BY THE OPTIMIST DAILY EDITORIAL TEAM
A team of researchers at the University of Cambridge developed an artificial intelligence tool that may drastically shorten the time it takes to diagnose celiac disease, offering hope to hundreds of thousands of patients in the UK and potentially easing pressure on the NHS.
Celiac disease, an autoimmune condition triggered by gluten, affects an estimated 700,000 people in the UK. Yet, for many, getting a diagnosis can be a drawn-out and frustrating process, often taking years. Left untreated, celiac disease can lead to severe complications, including malnutrition, osteoporosis, anemia, infertility, and even increased risks of certain cancers.
Currently, diagnosis usually involves a two-step process: a blood test for antibodies followed by a biopsy of the small intestine. Pathologists examine the biopsy for damage to the villi—tiny projections lining the gut that are essential for nutrient absorption.
But now, Cambridge scientists have introduced a machine-learning algorithm that could streamline this process. Trained on more than 4,000 biopsy images collected from five different hospitals, using equipment from four manufacturers, the AI model has demonstrated accuracy equal to that of human pathologists.
Fast, effective, and scalable
What makes the new AI tool especially promising is its speed. According to Dr. Florian Jaeckle, a co-author of the study, it typically takes a pathologist five to ten minutes to analyse each biopsy. In contrast, the AI model delivers a diagnosis in less than a minute— “as soon as a biopsy is scanned.”
“Duodenal biopsies (and in particular tests for celiac disease) are often put at the back of the pathologist’s lists as they are not as serious as, for example, a possible cancer case,” Jaeckle explained. “This means that patients often have to wait weeks or even months to find out if they have celiac disease. With AI, they could get a result almost instantly.”
Relieving pressure on health systems
The implications for healthcare providers are significant. At a time when diagnostic services are under enormous strain, this kind of AI technology could help reduce backlogs and cut NHS waiting times.
“It can take many years to receive an accurate diagnosis, and at a time of intense pressures on healthcare systems, these delays are likely to continue,” said Professor Elizabeth Soilleux, a consultant haematopathologist and senior author of the research. “AI has the potential to speed up this process, allowing patients to receive a diagnosis faster, while at the same time taking pressure off NHS waiting lists.”
The study, published in the New England Journal of Medicine AI, was supported by Coeliac UK, Innovate UK, the Cambridge Centre for Data-Driven Discovery, and the National Institute for Health and Care Research.
Pathology’s digital future
Experts in the field have applauded the research. Dr. Bernie Croal, president of the Royal College of Pathologists, noted the potential for the technology to “radically transform how we diagnose celiac disease, benefiting patients by speeding up diagnosis, improving health outcomes and shortening waiting lists.”
However, Croal also stressed the need for further development before the AI tool can be fully integrated into routine NHS practice. “While the advent of AI in pathology is very exciting, and the NHS could be a world leader in the development and use of AI in pathology, more work will be needed,” he said. That includes investment in digital infrastructure, better IT systems for data sharing, and specific training for pathologists to understand and use AI tools effectively.
Looking ahead
As the NHS and other healthcare systems seek innovative ways to improve care delivery and reduce bottlenecks, tools like this Cambridge-developed AI model could become a cornerstone of modern diagnostics. Its immediate application in celiac disease may be just the beginning.
With further investment, validation, and clinical integration, the technology could not only accelerate diagnosis but also help prioritize pathologists’ workloads, enabling them to focus on more complex or urgent cases. For the patients awaiting answers, that could mean a quicker path to relief, treatment, and improved quality of life.
Source study: New England Journal of Medicine AI—Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis
