Impact of Automatic Polyp Detection System on Adenoma Detection Rate

Impact of Automatic Polyp Detection System on Adenoma Detection Rate-a Multicenter,Prospective, Randomized Controlled Trial

In recent years, with the continuous development of artificial intelligence, automatic polyp detection systems have shown its potential in increasing the colorectal lesions. Yet, whether this system can increase polyp and adenoma detection rates in the real clinical setting is still need to be proved. The primary objective of this study is to examine whether a combination of colonoscopy and a deep learning-based automatic polyp detection system is a feasible way to increase adenoma detection rate compared to standard colonoscopy.

Study Overview

• Status: Recruiting
• Conditions: Colonic Polyps; Colorectal Adenomas
• Intervention / Treatment: Device: Automatic polyp detection system

• Study Type: Interventional
• Enrollment (Anticipated): 1118
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Zhaoshen Li, M.D; Phone Number: 86-21-31161365; Email: li.zhaoshen@hotmail.com
• Study Contact Backup: Name: Yu Bai, M.D; Phone Number: 86-21-31161335; Email: baiyu1998@hotmail.com

Study Locations

• China
  • Shanghai, China, 200433
    • Recruiting
    • Changhai Hospital, Second Military Medical University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 40 years to 85 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Patients aged between 40-85 years old who have indications for screening, surveillance and diagnostic.
• Patients who have signed inform consent form.

Exclusion Criteria:

• Patients who have undergone colonic resection
• Patients with intracranial and/or central nervous system disease, including cerebral infarction and cerebral hemorrhage.
• Patients with severe chronic cardiopulmonary and renal disease.
• Patients who are unwilling or unable to consent.
• Patients who are not suitable for colonoscopy
• Patients who received urgent or therapeutic colonoscopy
• Patients with pregnancy, inflammatory bowel disease, polyposis of colon, colorectal cancer, or intestinal obstruction
• Patients who are taking aspirin, clopidogrel or other anticoagulants
• Patients with withdrawal time < 6 min

Study Plan

How is the study designed?

Design Details

• Primary Purpose: DIAGNOSTIC
• Allocation: RANDOMIZED
• Interventional Model: PARALLEL
• Masking: NONE

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
EXPERIMENTAL: AI-assisted withdrawal group; A deep learning-based automatic polyp detection system was used to assist the endoscopist.	Device: Automatic polyp detection system; When colonoscopists withdraw the colonoscopies and inspect the colons, the video streaming of colonoscopies was real-time switched to the automatic polyp detection system, which made it feasible to detect lesions in real time. When any potential polyp is detected by the system， there will be a tracing box on an adjacent monitor to locate the lesion with a simultaneous sound alarm.
NO_INTERVENTION: Routine withdrawal group; Routine withdrawal without any assist.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
adenoma detection rate(ADR)	the number of patients with at least one adenoma divided by the total number of patients.	30 minutes

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
polyp detection rate(PDR)	the number of patients with at least one polyp divided by the total number of patients.	30 minutes
adenoma per colonoscopy	the number of adenomas detected during colonoscopy withdraw divided by the number of colonoscopies.	30 minutes
polyp per colonoscopy	the number of polyps detected during colonoscopy withdraw divided by the number of colonoscopies.	30 minutes

Collaborators and Investigators

• Sponsor: Changhai Hospital
• Collaborators: Wuhan Union Hospital, China; Wenzhou Central Hospital; The First Affiliated Hospital of Dalian Medical University

Publications and helpful links

General Publications

• Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F, Karnes W, Baldi P. Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. Gastroenterology. 2018 Oct;155(4):1069-1078.e8. doi: 10.1053/j.gastro.2018.06.037. Epub 2018 Jun 18.
• Ahmad OF, Soares AS, Mazomenos E, Brandao P, Vega R, Seward E, Stoyanov D, Chand M, Lovat LB. Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. Lancet Gastroenterol Hepatol. 2019 Jan;4(1):71-80. doi: 10.1016/S2468-1253(18)30282-6. Epub 2018 Dec 6.

Study record dates

Study Major Dates

• Study Start (ACTUAL): June 1, 2019
• Primary Completion (ANTICIPATED): July 20, 2021
• Study Completion (ANTICIPATED): October 1, 2021

Study Registration Dates

• First Submitted: May 28, 2019
• First Submitted That Met QC Criteria: May 28, 2019
• First Posted (ACTUAL): May 30, 2019

Study Record Updates

• Last Update Posted (ACTUAL): April 6, 2021
• Last Update Submitted That Met QC Criteria: April 3, 2021
• Last Verified: April 1, 2021

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Pathological Conditions, Anatomical; Intestinal Polyps; Adenoma; Polyps; Colonic Polyps
• Other Study ID Numbers: AI-2

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No