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

Not Applicable

Completed

• Conditions: Advanced Adenoma
• Interventions: Device: AI system of optical detection of advanced adenomas

• Registration Number: NCT05568992
• Lead Sponsor: Shanghai Jiao Tong University School of Medicine

Brief Summary

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

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 Timeline

• Status Verified: 2022-10
• Study First Submitted: 2022-10-03
• Study First Submitted QC: 2022-10-04
• Study Start: 2022-10-06
• Study First Posted: 2022-10-06
• Primary Completion: 2022-10-09
• Study Completion: 2022-10-14
• Last Update Submitted: 2022-10-14
• Last Update Posted: 2022-10-18

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 120

Inclusion Criteria

• Endoscopists with NBI experience

Exclusion Criteria

• Endoscopists without colonoscopy and NBI experience

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Arm && Interventions

Group	Intervention	Description
AI assisted group	AI system of optical detection of advanced adenomas	AI assisted endoscopist' optical detection of advanced adenomas among 100 images of polyps

Primary Outcome Measures

Name	Time	Method
Proportion of advanced adenomas for sending to histological examination	1 day	Proportion of advanced adenomas for sending to histological examination

Secondary Outcome Measures

Name	Time	Method
Proportion of high confidence optical diagnosis of polyps	1 day	Proportion of high confidence optical diagnosis of polyps
Optical diagnostic accuracy of non-advanced adenomas under high confidence	1 day	Optical diagnostic accuracy of non-advanced adenomas under high confidence

Trial Locations

Locations (1)

Departments of Gastroenterology and Clinical Laboratory, Shanghai Renji Hospital, Shanghai Jiaotong University School of Medicine; 🇨🇳 Shanghai, China