To mark World Antimicrobial Awareness Week, researchers supported by the Oxford Martin Program in Antimicrobial Resistance Testing at the University of Oxford report progress towards an innovative, rapid antimicrobial susceptibility test , capable of delivering results in just 30 minutes, which is significantly faster than current gold. -standard approaches.
The study titled “Deep learning and single-cell phenotyping for rapid detection of antimicrobial susceptibility in Escherichia coli” was published in Communication biology.
In their study, the team used a combination of fluorescence microscopy and artificial intelligence (AI) to detect antimicrobial resistance (AMR). This method relies on training deep learning models to analyze images of bacterial cells and detect structural changes that may occur in the cells when they are treated with antibiotics. The method has been shown to be effective across multiple antibiotics, achieving an accuracy of at least 80% per cell.
The researchers say their model could be used in the future to determine whether cells in clinical samples are resistant to a wide range of antibiotics.
Paper co-author Achillefs Kapanidis, professor of biological physics and director of the Oxford Martin Program in Antimicrobial Resistance Testing, said: “Antibiotics that stop the growth of bacterial cells also change the appearance of cells at the same time. microscope and affect cellular structures such as ”
The researchers tested their method on a range of clinical isolates of E. coli, each exhibiting varying levels of resistance to the antibiotic ciprofloxacin. Deep learning models were able to detect antibiotic resistance reliably and at least 10 times faster than established state-of-the-art clinical methods considered the gold standard.
The team hopes to continue developing their method so that it becomes faster and more scalable for clinical use, as well as adapting its use to different types of bacteria and antibiotics.
According to the Global Research Project on Antimicrobial Resistance (GRAM), a partnership involving the university, nearly 1.3 million people died in 2019 due to AMR.
Current testing methods rely on the growth of bacterial colonies in the presence of antibiotics. However, these tests are slow and often require several days to understand the degree of resistance of bacteria to a range of antibiotics.
This can be problematic when patients suffer from life-threatening infections, such as sepsis, requiring urgent treatment. This generally requires doctors to prescribe either specific antibiotics based on their clinical experience or a cocktail of antibiotics known to be effective against several bacterial infections.
However, if ineffective antibiotics are prescribed, patients’ infections may become worse and they will need to be treated with more antibiotics. One potential outcome of this situation is increased AMR to antibiotics in the community.
The researchers say that if developed further, the rapid nature of their method could facilitate targeted antibiotic treatments, helping to reduce treatment duration, minimize side effects and ultimately slow the rise of AMR.
Paper co-author Aleksander Zagajewski, a doctoral student in the university’s physics department, said: “Time is running out for our arsenal of antibiotics; We hope our new diagnostics will pave the way for a new generation of precision treatments for the sickest patients.
Alexander Zagajewski et al, Deep learning and single-cell phenotyping for rapid detection of antimicrobial susceptibility in Escherichia coli, Communication biology (2023). DOI: 10.1038/s42003-023-05524-4
Provided by the University of Oxford
Quote: Study shows how AI can detect antibiotic resistance in as little as 30 minutes (November 21, 2023) retrieved November 21, 2023 from https://phys.org/news/2023-11-ai-antibiotic-resistance -minutes.html
This document is submitted to . Except for fair use for private study or research purposes, no part may be reproduced without written permission. The content is provided for information only.