Calendário de eventos

Two Presentations: "An overview of Seasonal Malaria Chemoprevention (SMC) from implementation studies to scale-up." and "Assessing the effectiveness of Seasonal Malaria Chemoprevention in northern Mozambique with routine surveillance data."

Join us for the next AMMnet Hackathon! This two-hour hands-on extension session focuses on building practical data wrangling skills in R using the tidy verse, with an emphasis on structured, reproducible workflows for data analysis. Participants will learn how to recognise and address common data challenges in malaria analytics, including working with messy, fragmented, and multi-source datasets. The session will cover core data wrangling techniques such as transforming raw data into tidy, analysis-ready formats, reshaping datasets, and integrating multiple data sources. We will explore different approaches to solving the same wrangling problems, helping participants develop flexible and robust problem-solving strategies. The session will also emphasise best practices for improving clarity, reproducibility, and efficiency in data pipelines, and demonstrate how wrangled datasets can be directly used for downstream tasks such as visualisation and analysis. The session will be interactive, with opportunities for participant engagement. The session will also include a real-world dataset, guiding participants from raw data through to analysis-ready outputs.

This presentation explores how machine learning techniques are being used to improve the prediction and detection of malaria outbreaks. Drawing on a systematic review of research published between 2013 and 2023, the session highlights how models such as artificial neural networks, decision trees, random forests, and support vector machines are applied to analyze environmental and socio-economic factors including temperature, rainfall, and population density. These approaches have demonstrated diagnostic accuracies ranging from 80–95%, showing significant promise for forecasting outbreaks before they occur. The presentation will also discuss the strengths of these models, such as their predictive capability, as well as key challenges including data requirements and limitations in applying models across different settings.

This presentation, titled “Preliminary Analysis of the Impact of the Introduction of the Malaria Vaccine on the Incidence of Severe Malaria Among Children Under 5,” examines the epidemiological situation in the health districts of Edéa, Japoma, and Mbanga in Cameroon between 2020 and 2024. Malaria remains a major endemic disease in Cameroon, particularly affecting young children and pregnant women, which led to the inclusion of the malaria vaccine (MV) in the Expanded Program on Immunization in 2024. The study is based on a retrospective analysis of surveillance data and assesses the correlation between third-dose vaccination coverage and trends in severe malaria cases to determine the initial effectiveness of this public health intervention. The results highlight a persistent challenge with a high number of severe malaria cases, as well as a significant decline in vaccination coverage between the first and third doses across all districts studied. However, the analysis reveals a strong negative correlation (r = -0.86) between full vaccination coverage and the increase in severe cases in 2024 compared to 2023. This suggests that, although the overall incidence remains a concern, higher vaccination coverage helps limit the increase in severe forms of the disease. The study therefore underscores the importance of strengthening adherence to the full vaccination schedule to maximize the vaccine’s protective impact in infants.