beria-kalpelbe/malaria-risk-prediction

Enhancing Malaria Management in Africa # malaria-risk-prediction Bayesian Modelling for Malaria Risk Assessment in Chad: Identifying Spatiotemporal Hotspots for Targeted Interventions Malaria remains a major public health challenge in Chad, driven by environmental and climatic factors. This study employs advanced time series analysis and Bayesian modelling techniques to assess malaria risk across 23 regions in Chad, using data from the Programme National de Lutte contre le Paludisme (PNLP) and Era5 climate datasets spanning 2020 to 2023. By integrating malaria cases, deaths, and climate variables—particularly temperature and precipitation into a Bayesian panel data model, we identified significant spatial and temporal variations in malaria incidence. Precipitation emerged as a key driver of transmission, with the highest malaria risks observed in regions such as Mandoul, Logone Oriental, N’Djamena, Moyen Chari, Tandjile and Mayo Kebbi Est. The model also pinpointed the period from July to September as peak transmission period. With a Bayesian R-squared value of 87%, the model demonstrated strong forecast capability, offering valuable insights for targeted interventions, resource allocation, and policy-making. These findings provide a framework for enhancing malaria management strategies in Chad and contribute to global health initiatives aimed at reducing malaria incidence, in line with the third Sustainable Development Goal (SDG3).