Exploring a novel voice-guided artificial intelligence platform for real-time colonoscopy documentation: a pilot study
Our AI-assisted report generation tool demonstrates potential in standardizing colonoscopy documentation through AI-assisted, real-time NLP for generating reports. While effective, its performance depends on endoscopist engagement. Future improvements in NLP capabilities and structured reporting prompts can enhance completeness and usability, contributing to more efficient and accurate endoscopy documentation.
Authors
- Roupen Djinbachian (ORCID: https://orcid.org/0000-0002-0649-0691)
- David Armstrong (ORCID: https://orcid.org/0000-0003-2487-1479)
- Mahsa Taghiakbari (ORCID: https://orcid.org/0000-0001-6011-3400)
- Daniel von Renteln (ORCID: https://orcid.org/0000-0002-6125-0068)
- Mickaël Bouin (ORCID: https://orcid.org/0000-0003-4272-6793)
- Rohini Gaikar (ORCID: https://orcid.org/0000-0002-3681-0692)
- Robert Battat (ORCID: https://orcid.org/0000-0002-7421-9764)
- Timothy Wong (ORCID: https://orcid.org/0000-0003-1646-4494)
- Benoît Panzini
- Azar Azad
Institutions
- Institut de Recherche en Santé Digestive (FR)
- Vale (Canada) (CA)
- Centre Hospitalier de l’Université de Montréal (CA)
- Université de Montréal (CA)
Publication Details
- Journal
- Journal of the Canadian Association of Gastroenterology
- Published
- 2025-09-26
- DOI
- https://doi.org/10.1093/jcag/gwaf026
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Université de Montréal