Artificial Intelligence in Colonoscopy

Official title

Artificial Intelligence in Endoscopic Diagnosis of Colorectal Polyps: A Prospective Randomized Study.

Overview

Colorectal cancer is the second most common malignancy in the countries of the European Union. Colonoscopy is the primary method for detecting and preventing the development of colorectal cancer is endoscopic examination. This study aims to evaluate the impact of artificial intelligence on the detection rate of polyps and early stages of colorectal cancer.

Detailed description

Colorectal cancer is the second most common malignancy in the countries of the European Union. The primary method for detecting and preventing the development of colorectal cancer is endoscopic examination-colonoscopy, during which precancerous lesions such as adenomas and serrated polyps can be removed. The effectiveness of colonoscopy depends on the adenoma detection rate, which varies among endoscopists and is influenced by their skills and experience. It has been proven that high-quality colonoscopy prevents the omission of colorectal cancer, which might develop in the future as so-called interval cancer. A breakthrough in machine learning in recent years has enabled the development of commercial artificial intelligence systems. These systems aim to improve the detection rates of precancerous polyps and, consequently, potentially reduce the risk of developing colorectal cancer. Artificial intelligence is also expected to help standardize performance across endoscopic procedures of varying quality, thereby contributing to a reduction in colorectal cancer incidence in the future. This study aims to evaluate the impact of artificial intelligence on the detection rate of polyps and early stages of colorectal cancer.

Interventions

• Device Computer-aided detection (CADe)
  Endo-Aid CADe system is an AI-assisted computer-aided lesion detection application on ENDO-AID hardware. It uses a complex algorithm created via a neural network developed and taught by Olympus. With this new app, the sophisticated machine learning system can alert the endoscopist in real-time when a suspicious lesion appears on the screen. The image from the vision processor is transferred to the CADe device. The computer application recognizes the shape of the polyps and marks their place on t

Primary outcome measures

• Adenoma detection rate (ADR) [Time frame: During the colonoscopy examination]

Secondary outcome measures (3)

• Utility of artificial intelligence for both novice and experienced endoscopists [Time frame: During the colonoscopy examination]
• Assessing the morphology of polyps detected during colonoscopy [Time frame: During the colonoscopy examination]
• Cost analysis of procedures performed with the use of artificial intelligence [Time frame: Through study completion, an average of 6 months]

Eligibility criteria

Inclusion criteria

• Consent to participate in the study,
• Age between 50 and 65 years,
• Scheduled outpatient colonoscopy.

Exclusion criteria

• Previous colonoscopy,
• History of colorectal surgery,
• Ongoing biological therapy for any indication,
• Primary sclerosing cholangitis,
• Familial polyposis syndrome,
• Chronic diarrhea,
• Ulcerative colitis,
• Crohn's disease.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Diagnostic

Study locations

Poland · 2 centers

• MEDICINA Medical Center — Krakow
• Brothers Hospitallers Medical Center, Hospital of St John of god in Krakow — Krakow

Publications

• Boroff ES, Gurudu SR, Hentz JG, Leighton JA, Ramirez FC. Polyp and adenoma detection rates in the proximal and distal colon. Am J Gastroenterol. 2013 Jun;108(6):993-9. doi: 10.1038/ajg.2013.68. Epub 2013 Apr 9. PMID 23567353
• Mori Y, Kudo SE, East JE, Rastogi A, Bretthauer M, Misawa M, Sekiguchi M, Matsuda T, Saito Y, Ikematsu H, Hotta K, Ohtsuka K, Kudo T, Mori K. Cost savings in colonoscopy with artificial intelligence-aided polyp diagnosis: an add-on analysis of a clinical trial (with video). Gastrointest Endosc. 2020 Oct;92(4):905-911.e1. doi: 10.1016/j.gie.2020.03.3759. Epub 2020 Mar 30. PMID 32240683
• van Doorn SC, Klanderman RB, Hazewinkel Y, Fockens P, Dekker E. Adenoma detection rate varies greatly during colonoscopy training. Gastrointest Endosc. 2015 Jul;82(1):122-9. doi: 10.1016/j.gie.2014.12.038. Epub 2015 Mar 24. PMID 25817896
• Barua I, Vinsard DG, Jodal HC, Loberg M, Kalager M, Holme O, Misawa M, Bretthauer M, Mori Y. Artificial intelligence for polyp detection during colonoscopy: a systematic review and meta-analysis. Endoscopy. 2021 Mar;53(3):277-284. doi: 10.1055/a-1201-7165. Epub 2020 Sep 29. PMID 32557490
• Repici A, Badalamenti M, Maselli R, Correale L, Radaelli F, Rondonotti E, Ferrara E, Spadaccini M, Alkandari A, Fugazza A, Anderloni A, Galtieri PA, Pellegatta G, Carrara S, Di Leo M, Craviotto V, Lamonaca L, Lorenzetti R, Andrealli A, Antonelli G, Wallace M, Sharma P, Rosch T, Hassan C. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology. PMID 32371116
• Corley DA, Jensen CD, Marks AR, Zhao WK, Lee JK, Doubeni CA, Zauber AG, de Boer J, Fireman BH, Schottinger JE, Quinn VP, Ghai NR, Levin TR, Quesenberry CP. Adenoma detection rate and risk of colorectal cancer and death. N Engl J Med. 2014 Apr 3;370(14):1298-306. doi: 10.1056/NEJMoa1309086. PMID 24693890
• Kaminski MF, Regula J, Kraszewska E, Polkowski M, Wojciechowska U, Didkowska J, Zwierko M, Rupinski M, Nowacki MP, Butruk E. Quality indicators for colonoscopy and the risk of interval cancer. N Engl J Med. 2010 May 13;362(19):1795-803. doi: 10.1056/NEJMoa0907667. PMID 20463339

Identifiers

NCT: NCT06786793 · 2024.000.421

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗