5 Sources
[1]
AI is as good as pathologists at diagnosing Celiac disease, study finds
A machine learning algorithm developed by Cambridge scientists was able to correctly identify in 97 cases out of 100 whether or not an individual had coeliac disease based on their biopsy, new research has shown. The AI tool, which has been trained on almost 3,400 scanned biopsies from four NHS
[2]
AI matches pathologists in diagnosing celiac disease
University of CambridgeMar 27 2025 A machine learning algorithm developed by Cambridge scientists was able to correctly identify in 97 cases out of 100 whether or not an individual had celiac disease based on their biopsy, new research has shown. The AI tool, which has been trained on almost
[3]
AI is as good as pathologists at diagnosing celiac disease, study finds
A machine learning algorithm developed by Cambridge scientists was able to correctly identify in 97 cases out of 100 whether or not an individual had celiac disease based on their biopsy, new research has shown. The AI tool, which has been trained on almost 3,400 scanned biopsies from four NHS
[4]
Researchers develop AI tool that could speed up coeliac disease diagnosis
Cambridge study finds algorithm is as effective as a pathologist in detecting disease - and much quicker AI could speed up the diagnosis of coeliac disease, according to research. Coeliac disease is an autoimmune condition affecting just under 700,000 people in the UK, but getting an accurate
[5]
AI Improves Diagnosis Of Celiac Disease
FRIDAY, March 28, 2025 (HealthDay News) -- Liz Cox, 80, had been suffering from severe stomach pains and anemia for nearly 30 years before doctors finally diagnosed her with celiac disease. Cox first developed severe stomach pains in her 30s, after having her three children. "My doctor carried
Share
Copy Link
Cambridge researchers develop an AI tool that accurately diagnoses celiac disease from biopsy images, potentially speeding up diagnosis and reducing healthcare system pressures.

Researchers at the University of Cambridge have developed a machine learning algorithm that can diagnose celiac disease from biopsy images with an accuracy comparable to experienced pathologists. The study, published in the New England Journal of Medicine AI, demonstrates the potential of artificial intelligence to streamline and accelerate the diagnostic process for this common autoimmune condition
1
.Celiac disease, affecting approximately 1 in 100 people, is an autoimmune disorder triggered by gluten consumption. Diagnosis can be challenging due to the wide variety of symptoms and the subtle changes in intestinal tissue that must be identified through biopsy analysis
2
.The current gold standard for diagnosis involves a biopsy of the duodenum, which is then examined by pathologists using the Marsh-Oberhuber scale to assess the severity of villous damage. However, this process can be subjective and time-consuming, often leading to delays in diagnosis
3
.The Cambridge team trained their AI model on a diverse dataset of over 4,000 biopsy images from five different hospitals, using various scanners and imaging equipment. When tested on an independent set of nearly 650 images, the algorithm demonstrated remarkable accuracy:
4
Dr. Florian Jaeckle, a co-author of the study, highlighted the time-saving potential of the AI tool: "It takes a pathologist five to 10 minutes to analyze each biopsy, whereas the AI model can diagnose celiac disease straight away." This efficiency could significantly reduce waiting times for patients and alleviate pressure on healthcare systems
5
.Professor Elizabeth Soilleux, senior author of the research, emphasized the broader implications: "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."
Related Stories
The research team has been engaging with patient groups, including Celiac UK, to discuss the potential implementation of this technology. Patients have generally been receptive to the use of AI for diagnosis, likely due to their experiences with delays in receiving accurate diagnoses
1
.Dr. Bernie Croal, president of the Royal College of Pathologists, acknowledged the transformative potential of the AI tool but cautioned that further work is needed before it can be fully integrated into NHS practices. This includes investments in digital pathology infrastructure, IT systems, and training for pathologists
4
.The researchers plan to conduct larger clinical trials to further validate the algorithm's performance. Professor Soilleux and Dr. Jaeckle have also established a spinout company, Lyzeum Ltd, to commercialize the technology
2
.As AI continues to make inroads in medical diagnostics, this study represents a significant step forward in improving the speed and accuracy of celiac disease diagnosis, potentially benefiting patients and healthcare systems alike.
Summarized by
Navi
[2]
[3]
[5]
25 Oct 2024•Health

28 Aug 2025•Health

15 Nov 2024•Science and Research

1
Technology

2
Technology

3
Policy and Regulation
