Comparative evaluation of a hybrid machine learning-human adjudication paradigm for endoscopic scoring in ulcerative colitis
The 2M+1H central reading paradigm provides statistically non-inferior accuracy with greater operational efficiency and potentially enhanced reproducibility. Prospective validation against clinical, biomarker and histological outcomes is warranted.
Authors
- Shrujal S. Baxi (ORCID: https://orcid.org/0000-0002-8411-0658)
- Chakib Battioui (ORCID: https://orcid.org/0000-0003-1369-9044)
- Yeli Wang
- Mohammad Haft‐Javaherian (ORCID: https://orcid.org/0000-0002-8551-5008)
- Klaus Gottlieb (ORCID: https://orcid.org/0000-0002-3747-2541)
- Pavel Brodskiy (ORCID: https://orcid.org/0000-0002-1951-7734)
- Daniel Colucci (ORCID: https://orcid.org/0009-0007-8272-7228)
- Darren Thomason
Institutions
- Eli Lilly (United States) (US)
Publication Details
- Journal
- BMJ Open Gastroenterology
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1136/bmjgast-2025-001959
- Primary Topic
- Inflammatory Bowel Disease
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Eli Lilly and Company