Use of Artificial Intelligence for Duodenal Biopsy for Celiac Disease: Developing a Prediction Model for…

AI / informaticsClinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association· Aug 2026

Use of Artificial Intelligence for Duodenal Biopsy for Celiac Disease: Developing a Prediction Model for Histopathology Diagnosis.

Claire L Jansson-Knodell, Erica Savage, Katherine Poissant … Alberto Rubio-Tapia

Read paper

Gastrointestinal & Liver PathologyAI / informaticsDiagnosisQ1IF 7.0

AI model reliably distinguishes celiac disease from normal duodenal biopsy histology.

Use of Artificial Intelligence for Duodenal Biopsy for Celiac Disease: Developing a Prediction Model for Histopathology Diagnosis.

Claire L Jansson-Knodell … Alberto Rubio-Tapia

Clinical gastroenterology and hepatology · Aug 2026

Background

Duodenal biopsy combined with tissue transglutaminase (tTG-IgA) antibodies is the gold standard for celiac disease diagnosis.

Purpose

We aimed to determine if deep learning-based image analysis can be used on duodenal biopsies to accurately diagnose celiac disease.

Methods

Were grouped into 5 categories: normal, celiac disease, increased intraepithelial lymphocytes (intraepithelial lymphocytes) only, intraepithelial lymphocytes with a positive tTG-IgA antibody, and seronegative villous atrophy.

n = 2100 patients

Results

AUC 0.992

AUROC scale to 1.0; near-perfect at telling celiac from normal tissue

n = 2100 patients

More results

For all categories, the average AUC was 0.872 with an accuracy of 74%.

To distinguish celiac disease from seronegative villous atrophy the average AUC was 0.810 with accuracy 76%.

“

Conclusion · 1 of 2

This deep learning model can discriminate between celiac disease and normal histology.

Conclusion · 2 of 2

It can also separate patients into 5 classifications, representing a promising tool that would benefit from further optimization to improve diagnostic accuracy, reduce the manual pathology review burden, and enhance resource management.

Use of Artificial Intelligence for Duodenal Biopsy for Celiac Disease: Developing a Prediction Model for Histopathology Diagnosis.

Use of Artificial Intelligence for Duodenal Biopsy for Celiac Disease: Developing a Prediction Model for Histopathology Diagnosis.

Related papers