Can AI learn to grade endoscopy quality from video?

NCT ID NCT06822816

First seen Aug 11, 2026 · Last updated Aug 12, 2026 · Updated 1 time

Summary

This study aims to create a large library of recorded endoscopy procedures from adults undergoing upper or lower gastrointestinal exams. The goal is to use these videos to develop and validate artificial intelligence tools that can automatically detect and report quality metrics, such as how thoroughly the procedure was performed. The library may also help create educational modules to train future endoscopists. By collecting diverse procedure data, researchers hope to build AI systems that provide real-time feedback and improve overall endoscopy quality.

What this could mean

Our plain-language read of the trial. This is informational only — not medical advice or a prediction.

Active substance
Artificial intelligence-empowered endoscopy quality reporting and educational modules
What this could lead to
If successful, this could lead to AI tools that automatically assess endoscopy quality, improve training for doctors, and potentially enhance detection of polyps and other abnormalities.
What could go wrong
This is an observational study, so it does not test a treatment. The AI models may not perform as expected in real-world settings, and the library's diversity may be limited.

This is an AI summary of the original study and may miss details. Read our disclaimer.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for ARTIFICIAL INTELLIGENCE (AI) are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

Conditions

The condition(s) this trial relates to.

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.

Contacts and locations

Locations

  • Centre Hospitalier de l'Université de Montréal

    RECRUITING

    Montreal, Quebec, Canada

More trials for these conditions

Other studies related to the condition(s) this trial covers.