A Video-Based Artificial Intelligence Platform for Measuring Esophagogastroduodenoscopy Duration and Suggesting Real-Time Landmark Documentation
Eine videobasierte KI-Plattform zur Messung der Dauer der Ösophagogastroduodenoskopie und zur Echtzeit-Vorschlagsgebung für Landmarken-Dokumentation
Endoscopy International Open · 13.10.2026 · 14 (CP)
DOI: 10.1055/a-2965-6499 ↗Auf einen Blick
In 78.336 EGD war die KI-Zeitmessung mit der Expertenprüfung in 98,5 % der Fälle übereinstimmend. KI-Vorschläge senkten den Anteil von Verfahren ohne Landmarken-Dokumentation.
Fragestellung
Wurde eine videobasierte KI-Plattform zur Messung der EGD-Dauer und zur Echtzeit-Unterstützung der Landmarken-Dokumentation evaluiert?
Methode
Retrospektive Multizenterstudie mit 78.336 EGD von 213 Ärzt:innen; KI zur Zeitmessung, Landmarken-Vorschläge und Dokumentationsmessung; Validierung von 500 Verfahren durch 2 verblindete Expert:innen.
Ergebnisse
Median der Prozedurdauer 3,30 min (IQR 2,27–4,65). Übereinstimmung mit Experten: 98,5 % (95 %-KI 97,1–99,3%). KI-Vorschläge reduzierten Null-Landmarken-Verfahren von 27,5 % auf 15,8 % (P < 0,001).
Schlussfolgerung der Autor:innen
Die videobasierte KI maß EGD-Zeiten genau und verbesserte die Landmarken-Dokumentation. Die mediane Prozedurdauer von 3,3 min zeigte eine deutliche Lücke zu den Qualitätsstandards.
Kernaussagen
- 98,5 % Übereinstimmung der KI-Zeitmessung mit Experten
- Null-Landmarken-Verfahren: 27,5 % auf 15,8 %
- Nur 6,1 % erreichten den 7-min-Standard
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy International Open, erschienen am 13.10.2026. Verfasst von Zohar Levi und 12 weiteren Autor:innen. Beteiligte Einrichtung: GastroenterologyRabin Medical Center Beilinson HospitalPetah TikvaCenter DistrictIsrael. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background and Study Aims The European Society of Gastrointestinal Endoscopy (ESGE) sets key quality indicators for esophagogastroduodenoscopy (EGD), including a minimum procedural time of 7 min and photodocumentation of landmarks. We evaluated AI-derived procedural times, physician variations, and the impact of AI suggestions on landmark documentation rates.
Methods
This retrospective multicenter study included 78,336 EGDs performed by 213 physicians (01.01.2024–31.12.2025). A video-based AI platform (Theator Inc., Palo Alto, USA) measured procedural time, provided real-time landmark suggestions, and measured landmark documentation. Two blinded experts performed confirmatory validation of 500 procedures, with concordance defined as agreement within 2 s.
Results
Median procedural time was 3.30 min (IQR: 2.27–4.65). AI timestamps were concordant with expert review in 98.5% of cases (95% CI: 97.1–99.3%). Among 203 physicians performing at least 50 procedures, procedural time varied from 1.35 to 7.56 min (a 5.6-fold difference), with only 6.1% of procedures meeting the ESGE-recommended 7-min threshold. AI landmark suggestions reduced zero-landmark procedures by 42.6% (15.8 vs. 27.5%; P < 0.001), with improvements across all seven anatomical sites (P < 0.001 for each). Physicians in the slowest total EGD time quintile had fewer normal examinations than those in the fastest quintile: 19.8 versus 31.7% (P = 0.002), an association that persisted when physicians were restratified by biopsy-free procedural time.
Conclusions
Video-based AI accurately measured EGD procedure times and improved landmark documentation rate with AI-generated suggestions. A median procedural time of 3.3 min reveals a significant gap in quality standards. Automated, unattended measurement offers a scalable route to auditing upper endoscopy quality.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- GastroenterologyRabin Medical Center Beilinson HospitalPetah TikvaCenter DistrictIsrael.
- Gray Faculty of Medical and Health SciencesTel Aviv UniversityTel Aviv-YafoTel Aviv DistrictIsrael.
- Division of MedicineAssuta Medical CenterTel Aviv-YafoTel Aviv DistrictIsrael.
- MedicineTechnion Israel Institute of Technology The Ruth and Bruce Rappaport Faculty of MedicineHaifaHaifa DistrictIsrael.
- Data Based Clinical Quality UnitAssuta Medical CenterTel Aviv-YafoTel Aviv DistrictIsrael.
- Unit of Big Data ScienceAssuta Medical CenterTel Aviv-YafoTel Aviv DistrictIsrael.
ORCID-Profile: Zohar Levi
Zitieren
APA
Levi, Z., Brosh, S., Shpriz, M., Varsano, Z., Khodyrker, D., Asselman, D., Maril, S., Hod, K., Edelman-Klapper, H., Eizenstein, S., Gralnek, I. M., Segol, I., & Abu-Freha, N. (2026). A Video-Based Artificial Intelligence Platform for Measuring Esophagogastroduodenoscopy Duration and Suggesting Real-Time Landmark Documentation. Endoscopy International Open, 14(CP). https://doi.org/10.1055/a-2965-6499
Vancouver
Levi Z, Brosh S, Shpriz M, Varsano Z, Khodyrker D, Asselman D, et al. A Video-Based Artificial Intelligence Platform for Measuring Esophagogastroduodenoscopy Duration and Suggesting Real-Time Landmark Documentation. Endoscopy International Open. 2026;14(CP). doi:10.1055/a-2965-6499
BibTeX
@article{Levi2026,
author = {Levi, Zohar and Brosh, Shani and Shpriz, Manor and Varsano, Ziv and Khodyrker, Daniel and Asselman, Dotan and Maril, Sari and Hod, Keren and Edelman-Klapper, Hadar and Eizenstein, Sapir and Gralnek, Ian M and Segol, Inbar and Abu-Freha, Naim},
title = {A Video-Based Artificial Intelligence Platform for Measuring Esophagogastroduodenoscopy Duration and Suggesting Real-Time Landmark Documentation},
journal = {Endoscopy International Open},
year = {2026},
volume = {14},
number = {CP},
doi = {10.1055/a-2965-6499}
}
EUVIMED