article · Scientific Reports
Evaluating long-term trends in child health is vital for guiding public health planning and resource allocation. Using data from the Global Health Observatory covering 1990 to 2023, time-series forecasting techniques were applied to project under-five mortality rates in Ethiopia up to 2030. Three models were evaluated: Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing, and Bayesian Structural Time Series. ARIMA achieved the best overall performance, recording the lowest Mean Absolute Error and Mean Absolute Percentage Error alongside satisfactory residual diagnostics. Projections indicate that Ethiopia's under-five mortality rate will decrease to 34.96 deaths per 1,000 live births by 2030. This trajectory suggests the country will struggle to meet the Sustainable Development Goal target of 25 or fewer deaths per 1,000 live births unless the current annual rate of reduction approximately doubles through strengthened national health interventions.
Tracking child mortality projections provides critical evidence for national health planning and resource allocation. With millions of children dying globally before age five, accurate forecasting shows whether existing health initiatives are sufficient. For Ethiopia, identifying that mortality reduction is lagging behind global targets demonstrates an urgent need for government bodies to intensify life-saving child health policies and healthcare interventions.
The abstract does not indicate an application pathway.
AI-generated from the published abstract. Always read the original work before citing.
The under-five mortality rate (U5MR) refers to the probability a newborn would die before reaching exactly 5 years of age, expressed per 1,000 live births. It is a key indicator of child health and overall development. Despite global progress, an estimated 4.9 million children died before reaching age five in 2024. Ethiopia has made substantial progress in reducing U5MR; however, the current pace of decline raises concerns about achieving Sustainable Development Goal (SDG) 3.2.1, which aims to reduce U5MR to ≤ 25 deaths per 1,000 live births by 2030. Time-series forecasting is increasingly used in public health for evidence-based planning, yet evidence using updated data remains limited for Ethiopia. Therefore, this study aims to forecasts Ethiopia’s U5MR up to 2030 and assesses progress toward the SDG target. The study used U5MR estimates for Ethiopia from the Global Health Observatory Data Repository (1990–2023). Three time‑series forecasting models—Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS), and Bayesian Structural Time Series (BSTS)—were fitted. The final model was selected based on the lowest values of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) combined with satisfactory residual diagnostics, indicating no remaining autocorrelation. ARIMA achieved the lowest MAE (0.3872) and MAPE (0.7290%), while ETS showed a marginally lower RMSE (0.4441). ARIMA was selected based on overall performance and residual diagnostics. Using this model, Ethiopia’s U5MR is projected to decline to 34.96 deaths per 1,000 live births (95% PI: 26.45–43.48) by 2030. Ethiopia may face challenges in achieving the SDG 3.2.1 target if the current pace of decline continues; therefore, the annual rate of reduction would need to approximately double. Accordingly, the Ministry of Health should further strengthen child health interventions and related policies.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1038/s41598-026-66258-x
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
