The application of artificial intelligence in surveillance and control for antimicrobial resistance in hospital-acquired infections

This narrative review highlights how artificial intelligence (AI) can significantly enhance surveillance and control of antimicrobial resistance (AMR) in hospital-acquired infections (HAIs), addressing the limitations of traditional, often fragmented and reactive systems. AI applications—including machine learning models using microbiology data, electronic health records, and hospital workflows—can predict the emergence and spread of resistant pathogens, enable patient-level risk stratification, and support early-warning systems for outbreak detection. Case studies from Europe, Asia, and Africa demonstrate the practical potential of these tools, although variability in study design and implementation remains a challenge. The review concludes that, with appropriate ethical, regulatory, and capacity-building frameworks, AI could strengthen infection control, improve antimicrobial stewardship, and provide more proactive and resilient AMR management in hospital settings.