Computerized feedback during colonoscopy training leads to improved performance: a randomized trial
Open accessAbstract
Background and aims Simulation-based training in colonoscopy is increasingly replacing the traditional apprenticeship method to avoid patient-related risk. Mentoring during simulation is necessary to provide feedback and to motivate, but expert supervisors are a scarce resource. We aimed to determine whether computerized feedback in simulated colonoscopy would improve performance, optimize time spent practicing, and optimize the pattern of training. Methods Forty-four participants were recruited and randomized to either a feedback group (FG) or a control group (CG). Participants were allowed 2 hours of self-practice during which they could practice as they saw fit on 2 different cases: 1 easy and 1 difficult. The CG practiced without feedback, but the participants in the FG were given a score of progression every time they reached the cecum. All participants were tested on a different case after end of training. The primary outcome was the progression score in the final case, and secondary outcomes were time spent practicing and the training pattern. Results Regression analysis adjusting for sex was done because of an uneven sex distribution between groups (P = .026) and significantly higher performance scores by men (37.6, standard deviation [SD] 25.9) compared with women (19.7, SD 18.7); P = .012. The FG outperformed the CG in the final case, FG scoring 14.4 points (95% confidence interval [CI], 1.2-27.6) more than the CG; P = .033, and they spent more time practicing, FG practicing 25.8 minutes (95% CI, 11.6-39.9) more than the CG; P = .001. The FG practiced more on the easy case and reached the cecum 3.2 times more (95% CI, 2-4.5) during practice (P < .001). Conclusions Our findings of this study revealed that an automatic, computerized score of progression during simulated colonoscopy motivates the novices to improve performance, optimizes time spent practicing, and optimizes their pattern of training. (Clinical trial registration number: NCT03248453.).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI assistance may provide a valuable feedback tool for junior endoscopists, leading to enhanced performance and diagnostic accuracy over time.
“By receiving AI-supported feedback, junior endoscopists can gain valuable insights, learn from their mistakes, and refine their skills, ultimately leading to enhanced performance and diagnostic accuracy over time [43] .”
From Enhancing human-AI collaboration: The case of colonoscopy (2024) · cites this paper as [43]
The indexed Abstract reports that participants given computerized progression-score feedback during simulated colonoscopy training performed better on a final case than controls. It does not establish that the feedback was AI-supported, or that it improved diagnostic accuracy or performance over a longer period. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cited by
Sorted by citations
Enhancing human-AI collaboration: The case of colonoscopy
Introzzi, L., Zonca, J., Cabitza, F., Cherubini, P., & Reverberi, C. (2024) · Digestive and Liver Disease · doi:10.1016/j.dld.2023.10.018 · Cited by 28 · see citing works
- Authors
- Vilmann, A. S., Norsk, D., Svendsen, M. B. S., Reinhold, R., Svendsen, L. B., Park, Y. S., & Konge, L.
- Affiliations
- Rigshospitalet (DK)
- Technical University of Denmark (DK)
- University of Illinois Chicago (US)
- Corresponding author
- Vilmann, Andreas Slot
- Venue
- Gastrointestinal Endoscopy
- Publisher
- Elsevier BV
- Published
- 2018-11
- Volume
- 88
- Issue
- 5
- Pages
- 869-876
- ISSN
- 0016-5107 (ISSN-L)
- OpenAlex
- W2883486501
- Cited by
- 29
- References
- 0
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 4 · 2023: 5 · 2022: 6 · 2021: 4 · 2020: 3 · 2019: 1
- FWCI
- 2.04
- Type
- journal article
- Language
- en
- Open access
- green
- orbit.dtu.dk
- Licence
- Locations
- Gastrointestinal Endoscopy (publishedVersion)
- PubMed (publishedVersion)
- Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
- Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) (submittedVersion, other-oa)
- Topics
- Health Sciences › Medicine › Surgery › Surgical Simulation and Training
- Health Sciences › Medicine › Physiology › Simulation-Based Education in Healthcare
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Keywords
- colonoscopy training, simulation-based training, colonoscopy education, performance improvement, training time allocation, sex differences in performance, novice endoscopists
- MeSH terms
- Simulation Training, Adult, Clinical Competence, Colonoscopy, Computers, Denmark, Education, Medical, Graduate, Feedback, Female, Humans, Internship and Residency, Male, Multivariate Analysis, Logistic Models, Problem-Based Learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
