AI Improves Treatment of UTIs and Helps Address Antimicrobial Resistance

By HospiMedica International staff writers
Posted on 27 Nov 2024

Image: Artificial intelligence can improve how UTIs are treated and also help to address AMR (Photo courtesy of 123RF)

Antimicrobial resistance (AMR) occurs when microorganisms such as bacteria, viruses, fungi, and parasites evolve to become resistant to treatments that were previously effective. This resistance results in longer hospital stays, higher medical expenses, and increased mortality rates, presenting a major public health threat and potentially rendering common infections untreatable. Traditional diagnostic tests for urinary tract infections (UTIs), known as antimicrobial susceptibility testing (AST), use a standardized approach to identify the most effective antibiotics for treating bacterial or fungal infections. Now, new research has demonstrated that artificial intelligence (AI) can improve the treatment of UTIs and help combat AMR.

This research, conducted by the Centers for Antimicrobial Optimization Network (CAMO-Net) at the University of Liverpool (Liverpool, UK), utilized AI to develop prediction models for 12 antibiotics based on real patient data, comparing personalized AST with conventional methods. The personalized, data-driven approach resulted in more accurate treatment decisions, particularly with WHO Access antibiotics, which are less likely to lead to resistance. The findings of this research mark a significant advancement in addressing AMR. By prioritizing antibiotics from the WHO Access category and customizing treatment based on individual susceptibility, the personalized AST approach not only enhances the efficiency of testing but also contributes to global efforts to preserve the effectiveness of essential antibiotics.

“This research is important and timely for World AMR Awareness Week because it shows how combining routine health data with lab tests can help keep antibiotics working,” said Dr. Alex Howard, a consultant in medical microbiology at the University of Liverpool and researcher on the Wellcome Trust funded CAMO-Net, who led the research. “By using AI to predict when people with urine infections have antibiotic-resistant bugs, we show how lab tests can better direct their antibiotic treatment. This approach could improve the care of people with infections worldwide and help prevent the spread of antibiotic resistance.”

Related Links:
CAMO-Net