Antimicrobial resistance (AMR) is a major global health challenge that threatens the effective prevention and treatment of infections. It arises from increasing resistance rates, limited diagnostic capacity, inappropriate antimicrobial use, and a declining pipeline of new antibiotics. These challenges highlight the need for innovative approaches to complement existing AMR control strategies. Artificial intelligence (AI) has emerged as a valuable tool to address the complexity and scale of AMR. This narrative review examines how AI can be more effectively integrated into key components of AMR management. By analyzing large clinical and laboratory datasets, AI-based surveillance and predictive models enable near–real-time monitoring of resistance patterns and early outbreak detection. AI-powered diagnostic tools, including image analysis and genomic methods, improve rapid pathogen identification and prediction of antimicrobial susceptibility. In clinical practice, AI-driven decision support systems strengthen antimicrobial stewardship by optimizing prescribing and monitoring antibiotic use. In addition, deep learning approaches accelerate antimicrobial drug discovery and repurposing, reducing development timelines. AI also enhances the detection and surveillance of resistance genes through genomic and metagenomic analyses across human, animal, and environmental settings. Despite its potential, AI applications in AMR face challenges related to data quality, bias, interoperability, privacy, and clinician adoption. Therefore, AI should be seen as a tool that supports, rather than replaces, existing AMR strategies. When well-regulated and integrated within One Health frameworks, AI can strengthen surveillance, improve treatment decisions, and support evidence-based interventions to curb antimicrobial resistance.
Salama et al. (Sun,) studied this question.