Impact of AI on Trainee ADR

University of Southern California

Status: Enrolling

Conditions: Adenoma; Adenoma Colon; Colorectal Cancer

Treatments: Other: Non-AI use Standard of Care endoscopy room; Diagnostic Test: AI use in Endoscopy Room

Study type: Interventional

Funder types: Other

Identifiers

NCT05423964

HS-21-00094

Details and patient eligibility

About

Adenoma detection rate (ADR) is a validated quality metric for colonoscopy with higher ADR correlated with improved colorectal cancer outcomes. Artificial intelligence (AI) can automatically detect polyps on the video monitor which may allow endoscopists in training to improve their ADR. Objective and Purpose of the study: Measure the effect of AI in a prospective, randomized manner to determine its impact on ADR of Gastroenterology trainees.

Full description

Our objective is to determine the impact of AI on the adenoma detection rate of Gastroenterology trainees. The secondary aim of this quality improvement study is to determine the impact of AI based endoscopy on the rate of recording of quality improvement metrics versus historical performance in our program.

Fellows will undergo educational session prior to the start of study, describing commonly used metrics for assessing quality of colonoscopy and how to use the artificial intelligence software. Gastroenterology fellows will be consented for the study prior to initiation. The fellows will be randomized on a daily basis to perform colonoscopies in a room. Outcomes will measure the effects of AI in fellows

Enrollment: 25 estimated patients

Sex: All

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• All Gastroenterology fellows at USC performing Endoscopies will be included in the study.

Exclusion criteria

• If fellows refuse informed consent they will be excluded.
• Procedures performed in the intensive care unit or the operating room will not be counted toward the study metrics as the AI system will only be available in the endoscopy unit.
• If procedures are performed only by faculty, in which the fellow is not the primary operator, they will not be used for study metrics.

Trial design

Primary purpose: Diagnostic

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: None (Open label)

---

25 participants in 2 patient groups

Artificial Intelligence Endoscopy Room

Active Comparator group

Description:

The fellows will be randomized on a daily basis to perform colonoscopies in a room with AI (intervention)

Treatment:

Diagnostic Test: AI use in Endoscopy Room

Non-Artificial Intelligence Endoscopy Room

Active Comparator group

Description:

The fellows will be randomized on a daily basis to perform colonoscopies in a non-AI endoscopy room (standard of care).

Treatment:

Other: Non-AI use Standard of Care endoscopy room