Image source: Adobe Stock/fusebulb

News • Susceptibility detection in Escherichia coli

How AI can detect antibiotic resistance in 30 minutes

Researchers supported by the Oxford Martin Programme on Antimicrobial Resistance Testing at the University of Oxford have reported advances towards a novel and rapid antimicrobial susceptibility test that can return results within as little as 30 minutes - significantly faster than current gold-standard approaches.

In their study published in Communications Biology, 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 analyse bacterial cell images and detect structural changes that may occur in cells when they are treated with antibiotics. The method was shown to be effective across multiple antibiotics, achieving at least 80% accuracy on a per-cell basis. 

The researchers say their model could be used to identify whether cells in clinical samples are resistant to a range of a wide variety of antibiotics in the future.

In an era where AMR poses a critical public health threat, our team has made a ground-breaking advancement toward rapid detection of AMR

Piers Turner

Co-author of the paper Achillefs Kapanidis, Professor of Biological Physics and Director of the Oxford Martin Programme on Antimicrobial Resistance Testing, said: ‘Antibiotics that stop the growth of bacterial cells also change how cells look under a microscope, and affect cellular structures such as the bacterial chromosome. Our AI-based approach detects such changes reliably and rapidly. Equally, if a cell is resistant, the changes we selected are absent, and this forms the basis for detecting antibiotic resistance.’ 

‘In an era where AMR poses a critical public health threat, our team has made a ground-breaking advancement toward rapid detection of AMR. This innovation may hold the potential to revolutionise the way we respond to infectious diseases, allowing for more precise and timely treatment decisions, ultimately saving lives,’ added co-author Dr Piers Turner, from the Oxford Martin Programme on Antimicrobial Resistance Testing and Department of Physics. 

The researchers tested their method on a range of clinical isolates of Escherichia coli, each with varying levels of resistance to the antibiotic ciprofloxacin. The 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 to be 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 usage for different types of bacteria and antibiotics. 

According to the Global Research on Antimicrobial Resistance (GRAM) Project – a partnership involving the University – almost 1.3 million people died in 2019 due to AMR.

Recommended article

Photo

Article • Bacterial defense mechanism

Antibiotic resistance: a global threat to healthcare

Antimicrobial resistance (AMR) is becoming more prevalent around the world, constituting a serious threat to public health. When bacteria acquire resistance against antibiotics, common medical procedures – for example, in surgery – become impossible due to the high infection risk. Keep reading to find out about AMR research, development of new antibiotics and antibiotic alternatives.

Current testing methods rely on growing bacterial colonies in the presence of antibiotics. However, such tests are slow, often requiring several days to understand how resistant bacteria are to a range of antibiotics.

hand in blue medical rubber glove holding petri dish with bacterial cultures, to determine antimicrobial resistance

Image source: Adobe Stock/jarun011

This can be problematic when patients have potentially life-threatening infections, such as sepsis, requiring urgent treatment. This usually forces doctors to either prescribe specific antibiotics based on their clinical experience or a cocktail of antibiotics known to be effective across multiple bacterial infections. However, if ineffective antibiotics are prescribed the patients’ infections may get worse and they will need to be treated with more antibiotics. One potential outcome of this is increased AMR to antibiotics in the community. 

The researchers say that if developed further, the rapid nature of their method may facilitate targeted antibiotic treatments – helping to decrease treatment times, minimise side effects, and ultimately slow down the rise of AMR. Co-author of the paper Aleksander Zagajewski, doctoral student with the University’s Department of Physics, said: ‘Time is beginning to run out for our antibiotic arsenal; we are hoping our novel diagnostics will pave the way for a new generation of precision treatments for the most sick patients.’ 

Researchers from across the University contributed to the study, including from the Department of Physics, Nuffield Department of Medicine, Sir William Dunn School of Pathology and Nuffield Department of Women’s Reproductive Health. Researchers from the Oxford University Hospitals NHS Foundation Trust’s Department of Microbiology and Infectious Diseases were also involved. 


Source: University of Oxford

26.11.2023

Related articles

Photo

News • Sensor solution

Wearable lung patch uses deep learning to detect asthma and COPD

Early detection and management of asthma and COPD is critical. US researchers have developed a deep learning model paired with a wearable sensor patch to automatically detect wheezing sounds.

Photo

News • Non-invasive risk assessment

Prostate cancer: avoiding unnecessary biopsies with AI

Combining risk markers, systematic evaluation of MRI images and AI, researchers aim to predict the risk of prostate cancer more accurately than before. This could save many patients from a biopsy.

Photo

News • Three-dimensional tissue processing

Pathology performs leap into 3D with AI

Adding a new dimension to pathology: Researchers explore new, deep learning models that can use 3D pathology datasets to make clinical outcome predictions for curated prostate cancer specimens.

Related products

Subscribe to Newsletter