Hybrid Probabilistic Forecasting of Under-Five Malaria Admissions in Ghana: A Gaussian Process Regression with Holt-Winters Smoothing
arXiv:2606.00834v1 Announce Type: cross Abstract: Accurate malaria forecasting remains a major challenge in sub-Saharan Africa, where strong seasonality, reporting uncertainty, and non-stationary transmission dynamics reduce the reliability of conventional models. In Ghana, district-level malaria surveillance requires forecasting frameworks that are probabilistically rigorous and robust under limited data. This study proposes a hybrid framework integrating Gaussian Process Regression (GPR) with Holt-Winters exponential smoothing for modelling monthly under-five malaria admissions. GPR captures
The continuous advancements in AI and statistical modeling, combined with ongoing public health challenges in regions like sub-Saharan Africa, drive the development of more robust forecasting tools.
Accurate, probabilistic forecasting of health crises, especially in data-limited environments, is crucial for effective resource allocation and public health interventions, improving outcomes and potentially saving lives via more efficient policy making.
This paper offers a more reliable method for predicting disease outbreaks in challenging contexts, moving beyond conventional models by integrating AI with established statistical techniques.
- · Public Health Organizations
- · African Governments
- · Healthcare Tech Providers
- · AI/ML Researchers
- · Conventional Forecasting Models
Improved malaria control and prevention strategies in affected regions.
Reduced healthcare burden and economic impact due to more proactive health interventions.
Enhanced trust in AI-driven public health initiatives, potentially leading to wider adoption across other health challenges.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG