{ "background": "Emergency care systems in low-resource settings require robust tools for predicting clinical demand and outcomes to optimise resource allocation and improve patient care. Existing forecasting models often lack methodological rigour or are not validated within the specific operational constraints of such settings. ", "purpose and objectives": "This study aimed to develop and methodologically evaluate a novel time-series forecasting model for key clinical outcomes in a resource-constrained emergency care context, assessing its predictive accuracy and operational utility. ", "methodology": "We conducted a retrospective analysis of routinely collected clinical data from multiple emergency units. The core forecasting model was a seasonal autoregressive integrated moving average (SARIMA) model, specified as \ (B) \ (Bˢ) \ᵈ\D yt = \ (B) \ (Bˢ) \, where yt represents the clinical outcome time series. Model performance was evaluated using rolling-origin forecast validation, with uncertainty quantified via 95% prediction intervals. ", "findings": "The SARIMA model demonstrated statistically significant forecasting capability for patient mortality rates. A key finding was a consistent seasonal pattern, with a 15% increase in predicted mortality during peak seasonal periods compared to the annual baseline. The model's mean absolute percentage error was 8. 7% (95% CI: 7. 2 to 10. 3) on the test set. ", "conclusion": "The proposed time-series model provides a statistically sound and operationally feasible method for forecasting clinical outcomes in emergency care. Its ability to identify predictable seasonal variations offers a foundation for proactive capacity planning. ", "recommendations": "Health system managers should integrate validated forecasting models into routine operational dashboards to guide staffing and supply chain decisions. Further research should focus on integrating exogenous variables, such as disease outbreak data, to enhance predictive precision. ", "key words": "forecasting, clinical outcomes, emergency care, time-series analysis, health systems, low-resource settings", "contribution statement": "This paper provides the first methodological
Nalwadda et al. (Sun,) studied this question.