Using artificial intelligence to model expert panel diagnosis of cholecystitis severity
A transformer-based AI model can be trained on consensus from an expert panel to predict ratings of cholecystitis severity (Parking Grading Scale), performing competitively with some individual experts at predicting PGS when compared to the panel-based ground truth. However, variance and subjectivity of PGS remain, thus presenting its limitations as a ground truth for computer vision-based models.
Authors
- Griffin Olsen
- Eric C. Sorenson (ORCID: https://orcid.org/0009-0004-1991-9647)
- Sebastiano Bartoletti (ORCID: https://orcid.org/0009-0007-1502-1233)
- Janice H. Yang
- Emmett D. Goodman (ORCID: https://orcid.org/0000-0003-4971-8622)
- Jeffrey K. Jopling (ORCID: https://orcid.org/0000-0002-0694-1704)
- Kay S. Hung (ORCID: https://orcid.org/0009-0001-0724-0379)
- Dan E. Azagury (ORCID: https://orcid.org/0000-0002-3992-8792)
- Serena Yeung
- Josiah Aklilu (ORCID: https://orcid.org/0000-0001-5231-3349)
Institutions
- Intermountain Healthcare (US)
- Johns Hopkins University (US)
- Johns Hopkins Medicine (US)
- Intermountain Medical Center (US)
- Stanford University (US)
Publication Details
- Journal
- Surgical Endoscopy
- Published
- 2025-08-18
- DOI
- https://doi.org/10.1007/s00464-025-12015-6
- Citations
- 2
- Primary Topic
- Gallbladder and Bile Duct Disorders
- Type
- article
- Field-Weighted Citation Impact
- 3.04
Funders
- National Science Foundation
- National Institutes of Health
- U.S. National Library of Medicine