An artificial intelligence algorithm developed by researchers at the University of Liverpool is demonstrating success in assisting doctors with antibiotic prescriptions for urinary tract infections (UTIs), a common bacterial infection, with the aim of slowing the rise of antimicrobial resistance (AMR). The system, detailed in recent research, blends the judgment of experienced physicians with data-driven predictions to determine the most appropriate antibiotic for individual patients.
Unlike standard antibiotic prescribing guidelines, the novel AI utilizes a “utility function” to assess the benefits and drawbacks of each antibiotic option on a case-by-case basis. This allows for a more personalized approach to treatment, potentially reducing the overuse of broad-spectrum antibiotics and mitigating the development of resistance. The research, published in September 2025 in The Lancet Infectious Diseases, highlights the potential of AI to address one of the most pressing global health threats.
According to Dr. Alexander Howard, from the University of Liverpool’s Department of Pharmacology &. Therapeutics, AMR represents a “top global public health and development threat.” He cited statistics indicating that bacterial AMR was directly linked to 1.27 million deaths globally in 2019 and contributed to a further 4.95 million deaths. “In an era where antimicrobial resistance continues to increase, innovative solutions to facilitate precision use of antimicrobials are required – our utility-based system may present such a solution,” Dr. Howard stated.
Simulation studies, utilizing real-world healthcare data, revealed that the AI’s recommendations were comparable in quality to those made by human doctors. However, the algorithm demonstrated a lower propensity to suggest antibiotics that contribute to resistance and a greater inclination to recommend oral medications over intravenous administration. The AI also incorporates a safety mechanism designed to prioritize the most effective antibiotic when a patient presents with severe illness.
The development of this AI-driven system is part of a broader effort at the University of Liverpool focused on “Therapeutics Innovation and Infection Resilience.” Researchers emphasize that antibiotic resistance jeopardizes numerous medical procedures, from routine surgeries to cancer treatments, and significantly increases healthcare costs. The university’s research aims to develop predictive and preventative strategies to safeguard the long-term effectiveness of antibiotics.
Dr. Howard emphasized the need for further research across diverse global settings to validate the findings, particularly in regions heavily impacted by antibiotic resistance. He noted that while the study demonstrates the potential of combining AI with clinical expertise to improve antibiotic prescribing practices, further investigation is crucial to ensure widespread applicability and patient safety.
