Hybrid Probabilistic Forecasting of Under-Five Malaria Admissions in Ghana: A Gaussian Process Regression with Holt-Winters Smoothing

2026-05-30 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

A new hybrid framework integrates Gaussian Process Regression (GPR) with Holt-Winters exponential smoothing to forecast monthly under-five malaria admissions in Ghana. This model addresses challenges like strong seasonality, reporting uncertainty, and non-stationary transmission dynamics prevalent in sub-Saharan Africa. Using ten years of district-level data (2014-2023), the hybrid approach achieved an R^2 = 0.9906, significantly outperforming Holt-Winters alone (R^2 = 0.8213). It also demonstrated 94.2% of residuals within ± 2σ bounds. Forecasts for 2024-2028 project average monthly admissions between approximately 8,000 and 12,200 cases. Spatio-temporal analysis revealed pronounced ecological heterogeneity, with northern high-burden districts maintaining stable relative patterns despite large absolute fluctuations. This scalable probabilistic framework supports Ghana's national malaria control strategy.

Key takeaway

For public health analysts and epidemiologists tasked with improving malaria surveillance in endemic regions, this hybrid GPR and Holt-Winters model offers significantly enhanced forecasting accuracy. You should consider integrating such probabilistic frameworks to better account for seasonality and non-linear dynamics, enabling more reliable early warning systems and resource allocation. This approach provides robust, scalable predictions crucial for national malaria control strategies.

Key insights

Combining GPR with Holt-Winters provides robust probabilistic malaria forecasting, capturing non-linearity and seasonality.

Principles

• GPR captures non-linear behavior and predictive uncertainty.
• Holt-Winters stabilizes long-horizon forecasts and preserves seasonal structure.
• Ecological heterogeneity impacts malaria transmission patterns.

Method

A hybrid framework integrates Gaussian Process Regression with Holt-Winters exponential smoothing, validated using rolling-origin expanding-window analysis.

In practice

• Apply for malaria early warning systems.
• Use for operational planning in endemic regions.
• Support national malaria control strategies.

Topics

• Malaria Forecasting
• Gaussian Process Regression
• Holt-Winters Smoothing
• Public Health Surveillance
• Ghana
• Probabilistic Models

Best for: AI Scientist, Research Scientist, Data Scientist

Related on AIssential

• ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting — ProbRes is a post-hoc calibration method that learns volatility dynamics for robust probabilistic time series forecasting in heteroskedastic data.
• Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation — Time-aware diffusion and preference disentanglement significantly enhance generative recommender performance by modeling evolving user interests.
• Bridging the Last Mile of Time Series Forecasting with LLM Agents — LLM agents can bridge the gap between statistical time series forecasts and business-ready predictions by integrating weakly structured contextual information.
• Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations — Embedding physical priors into continuous-time latent dynamics improves Remaining Useful Life prediction under irregular observations.
• VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting — VLBM improves multivariate time series forecasting by explicitly separating stable dynamics from OOD deviations using a latent basis model.
• Why Do Time Series Models Need Long Context Windows? — Long context windows in time series forecasting primarily reduce uncertainty in identifying the data-generating process, crucial for optimal predictions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.