ChatGPT 5 vs Expert Endoscopists: A Comparative Evaluation of Adherence to the ESGE STAR Project
Endoscopy · 01.06.2026 · 58 (S 03 S 03) · S772
DOI: 10.1055/s-0046-1822161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.06.2026. Verfasst von A Ait Errami und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Aims
The ESGE STAR Project provides a 55-item standardized framework for upper GI endoscopy reporting, based on expert consensus due to the absence of high-quality evidence. The ability of artificial intelligence (AI) systems to apply these structured criteria remains unknown. This study compares the adherence of ChatGPT-Audio, using voice-dictation input, to that of expert endoscopists when both are instructed to follow the STAR recommendations.
Methods
A total of 104 EGD reports were analyzed: 52 generated by ChatGPT 5.1 and 52 written by expert endoscopists, all under explicit instruction to follow the 55-item ESGE STAR checklist. Two blinded senior reviewers independently evaluated each report for item-level compliance across pre-, intra- and post-procedural domains. Primary outcome: overall compliance rate. Secondary outcomes: domain-specific compliance, number of missing items, inter-rater reliability (κ), and ROC analysis.
Results
Overall compliance was 87.6%±4.8 for ChatGPT-Audio and 93.1%±3.5 for experts (p=0.002). ChatGPT-Audio missed 6.8±3.2 items per report compared with 3.7±2.1 for experts. Domain-specific compliance was:• Pre-procedural: 81% vs 94%• Intra-procedural: 92% vs 95%• Classification usage (LA, Prague, Forrest, Paris): 89% vs 94%• Post-procedural: 76% vs 90%Inter-rater agreement was excellent (κ=0.84). ROC analysis identified a threshold of≥90% compliance (AUC=0.86).
Conclusions
When explicitly instructed to apply the ESGE STAR criteria, ChatGPT-Audio produced highly structured and guideline-conformant EGD reports, approaching expert performance. Human endoscopists nonetheless demonstrated superior compliance, particularly regarding pre- and post-procedural elements. This study provides the first controlled assessment of an AI voice-dictation system’s ability to apply the ESGE STAR reporting standard and supports its potential role in advancing standardized endoscopy documentation. Publication History Article published online: 05 June 2026 © 2026. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany
Zitieren
APA
Errami, A. A., Zouaki, I., Nacir, O., Ezzahra, L. F., & Krati, K. (2026). ChatGPT 5 vs Expert Endoscopists: A Comparative Evaluation of Adherence to the ESGE STAR Project. Endoscopy, 58(S 03 S 03), S772. https://doi.org/10.1055/s-0046-1822161
Vancouver
Errami AA, Zouaki I, Nacir O, Ezzahra LF, Krati K. ChatGPT 5 vs Expert Endoscopists: A Comparative Evaluation of Adherence to the ESGE STAR Project. Endoscopy. 2026;58(S 03 S 03):S772. doi:10.1055/s-0046-1822161
BibTeX
@article{Errami2026,
author = {Errami, A Ait and Zouaki, I and Nacir, O and Ezzahra, L Fatima and Krati, K},
title = {ChatGPT 5 vs Expert Endoscopists: A Comparative Evaluation of Adherence to the ESGE STAR Project},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {S 03 S 03},
pages = {S772},
doi = {10.1055/s-0046-1822161}
}
EUVIMED