Prospective, Randomized Controlled Study to Evaluate the Effect of Artificial Intelligence Assisted Optical Diagnosis of Advanced Adenomas

This study is a clinical validation of our developed a computer-aided optical dignosis of advanced adenoma using non-magnified NBI image. This study is a randomized clinical trial comparing endoscopists' optical recognition of advanced adenoma for sending to histological examination with our computer-aided system. The hypothesis of the study is that the developed computer-aided system increases the percent of sending actual advanced adenoma Intelligence Assisted Optical Diagnosis of Advanced Adenomas

Study Overview

• Status: Completed
• Conditions: Advanced Adenoma
• Intervention / Treatment: Device: AI system of optical detection of advanced adenomas

Detailed Description

Colorectal polyp diagnosis is based on endoscopic resection and histological analysis. An accurate optical diagnosis could avoid histological lesion of smaller lesions, reducing the costs associated with histological diagnosis. However, it should be noted this policy could only be applied in diminutive polys considering high proposition of advanced adenomas in polyps more than 5 mm. In addition, optical diagnosis criteria of advanced adenomas have not been validated for finding advanced adenomas among adenoma polyps. If as many as advanced adenomas as possible could be differentiated from non-advanced adenomas and be further sent for histological examination, this policy could be generalized to small polyps.

Considering this situation, the investigators tried to develop computer-aided optical dignosis of advanced adenoma using non-magnified NBI image with preliminary, satisfied results. In this study, the investigators next validate the investigators' developed computer-aided system for detecting advanced adenomas by comparing endoscopists' optical detection of advanced adenomas with or without the investigators' computer-aided system.

• Study Type: Interventional
• Enrollment (Actual): 120
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Shanghai, China, 200001
    • Departments of Gastroenterology and Clinical Laboratory, Shanghai Renji Hospital, Shanghai Jiaotong University School of Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 65 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Endoscopists with NBI experience

Exclusion Criteria:

• Endoscopists without colonoscopy and NBI experience

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 group; AI assisted endoscopist' optical detection of advanced adenomas among 100 images of polyps	Device: AI system of optical detection of advanced adenomas; AI system of optical detection of advanced adenomas
NO_INTERVENTION: non-AI assisted group; Endoscopist' optical detection of advanced adenomas among 100 images of polyps using their experience of colonoscopy

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of advanced adenomas for sending to histological examination	Proportion of advanced adenomas for sending to histological examination	1 day

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Optical diagnostic accuracy of non-advanced adenomas under high confidence	Optical diagnostic accuracy of non-advanced adenomas under high confidence	1 day
Proportion of high confidence optical diagnosis of polyps	Proportion of high confidence optical diagnosis of polyps	1 day

Collaborators and Investigators

• Sponsor: Shanghai Jiao Tong University School of Medicine

Study record dates

Study Major Dates

• Study Start (ACTUAL): October 6, 2022
• Primary Completion (ACTUAL): October 9, 2022
• Study Completion (ACTUAL): October 14, 2022

Study Registration Dates

• First Submitted: October 3, 2022
• First Submitted That Met QC Criteria: October 4, 2022
• First Posted (ACTUAL): October 6, 2022

Study Record Updates

• Last Update Posted (ACTUAL): October 18, 2022
• Last Update Submitted That Met QC Criteria: October 14, 2022
• Last Verified: October 1, 2022

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Adenoma
• Other Study ID Numbers: Renji KY[2019]009

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