Translational applications of artificial intelligence and machine learning for mosquito-borne disease control in low- and middle-income countries.

OBJECTIVES: To synthesize evidence on the application of artificial intelligence (AI) and machine learning (ML) for mosquito-borne disease (MBD) control in low- and middle-income countries (LMICs), with emphasis on translational integration into routine public health decision-making systems. STUDY DESIGN: Structured narrative review. METHODS: Peer-reviewed studies published between 2010 and 2025 were identified from PubMed, Scopus, and Google Scholar using predefined search terms combining mosquito-borne diseases, AI/ML techniques, and LMIC relevance. Studies were included if they applied AI/ML to surveillance, outbreak prediction, vector monitoring, diagnostics, or intervention planning in LMIC contexts. Evidence was thematically synthesized and qualitatively appraised for translational readiness, implementation feasibility, and public health relevance. RESULTS: AI/ML applications demonstrate strong technical performance in outbreak forecasting, mosquito species identification, spatial risk mapping, and microscopy-based malaria diagnostics. However, approximately half of identified studies focus on surveillance and forecasting, while fewer address intervention optimization or policy integration. Most applications remain proof-of-concept, relying on retrospective datasets with limited prospective validation, cost-effectiveness evaluation, or sustained embedding within national health systems. Translational bottlenecks are most pronounced between model validation and real-world deployment. CONCLUSIONS: AI/ML holds meaningful potential to strengthen MBD control in LMICs when embedded within integrated digital public health systems. Advancing translational impact will require investments in interoperable data infrastructure, local technical capacity, ethical governance frameworks, and implementation science to ensure scalable, sustainable, and policy-aligned deployment.