Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial
Lern- und Deskilling-Effekte von künstlicher Intelligenz in der Koloskopie bei Endoskopiker:innen mit unterschiedlicher Erfahrung: pragmatische prospektive Studie
Endoscopy · 2026-09 · 58 (09) · 1003-1014
DOI: 10.1055/a-2858-7084 ↗Auf einen Blick
Bei 13 Endoskopiker:innen erhöhte CADe vorübergehend die PDR-5 bei unerfahrenen Endoskopiker:innen. Nach Entfernen von CADe zeigte sich kein Upskilling oder Deskilling.
Fragestellung
Verbessert oder verschlechtert der Einsatz von CADe die Detektion von Polypen bei Endoskopiker:innen je nach Erfahrung?
Methode
Prospektive, multizentrische, registerbasierte, pragmatische klinische Studie mit 3 Phasen vor, während und nach CADe-Einsatz.
Ergebnisse
13 Endoskopiker:innen führten 5013 Koloskopien durch. Unerfahrene: PDR-5 31,9 % (216/678) zu 39,5 % (257/651) mit CADe; OR 1,43 (95 %-KI 1,11–1,84). Nach CADe: 31,9 % (216/678) zu 36,3 % (173/476); OR 1,03 (95 %-KI 0,79–1,34).
Schlussfolgerung der Autor:innen
Bei unerfahrenen Endoskopiker:innen stieg die PDR-5 unter CADe; nach der CADe-Phase zeigte sich in der nicht CADe-unterstützten Koloskopie weder Upskilling noch Deskilling.
Kernaussagen
- CADe erhöhte die PDR-5 bei unerfahrenen Endoskopiker:innen vorübergehend.
- Nach CADe-Entfernung kein signifikanter Effekt auf die PDR-5.
- Bei erfahrenen Endoskopiker:innen kein signifikanter CADe-Effekt.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Multizentrische Studie in der Zeitschrift Endoscopy, online erschienen am 03.06.2026. Verfasst von Tom Andre Pedersen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Haukeland University Hospital, Department of Medicine, Norway, Bergen. Hauptthemen laut MEDLINE: Artificial Intelligence, Clinical Competence, Colonic Polyps, Colonoscopy. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medtronic Europe.
Abstract (Originalsprache)
The effect of computer-aided detection (CADe) on performance of endoscopists with different experience levels is not well understood. This study assessed whether CADe use promotes learning or deskilling. We performed a prospective, multicenter, registry-based, pragmatic clinical trial. The primary end point was change in the proportion of colonoscopies with detection of at least one polyp ≥5 mm (PDR-5). Each endoscopist performed colonoscopies in three successive phases: 1) before CADe exposure, 2) during CADe use, and 3) after CADe removal. To assess the impact of CADe on PDR-5, we compared phase 1 with phases 2 and 3, adjusting for patient and endoscopist characteristics and endoscopy performance measures. Generalized linear mixed models were used and presented according to endoscopist experience. 13 endoscopists (7 inexperienced, 6 experienced) performed 5013 colonoscopies; median patient age was 59 years (interquartile range 44–71) and 2703 (53.9%) were women. Patient sex and age were similar across the two experience groups, whereas indications differed (e.g. more inflammatory bowel disease in the inexperienced group). CADe temporarily increased PDR-5 among inexperienced endoscopists from phase 1 to 2 (31.9% [216/678] to 39.5% [257/651]; odds ratio [OR] 1.43, 95%CI 1.11–1.84). There was no significant change between phases 1 and 3 (31.9% [216/678] to 36.3% [173/476]; OR 1.03, 95%CI 0.79–1.34). There was no significant CADe effect on PDR-5 among experienced endoscopists between phases. PDR-5 of inexperienced endoscopists increased when CADe was used. In non-CADe-assisted colonoscopy, no upskilling or deskilling was observed following a period of CADe exposure.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Haukeland University Hospital, Department of Medicine, Norway, Bergen.
- Haraldsplass Deaconess Hospital, Department of Medicine, Norway, Bergen.
- University of Bergen, Bergen Research Group for Advanced Gastrointestinal Endoscopy (BRAGE), Department of Clinical Medicine (K1), Norway, Bergen.
- University of Oslo, Clinical Effectiveness Research Group, Norway, Oslo.
- Cancer Registry of Norway, Norwegian Institute of Public Health, Department of Colorectal Cancer Screening, Norway, Oslo.
- Cancer Registry of Norway, Norwegian Institute of Public Health, Department of Research, Norway, Oslo.
ORCID-Profile: Tom Andre Pedersen, Yuichi Mori
Förderung
- Medtronic Europe
Zitieren
APA
Pedersen, T. A., Mori, Y., Botteri, E., Engjom, T., Seip, B., Dimcevski, G. G., & Havre, R. F. (2026). Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial. Endoscopy, 58(09), 1003-1014. https://doi.org/10.1055/a-2858-7084
Vancouver
Pedersen TA, Mori Y, Botteri E, Engjom T, Seip B, Dimcevski GG, et al. Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial. Endoscopy. 2026;58(09):1003-1014. doi:10.1055/a-2858-7084
BibTeX
@article{Pedersen2026,
author = {Pedersen, Tom Andre and Mori, Yuichi and Botteri, Edoardo and Engjom, Trond and Seip, Birgitte and Dimcevski, Georg Gjorgji and Havre, Roald Flesland},
title = {Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {09},
pages = {1003--1014},
doi = {10.1055/a-2858-7084}
}
EUVIMED