Comparative performance of artificial intelligence optical diagnosis systems for leaving in situ colorectal polyps
Open accessThe 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?
Performance of available CADx systems is comparable, if not inferior, to that of experienced endoscopists.
“Furthermore, the performance of available CADx systems is comparable, if not inferior, to that of experienced endoscopists [66 , 94-96] .”
From Enhancing human-AI collaboration: The case of colonoscopy (2024) · cites this paper as [95]
The Results (page unavailable) report that unassisted endoscopist diagnosis had a 97.8% negative predictive value, not significantly different from either CADx system, and higher agreement with histopathology than either system under the American surveillance guidelines. However, the study compared two CADx systems at one academic center, and the Colonoscopy Procedures section says both experienced endoscopists and trainees participated. It does not establish the comparison for available systems generally or for experienced endoscopists alone. (LLM, conf=0.82)
Experimental — accuracy not yet measuredExperienced endoscopists' optical diagnosis performance did not significantly benefit from AI assistance.
“Results show that experienced endoscopists' optical diagnosis performance did not significantly benefit from AI assistance”
From Enhancing human-AI collaboration: The case of colonoscopy (2024) · cites this paper as [95]
The paper reports no statistically significant difference between CADx-assisted and unassisted optical diagnosis for diminutive rectosigmoid polyps, and its discussion describes a lack of benefit in diagnostic accuracy and clinical outcomes (main text; page unavailable). However, the Methods state that both experienced endoscopists and trainees participated; the cited result is not reported separately for experienced endoscopists. (LLM, conf=0.81)
Experimental — accuracy not yet measuredNo harmful effects occurred even when AI performance was inferior to human experts.
“and no harmful effects occurred even when AI performance was inferior to human experts [95 , 96] .”
From Enhancing human-AI collaboration: The case of colonoscopy (2024) · cites this paper as [95]
The Results (page unavailable) report total agreement between unassisted and AI-assisted endoscopist interpretations in surveillance-interval assignments, despite no significant improvement in diagnostic performance. That supports no worsening on this measured outcome, but not the broader claim that no harmful effects occurred: all polyps were removed, and the paper does not establish an absence of patient harm. (LLM, conf=0.84)
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.
Cites
Mori, Y., Kudo, S.-E., Misawa, M., Saito, Y., Ikematsu, H., Hotta, K., Ohtsuka, K., Urushibara, F., Kataoka, S., Ogawa, Y., et al. (2018) · Annals of Internal Medicine · doi:10.7326/m18-0249 · Cited by 509 · see citing works
Self-citationReal-Time Artificial Intelligence–Based Optical Diagnosis of Neoplastic Polyps during Colonoscopy
Barua, I., Wieszczy, P., Kudo, S.-E., Misawa, M., Holme, Ø., Gulati, S., Williams, S., Mori, K., Itoh, H., Takishima, K., et al. (2022) · NEJM Evidence · doi:10.1056/evidoa2200003 · Cited by 119 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 10
- Senore C, et al. Gut 2019;68:1232-1244.
- Krzeczewski B, et al. Pol Arch Intern Med 2021; 131:128-135.
- Hassan C, et al. Clin Gastroenterol Hepatol 2022; 20:2505-2513.e4.
- Rondonotti E, et al. Endoscopy 2023;55:14-22.
- Weigt J, et al. Endoscopy 2022;54:180-184.
- Rex DK, et al. Gastrointest Endosc 2011;73:419-422.
- Biffi C, et al. NPJ Digit Med 2022;5:84.
- Mori Y, et al. Ann Intern Med 2018;169:357-366.
- Gupta S, et al. Gastrointest Endosc 2020;91:463-485.e5.
- Hassan C, et al. Endoscopy 2020;52:687-700.
Cited by
Sorted by citations
Hassan, C., Misawa, M., Rizkala, T., Mori, Y., Sultan, S., Facciorusso, A., Antonelli, G., Spadaccini, M., Houwen, B. B. S. L., Rondonotti, E., et al. (2024) · Annals of Internal Medicine · doi:10.7326/m23-2865 · Cited by 56 · see citing works
Self-citationEnhancing 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
Artificial Intelligence-assisted colonoscopy and colorectal cancer screening: Where are we going?
Spadaccini, M., Troya, J., Khalaf, K., Facciorusso, A., Maselli, R., Hann, A., & Repici, A. (2024) · Digestive and Liver Disease · doi:10.1016/j.dld.2024.01.203 · Cited by 20 · see citing works
Self-citation
- Authors
- Hassan, C., Sharma, P., Mori, Y., Bretthauer, M., Rex, D. K., Spadaccini, M., Selvaggio, C., Antonelli, G., Khalaf, K., Rizkala, T., Ferrara, E., Savevski, V., Maselli, R., Fugazza, A., Capogreco, A., Poletti, V., Ferretti, S., Alkandari, A., Correale, L., & Repici, A.
- Affiliations
- Humanitas University (IT)
- University of Kansas (US)
- University of Oslo (NO)
- Indiana University School of Medicine (US)
- SHOWA Medical University Northern Yokohama Hospital (JP)
- Corresponding author
- Hassan, Cesare
- ORCID
- Venue
- Gastroenterology
- Publisher
- Elsevier BV
- Published
- 2023-03
- Volume
- 164
- Issue
- 3
- Pages
- 467-469.e4
- ISSN
- 0016-5085 (ISSN-L)
- OpenAlex
- W4307896057
- Cited by
- 46
- References
- 2
- Citations by year
- 2026: 5 · 2025: 13 · 2024: 14 · 2023: 14
- FWCI
- 4.29
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Gastroenterology (publishedVersion)
- PubMed (publishedVersion)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- IUScholarWorks (Indiana University) (submittedVersion)
- Funders
- Universitetet i Oslo
- Humanitas University
- School of Medicine, University of Kansas
- School of Medicine, Indiana University
- Japan Society for the Promotion of Science (23K24615)
- Topics
- Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Keywords
- artificial intelligence, computer-aided diagnosis, optical diagnostics, colorectal polyps, polypectomy, negative predictive value, rectosigmoid polyps, colorectal cancer screening, cost reduction
- MeSH terms
- Artificial Intelligence, Colonic Polyps, Colonoscopy, Humans, Colorectal Neoplasms, Intestinal Polyposis
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
