The global antimicrobial resistance (AMR) crisis is a major global health challenge, threatening 10 million lives a year by 2025, and new research presented at ESCMID Global 2026 reveals that the burden will continue to grow.
Rasha Elshenawy from the University of Hertfordshire’s Public Health and Patient Safety Unit in Hertfordshire, UK, presented research at ESCMID Global 2026 exploring how hospitals and clinicians can leverage AI in antimicrobial stewardship (AMS).1
After researching the use of AI at two NHS Foundation Trust hospitals in the UK, El-Shennawy found that machine learning algorithms can help predict the appropriateness of prescribing, timing of interventions and risks of antibiotics.1
How AI can help fight the AMR crisis
She explained: “AI can help generate warning signs and take corrective action based on antibiotic usage patterns when high resistance is predicted in specific locations within the hospital or in specific patient conditions.
“So AI can be used as an accelerator, it can be used as a decision support, it can be used as guidance for doctors to prescribe appropriately, and it can also be used by all healthcare professionals such as dispensing pharmacists, clinical pharmacists on ward rounds, nurses, etc.
“Appropriate use of AI holds great promise when it comes to antibiotic resistance and management.”
In this study, the predictive accuracy of the AI for prescription appropriateness was 84.7%.1
The AI system also identified 156 drug interactions and 89 dose adjustments that required intervention.1
Following the success of AI in supporting clinical care, technical validation confirmed 99.2% data accuracy and expert validation demonstrated strong clinical relevance.1
Despite a 40% increase in workload, the observed improvements remained robust across waves of the pandemic.1
Implementation in low- and middle-income countries
AMR disproportionately affects low- and middle-income countries (LMICs) and results in high mortality rates in certain regions.
In a separate study, El-Shennawy and his research team found that AI-enabled stewardship is technically feasible in LMICs, but implementation gaps are significant.2
“Low- and middle-income countries have severe constraints on supply chains, resources, policies, guidelines, education, and access that maintain all these barriers,” he said.
“It’s really important to focus on the facilitators who will help implement AI.”
The team called for mandatory cost-effectiveness analysis, patient-centered outcomes, co-design requirements, sustainable domestic funding, and capacity building for autonomous LMIC-led innovation in this area.2
El-Shenawy added: “Based on real-world data from these countries, we can implement tailored and targeted interventions for antibiotic stewardship.
“Another important issue is education: how these management strategies can be used to educate health care professionals in patient care and promote effective use of antibiotics.”
Responsible use of AI
In particular, El-Shenawy cautioned that AI needs to be properly validated before being implemented in clinical settings.
She warned: “If used appropriately, AI in antibiotic stewardship implementation, decision support, prediction, and antibiotic measurement will have a significant impact on patients. This is the most important impact of using AI.”
“In this regard, I am promoting the use of AI, but I am also promoting the responsible use of AI.
“Before we apply AI, we first need to validate it.
“It’s really important to make sure this AI provides good recommendations.”
El-Shenawy stressed that AI could only be used against the AMR crisis if hospitals put in place robust testing protocols.
“As hospitals and leaders implement AI, they must examine how well-suited it is as a tool and guide for decision support systems,” she concluded.
References
1 Elshenawy R. Real-time antimicrobial stewardship dashboard powered by machine learning for predictive prescribing and pandemic-resilient quality improvement. P2998. ESCMID Global 2026, April 17-21, 2026.
2 Aser M et al. Application of artificial intelligence in antimicrobial stewardship: A systematic review of effectiveness, implementation challenges, and equity considerations in low- and middle-income countries (LMICs). P3063. ESCMID Global 2026, April 17-21, 2026.
Featured image: I Viewfinder by Adobe Stock
