Performance of an artificial intelligence system versus endoscopists for interrogation of scars after piecemeal endoscopic mucosal resection
Endoscopy International Open · 04.05.2026 · 14 (CP)
DOI: 10.1055/a-2840-7149 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy International Open, erschienen am 04.05.2026. Verfasst von Oswaldo Ortiz und 11 weiteren Autor:innen. Beteiligte Einrichtung: Hospital Clinic Barcelona, Gastroenterology Department, Endoscopy UnitUniversitat de BarcelonaBarcelonaSpain. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background and study aims Detection and management of recurrence after piecemeal endoscopic mucosal resection (p-EMR) of large colorectal polyps is crucial for preventing post-colonoscopy colorectal cancer. Colonoscopy assisted with artificial intelligence systems for lesion detection (CADe) has shown efficacy in identifying polyps, particularly small lesions (< 10 mm). Our aim was to evaluate sensitivity and negative predictive value of CADe compared with endoscopists in detecting recurrence after p-EMR.
Methods
Sixty-six pseudo anonymized high-quality videos (25 with recurrence and 15 with previously clipped defects) of > 15 mm polyps post-EMR scars were assessed. Recurrence size was < 10 mm in 19 of 25 cases (76.0%). Six endoscopists—three experts and three non-experts—predicted recurrence (yes/no) with confidence level (high/low). The same videos were analyzed with CAD-e detection mode superimposed. The gold standard was histopathology.
Results
Endoscopists had higher sensitivity than CADe (96.0% vs 72.0%; P = 0.03). Experts performed better than non-experts in ruling out recurrence (specificity: 92.7% vs 58.5%; P = 0.001) and accuracy (92.4% vs 72.7%; P < 0.001). In non-clipped defects, endoscopists maintained higher sensitivity than CADe (95.0% vs 65.0%; P = 0.03). Concordance was moderate overall (Kappa 0.57) but substantial among experts (0.70) and when excluding clipped defects (0.61)
Conclusions
Endoscopists outperformed CADe in interrogating post-EMR scars. Training CADe with images of post-polypectomy scars may further improve its performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hospital Clinic Barcelona, Gastroenterology Department, Endoscopy UnitUniversitat de BarcelonaBarcelonaSpain.
- Faculty of Medicine and Health SciencesUniversitat de BarcelonaBarcelonaBarcelonaSpain.
- Institut d'Investigacions Biomediques August Pi i Sunyer (IDIBAPS)BarcelonaSpain.
ORCID-Profile: Oswaldo Ortiz, Ricard Prat, Maria Daca-Alvarez, Liseth Rivero-Sánchez, Maria Pellisé
Zitieren
APA
Ortiz, O., Prat, R., Soy, G., Bofill, A., Llach, J., Daca-Alvarez, M., Balaguer, F., Brunori, A., Kumari, H., Vergara, R., Rivero-Sánchez, L., & Pellisé, M. (2026). Performance of an artificial intelligence system versus endoscopists for interrogation of scars after piecemeal endoscopic mucosal resection. Endoscopy International Open, 14(CP). https://doi.org/10.1055/a-2840-7149
Vancouver
Ortiz O, Prat R, Soy G, Bofill A, Llach J, Daca-Alvarez M, et al. Performance of an artificial intelligence system versus endoscopists for interrogation of scars after piecemeal endoscopic mucosal resection. Endoscopy International Open. 2026;14(CP). doi:10.1055/a-2840-7149
BibTeX
@article{Ortiz2026,
author = {Ortiz, Oswaldo and Prat, Ricard and Soy, Guillem and Bofill, Alex and Llach, Joan and Daca-Alvarez, Maria and Balaguer, Francesc and Brunori, Angelo and Kumari, Hardeep and Vergara, Romina and Rivero-Sánchez, Liseth and Pellisé, Maria},
title = {Performance of an artificial intelligence system versus endoscopists for interrogation of scars after piecemeal endoscopic mucosal resection},
journal = {Endoscopy International Open},
year = {2026},
volume = {14},
number = {CP},
doi = {10.1055/a-2840-7149}
}
EUVIMED