Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis
Our model achieved pathologist-level performance in diagnosing the presence or absence of coeliac disease from a representative set of duodenal biopsies, representing a significant advancement towards the adoption of machine learning in clinical practice. Additionally, it demonstrated strong generalisability, performing equally well on biopsies from a previously unseen hospital. We concluded that our model has the potential to revolutionise duodenal biopsy diagnosis by accurately identifying or ruling out coeliac disease, thereby significantly reducing the time required for pathologists to make a diagnosis.
Authors
- Benjamin Schreiber (ORCID: https://orcid.org/0000-0001-9555-8880)
- James Denholm (ORCID: https://orcid.org/0000-0002-2389-3134)
- Shelley Evans (ORCID: https://orcid.org/0000-0003-3242-6017)
- Mark J. Arends (ORCID: https://orcid.org/0000-0002-6826-8770)
- Adrian C Bateman (ORCID: https://orcid.org/0000-0003-2222-4104)
- James Chan
- Florian Jaeckle (ORCID: https://orcid.org/0009-0002-4607-6476)
- Elizabeth J. Soilleux (ORCID: https://orcid.org/0000-0002-4032-7249)
- Sonali Natu
- Mike N. Wicks
Institutions
- North Tees and Hartlepool NHS Foundation Trust (GB)
- University of Cambridge (GB)
- University Hospital of North Tees (GB)
- Cambridge University Hospitals NHS Foundation Trust (GB)
- Edinburgh Cancer Research (GB)
- University Hospital Southampton NHS Foundation Trust (GB)
Publication Details
- Journal
- NEJM AI
- Published
- 2025-03-27
- DOI
- https://doi.org/10.1056/aioa2400738
- Citations
- 13
- Primary Topic
- Celiac Disease Research and Management
- Type
- article
- Field-Weighted Citation Impact
- 23.54