EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

The impact of artificial intelligence on the adenoma detection rate

Sebastian Bernhofer, Julian Prosenz, David Venturi, Andreas Maieron

Wiener klinische Wochenschrift · 2026-01 · 138 (1-2) · 1-8

DOI: 10.1007/s00508-025-02561-3 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Wiener klinische Wochenschrift, online erschienen am 25.06.2025. Verfasst von Sebastian Bernhofer und 3 weiteren Autor:innen. Beteiligte Einrichtung: Karl Landsteiner University of Health Sciences, Dr. Karl-Dorrek-Straße 30, 3500, Krems, Austria. Sebastian.Bernhofer@stpoelten.lknoe.at. Hauptthemen laut MEDLINE: Adenoma, Colonoscopy, Artificial Intelligence, Clinical Competence. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Karl Landsteiner Privatuniversität für Gesundheitswissenschaften.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) is a promising tool to achieve a high adenoma detection rate (ADR). The aim of this study is to evaluate the impact of a computer-aided detection (CADe) device on the ADRs of endoscopists with different levels of expertise.

Methods

Data were collected from patients who underwent colonoscopy with CADe within a 12-month period. Endoscopists were divided into three groups, a trainee group (< 500 colonoscopies), an intermediate group (500–1000 colonoscopies) and an expert group (> 2000 colonoscopies). Endoscopists with the same definition of experience without CADe support served as the control cohort. For the differences in ADR between the groups a 2-sided 95% confidence interval (CI) and odds ratios (OR) were calculated.

Results

In this study 335 patients (155 females, 177 males) with a mean age 62.1 years (SD ± 16.2 years) were included in the CADe cohort. In this cohort 508 polyps were resected. The ADRs for the groups and control groups (without CADe) were as follows: 42.9% (95% CI: 28.5–57.2%) and 21.5% (95% CI: 11.3–31.8%) in the trainee group, 41.3% (95% CI: 33.5–49.0%) and 36.8% (95% CI: 27.9–45.6%) in the intermediate group and 39.8% (95% CI: 30.9–48.8%) and 33.3% (95% CI: 26.3–40.4%) in the expert group. There were no significant differences among the CADe groups when trainees were compared to experts ( p = 0.72, OR 1.13, 95% CI: 0.58–2.16) or when intermediate endoscopists were compared to experts ( p = 0.81, OR 1.06, 95% CI: 0.65–1.74).

Conclusion

The use of AI appears to provide an opportunity to match the ADR-based quality of colonoscopy at an early stage of endoscopy training with experts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AdenomaColonoscopyArtificial IntelligenceClinical CompetenceColorectal NeoplasmsDiagnosis, Computer-AssistedHumansFemaleMaleMiddle AgedReproducibility of ResultsSensitivity and SpecificityAgedEarly Detection of Cancer

Stichwörter der Autor:innen

Adenoma detection rateColonoscopyComputer-aided detectionEndoscopy trainingInexperienced endoscopists

Autor:innen und Institutionen

  • Karl Landsteiner University of Health Sciences, Dr. Karl-Dorrek-Straße 30, 3500, Krems, Austria. Sebastian.Bernhofer@stpoelten.lknoe.at.
  • Department of Internal Medicine 2 Gastroenterology & Hepatology, University Hospital St. Pölten, Dunant-Platz 1, 3100, St. Pölten, Austria. Sebastian.Bernhofer@stpoelten.lknoe.at.
  • Karl Landsteiner University of Health Sciences, Dr. Karl-Dorrek-Straße 30, 3500, Krems, Austria.
  • Department of Internal Medicine 2 Gastroenterology & Hepatology, University Hospital St. Pölten, Dunant-Platz 1, 3100, St. Pölten, Austria.
  • Medical Science Research Program, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.

Förderung

  • Karl Landsteiner Privatuniversität für Gesundheitswissenschaften

Zitieren

APA

Bernhofer, S., Prosenz, J., Venturi, D., & Maieron, A. (2026). The impact of artificial intelligence on the adenoma detection rate. Wiener klinische Wochenschrift, 138(1-2), 1-8. https://doi.org/10.1007/s00508-025-02561-3

Vancouver

Bernhofer S, Prosenz J, Venturi D, Maieron A. The impact of artificial intelligence on the adenoma detection rate. Wiener klinische Wochenschrift. 2026;138(1-2):1-8. doi:10.1007/s00508-025-02561-3

BibTeX
@article{Bernhofer2026,
  author = {Bernhofer, Sebastian and Prosenz, Julian and Venturi, David and Maieron, Andreas},
  title = {The impact of artificial intelligence on the adenoma detection rate},
  journal = {Wiener klinische Wochenschrift},
  year = {2026},
  volume = {138},
  number = {1-2},
  pages = {1--8},
  doi = {10.1007/s00508-025-02561-3}
}
Kostenlos starten →