Efficacy of artificial intelligence for adenoma detection in water exchange colonoscopy: a two-center randomized controlled trial
Wirksamkeit von künstlicher Intelligenz zur Adenomdetektion bei Wasserwechsel-Koloskopie: eine zwei-zentrische randomisierte kontrollierte Studie
Endoscopy · 2026-02 · 58 (02) · 141-150
DOI: 10.1055/a-2681-5544 ↗Auf einen Blick
Bei 560 Patient:innen war die Adenome pro Koloskopie (APC) unter Wasserwechsel plus CADe höher als unter Wasserwechsel allein. Die ADR unterschied sich nicht signifikant.
Fragestellung
Verbessert die Kombination von Wasserwechsel-Koloskopie und CADe die APC gegenüber Wasserwechsel allein?
Methode
Randomisierte kontrollierte Studie in Italien und Taiwan; Patient:innen 45–75 Jahre; 752 zur Randomisierung geplant; Interimsanalyse bei 560 Patient:innen.
Ergebnisse
APC höher mit Wasserwechsel+CADe als mit Wasserwechsel allein: 1,39 (95 %-KI 1,06–1,72) vs. 1,05 (95 %-KI 0,87–1,23); IRR 1,32 (95 %-KI 1,14–1,54), absolute Zunahme 0,34. ADR: 54,1 % vs. 50,2 % (P = 0,35).
Einschränkungen
Interimsanalyse; Studie war für Unterschiede in ADR und sessilen serratierten Läsionen nicht gepowert.
Schlussfolgerung der Autor:innen
Bei Wasserwechsel-Koloskopie erhöhte CADe statistisch die APC, ohne die Rückzugszeit zu verlängern oder die Resektion nicht-neoplastischer Läsionen zu erhöhen.
Kernaussagen
- APC höher mit Wasserwechsel+CADe als mit Wasserwechsel allein
- IRR 1,32 (95 %-KI 1,14–1,54)
- ADR und sessile serrated lesion detection nicht signifikant verschieden
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 22.09.2025. Verfasst von Chi-Liang Cheng und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gastroenterology, Department of Medicine, Evergreen General Hospital, Taoyuan, Taiwan. Hauptthemen laut MEDLINE: Adenoma, Artificial Intelligence, Colonoscopy, Colorectal Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben.
Abstract (Originalsprache)
Water exchange and artificial intelligence-based computer-aided detection (CADe) separately improve the adenoma detection rate (ADR) and number of adenomas detected per colonoscopy (APC). We aimed to determine whether combining water exchange with CADe enhanced APC versus water exchange alone. This randomized controlled trial was conducted at hospitals in Italy and Taiwan using different CADe devices. Patients aged 45–75 years undergoing colonoscopy for screening, surveillance, or positive fecal blood tests were randomized to either water exchange with CADe assistance or water exchange alone. The primary outcome was APC, with 752 patients planned for randomization. An interim analysis was conducted on 560 patients (75% of the enrollment target; mean age 59.4 years; male 299; water exchange+CADe 279), with similar baseline characteristics between the two groups. APC was significantly higher with water exchange+CADe compared with water exchange alone (1.39 [95%CI 1.06–1.72] vs. 1.05 [95%CI 0.87–1.23]) with an incidence rate ratio of 1.32 (95%CI 1.14–1.54), representing an absolute increase of 0.34. The observed significant difference led to early trial termination. No significant differences were found in ADR and sessile serrated lesion detection rates between the groups (54.1% vs. 50.2% [P = 0.35] and 3.6% vs. 3.6% [P = 0.99], respectively), but this study was not powered to detect such differences. Withdrawal times and the mean number of non-neoplastic lesions per colonoscopy were comparable. For water exchange colonoscopy, integrating CADe statistically increased APC without prolonging withdrawal times or causing a concomitant increase in resection of non-neoplastic lesions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Division of Gastroenterology, Department of Medicine, Evergreen General Hospital, Taoyuan, Taiwan.
- Digestive Endoscopy Unit, CTO Hosptital, Iglesias, Italy.
- Department of Biotechnology, School of Health Technology, Ming Chuan University, Taoyuan, Taiwan.
- Medicine, Indiana University School of Medicine, Indianapolis, United States.
- Endoscopy Unit, IRCCS Humanitas Research Hospital, Rozzano, Italy.
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy.
ORCID-Profile: Chi-Liang Cheng, Sergio Cadoni
Zitieren
APA
Cheng, C. L., Cadoni, S., Gallittu, P., Mura, D., Utzeri, E., Kuo, Y. L., Su, I. C., Lee, Y. S., Chen, Z. W., Cheng, W. Y., Tsui, Y. N., Lee, B. P., Hassan, C., & Leung, F. W. (2026). Efficacy of artificial intelligence for adenoma detection in water exchange colonoscopy: a two-center randomized controlled trial. Endoscopy, 58(02), 141-150. https://doi.org/10.1055/a-2681-5544
Vancouver
Cheng CL, Cadoni S, Gallittu P, Mura D, Utzeri E, Kuo YL, et al. Efficacy of artificial intelligence for adenoma detection in water exchange colonoscopy: a two-center randomized controlled trial. Endoscopy. 2026;58(02):141-150. doi:10.1055/a-2681-5544
BibTeX
@article{Cheng2026,
author = {Cheng, Chi-Liang and Cadoni, Sergio and Gallittu, Paolo and Mura, Donatella and Utzeri, Erika and Kuo, Yen-Lin and Su, I-Chia and Lee, Yun-Shien and Chen, Zi-Wei and Cheng, William Y and Tsui, Yi-Ning and Lee, Bai-Ping and Hassan, Cesare and Leung, Felix W},
title = {Efficacy of artificial intelligence for adenoma detection in water exchange colonoscopy: a two-center randomized controlled trial},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {02},
pages = {141--150},
doi = {10.1055/a-2681-5544}
}
EUVIMED