Artificial Intelligence-Assisted Colonoscopy in Colorectal Cancer Screening in a General Hospital

Official title

Real-World Experience of Artificial Intelligence-Assisted Colonoscopy in Colorectal Cancer Screening in a General Hospital: A Single-Center Cohort Phase IV Study

Overview

Cancer can develop in the colon, or large bowel. Examination of the colon with a tube fitted with a camera is called a colonoscopy. Colonoscopy allows detection of small growths in the colon, called "polyps". Polyps can often be removed during colonoscopy. Some of these polyps are called adenomas and can become cancer after several years. A good colonoscopy aims to find and take out as many of these polyps as possible. A quality indication of colonoscopy is the "adenoma detection rate" (ADR). It should be high, meaning many polyps are detected and taken out. New artificial intelligence devices to assist colonoscopy seem to increase the ADR, and maybe help prevent cancer even better than normal colonoscopy. The goal of this clinical trial is to compare the ADR when using standard colonoscopy to the ADR with artificial intelligence (AI)-assisted colonoscopy.

Detailed description

The colon is a part of the bowel where colon cancer can develop.

It is possible to prevent colon cancer by doing a screening test called a colonoscopy.

The colonoscopy procedure allows detection of "polyps" which can often be removed during the procedure. Some of these polyps are called adenomas and can become cancer after several years.

A good colonoscopy aims to find and take out as many of these polyps as possible.

A quality indication of colonoscopy is the "adenoma detection rate" (ADR). It should be high, meaning many polyps are detected and taken out.

New artificial intelligence devices to assist colonoscopy seem to increase the ADR, and maybe help prevent cancer even better than normal colonoscopy.

The goal of this clinical trial is to compare the ADR when using standard colonoscopy to the ADR with artificial intelligence (AI)-assisted colonoscopy.

Patients who are scheduled to have screening colonoscopy and who agree to participate, and are aged 45 years or more, will be randomly assigned to receive either standard colonoscopy or AI-assisted colonoscopy.

The main objective of this study is the difference in the ADR between a conventional colonoscopy procedure and an AI-assisted colonoscopy procedure.

Secondary objectives will compare the 2 groups (conventional colonoscopy and AI-assisted colonoscopy) regarding polyp size, polyp quantity, polyp histology (laboratory analysis of the polyp that was taken out), polyp dysplasia grade (how close the polyp is to cancer), polyp location in the colon, endoscopist experience (older or younger doctor), time of day and colonoscopy preparation quality (how clean the bowel is).

With these results we can show that AI-assisted colonoscopy is useful or not to help better prevent colon cancer.

Interventions

• Other conventional colonoscopy procedure
  Study subjects in this interventional arm will undergo conventional colonoscopy.
• Other artificial intelligence-assisted colonoscopy procedure
  Study subjects in this interventional arm will undergo colonoscopy done with a commercially-available module that uses artificial intelligence to highlight suspected polyps on the screen during colonoscopy. This module also attempts to characterize the detected polyp as adenomatous or not. The detection and characterization of polyps is in real time, during the procedure.

Primary outcome measures

• Adenoma Detection Rate in Conventional versus Artificial Intelligence-Assisted Colonoscopy [Time frame: 1 day]

Secondary outcome measures (8)

• The difference in the detection rate of colorectal adenomas according to size by group (5 mm/6-9 mm/>10 mm) between a conventional colonoscopic procedure (CCP) and a colonoscopy procedure with AI (ACP). [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas according to the number per group (n=1-2/n= 3-10/n >10) between a conventional colonoscopic procedure (CCP) and a colonoscopy procedure with AI (ACP). [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas based on histology by group (hyperplastic/conventional adenomas/serrated adenomas/adenocarcinoma) between a conventional colonoscopic procedure (PCC) and a colonoscopy procedure with AI. [Time frame: 1 month]
• The difference in detection rate of colorectal adenomas based on dysplastic grade by group [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas depending on the location by group (rectum/left colon/transverse colon/right colon) between a conventional colonoscopic procedure (CCP) and a colonoscopy procedure with AI (ACP). [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas according to experience by group of colonoscopists [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas depending on the time of day . [Time frame: 1 day]
• The difference in the detection rate of colorectal adenomas according to colonic preparation by group (Boston Score 9/6-8/<6) between a conventional colonoscopic procedure (PCC) and a colonoscopy procedure with AI (ACP). [Time frame: 1 day]

Eligibility criteria

Inclusion criteria

• Patient (woman or man) candidate for a screening colonoscopy - Age: 45 to 74 years included
• Absence of inflammatory bowel disease
• Absence of significant digestive symptoms indicating colonoscopy (i.e. screening is the only indication for the examination)
• Patient able to understand the concept of the study and agreeing to participate

Exclusion criteria

• Patient outside the inclusion age
• All exclusion criteria for a colonoscopy.
• The indication for colonoscopy is not simple screening; for example, assessment of anemia, rectal bleeding, weight loss or abdominal pain.
• Patient's refusal to participate, or patient's inability to understand the study concept
• Any patient with major psychological or psychiatric disorders.

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

Healthy volunteers: Yes

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Diagnostic

Study locations

Belgium · 1 center

• Hopital Delta Chirec — Auderghem

Publications

• Spadaccini M, Marco A, Franchellucci G, Sharma P, Hassan C, Repici A. Discovering the first US FDA-approved computer-aided polyp detection system. Future Oncol. 2022 Apr;18(11):1405-1412. doi: 10.2217/fon-2021-1135. Epub 2022 Jan 27. PMID 35081745
• 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
• Gupta S, Lieberman D, Anderson JC, Burke CA, Dominitz JA, Kaltenbach T, Robertson DJ, Shaukat A, Syngal S, Rex DK. Recommendations for Follow-Up After Colonoscopy and Polypectomy: A Consensus Update by the US Multi-Society Task Force on Colorectal Cancer. Gastrointest Endosc. 2020 Mar;91(3):463-485.e5. doi: 10.1016/j.gie.2020.01.014. Epub 2020 Feb 7. No abstract available. PMID 32044106
• Kaminski MF, Thomas-Gibson S, Bugajski M, Bretthauer M, Rees CJ, Dekker E, Hoff G, Jover R, Suchanek S, Ferlitsch M, Anderson J, Roesch T, Hultcranz R, Racz I, Kuipers EJ, Garborg K, East JE, Rupinski M, Seip B, Bennett C, Senore C, Minozzi S, Bisschops R, Domagk D, Valori R, Spada C, Hassan C, Dinis-Ribeiro M, Rutter MD. Performance measures for lower gastrointestinal endoscopy: a European Societ PMID 28507745
• Hassan C, Antonelli G, Dumonceau JM, Regula J, Bretthauer M, Chaussade S, Dekker E, Ferlitsch M, Gimeno-Garcia A, Jover R, Kalager M, Pellise M, Pox C, Ricciardiello L, Rutter M, Helsingen LM, Bleijenberg A, Senore C, van Hooft JE, Dinis-Ribeiro M, Quintero E. Post-polypectomy colonoscopy surveillance: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2020. Endoscopy. 2020 A PMID 32572858
• Brenner H, Hoffmeister M, Stegmaier C, Brenner G, Altenhofen L, Haug U. Risk of progression of advanced adenomas to colorectal cancer by age and sex: estimates based on 840,149 screening colonoscopies. Gut. 2007 Nov;56(11):1585-9. doi: 10.1136/gut.2007.122739. Epub 2007 Jun 25. PMID 17591622
• Saftoiu A, Hassan C, Areia M, Bhutani MS, Bisschops R, Bories E, Cazacu IM, Dekker E, Deprez PH, Pereira SP, Senore C, Capocaccia R, Antonelli G, van Hooft J, Messmann H, Siersema PD, Dinis-Ribeiro M, Ponchon T. Role of gastrointestinal endoscopy in the screening of digestive tract cancers in Europe: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy. 2020 Apr;52(4 PMID 32052404
• Hassan C, Spadaccini M, Iannone A, Maselli R, Jovani M, Chandrasekar VT, Antonelli G, Yu H, Areia M, Dinis-Ribeiro M, Bhandari P, Sharma P, Rex DK, Rosch T, Wallace M, Repici A. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis. Gastrointest Endosc. 2021 Jan;93(1):77-85.e6. doi: 10.1016/j.gie.2020.06.059. Epub 2020 Jun 26. PMID 32598963

Identifiers

NCT: NCT06792292 · 2024 Chirec Delta Colo-AI

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗