"background": "Community health centres are critical for delivering primary care in Kenya, yet systematic assessments of their operational efficiency are limited. Evaluating efficiency gains requires robust analytical frameworks, with time-series forecasting emerging as a key methodological approach for resource planning and performance measurement. ", "purpose and objectives": "This systematic review aims to critically appraise methodological approaches, specifically time-series forecasting models, used to evaluate efficiency gains within Kenyan community health centres. It seeks to identify prevalent modelling techniques, their applications, and methodological strengths and limitations. ", "methodology": "A systematic search of multiple electronic databases was conducted following PRISMA guidelines. Peer-reviewed studies and relevant grey literature employing quantitative time-series analyses to assess efficiency metrics (e. g. , patient throughput, resource utilisation) were included. Studies were screened, selected, and their methodological quality assessed using a standardised checklist. ", "findings": "The review identified a predominant reliance on autoregressive integrated moving average (ARIMA) models, represented generally as Xt = c + =1^{p\ Xt-i + \ + =1^q\ -i, for forecasting service demand. A key theme was the consistent under-reporting of model uncertainty, with fewer than 30% of studies reporting prediction intervals. Model performance was frequently compromised by short, sparse, or non-stationary data series. ", "conclusion": "While time-series forecasting is a valuable tool for evaluating efficiency, its application in this context is often methodologically constrained. The lack of robust uncertainty quantification limits the utility of forecasts for strategic decision-making in health centre management. ", "recommendations": "Future research should prioritise the use of ensemble modelling techniques and explicitly report prediction intervals. Investment in building longer, higher-frequency administrative data series is essential to improve model reliability and support evidence-based health systems planning. ", "key words": "health systems research, operational efficiency, forecasting, time-series analysis, primary health care, resource allocation", "
Hassan et al. (Thu,) studied this question.