Impact of Artificial Intelligence on Trainee Polyp Miss Rates

NCT06676930 | Recruiting FDA Device

• 1 other identifier: STU00221977
• Study Type: interventional
• Target: 180
• Locations: 1 country
• Sites: 1

Brief Summary

Based on prior studies, trainee and practicing gastroenterologists miss pre-cancerous polyps (adenomas and serrated polyps) during colonoscopy. The use of computer-aided detection (CADe) systems, a form of artificial intelligence (AI) has been shown to help identify colorectal lesions for practicing gastroenterologists. However, less is known how AI impacts polyp detection for trainees. The investigators are conducting a tandem colonoscopy study wherein a portion of the colon is examined first by the trainee and then the attending physician. For each procedure, randomization will occur which will determine whether or not the trainee will utilize AI for their examination of the colon. At the end of the study, the investigators will determine whether AI helps trainees miss fewer polyps during colonoscopy. The investigators will also conduct interviews with trainees to understand how AI impacts colonoscopy training.

Conditions

Colon Polyps; Colonoscopy; Artificial Intelligence (AI)

Keywords

tandem colonoscopy; randomized controlled trial; adenoma miss rate

Outcome Measures

Primary Outcomes (1)

• Neoplastic polyp miss rate

  Proportion of neoplastic (adenomas or serrated polyps) missed during trainee inspection

  1 week

Secondary Outcomes (2)

• Adenoma miss rate

  1 week

• Serrated polyp miss rate

  1 week

Study Arms (2)

Colonoscopy with AI

ACTIVE COMPARATOR

Trainee using AI during colonoscopy inspection

Device: Colonoscopy With Computer-Aided Detection

Colonoscopy without AI

ACTIVE COMPARATOR

Trainee not using AI during colonoscopy inspection

Procedure: Colonoscopy without Computer-Aided Detection

Interventions

Colonoscopy With Computer-Aided Detection DEVICE

Use of Computer-Aided Detection During Colonoscopy

Colonoscopy with AI

Colonoscopy without Computer-Aided Detection PROCEDURE

Colonoscopy without Computer-Aided Detection (AI)

Colonoscopy without AI

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adult patients referred for screening or surveillance colonoscopy

You may not qualify if:

• Patients referred for polypectomy or diagnostic colonoscopy
• Patients with prior right colon surgery
• Prolonged insertion time (\>20 minutes)
• Poor bowel preparation (Boston Bowel Preparation Score less than or equal to 6)

Sponsors & Collaborators

• Northwestern University: lead

Study Sites (1)

Northwestern Memorial Hospital

Chicago, Illinois, 60611, United States

RECRUITING

MeSH Terms

Conditions

Colonic Polyps

Interventions

Colonoscopy

Condition Hierarchy (Ancestors)

Intestinal Polyps; Polyps; Pathological Conditions, Anatomical; Pathological Conditions, Signs and Symptoms

Intervention Hierarchy (Ancestors)

Endoscopy, Gastrointestinal; Endoscopy, Digestive System; Diagnostic Techniques, Digestive System; Diagnostic Techniques and Procedures; Diagnosis; Endoscopy; Diagnostic Techniques, Surgical; Digestive System Surgical Procedures; Surgical Procedures, Operative; Minimally Invasive Surgical Procedures

Study Officials

• Rajesh Keswani, MD

  Northwestern Medicine

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Rajesh Keswani, MD

CONTACT

312-695-5620; raj-keswani@northwestern.edu

Zack Jacob

CONTACT

zack.jacob@northwestern.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: PREVENTION
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Study Record Dates

• First Submitted: October 30, 2024
• First Posted: November 6, 2024
• Study Start: September 10, 2024
• Primary Completion: December 1, 2025
• Study Completion (Estimated): September 1, 2026
• Last Updated: November 6, 2024

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)