Abstract
{ "background": "Urban primary care networks are critical for health system resilience, yet robust tools for forecasting their clinical performance are lacking, particularly in resource-constrained settings. This gap impedes proactive resource allocation and strategic planning.", "purpose and objectives": "This study aimed to methodologically evaluate a novel time-series forecasting model designed to predict key clinical outcomes within urban primary care networks. The objective was to assess its predictive accuracy and operational utility for health system managers.", "methodology": "We conducted an intervention study applying a Seasonal AutoRegressive Integrated Moving Average with eXogenous factors (SARIMAX) model to longitudinal clinical data. The core model is defined as $\\phi(B)\\Phi(B^s)\\nabla^d\\nablas^D yt = \\theta(B)\\Theta(B^s)\\epsilont + \\beta Xt$, where $X_t$ represents intervention covariates. Model fit was evaluated using rolling-origin forecast evaluation, with uncertainty quantified via 95% prediction intervals.", "findings": "The model demonstrated clinically useful forecasting accuracy for hypertension control rates up to 12 months ahead. Forecasts indicated a stable but suboptimal trajectory, with a predicted marginal improvement of 2.3 percentage points (95% PI: 0.8 to 3.7) over the forecast horizon, contingent on maintaining current intervention levels.", "conclusion": "The evaluated SARIMAX model provides a statistically sound and operationally feasible tool for forecasting clinical outcomes in complex primary care systems. It offers a mechanism for data-driven stewardship.", "recommendations": "Health authorities should integrate this forecasting methodology into routine performance dashboards. Future research should focus on embedding these models within real-time health information systems for dynamic scenario planning.", "key words": "forecasting, primary health care, time-series analysis, clinical outcomes, health systems, South Africa", "contribution statement": "This paper provides the first application and validation of a SARIMAX forecasting framework for clinical outcomes in African urban primary care networks, demonstrating its