Artificial Intelligence-Assisted Colonoscopy for the Early Detection of Colorectal Neoplasia: A Systematic Review of Randomised Controlled Trials
Downloads
This systematic review aimed to evaluate randomized controlled trials comparing artificial intelligence (AI)-assisted colonoscopy with standard colonoscopy for the detection of colorectal neoplasia and to assess the direction, magnitude, and consistency of effects across detection outcomes. Two independent reviewers searched PubMed/MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Scopus, and Web of Science from database inception through July 2026. They independently screened records, extracted data, and assessed the risk of bias using the Cochrane Risk of Bias 2 (RoB 2) tool. Randomized controlled trials involving adults that compared real-time computer-aided detection (CADe), with or without computer-aided diagnosis (CADx), against standard or sham-assisted colonoscopy were eligible for inclusion. Findings were synthesized narratively according to outcome domains, and the certainty of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. A quantitative meta-analysis was not performed because of clinical and methodological heterogeneity. Thirteen randomized controlled trials involving more than 12,000 participants were included, encompassing parallel-group and tandem designs and several commercially available CADe systems. The adenoma detection rate (ADR) was higher with CADe in most parallel-group trials, with statistically significant improvements observed in seven of ten trials and nonsignificant differences in the remaining three. Representative effect estimates included a risk ratio (RR) of 1.30 (95% confidence interval [CI], 1.14–1.45) and an adjusted odds ratio (aOR) of 1.47 (95% CI, 1.21–1.78). The mean number of adenomas detected per colonoscopy (APC) was consistently higher with CADe. In two tandem colonoscopy trials, the adenoma miss rate (AMR) was lower with CADe, including a reported rate of 15.5% versus 32.4% (aOR, 0.38; 95% CI, 0.23–0.62). However, the effects of CADe on advanced adenoma detection and sessile serrated lesion detection were less consistent.
Barua, I., Vinsard, D. G., Jodal, H. C., Loberg, M., Kalager, M., & Holme, O. (2021). Artificial intelligence for polyp detection during colonoscopy: A systematic review and meta-analysis. Endoscopy, 53(3), 277–284. https://doi.org/10.1055/a-1201-7165
Bretthauer, M., Loberg, M., Wieszczy, P., Kalager, M., Emilsson, L., & Garborg, K. (2022). Effect of colonoscopy screening on risks of colorectal cancer and related death. New England Journal of Medicine, 387(17), 1547–1556. https://doi.org/10.1056/NEJMoa2208375
Byrne, M. F., Chapados, N., Soudan, F., Oertel, C., Linares Perez, M., & Kelly, R. (2019). Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut, 68(1), 94–100. https://doi.org/10.1136/gutjnl-2017-314547
Corley, D. A., Levin, T. R., & Doubeni, C. A. (2014). Adenoma detection rate and risk of colorectal cancer and death. New England Journal of Medicine, 370(14), 1298–1306. https://doi.org/10.1056/NEJMoa1309086
Gong, D., Wu, L., Zhang, J., Mu, G., Shen, L., & Liu, J. (2020). Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): A randomised controlled study. The Lancet Gastroenterology & Hepatology, 5(4), 352–361. https://doi.org/10.1016/S2468-1253(19)30413-3
Guyatt, G. H., Oxman, A. D., Vist, G. E., Kunz, R., Falck-Ytter, Y., Alonso-Coello, P., & Schunemann, H. J. (2008). GRADE: An emerging consensus on rating quality of evidence and strength of recommendations. BMJ, 336(7650), 924–926. https://doi.org/10.1136/bmj.39489.470347.AD
Hassan, C., Spadaccini, M., Iannone, A., Maselli, R., Jovani, M., & Chandrasekar, V. T. (2021). Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: A systematic review and meta-analysis. Gastrointestinal Endoscopy, 93(1), 77–85. https://doi.org/10.1016/j.gie.2020.06.059
Kaminski, M. F., Regula, J., Kraszewska, E., Polkowski, M., Wojciechowska, U., & Didkowska, J. (2010). Quality indicators for colonoscopy and the risk of interval cancer. New England Journal of Medicine, 362(19), 1795–1803. https://doi.org/10.1056/NEJMoa0907667
Liu, P., Wang, P., Glissen Brown, J. R., Berzin, T. M., Zhou, G., & Liu, W. (2020). The single-monitor trial: An embedded CADe system increased adenoma detection during colonoscopy: A prospective randomized study. Therapeutic Advances in Gastroenterology, 13, 1756284820979165. https://doi.org/10.1177/1756284820979165
Mori, Y., Kudo, S. E., Misawa, M., Saito, Y., Ikematsu, H., & Hotta, K. (2018). Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: A prospective study. Annals of Internal Medicine, 169(6), 357–366. https://doi.org/10.7326/M18-0249
Page, M. J. (2021). The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. International Journal of Surgery, 88, 105906.
Repici, A., Badalamenti, M., Maselli, R., Correale, L., Radaelli, F., & Rondonotti, E. (2020). Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology, 159(2), 512–520. https://doi.org/10.1053/j.gastro.2020.04.062
Rex, D. K., Boland, C. R., Dominitz, J. A., Giardiello, F. M., Johnson, D. A., & Kaltenbach, T. (2017). Colorectal cancer screening: Recommendations for physicians and patients from the U.S. Multi-Society Task Force on Colorectal Cancer. Gastroenterology, 153(1), 307–323. https://doi.org/10.1053/j.gastro.2017.05.013
Shaukat, A., Kahi, C. J., Burke, C. A., Rabeneck, L., Sauer, B. G., & Rex, D. K. (2021). ACG clinical guidelines: Colorectal cancer screening 2021. American Journal of Gastroenterology, 116(3), 458–479. https://doi.org/10.14309/ajg.0000000000001122
Spadaccini, M., Iannone, A., Maselli, R., Badalamenti, M., Desai, M., & Chandrasekar, V. T. (2021). Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: A systematic review and network meta-analysis. The Lancet Gastroenterology & Hepatology, 6(10), 793–802. https://doi.org/10.1016/S2468-1253(21)00215-6
Sterne, J. A. C., Savovic, J., Page, M. J., Elbers, R. G., Blencowe, N. S., & Boutron, I. (2019). RoB 2: A revised tool for assessing risk of bias in randomised trials. BMJ, 366, l4898. https://doi.org/10.1136/bmj.l4898
Su, J. R., Li, Z., Shao, X. J., Ji, C. R., Ji, R., & Zhou, R. C. (2020). Impact of a real-time automatic quality control system on colorectal polyp and adenoma detection: A prospective randomized controlled study (with videos). Gastrointestinal Endoscopy, 91(2), 415–424. https://doi.org/10.1016/j.gie.2019.08.026
Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021). Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 71(3), 209–249. https://doi.org/10.3322/caac.21660
van Rijn, J. C., Reitsma, J. B., Stoker, J., Bossuyt, P. M., van Deventer, S. J., & Dekker, E. (2006). Polyp miss rate determined by tandem colonoscopy: A systematic review. American Journal of Gastroenterology, 101(2), 343–350. https://doi.org/10.1111/j.1572-0241.2006.00390.x
Wang, P., Berzin, T. M., Glissen Brown, J. R., Bharadwaj, S., Becq, A., & Xiao, X. (2019). Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: A prospective randomised controlled study. Gut, 68(10), 1813–1819. https://doi.org/10.1136/gutjnl-2018-317500
Wang, P., Liu, X., Berzin, T. M., Glissen Brown, J. R., Liu, P., & Zhou, C. (2020). Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): A double-blind randomised study. The Lancet Gastroenterology & Hepatology, 5(4), 343–351. https://doi.org/10.1016/S2468-1253(19)30411-X
Wang, P., Xiao, X., Glissen Brown, J. R., Berzin, T. M., Tu, M., & Xiong, F. (2018). Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nature Biomedical Engineering, 2(10), 741–748. https://doi.org/10.1038/s41551-018-0301-3
Winawer, S. J., Zauber, A. G., Ho, M. N., O’Brien, M. J., Gottlieb, L. S., & Sternberg, S. S. (1993). Prevention of colorectal cancer by colonoscopic polypectomy. New England Journal of Medicine, 329(27), 1977–1981. https://doi.org/10.1056/NEJM199312303292701
Wolf, A. M. D., Fontham, E. T. H., Church, T. R., Flowers, C. R., Guerra, C. E., & LaMonte, S. J. (2018). Colorectal cancer screening for average-risk adults: 2018 guideline update from the American Cancer Society. CA: A Cancer Journal for Clinicians, 68(4), 250–281. https://doi.org/10.3322/caac.21457
Zhao, S., Wang, S., Pan, P., Xia, T., Chang, X., & Yang, X. (2019). Magnitude, risk factors, and factors associated with adenoma miss rate of tandem colonoscopy: A systematic review and meta-analysis. Gastroenterology, 156(6), 1661–1674. https://doi.org/10.1053/j.gastro.2019.01.260
Copyright (c) 2026 OK Yulizal, Dandy Daffa Anwar, Christina J.R Esmeralda Lumantobing
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
