The CERTAIN Study: Combining Endo-cuff in a Randomized Trial for Artificial Intelligence Navigation (CERTAIN)

Colonoscopy is clinically used as the gold standard for detection of colon cancer (CRC) and removal of adenomatous polyps. Despite the success of colonoscopy in reducing cancer-related deaths, there exists a disappointing level of adenomas missed at colonoscopy. "Back-to-back" colonoscopies have indicated significant miss rates of 27% for small adenomas (< 5 mm) and 6% for adenomas of more than 10 mm in diameter. Studies performing both CT colonography and colonoscopy estimate that the colonoscopy miss rate for polyps over 10 mm in size may be as high as 12%. The clinical importance of missed lesions should be emphasized because these lesions may ultimately progress to CRC. Limitations in human visual perception and other human biases such as fatigue, distraction, level of alertness during examination increases recognition errors and way of mitigating them may be the key to improve polyp detection and further reduction in mortality from CRC.

Recent advances in artificial intelligence (AI), deep learning (DL), and computer vision have permitted to develop several AI platforms which have already proved their efficacy in increasing adenoma detection during colonoscopy9,10. As a matter of fact, the improvement in detection due to AI systems is only related to the increased capacity of detecting lesions within the visual field, that is dependent on the amount of mucosa exposed by the endoscopist during the scope withdrawal.

Increasing the mucosa exposure would theoretically be a complementary strategy to further improve polyps detection. A number of distal attachments have been tested to increase the mucosal exposure by flattening mucosal folds, including a transparent cap, cuff or rings. The additional diagnostic yield obtained by the second generation of cuff (Endocuff Vision; Olympus America, Center Valley, Pa, USA) was recently investigated by a meta-analysis of randomized controlled trials, showing a significant improvement in adenoma detection rate, and adenomas per colonoscopy, with a reduction in the mean withdrawal time without any increase in adverse events compared with standard high-definition colonoscopy without any distal attachment.

In conclusion, technologies providing either mucosal image enhancement (Artificial Intelligence assisted colonoscopy) or mucosal exposure device (Endocuff Vision assisted colonoscopy) significantly improved adenoma detection rate (ADR). However, the diagnostic yield obtained by combining the different strategies is still unknown.

Study Overview

• Status: Completed
• Conditions: Artificial Intelligence
• Intervention / Treatment: Other: Artificial Intelligence

• Study Type: Observational
• Enrollment (Actual): 1300

Contacts and Locations

Study Locations

• Italy
  • Milano
    • Rozzano, Milano, Italy, 20089
      • Endoscopy Unit, Humanitas Research Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 40 years to 80 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

All 40-80 years-old subjects undergoing a colonoscopy for gastrointestinal symptoms, fecal immunohistochemical test positivity, primary screening or post-polypectomy surveillance.

Description

Inclusion Criteria:

• subjects undergoing a colonoscopy for gastrointestinal symptoms, fecal immunohistochemical test positivity, primary screening or post-polypectomy surveillance

Exclusion Criteria:

• subjects with personal history of CRC, or IBD.
• subjects affected with genetic mutations such as Lynch syndrome or Familiar Adenomatous Polyposis.
• patients with inadequate bowel preparation (defined as Boston Bowel Preparation Scale > 2 in any colonic segment).
• patients with previous colonic resection.
• patients on antithrombotic therapy, precluding polyp resection.
• patients with history of colonic strictures, precluding ECV use.
• patients who were not able or refused to give informed written consent.

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
AI arm; Standard colonoscopy with Artificial Intelligence-GI GeniusTM	Other: Artificial Intelligence; Artificial intelligence
Cuff arm; Endo-cuff Vision aided colonoscopy with Artificial Intelligence -GI GeniusTM	Other: Artificial Intelligence; Artificial intelligence

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic yield	To compare the additional diagnostic yield obtained by EndoCuff Vision aided-colonoscopy to the yield obtained by the Standard colonoscopy performed with the Artificial Intelligence ¬-GI GeniusTM- assistance in different colonoscopy settings.	12 Months

Collaborators and Investigators

• Sponsor: Istituto Clinico Humanitas

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2021
• Primary Completion (Actual): May 31, 2022
• Study Completion (Actual): May 31, 2022

Study Registration Dates

• First Submitted: December 15, 2020
• First Submitted That Met QC Criteria: December 15, 2020
• First Posted (Actual): December 21, 2020

Study Record Updates

• Last Update Posted (Actual): September 14, 2022
• Last Update Submitted That Met QC Criteria: September 13, 2022
• Last Verified: September 1, 2022

More Information

Terms related to this study

• Other Study ID Numbers: 1766

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: No

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No