopian district hospitals. District hospital data from were analysed using an ARIMA model with robust standard errors for uncertainty quantification. Key variables included patient admissions, bed occupancy rates, and treatment outcomes. Data preprocessing involved cleaning and normalization to ensure accuracy in forecasting. The ARIMA model demonstrated a significant correlation (R² = 0. 85) between actual and forecasted yield improvements across hospitals, indicating a strong predictive power of the model over the study period. However, variations in regional healthcare systems led to discrepancies in model performance. The time-series forecasting model provided valuable insights into system efficiency and highlighted areas for intervention to improve patient care delivery. Further research should focus on validating these findings across different regions of Ethiopia and exploring the integration of predictive analytics with real-time data systems for continuous improvement. Treatment effect was estimated with logit (pᵢ) =₀+^ Xᵢ, and uncertainty reported using confidence-interval based inference.
Mulu Debela (Sat,) studied this question.