Get Healthy!

• Posted March 28, 2025

AI Improves Diagnosis Of Celiac Disease

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 out various tests, but celiac disease wasn't very well known then, so I wasn't tested for that,” Cox, who lives in Linton, England, recalls. “I was quite tired, but I just carried on because you have to when you've got three children and a husband, don't you?”

Now, a new artificial intelligence-driven breakthrough might be able to prevent others from suffering in silence as Cox did, researchers said.

An AI program correctly identified in 97 out of 100 cases whether a person had celiac disease based on biopsy results, researchers reported March 27 in the New England Journal of Medicine AI.

The AI could speed up diagnosis of celiac disease, researchers said.

“Celiac disease affects as many as 1 in 100 people and can cause serious illness, but getting a diagnosis is not straightforward,” senior researcher Elizabeth Soilleux, a professor of pathology at the University of Cambridge in the U.K., said in a news release.

“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,” Soilleux continued. “AI has the potential to speed up this process, allowing patients to receive a diagnosis faster.”

Celiac disease is an autoimmune disorder in which eating gluten causes the immune system to turn on the digestive system, leading to damage in the small intestine.

Symptoms can include stomach cramps, diarrhea, skin rashes, weight loss, fatigue and anemia, researchers said.

Only about 30% of people with celiac disease are properly diagnosed, according to the Celiac Disease Foundation.

The gold standard for diagnosing celiac disease is through a biopsy of the duodenum, which is part of the small intestine, researchers said.

Pathologists examine biopsy samples under a microscope to look for damage to the villi, the tiny finger-like projections that line the inside of the small intestine and absorb nutrients from digested food.

However, it can be tough for pathologists to properly judge these biopsies, which might feature very subtle changes in a person’s villi. Previous studies have found that pathologists disagree on celiac disease diagnoses in more than 1 in 5 cases.

To try and improve diagnosis, researchers trained a new AI tool on nearly 3,400 biopsies from hospitals in the U.K.’s National Health Service, including more than 4,000 images captured from those biopsies.

The team then tested the AI on another set of nearly 650 biopsy images.

The AI correctly identified more than 95 cases out of 100 people who’d been diagnosed with celiac disease, results show.

It also correctly ruled out celiac disease in nearly 98 of 100 cases among people who didn't have the disorder.

Pathologists asked to look at the same images were as likely to agree with the AI model as they were with a second pathologist, the study found.

“This is the first time AI has been shown to diagnose as accurately as an experienced pathologist whether an individual has celiac or not,” lead investigator Florian Jaeckle, a research fellow at the University of Cambridge, said in a news release.

“Because we trained it on data sets generated under a number of different conditions, we know that it should be able to work in a wide range of settings, where biopsies are processed and imaged differently,” he added.

Researchers next plan to test the AI in a much larger group of patients before submitting it to review by regulators.

In Cox’s case, a strict gluten-free diet improved her symptoms almost immediately.

“Some people say, ‘Have a little bit’, but no, it's a strict diet, because you don't know what it's doing to your insides,” Cox said. “It's just mind over matter, isn't it? You can't have it, end of story.”

Cox is impressed with the new AI program developed at Cambridge, and hopes it will help others get a diagnosis more quickly than she did.

“You hear stories from other people, and they've waited a long time. They go back and forward to the doctor's often, with various odd symptoms, and perhaps the doctors don't always test them for that,” she said.

“Anything that makes the system quicker must be a good thing, because once you've been diagnosed and you know you can't have gluten, then you know what to do, and you feel so much better,” Cox concluded.

More information

The Celiac Disease Foundation has more on celiac disease.

SOURCE: University of Cambridge, news release, March 27, 2025