Harnessing Artificial Intelligence for malaria vector control in high malaria-burden Sub-Saharan African countries: A scoping review

Introduction: Malaria remains a leading cause of morbidity and mortality worldwide, with sub-Saharan Africa bearing the highest burden. Despite advances in vector control strategies, such as insecticide-treated nets and indoor residual spraying, challenges, including insecticide resistance and changing mosquito behaviour, threaten progress. Artificial intelligence (AI) offers innovative approaches to enhance malaria vector control through improved surveillance, environmental risk mapping and intervention optimisation. This review maps the application of AI in malaria vector control in the top 10 malaria-endemic countries in sub-Saharan Africa. Methods: A scoping review was conducted following the PRISMA-ScR guidelines. Systematic searches of PubMed and Google Scholar were performed in March 2025 using predefined AI- and malaria-related keywords combined with the names of the top 10 endemic countries: Nigeria, the Democratic Republic of the Congo, Uganda, Mozambique, Angola, Burkina Faso, Ghana, Mali, Niger, and Tanzania. Eligible studies included primary research articles in English that reported AI applications in malaria vector control. Data were extracted using a standardised form and synthesised narratively, focusing on AI techniques, vector control aspects, benefits, challenges, and research gaps. Results: The review identified diverse AI applications, including mosquito surveillance (age-grading, species identification, and blood meal analysis), and environmental risk mapping. Machine learning classifiers, deep learning models, and hybrid AI approaches are commonly used. The benefits of AI include improved accuracy, cost-effectiveness, scalability, and enhanced decision-making transparency. However, barriers such as limited field validation, ecological variability, data and infrastructure constraints, and ethical considerations have been noted. Significant research gaps include limited operational integration, sparse cross-country studies, and a lack of longitudinal evaluations. Conclusion: AI has significant potential to transform malaria vector control in sub-Saharan Africa by enabling data-driven, context-specific interventions. Addressing current implementation challenges and research gaps through enhanced validation, capacity building, and ethical governance is essential for leveraging AI tools to achieve malaria elimination goals in the region.