Artificial Intelligence for Real-time Detection and Monitoring of Colorectal Polyps

The investigators hypothesize that the clinical implementation of a deep learning AI system is an optimal tool to monitor, audit and improve the detection and classification of polyps and other anatomical landmarks during colonoscopy. The objectives of this study are to generate preliminary data to evaluate the effectiveness of AI-assisted colonoscopy on: a) the rate of detection of adenomas; b) the automatic detection of the anatomical landmarks (i.e., ileocecal valve and appendiceal orifice).

Study Overview

• Status: Completed
• Conditions: Adenomatous Polyps
• Intervention / Treatment: Diagnostic test: Polyps detection by Artificial Intelligence

Detailed Description

In this trial, the investigators aim to evaluate the followings:

1. the accuracy of automatic detection of important anatomical landmarks (i.e., ileocecal valve, appendiceal orifice);
2. the accuracy of automatic detection of polyps/adenomas (PDR/ADR);

• Study Type: Interventional
• Enrollment (Actual): 372
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Canada
  • Quebec
    • Montréal, Quebec, Canada
      • Centre hospitalier universitaire de Montréal
    • Montréal, Quebec, Canada, QC H3T 1J4
      • Université de Montréal
• France
  • Strasbourg, France, 67000
    • IHU Strasbourg

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 45 years to 80 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria :

• Signed informed consent
• Age 45-80 years
• Indication to undergo a lower GI endoscopy.

Exclusion Criteria :

• Coagulopathy
• Poor general health, defined as an American Society of Anesthesiologists (ASA) physical status class >3
• Emergency colonoscopies
• Hospitalized patients
• Known inflammatory bowel disease (IBD)
• Patients currently in the emergency room

Study Plan

How is the study designed?

Design Details

• Primary Purpose: DIAGNOSTIC
• Allocation: NA
• Interventional Model: SINGLE_GROUP
• Masking: NONE

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

EXPERIMENTAL: Artificial intelligence for real-time detection and monitoring of colorectal polyps; A standard colonoscopy will be performed according to the standard of routine care. All optically diagnosed polyps will be removed and sent to the CHUM pathology laboratory for histopathological evaluation according to institutional standards. The AI system will capture video of the procedure in real time, and provide additional information on the detection of polyps, follow-up and prediction of pathology. The full-length colonoscopy videos will be annotated for the exact time of the identification of the anatomical landmarks, polyps, also for polyp- and procedural-related characteristics.

Diagnostic test: Polyps detection by Artificial Intelligence; The AI system will capture the live video of the procedure and the AI feedback (polyp detection, tracking, and pathology prediction) will be shown on a second screen installed next to the regular endoscopy screen. Screen A will show the regular endoscopy image and screen B will show the regular endoscopy image together with the areas that might harbor a polyp or the information to predict pathology

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of polyps detected	Efficacy of AI assisted colonoscopy to detect the proportion of patients with at least 1 polyp. Polyp detection rate with an AI.	Day 1
Evaluation of the automatic report of the colonoscopy quality indicators	Compare of the automatic detection of the ileocecal valve, appendiceal orifice, and the automatic calculation of the withdrawal time with manual detection	Day 1

Collaborators and Investigators

• Sponsor: Centre hospitalier de l'Université de Montréal (CHUM)

Study record dates

Study Major Dates

• Study Start (ACTUAL): December 18, 2020
• Primary Completion (ACTUAL): March 31, 2022
• Study Completion (ACTUAL): May 11, 2022

Study Registration Dates

• First Submitted: October 1, 2020
• First Submitted That Met QC Criteria: October 7, 2020
• First Posted (ACTUAL): October 14, 2020

Study Record Updates

• Last Update Posted (ACTUAL): November 25, 2022
• Last Update Submitted That Met QC Criteria: November 23, 2022
• Last Verified: November 1, 2022

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Quality indicators; Polyps detection; Adenoma detection; Polyps classification
• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Pathological Conditions, Anatomical; Adenoma; Polyps; Adenomatous Polyps
• Other Study ID Numbers: 20.198

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