by University of Liverpool

Design of the microsimulation study. Credit: Nature Communications (2024). DOI: 10.1038/s41467-024-54192-3

New research from the Centers for Antimicrobial Optimization Network (CAMO-Net) at the University of Liverpool has shown that using artificial intelligence (AI) can improve how we treat urinary tract infections (UTIs), and help to address antimicrobial resistance (AMR).

AMR occurs when bacteria, viruses, fungi, and parasites evolve and no longer respond to treatments that were once effective. This resistance leads to longer hospital stays, higher medical costs, and increased mortality rates, posing a significant threat to public health and potentially rendering common infections untreatable.

Traditional UTI diagnostic tests, known as antimicrobial susceptibility testing (AST), uses a one-size-fits-all approach to determine which antibiotics are most effective against a specific bacterial or fungal infection.

This new research, published in Nature Communications, proposes a personalized method, using real-time data to help clinicians target infections more accurately and reduce the chance of bacteria becoming resistant to antibiotic treatment.

The research, led by Dr. Alex Howard, a consultant in medical microbiology at the University of Liverpool and researcher on the CAMO-Net, used AI to test prediction models for 12 antibiotics using real patient data and compared personalized AST with standard methods. The data-driven personalized approach led to more accurate treatment options, especially with WHO Access antibiotics, known for being less likely to cause resistance.

Dr. Alex Howard, said, “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. 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.”

The results of this study represent a significant step forward in addressing AMR. By prioritizing WHO access category antibiotics and tailoring treatment to individual susceptibility profiles, the personalized AST approach not only improves the efficiency of the testing process but also supports global efforts to preserve the effectiveness of critical antibiotics.

More information: Alex Howard et al, Personalised antimicrobial susceptibility testing with clinical prediction modelling informs appropriate antibiotic use, Nature Communications (2024). DOI: 10.1038/s41467-024-54192-3

Journal information:Nature Communications

Provided by University of Liverpool

---

Explore further

Using machine learning to identify bacterial resistance genes and the drugs to block them

ReplyReply to allForward