Effect of the Computer Aided Diagnosis with Explainable Artificial Intelligence for Colon Polyp on Optical Diagnosis and Acceptance of Technology

NCT06617468 — Not applicable, Unknown, 120 participants, Seoul National University Hospital

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

Registry	NCT06617468
Status	Unknown
Phase	Not applicable
Study type	Interventional; randomized, parallel, masking: none, diagnostic
Enrollment	120 (Estimated)
Sponsor	Seoul National University Hospital (Other)
Conditions	Colon Polyp
Interventions	computer-aided diagnosis with explainable AI, computer-aided diagnosis with deep learning (Diagnostic test)
Dates	start 2024-09-20, primary completion 2024-12-31 (estimated), completion 2024-12-31 (estimated), first posted 2024-09-27, last updated 2024-10-04
Locations	1 site in South Korea

-Summary

The goal of this clinical trial is to learn if computer-aided diagnosis with deep learning and computer-aided diagnosis with explainable AI work to optical diagnosis performance and acceptance of technology in endoscopists. The main questions it aims to answer are:

Do computer-aided diagnosis with deep learning and computer-aided diagnosis with explainable AI improve optical diagnosis performance in endoscopists?

Does experience using deep learning-based computer-assisted diagnosis and explainable AI-based computer-assisted diagnosis improve endoscopists' acceptance of computer-aided diagnosis as a technology?

Participants will:

Conduct a survey on acceptance and use of technology about computer-aided diagnosis.

Perform a test to estimate the pathologic diagnosis on 200 NBI still images without the aid of computer-aided diagnosis.

More than 1 month later, perform a same test to estimate the pathologic diagnosis on 200 NBI still images with computer-aided diagnosis with deep learning or explainable AI.

Conduct a survey on acceptance and use of technology about computer-aided diagnosis.

Expand all sections · Collapse all

+Arms and interventions

Arm	Type	Interventions	Description
computer-aided diagnosis with explainable AI	Experimental	Diagnostic Test: computer-aided diagnosis with explainable AI	Perform a same test to estimate the pathologic diagnosis on 200 NBI still images with computer-aided diagnosis with explainable AI
computer-aided diagnosis with deep learning	Active comparator	Diagnostic Test: computer-aided diagnosis with deep learning	Perform a same test to estimate the pathologic diagnosis on 200 NBI still images with computer-aided diagnosis with deep learning

computer-aided diagnosis with explainable AI (Diagnostic test): Perform a same test to estimate the pathologic diagnosis on 200 NBI still images with computer-aided diagnosis with explainable AI.
computer-aided diagnosis with deep learning (Diagnostic test): Perform a same test to estimate the pathologic diagnosis on 200 NBI still images with computer-aided diagnosis with deep Iearning.

+Outcome measures

Primary outcomes

Accuracy of optical diagnosis [From baseline test to the follow up test (more than 1 month later from baseline test)]: The proportion of cases in which pathological results are consistent with endoscopic estimation of adenoma and hyperplastic polyp

Secondary outcomes

acceptance of computer-aided diagnosis as a technology [From baseline test to the follow up test (more than 1 month later from baseline test)]: Survey on acceptance and use of technology about computer-aided diagnosis.

+Eligibility

Sex: All

Inclusion Criteria:

* Endoscopists with colonoscopy experience

Exclusion Criteria:

* Who can not perform colonoscopy

+Locations (1)

Facility	City	Country	Status
Healthcare System Gangnam Center, Seoul National University Hospital	Seoul	South Korea