Autonomous Artificial Intelligence vs Artificial Intelligence–Assisted Human Optical Diagnosis of Colorectal Polyps: A Randomized Controlled Trial
Open accessAbstract
BACKGROUND & AIMS: Artificial intelligence (AI)-based optical diagnosis systems (CADx) have been developed to allow pathology prediction of colorectal polyps during colonoscopies. However, CADx systems have not yet been validated for autonomous performance. Therefore, we conducted a trial comparing autonomous AI to AI-assisted human (AI-H) optical diagnosis. METHODS: We performed a randomized noninferiority trial of patients undergoing elective colonoscopies at 1 academic institution. Patients were randomized into (1) autonomous AI-based CADx optical diagnosis of diminutive polyps without human input or (2) diagnosis by endoscopists who performed optical diagnosis of diminutive polyps after seeing the real-time CADx diagnosis. The primary outcome was accuracy in optical diagnosis in both arms using pathology as the gold standard. Secondary outcomes included agreement with pathology for surveillance intervals. RESULTS: A total of 467 patients were randomized (238 patients/158 polyps in the autonomous AI group and 229 patients/179 polyps in the AI-H group). Accuracy for optical diagnosis was 77.2% (95% confidence interval [CI], 69.7-84.7) in the autonomous AI group and 72.1% (95% CI, 65.5-78.6) in the AI-H group (P = .86). For high-confidence diagnoses, accuracy for optical diagnosis was 77.2% (95% CI, 69.7-84.7) in the autonomous AI group and 75.5% (95% CI, 67.9-82.0) in the AI-H group. Autonomous AI had statistically significantly higher agreement with pathology-based surveillance intervals compared to AI-H (91.5% [95% CI, 86.9-96.1] vs 82.1% [95% CI, 76.5-87.7]; P = .016). CONCLUSIONS: Autonomous AI-based optical diagnosis exhibits noninferior accuracy to endoscopist-based diagnosis. Both autonomous AI and AI-H exhibited relatively low accuracy for optical diagnosis; however, autonomous AI achieved higher agreement with pathology-based surveillance intervals. (ClinicalTrials.gov, Number NCT05236790).
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Moher, D., Hopewell, S., Schulz, K. F., Montori, V., Gotzsche, P. C., Devereaux, P. J., Elbourne, D., Egger, M., & Altman, D. G. (2010) · BMJ · doi:10.1136/bmj.c869 · Cited by 8,883 · see citing works
Rex, D. K., Kahi, C., O'Brien, M., Levin, T. R., Pohl, H., Rastogi, A., Burgart, L., Imperiale, T., Ladabaum, U., Cohen, J., et al. (2011) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2011.01.023 · Cited by 629 · see citing works
Self-citationGupta, S. N., Lieberman, D. A., Anderson, J. C., Burke, C. A., Dominitz, J. A., Kaltenbach, T. R., Robertson, D. J., Shaukat, A., Syngal, S., & Rex, D. K. (2020) · Gastroenterology · doi:10.1053/j.gastro.2019.10.026 · Cited by 482 · see citing works
Lieberman, D. A., Moravec, M. D., Holub, J. L., Michaels, L. C., & Eisen, G. M. (2008) · Gastroenterology · doi:10.1053/j.gastro.2008.06.083 · Cited by 457 · see citing works
Prevalence of Clinically Important Histology in Small Adenomas
Butterly, L. F., Chase, M. P., Pohl, H., & Fiarman, G. S. (2006) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2005.12.021 · Cited by 269 · see citing works
Self-citationRondonotti, E., Hassan, C., Tamanini, G., Antonelli, G., Andrisani, G., Leonetti, G., Paggi, S., Amato, A., Scardino, G., Di Paolo, D., et al. (2023) · Endoscopy · doi:10.1055/a-1852-0330 · Cited by 128 · see citing works
Real-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
Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps
Hassan, C., Balsamo, G., Lorenzetti, R., Zullo, A., & Antonelli, G. (2022) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2022.04.045 · Cited by 119 · see citing works
Natural history of diminutive and small colorectal polyps: a systematic literature review
Vleugels, J. L. A., Hazewinkel, Y., Fockens, P., & Dekker, E. (2016) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2016.12.014 · Cited by 118 · see citing works
Accuracy for Optical Diagnosis of Small Colorectal Polyps in Nonacademic Settings
Kuiper, T., Marsman, W. A., Jansen, J. M., van Soest, E. J., Haan, Y. C. L., Bakker, G. J., Fockens, P., & Dekker, E. (2012) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2012.05.004 · Cited by 110 · see citing works
Endoscopic Trimodal Imaging Detects Colonic Neoplasia as Well as Standard Video Endoscopy
Kuiper, T., van den Broek, F. J. C., Naber, A. H. J., van Soest, E. J., Scholten, P., Mallant–Hent, R. C., den Brande, J. V., Jansen, J. M., van Oijen, A. H. A. M., Marsman, W. A., et al. (2011) · Gastroenterology · doi:10.1053/j.gastro.2011.03.008 · Cited by 91 · see citing works
van den Broek, F. J. C., van Soest, E. J., Naber, A. H. J., van Oijen, A. H. A. M., Mallant–Hent, R. C., Böhmer, C. J. M., Scholten, P., Stokkers, P. C. F., Marsman, W. A., Mathus-Vliegen, E. M. H., et al. (2009) · The American Journal of Gastroenterology · doi:10.1038/ajg.2009.161 · Cited by 73 · see citing works
Uptake and barriers for implementation of the resect and discard strategy: an international survey
Willems, P., Djinbachian, R., Ditisheim, S., Orkut, S., Pohl, H., Barkun, A. N., Bouin, M., Faulques, B., & Renteln, D. A. V. (2020) · Endoscopy International Open · doi:10.1055/a-1132-5371 · Cited by 37 · see citing works
Self-citationPolyp Resection - Controversial Practices and Unanswered Questions
Renteln, D. A. V., & Pohl, H. (2017) · Clinical and Translational Gastroenterology · doi:10.1038/ctg.2017.6 · Cited by 24 · see citing works
Self-citationQuality of optical diagnosis of diminutive polyps and associated factors
Pohl, H., Bensen, S. P., Toor, A., Gordon, S. R., Levy, L. C., Anderson, P. L., Anderson, J., Rothstein, R. I., & Robertson, D. J. (2016) · Endoscopy · doi:10.1055/s-0042-108432 · Cited by 18 · see citing works
Self-citationImplementation of Optical Diagnosis for Colorectal Polyps: Standardization of Studies Is Needed
Kaltenbach, T. R., Rex, D. K., Wilson, A., Hewett, D. G., Sanduleanu, S., Rastogi, A. N., Wallace, M. B., & Soetikno, R. M. (2014) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2014.10.009 · Cited by 16 · see citing works
Polyp characterization at colonoscopy: Clinical implications
Allen, J. E., & Sharma, P. (2017) · Best Practice & Research Clinical Gastroenterology · doi:10.1016/j.bpg.2017.07.001 · Cited by 15 · see citing works
Glover, B. M., Patel, N., Ashrafian, H., & TEARE, J. P. (2018) · Therapeutic Advances in Gastroenterology · doi:10.1177/1756284818814948 · Cited by 13 · see citing works
Serrated polyps and polyposis of the colon: a brief review for surgeon endoscopists
Hyun, E., Helewa, R. M., Singh, H., Wightman, H. R., & Park, J. (2021) · Canadian Journal of Surgery · doi:10.1503/cjs.018820 · Cited by 11 · see citing works
Djinbachian, R., Marchand, E., Pohl, H., Aguilera-Fish, A. H., Bouin, M., Deslandres, É., Weber, A. M., Bouchard, S., Panzini, B., & Renteln, D. A. V. (2020) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2020.11.023 · Cited by 8 · see citing works
Self-citationWhat size cutoff level should be used to implement optical polyp diagnosis?
Taghiakbari, M., Pohl, H., Djinbachian, R., et al. (2022) · Endoscopy · doi:10.1055/a-1843-9535 · Cited by 8 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Still being checked.
- Authors
- Djinbachian, R., Haumesser, C., Taghiakbari, M., Pohl, H., Barkun, A., Sidani, S., Liu Chen Kiow, J., Panzini, B., Bouchard, S., Deslandres, E., Alj, A., & von Renteln, D.
- Affiliations
- Université de Montréal (CA)
- Dartmouth–Hitchcock Medical Center (US)
- McGill University Health Centre (CA)
- Venue
- Gastroenterology
- Publisher
- Elsevier BV
- Published
- 2024-07
- Volume
- 167
- Issue
- 2
- Pages
- 392-399.e2
- ISSN
- 0016-5085 (ISSN-L)
- OpenAlex
- W4392391621
- Cited by
- 70
- References
- 21
- Citations by year
- 2026: 19 · 2025: 33 · 2024: 18
- FWCI
- 11.91
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Gastroenterology (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Fujifilm Holdings Corporation
- Topics
- Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- artificial intelligence, computer-aided diagnosis, colorectal polyps, diminutive polyps, colonoscopy, autonomous AI systems, optical diagnostics, surveillance interval, non-inferiority
- MeSH terms
- Adult, Aged, Artificial Intelligence, Colonic Polyps, Colonoscopy, Diagnosis, Computer-Assisted, Female, Humans, Male, Middle Aged, Predictive Value of Tests, Colorectal Neoplasms, Reproducibility of Results
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
