{ "background": "Community health centres are critical nodes in Rwanda's healthcare system, yet their operational resilience is challenged by fluctuating demand and supply chain vulnerabilities. A robust, predictive methodology for quantifying systemic risk is lacking.", "purpose and objectives": "This study aimed to develop and methodologically evaluate a novel time-series forecasting model to measure and predict risk reduction in the operational continuity of community health centres.", "methodology": "We conducted an intervention study using longitudinal, facility-level data on stock-outs, patient attendance, and referral rates. The core analytical framework was an autoregressive integrated moving average with exogenous variables (ARIMAX) model, specified as $yt = \\mu + \\sum{i=1}^{p}\\phii y{t-i} + \\sum{j=1}^{q}\\thetaj \\epsilon{t-j} + \\sum{k=1}^{r}\\betak X{t,k} + \\epsilont$, where $Xt$ represents intervention covariates. Model performance was assessed via rolling-origin forecast evaluation and robust standard errors.", "findings": "The ARIMAX(2,1,1) model demonstrated superior forecasting accuracy against benchmarks, reducing one-step-ahead forecast error for essential medicine stock-out risk by 34% (95% CI: 28 to 40). The inclusion of community health worker deployment density as an exogenous variable was a significant predictor of reduced operational risk.", "conclusion": "The proposed forecasting model provides a validated methodological tool for proactively quantifying risk in decentralised health systems, demonstrating significant predictive utility.", "recommendations": "Health system planners should integrate predictive, model-based risk assessments into routine supply chain management and resource allocation decisions for community health centres.", "key words": "health systems resilience, predictive modelling, supply chain management, ARIMAX, operational research, public health", "contribution statement": "This paper provides the first application of a tailored ARIMAX forecasting framework to quantify dynamic risk in a community-based health system, offering a