Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation
Endoscopy International Open · 2024-07 · 12 (07) · E849-E853
DOI: 10.1055/a-2333-8138 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy International Open, online erschienen am 03.07.2024. Verfasst von Matthew Wittbrodt und 5 weiteren Autor:innen. Beteiligte Einrichtung: Information Services, Northwestern Medicine, Chicago, United States. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Betty and Gordon Moore Foundation, Digestive Health Foundation.
Abstract (Originalsprache)
Background and study aims Low-quality colonoscopy increases cancer risk but measuring quality remains challenging. We developed an automated, interactive assessment of colonoscopy quality (AI-CQ) using machine learning (ML).
Methods
Based on quality guidelines, metrics selected for AI development included insertion time (IT), withdrawal time (WT), polyp detection rate (PDR), and polyps per colonoscopy (PPC). Two novel metrics were also developed: HQ-WT (time during withdrawal with clear image) and WT-PT (withdrawal time subtracting polypectomy time). The model was pre-trained using a self-supervised vision transformer on unlabeled colonoscopy images and then finetuned for multi-label classification on another mutually exclusive colonoscopy image dataset. A timeline of video predictions and metric calculations were presented to clinicians in addition to the raw video using a web-based application. The model was externally validated using 50 colonoscopies at a second hospital.
Results
The AI-CQ accuracy to identify cecal intubation was 88%. IT (P = 0.99) and WT (P = 0.99) were highly correlated between manual and AI-CQ measurements with a median difference of 1.5 seconds and 4.5 seconds, respectively. AI-CQ PDR did not significantly differ from manual PDR (47.6% versus 45.5%, P = 0.66). Retroflexion was correctly identified in 95.2% and number of right colon evaluations in 100% of colonoscopies. HQ-WT was 45.9% of, and significantly correlated with (P = 0.85) WT time.
Conclusions
An interactive AI assessment of colonoscopy skill can automatically assess quality. We propose that this tool can be utilized to rapidly identify and train providers in need of remediation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Information Services, Northwestern Medicine, Chicago, United States.
- Anesthesiology, Northwestern University Feinberg School of Medicine, Chicago, United States.
- Surgery, Indiana University School of Medicine, Indianapolis, United States.
- Medicine, Northwestern University Feinberg School of Medicine, Chicago, United States.
Förderung
- Betty and Gordon Moore Foundation
- Digestive Health Foundation
Zitieren
APA
Wittbrodt, M., Klug, M., Etemadi, M., Yang, A., Pandolfino, J. E., & Keswani, R. N. (2024). Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation. Endoscopy International Open, 12(07), E849-E853. https://doi.org/10.1055/a-2333-8138
Vancouver
Wittbrodt M, Klug M, Etemadi M, Yang A, Pandolfino JE, Keswani RN. Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation. Endoscopy International Open. 2024;12(07):E849-E853. doi:10.1055/a-2333-8138
BibTeX
@article{Wittbrodt2024,
author = {Wittbrodt, Matthew and Klug, Matthew and Etemadi, Mozziyar and Yang, Anthony and Pandolfino, John E and Keswani, Rajesh N},
title = {Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation},
journal = {Endoscopy International Open},
year = {2024},
volume = {12},
number = {07},
pages = {E849--E853},
doi = {10.1055/a-2333-8138}
}
EUVIMED