{ "background": "Community health centres are critical for primary care delivery in sub-Saharan Africa, yet systematic evaluations of their long-term performance and risk resilience are lacking. Existing assessments often rely on cross-sectional data, which cannot capture temporal dynamics or forecast future vulnerabilities in health system functions. ", "purpose and objectives": "This protocol details a novel methodological framework for evaluating the systemic performance of community health centres. Its primary objective is to develop and validate a time-series forecasting model to measure and project risk reduction in service delivery and resource adequacy. ", "methodology": "We propose a longitudinal, quantitative analysis using administrative panel data. The core model is a seasonal autoregressive integrated moving average with exogenous variables (SARIMAX), specified as \ (B) \ (Bˢ) \ᵈ\D yt = \ (B) \ (Bˢ) \ + \ Xt, where Xₜ includes covariates for staffing, drug supply, and funding. Model parameters will be estimated via maximum likelihood, with forecast uncertainty quantified using 95% prediction intervals. Robust standard errors will be applied to address potential heteroskedasticity. ", "findings": "As a research protocol, this paper does not present empirical results. The anticipated findings from applying the protocol include forecasting the direction and magnitude of change in key performance indicators, such as the projected proportion of centres expected to fall below critical staffing thresholds within a given forecast horizon. ", "conclusion": "This protocol provides a rigorous, replicable method for moving beyond descriptive analysis to predictive modelling of health system performance. It is designed to generate evidence that can inform proactive, rather than reactive, health systems strengthening. ", "recommendations": "Future research applying this protocol should prioritise the integration of high-frequency data streams and explore the inclusion of climate variables as exogenous shocks. Policymakers should invest in the routine collection and curation of time-series data at the facility level to enable such analyses. ", "key words": "health systems evaluation, forecasting model, risk assessment, time-series
Amina Mwinyi (Sun,) studied this question.