Development and Validation of an Artificial Intelligence System for Bowel Preparation Quality Scoring

The purpose of this study is to develop and validate the accuracy and reliability of an artificial intelligence(AI) system for bowel preparation quality scoring based of Boston Bowel preparation Scoring(BBPS). Then evaluate whether this AI system can help endoscopists to improve the quality of colonoscopy in clinical practice.

Study Overview

• Status: Completed
• Conditions: Colonic Disease
• Intervention / Treatment: Device: AI

Detailed Description

Bowel preparation is one of the most important factors which decide the quality of colonoscopy. Adequate bowel preparation is essential to guarantee a clear vision of colonic mucosa, complete inspection of entire colon and improves the adenoma detection rates(ADRs). Therefore, the quality of bowel preparation should be evaluated accurately and objectively. However, current bowel preparation quality scales depend on memories and subjective decision of endoscopists. Recently, articifial intelligence system based on deep learning algorithm has been used widely in medical fields. But, few studies have been reported to evaluate the performance of AI system based on deep learning in bowel preparation quality scoring. This study aims to develop and train an AI system to assess bowel preparation quality using the BBPS, and validate the AI system to improve the quality of colonoscopy.

• Study Type: Interventional
• Enrollment (Actual): 100
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Korea, Republic of
  • Gyeonggi-do
    • Goyang-si, Gyeonggi-do, Korea, Republic of, 410-769
      • National Cancer Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 20 years to 80 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Patients aged 20-80 years undergoing elective colonoscopy

Exclusion Criteria:

• Patients received colon or rectal surgery

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Artificial Intelligence assisted Scoring Group; Patients in this group go through colonoscopy under the AI monitoring device.	Device: AI; After taking standard bowel preparation regimen, patients receive colonoscopy under the AI system device. During the withdrawal phase, bowel preparation quality is assessed by AI-associated scoring system. The withdrawal time is targeted at least 6min. Every detected polyp will be removed and obtained for pathological assessment.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
accuracy of bowel preparation score	Bowel preparation quality was measured by BBPS. After fully washing or suctioning of colonic contents, three segments including right colon (containing cecum and ascending colon), transvers colon (containing hepatic and splenic flexures) and left colon (containing descending and sigmoid colon) were individually scored from 0 to 3. Point 0 refers to unprepared colon segment with obscured solid stool making mucosa cannot be seen; Point 1 refers to part of mucosa can be seen, but some areas are covered by staining, residual stool, and/or opaque liquid; Point 2 refers to entire mucosa is well-seen; Point 3 refers to clean colon segment without staining, fecal materials or liquids. A sub-score of each colon segment was used, ranging from minimum 0 to maximum 3. The highest score means the excellent bowel preparation. Adequate bowel preparation was defined as a total BBPS≥6 and sub-BBPS≥2 per segment.	6 months

Collaborators and Investigators

• Sponsor: National Cancer Center, Korea

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2020
• Primary Completion (Actual): October 1, 2020
• Study Completion (Actual): December 30, 2020

Study Registration Dates

• First Submitted: July 22, 2020
• First Submitted That Met QC Criteria: July 22, 2020
• First Posted (Actual): July 27, 2020

Study Record Updates

• Last Update Posted (Actual): March 3, 2021
• Last Update Submitted That Met QC Criteria: March 1, 2021
• Last Verified: March 1, 2021

More Information

Terms related to this study

• Keywords: artificial intelligence, deep learning, bowel preparation
• Additional Relevant MeSH Terms: Digestive System Diseases; Gastrointestinal Diseases; Intestinal Diseases; Colonic Diseases
• Other Study ID Numbers: NCC2020-0159

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