Efficacy of an AI System in Training Endoscopists to Assess Gastric Intestinal Metaplasia Via the EGGIM Score

Shandong University

Status: Not yet enrolling

Conditions: Gastric Intestinal Metaplasia

Treatments: Diagnostic Test: AI-assisted EGGIM scoring; Diagnostic Test: Conventional EGGIM scoring

Study type: Interventional

Funder types: Other

Identifiers

NCT07208864

2025SDU-QILU-4

Details and patient eligibility

About

This prospective randomized controlled trial with a crossover design incorporated image-enhanced endoscopy (IEE) videos demonstrating complete standardized examinations of five standard gastric areas (antrum greater curvature, antrum lesser curvature, incisura, corpus lesser curvature, and corpus greater curvature). Endoscopists were stratified by experience level and randomly assigned to either the AI-assisted scoring first group, which performed EGGIM scoring with AI assistance in the initial phase followed by conventional scoring after a washout period, or the conventional scoring first group, which completed the assessments in reverse order. The study primarily evaluated the training efficacy of the EGGIM-AI system for improving endoscopists' EGGIM scoring performance by comparing diagnostic accuracy metrics including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity between groups at different study phases, with histopathological results serving as the gold standard.

Enrollment: 8 estimated patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

Endoscopists who have performed ≥50 image-enhanced endoscopy (IEE) procedures per year and demonstrated competency in performing standardized IEE.

Exclusion criteria

Endoscopists who participated in data acquisition or were unblinded to patients' identifiable information and clinical data.

Trial design

Primary purpose: Diagnostic

Allocation: Randomized

Interventional model: Crossover Assignment

Masking: Single Blind

---

8 participants in 2 patient groups

AI-assisted scoring first group

Experimental group

Description:

Endoscopists will first evaluate the videos with the assistance of the AI system via EGGIM score, and after the washout period, the videos will be evaluated again without the assistance of the AI system.

Treatment:

Diagnostic Test: AI-assisted EGGIM scoring

Conventional scoring first group

Active Comparator group

Description:

Endoscopists will first evaluate the videos without the assistance of the AI system via EGGIM score, and after the washout period, the videos will be evaluated again with the assistance of the AI system.

Treatment:

Diagnostic Test: Conventional EGGIM scoring