Applications of Artificial Intelligence in Malaria Vector Control in East Africa: A Scoping Review of Existing Evidence, Challenges, and Future Prospects

Abstract

Background: Malaria remains a leading cause of morbidity and mortality in East Africa despite decades of control efforts. Interventions such as long-lasting insecticidal nets (LLINs), indoor residual spraying (IRS), and larval source management have reduced transmission, yet progress is threatened by insecticide resistance, climate variability, and evolving mosquito behaviour.
Objective: This scoping review explores the application of artificial intelligence (AI) malaria vector control across East Africa. It aims to synthesize existing evidence, identify challenges, and inform future research and policy directions.
Methods: A comprehensive literature search was conducted using electronic databases and grey literature sources, following the PRISMA for Scoping Review guidelines. PubMed, Google Scholar, Science Direct and IEEE Xplore were databases used to search for scientific evidence. Studies were included if they addressed artificial intelligence applications in malaria surveillance, prediction, or intervention optimization within East African contexts. Data were charted synthesised across key thematic domains.
Results: Six scientific studies met the inclusion criteria for this scoping review. Evidence suggests growing interest in the use of artificial intelligence for vector habitat mapping, transmission risk forecasting, and malaria vector identification and surveillance. While these approaches show promise in enhancing malaria control, challenges persist, including limited data quality, algorithmic bias, and weak integration into national malaria programs.
Conclusion: Artificial intelligence offers significant potential to strengthen malaria vector control in East Africa by supporting data-driven, targeted interventions particularly through improved prediction, surveillance, and decision-making tools. However, their implementation remains limited, with notable regional gaps and operational challenges. Future work should focus on translating existing innovations into field-ready tools, expanding research across underrepresented countries, and fostering cross-sector collaboration to ensure AI contributes meaningfully to malaria vector control with elimination goals.