{ "background": "Persistent challenges in maternal healthcare systems in sub-Saharan Africa necessitate robust analytical tools for forecasting clinical outcomes to inform resource allocation and policy. Existing models often lack integration of longitudinal facility-level data with systemic performance indicators. ", "purpose and objectives": "This study aimed to develop and methodologically evaluate a novel time-series forecasting model for key maternal clinical outcomes, specifically designed for the operational context of care facilities in Kenya. ", "methodology": "We utilised a longitudinal national dataset of facility-level maternal health indicators. The core forecasting model is a seasonal autoregressive integrated moving average with exogenous variables (SARIMAX), specified as \ (B) \ (Bˢ) \ᵈ\D yt = \ (B) \ (Bˢ) \ + \ Xt, where Xₜ captures systemic covariates including staffing ratios and drug availability. Model performance was evaluated using rolling-origin forecast validation and Diebold-Mariano tests. ", "findings": "The model demonstrated robust predictive accuracy for forecasting maternal mortality ratios (MMR) up to 36 months ahead. A key finding was a projected stabilisation of the national MMR, with forecasts indicating a plateau within a range of 342–358 per 100, 000 live births (95% prediction interval). Forecast uncertainty was significantly reduced by incorporating supply-chain reliability metrics as an exogenous variable. ", "conclusion": "The proposed SARIMAX framework provides a statistically sound and operationally relevant tool for forecasting maternal outcomes at the facility-system level. It successfully captures complex temporal dynamics influenced by systemic factors. ", "recommendations": "Health ministries should integrate similar forecasting methodologies into routine health management information systems for proactive planning. Future research should focus on real-time model updating mechanisms and cost-effectiveness analyses. ", "key words": "maternal health, forecasting, time-series analysis, health systems, SARIMAX, clinical outcomes, Kenya", "contribution statement": "This paper introduces a novel application of a SARIMAX model with health-system covariates for forecasting
Abdi et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: