AI-Assisted Optical Diagnosis (CADx) for Diminutive Colorectal Polyps
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age45-80
SponsorCentre hospitalier de l'Université de Montréal (CHUM)
About this trial
This study evaluates whether an artificial intelligence system (GI Genius, Medtronic), already approved by Health Canada, can help doctors accurately identify, in real time during colonoscopy, which small colorectal polyps (5 mm or less) need to be monitored (adenomas) versus those that do not (for example, hyperplastic polyps). For each small polyp found, the endoscopist will first record a diagnosis without the help of the artificial intelligence system, then activate the system and record a second diagnosis after seeing its assessment. Both diagnoses will be compared to the final result from standard pathology testing, which remains the reference standard. This is an observational diagnostic accuracy study: it does not change any clinical care. All polyps continue to be removed and sent for pathology analysis as usual, whether or not the artificial intelligence system agrees with the doctor. The study will take place during colonoscopies already scheduled for standard clinical reasons (screening, surveillance, or diagnostic work-up), with no additional visits, blood draws, imaging, or sedation. Approximately 840 participants will be enrolled across three Canadian centres (Santé Québec - CHUM, McGill University Health Centre, and St. Paul's Hospital, Vancouver). The goal is to determine whether this AI-assisted approach helps doctors reach the internationally recognized performance thresholds (at least 80% sensitivity and 80% specificity) needed to support clinical adoption of real-time optical diagnosis, which could eventually reduce unnecessary pathology testing.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Signed informed consent, obtained before the colonoscopy and before sedation
Age 45-80 years
Indication for elective colonoscopy (screening, surveillance, or diagnostic)
At least one diminutive polyp (≤5 mm) detected during the procedure (required for inclusion in the analytic cohort; consented patients without an eligible polyp are documented as screen failures)
Disqualifiers
Known inflammatory bowel disease
Active colitis
Coagulopathy or thrombocytopenia (INR ≥1.5 or platelets <50×10⁹/L)
Familial polyposis syndrome
Trial population
Consecutive patients aged 45-80 years undergoing elective colonoscopy (screening, surveillance, or diagnostic) at three Canadian academic centres (CHUM, CUSM, St. Paul's Hospital), providing written informed consent before the procedure and before sedation. Patients become eligible for the analytic cohort if at least one diminutive polyp (≤5 mm) is detected during colonoscopy; those without an eligible polyp are recorded as screen failures. Key exclusions: inflammatory bowel disease, active colitis, coagulopathy/thrombocytopenia, familial polyposis syndrome, ASA \>III, emergency colonoscopy, or inadequate bowel preparation. Target: 840 patients (\~1,605 diminutive polyps) across the three centres over 24 months.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
GI Genius CADx module (Medtronic)
DeviceComputer-aided diagnosis (CADx) device recently approved by Health Canada, used to provide real-time optical characterization of diminutive colorectal polyps (≤5 mm) during colonoscopy. For each diminutive polyp detected, the endoscopist first records a CADx-unassisted optical diagnosis (electronically locked before device activation), then activates the GI Genius CADx module, which displays a device-provided characterization. The endoscopist then records a final CADx-assisted optical diagnosis, which may agree or disagree with the device output. The study evaluates the CADx-assisted optical-diagnosis strategy (endoscopist + device combined) rather than autonomous or standalone CADx performance.
Treatment groups
840 Participants
are divided into 1 treatment groupGroup A: Diminutive Colorectal Polyps - CADx-Assisted Optical Diagnosis1 intervention
Trial outcomes
Primary outcomes
1
Sensitivity of CADx-assisted optical diagnosis for adenomatous histology
Number of correct adenomatous optical diagnoses divided by the number of histologically confirmed adenomas, among all diminutive (≤5 mm) colorectal polyps, benchmarked against the ESGE SODA threshold (≥80%)
Time frame
Within 14 to 45 days after polypectomy (colorectal polyp resection during the index colonoscopy), once histopathology results are available2
Specificity of CADx-assisted optical diagnosis for adenomatous histology
Number of correct non-adenomatous optical diagnoses divided by the number of histologically confirmed non-adenomas, among all diminutive (≤5 mm) colorectal polyps, benchmarked against the ESGE SODA threshold (≥80%)
Time frame
Within 14 to 45 days after polypectomy (colorectal polyp resection during the index colonoscopy), once histopathology results are availableSecondary outcomes
1
NPV of CADx-assisted optical diagnosis for adenomatous histology (rectosigmoid, high confidence)
Benchmark : ASGE PIVI ≥90%.
Time frame
Within 14 to 45 days after polypectomy (colorectal polyp resection during the index colonoscopy), once histopathology results are available2
Surveillance interval agreement
Proportion of patients with agreement between CADx-assisted and pathology-based surveillance interval recommendations (ASGE PIVI ≥90%).
Time frame
Outcome assessed throughout the 24-month recruitment period, with total study duration of 36 months3
Sensitivity and specificity, rectosigmoid subset
ESGE SODA Recommendation 1 (sensitivity ≥90%, specificity ≥80%)
Time frame
Outcome assessed throughout the 24-month recruitment period, with total study duration of 36 months4
CADx-assisted vs. CADx-unassisted diagnostic performance
Paired within-polyp comparison of adenoma sensitivity/specificity
Time frame
Outcome assessed throughout the 24-month recruitment period, with total study duration of 36 monthsOther outcomes
1
Health economic outcome
Incremental cost-effectiveness of the CADx-assisted strategy vs. universal histopathological examination
Time frame
Outcomes assessed throughout the 24-month recruitment period, with total study duration of 36 months2
Subgroup diagnostic performance
By polyp size (≤3 mm vs. 4-5 mm), morphology (Paris classification), colonic location, endoscopist experience, patient sex, and centre
Time frame
Outcome assessed throughout the 24-month recruitment period, with total study duration of 36 monthsLocations
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: