This ongoing scoping review aims to systematically map the evidence on artificial intelligence (AI) and machine learning (ML) applications for antimicrobial resistance (AMR) prediction, with a specific focus on implications for low- and middle-income countries (LMICs), particularly sub-Saharan Africa and Kenya.
The review follows the Arksey and O'Malley (2005) framework and will be reported according to the PRISMA Extension for Scoping Reviews (PRISMA-ScR). A systematic search of PubMed/MEDLINE and Google Scholar is being conducted between January and March 2025 using twelve predefined search term combinations. Studies published from January 2015 to March 2025 that apply AI or ML to predict AMR phenotypes are eligible for inclusion.
To date, 43 studies have met the inclusion criteria and are being extracted. The objectives are: (1) to map the current evidence landscape across geographic regions, algorithms, and data types; (2) to critically appraise the clinical value and predictive performance of existing models; (3) to identify disparities between high-income and LMIC research outputs; and (4) to delineate barriers to equitable global deployment, including data infrastructure gaps and the absence of explainable AI applications.
Data extraction and qualitative synthesis are ongoing. Results will be submitted for publication upon completion.