Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial
Verbesserung der Adenomdetektionsrate durch KI-gestützte Koloskopie: multizentrische quasi-randomisierte kontrollierte Studie
Endoscopy International Open · 26.02.2025 · 13 (CP)
DOI: 10.1055/a-2521-5169 ↗Auf einen Blick
Bei 795 Patient:innen war die Adenomdetektionsrate unter KI-gestützter Koloskopie höher als unter konventioneller Koloskopie (59,1 % vs. 46,6 %).
Fragestellung
Verbessert KI-gestützte Koloskopie die Adenomdetektionsrate bei dänischen Endoskopiker:innen unterschiedlicher Erfahrung?
Methode
Prospektive, quasi-randomisierte, kontrollierte multizentrische Studie an 4 Zentren; Patient:innen ab 18 Jahren; KI-gestützte vs. konventionelle Koloskopie; Endoskopiker:innen als Expert:innen oder Nicht-Expert:innen eingeteilt.
Ergebnisse
795 Patient:innen: 400 mit KI und 395 Kontrolle. ADR höher mit KI (59,1 % vs. 46,6 %, P < 0,001); bei Expert:innen (59,9 % vs. 47,3 %, P < 0,002), nicht bei Nicht-Expert:innen. Screening: 74,4 % vs. 58,1 %, P = 0,003; PDR 69,8 % vs. 56,2 %, P < 0,001; NNRR 15,1 % vs. 17,1 %, P = 0,542.
Schlussfolgerung der Autor:innen
Die Autoren berichten, dass KI-gestützte Koloskopie die ADR insgesamt und in der Screening-Population signifikant erhöhte.
Kernaussagen
- ADR unter KI: 59,1 % vs. 46,6 %
- Effekt vor allem bei Expert:innen und im Screening
- NNRR unverändert: 15,1 % vs. 17,1 %
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Randomisierte kontrollierte Studie in der Zeitschrift Endoscopy International Open, erschienen am 26.02.2025. Verfasst von Ronja Maria Birgitta Lagström und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Zealand University Hospital Koge, Køge, Denmark. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Adenoma detection rate (ADR) is a key performance measure with variability among endoscopists. Artificial intelligence (AI) in colonoscopy could reduce this variability and has shown to improve ADR. This study assessed the impact of AI on ADR among Danish endoscopists of varying experience levels. We conducted a prospective, quasi-randomized, controlled, multicenter trial involving patients aged 18 and older undergoing screening, surveillance, and diagnostic colonoscopy at four centers. Participants were assigned to AI-assisted colonoscopy (GI Genius, Medtronic) or conventional colonoscopy. Endoscopists were classified as experts (> 1000 colonoscopies) or non-experts (≤ 1000 colonoscopies). The primary outcome was ADR. We performed a subgroup analysis stratified on endoscopist experience and a subset analysis of the screening population. A total of 795 patients were analyzed: 400 in the AI group and 395 in the control group. The AI group demonstrated a significantly higher ADR than the control group (59.1% vs. 46.6%, P < 0.001). The increase was significant among experts (59.9% vs. 47.3%, P < 0.002) but not among non-experts. AI assistance significantly improved ADR (74.4% vs. 58.1%, P = 0.003) in screening colonoscopies. Polyp detection rate (PDR) was also higher in the AI group (69.8% vs. 56.2%, P < 0.001). There was no significant difference in the non-neoplastic resection rate (NNRR) (15.1% vs. 17.1%, P = 0.542). AI-assisted colonoscopy significantly increased ADR by 12.5% overall, with a notable 16.3% increase in the screening population. The unchanged NNRR indicates that the higher PDR was due to increased ADR, not unnecessary resections.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Surgery, Zealand University Hospital Koge, Køge, Denmark.
- Department of Surgery, Slagelse Hospital, Slagelse, Denmark.
- Department of Surgery, Holbæk Sygehus, Holbæk, Denmark.
- Department of Surgery, Næstved Hospital, Næstved, Denmark.
- Department of Clinical Medicine, University of Copenhagen Faculty of Health and Medical Sciences, Copenhagen, Denmark.
- Copenhagen Academy for Medical Education and Simulation (CAMES), Copenhagen, Denmark.
ORCID-Profile: Ronja Maria Birgitta Lagström
Zitieren
APA
Lagström, R. M. B., Bräuner, K. B., Bielik, J., Rosen, A. W., Crone, J. G., Gögenur, I., & Bulut, M. (2025). Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial. Endoscopy International Open, 13(CP). https://doi.org/10.1055/a-2521-5169
Vancouver
Lagström RMB, Bräuner KB, Bielik J, Rosen AW, Crone JG, Gögenur I, et al. Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial. Endoscopy International Open. 2025;13(CP). doi:10.1055/a-2521-5169
BibTeX
@article{Lagstrm2025,
author = {Lagström, Ronja Maria Birgitta and Bräuner, Karoline Bendix and Bielik, Julia and Rosen, Andreas Weinberger and Crone, Julie Gräs and Gögenur, Ismail and Bulut, Mustafa},
title = {Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial},
journal = {Endoscopy International Open},
year = {2025},
volume = {13},
number = {CP},
doi = {10.1055/a-2521-5169}
}
EUVIMED