Computer-aided Detection Device in Standard Colonoscopy

Colorectal Cancer Clinical Trial

Official title:

Randomized, Controlled Trial of Computer-Aided Detection Device in Standard Colonoscopy

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT04149184
• Other study ID #: STUDY00007252
• Status: Recruiting
• Phase: N/A
• Start date: October 1, 2019
• Est. completion date: December 31, 2020

Study information

• Verified date: October 2019
• Source: University of Minnesota
• Contact: Aasma Shaukat, MD, MPH
• Phone: 612-208-1570
• Email: shaukat[@]umn.edu
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The aim of this study is to evaluate the clinical benefit and safety of using an AI device in colonoscopy procedures with the indication of screening or surveillance.

Description:

Colorectal cancer is the second most common cause of cancer related mortality in the U.S., and affecting 150,000 people annually. Colonoscopy is the gold standard for the screening and detection of colorectal polyps and cancers. Screening for colorectal cancer has been shown to be effective in reducing both incidence and mortality. The capability of colonoscopy as an effective screening tool is based on the accurate detection and removal of precancerous polyps. However, it has been documented in several tandem colonoscopy studies that up to 28% of colorectal polyps are missed. Detection and identification of adenomatous polyps is provider dependent, as evidenced by the large variability in adenoma detection rates between providers.

Additionally, procedural factors, such as poor bowel preparation, and histomorphological qualities, such as those of serrated polyps, can impact a clinician's ability to detect and characterize polyps. Iterative Scopes has developed a computer aided detection (CADe) or AI model that can identify colorectal polyps in real-time during colonoscopy. The Iterative Scopes AI model analyzes video digital images taken during endoscopy and then directs the gastroenterologist's attention to areas of interest on the colon wall.

The purpose of this study is to evaluate the health benefits and safety in using the AI device during screening and surveillance colonoscopy. One of the reasons for the development of interval colorectal cancers is polyps missed during colonoscopy. Our hypothesis is that with the aid of AI device, the adenomas detected per colonoscopy will increase, and it is plausible to believe that this increase in detection could reduce the incidence of interval cancers.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 1000
• Est. completion date: December 31, 2020
• Est. primary completion date: December 31, 2020
• Accepts healthy volunteers: No
• Gender: All
• Age group: 40 Years and older

Eligibility

Inclusion Criteria:

• Participants undergoing colonoscopy with screening or surveillance indications

• Participants whose endoscopist is a participating provider

Exclusion Criteria:

• inflammatory bowel disease

• history of familial adenomatous polyposis

• poor bowel preparation (inadequate for procedure)

• use of anti-platelet agents or anticoagulants that preclude the removal of polyps during the procedure

• have high risk indicators including anemia, abnormal CT imaging, weight loss, family history, blood in stool or FIT positive test

Related Conditions & MeSH terms

• Colon Cancer
• Colonic Polyp
• Colonic Polyps
• Colorectal Cancer
• Colorectal Polyp
• Polyps

Intervention

Device:
• AI Colonoscopy Device
The Iterative Scopes Skout device is a software-based computer-aided detection (CADe) system for the analysis of high definition white light imaging (WLI) endoscopic images and video during colonoscopy procedures. Skout is intended to aid endoscopists with detection of potential colorectal polyps during colonoscopies by providing an informational visual aid on a display monitor (Note: display monitor is not packaged as part of the Skout system) through the use of trained software that processes the endoscopic video feed in real time. The device performs automated analysis on WLI endoscopic image/video data to identify potential polyps and produces a visual indicator (bounding box) on the appropriate sections of the video frames displayed on a monitor to assist colonoscopists with the detection of potential polyps during colonoscopy. The Skout system connects directly to the endoscopic video system in use by the endoscopist during colonoscopy procedures.

Locations

Country	Name	City	State
United States	University of Minnesota - Twin Cities	Minneapolis	Minnesota

Sponsors (1)

Lead Sponsor	Collaborator
University of Minnesota

Country where clinical trial is conducted

United States, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Adenomas Per Colonoscopy (APC),	The total number of adenomas detected during the colonoscopy divided by the number of total colonoscopies	1 day
Primary	Positive Predictive Value (PPV)	The percentage of adenomas detected divided by the total number of extractions (APE)	1 day