Vision-language large learning model, GPT4V, accurately classifies the Boston Bowel Preparation Scale score
This study provides proof-of-concept that a vision-language LLM is able to perform BBPS classification accurately, without large training datasets. This represents a paradigm shift in AI classification methods in medicine, where many diseases lack sufficient data to train traditional AI models. An LLM with appropriate examples may be used in such cases.
Authors
- Chee‐Kiat Tan (ORCID: https://orcid.org/0000-0001-6992-2319)
- Jasmine Chiat Ling Ong (ORCID: https://orcid.org/0000-0001-6916-5960)
- Jin Li (ORCID: https://orcid.org/0000-0001-6689-3241)
- Damien Meng Yew Tan (ORCID: https://orcid.org/0000-0002-7282-0900)
- Gerald Gui Ren Sng (ORCID: https://orcid.org/0000-0002-8795-7491)
- Daniel Yan Zheng Lim (ORCID: https://orcid.org/0000-0002-9715-6970)
- Joshua Yi Min Tung (ORCID: https://orcid.org/0000-0003-4991-9790)
- Kabilan Elangovan (ORCID: https://orcid.org/0000-0002-7711-7368)
- Jen Hong Tan (ORCID: https://orcid.org/0000-0002-7785-2987)
- Ren Yi Jonas Ho (ORCID: https://orcid.org/0000-0003-2443-1748)
- Yu Bin Tan (ORCID: https://orcid.org/0000-0002-4639-5760)
- Sushmitha Carkarine
- Tian Wei Valerie Chew
- Yuhe Ke (ORCID: https://orcid.org/0000-0001-7193-4749)
- Ting Fang Tan
- Le Quan (ORCID: https://orcid.org/0009-0002-9787-2464)
Institutions
- SingHealth (SG)
- Singapore General Hospital (SG)
- Duke-NUS Medical School (SG)
Publication Details
- Journal
- BMJ Open Gastroenterology
- Published
- 2025-03-01
- DOI
- https://doi.org/10.1136/bmjgast-2024-001496
- Citations
- 5
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 5.23