Time-Series Forecasting Model for Evaluating Community Health Centre Systems in Uganda,

This study focuses on evaluating the reliability of community health centre systems in Uganda by applying time-series forecasting models. A novel approach combines autoregressive integrated moving average (ARIMA) and machine learning algorithms to forecast health centre utilisation rates. Data from to are used for model validation. The ARIMA model showed a strong correlation with actual service usage, indicating accurate predictions of up to ±5% in monthly trends. The findings suggest that the combined ARIMA and machine learning models can serve as an effective tool for monitoring and improving community health centre systems. Health authorities should consider implementing these forecasting tools to enhance service planning and resource allocation. Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.