Oxford Researchers Use AI To Detect Antibiotic Resistance Faster Than Gold-Standard Testing
There is a lot of excitement about the potential of artificial intelligence (AI) in medicine. One of the most pressing health concerns around the globe is the rise in antibiotic resistance. Antibiotics are losing their effectiveness and this has created a critical need to develop better methods to detect and combat antibiotic resistance.
Researchers from the Oxford Martin School published a ground-breaking study where they used artificial intelligence AI to detect antimicrobial resistance (AMR). This new advancement will help novel and rapid antimicrobial susceptibility tests that can return results within as little as 30 minutes.
The new method to detect AMR relies on an innovative combination of fluorescence microscopy and AI. Deep training models are used to analyze bacterial cell images and detect the structural changes that occur in cells when they are treated with antibiotics. The study claims an accuracy of at least 80 percent on a per-cell basis across multiple antibiotics.
The method was tested on a range of clinical isolates of E.coli, and the deep-learning models were able to detect antibiotic resistance 10 times faster than established clinical methods considered to be the gold standard. According to the researchers, the new model can be used to identify whether cells in the clinical samples are resistant to a range of different antibiotics in the future.
There has been an increased interest in research on AI technologies, especially at educational institutions. The Oxford Martin School is a leading research department at the University of Oxford. It has over 30 pioneering research programs with over 200 academics working on finding solutions to the most pressing challenges around the globe. Earlier this week, an Oxford University study revealed how large Language Models (LLMs) pose a risk to science with false answers.
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.”
The Oxford team believes that the next step is to continue developing this method so it is more scalable for clinical use and make it more adaptable for use with different types of antibiotics and bacteria
According to the Global Antimicrobial Resistance (GRAM) Project in collaboration with the University of Oxford, almost 1.3 million people died due to AMR in 2019. The current testing methods rely on growing bacterial colonies in the presence of antibiotics. This method takes several days and is too slow for patients suffering from life-threatening conditions, such as sepsis, that require urgent treatment.
Doctors often prescribe antibiotics based on their medical experience rather than clinical tests. Ineffective antibiotics can make the condition worse and can even lead to increased antimicrobial resistance to antibiotics in the community.
The Oxford researchers believe that with further development, the new model can help decrease treatment times, minimize 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.”
The integration of AI in healthcare research and development has the potential to be revolutionary. Organizations are embracing these new technologies to gain valuable insights and uncover new methods to detect and treat medical conditions. Incilicio Medicine recently developed a new AI technique to find Alzheimer’s drug targets. As we step into 2024, AI is poised to begin shifting from excitement to deployment.