Single-center, Randomized, Superiority Pivotal Clinical Study to Evaluate the Efficacy of Artificial Intelligence-based Upper Gastrointestinal Endoscopy Image

NCT06969794 | Completed

• 1 other identifier: AI RCT2
• Study Type: observational
• Target: 3,385
• Locations: 1 country
• Sites: 1

Brief Summary

We will conduct a single-center retrospective study at a university hospital. A total of 3,385 gastroscopic white-light images from patients with pathologically confirmed findings will be analyzed. The AI software will automatically identify images as non-neoplastic or neoplastic (low-grade dysplasia, high-grade dysplasia, early gastric cancer with mucosal or submucosal invasion, or advanced gastric cancer) and highlighted lesion locations. Two experienced endoscopists will independently review the same image set without AI assistance for comparison. Primary outcomes are sensitivity and specificity of the AI in detecting gastric neoplasms (by category and overall), and the localization accuracy measured by the localization receiver operating characteristic (LROC) curve area. Secondary outcomes is includes comparison of the AI's diagnostic performance with that of endoscopists.

Conditions

Gastric Neoplasm; Gastric Lesion; Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• AI performance

  sensitivity and specificity of the AI in detecting gastric neoplasms (by category and overall), and the localization accuracy measured by the localization receiver operating characteristic (LROC) curve area.

  Day 1

Secondary Outcomes (1)

• comparison of the AI's diagnostic performance with that of endoscopists.

  Day 1

Eligibility Criteria

• Age: 20 Years - 100 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

A total of 3,385 endoscopic images were collected from patients who underwent gastroscopy at our institution (Chuncheon Sacred Heart Hospital from 2010 to 2017) and had adequate reference standards. Images were selected to include both neoplastic lesions and non-neoplastic findings. Inclusion criteria were images of gastric lesions that had definitive histopathology diagnoses (from endoscopic biopsy or resection) of one of five severity categories: LGD, HGD, EGC-M (mucosal early gastric carcinoma), EGC-SM (submucosal invasive early carcinoma), or AGC (advanced gastric cancer). Additionally, a set of non-neoplastic images (normal or benign findings with negative biopsies) was included as controls.

You may qualify if:

• Age 19 or older
• At least one gastric lesion biopsied with a definitive pathological diagnosis
• Availability of high-quality white-light endoscopy images of the lesion and surrounding mucosa

You may not qualify if:

• Poor-quality images (e.g., out of focus or obscured)
• Lack of histopathological confirmation of the lesion

Sponsors & Collaborators

• Chuncheon Sacred Heart Hospital: lead

Study Sites (1)

Chuncheon Sacred Heart hospital

Chuncheon, Gangwon-do, 24253, South Korea

Location

MeSH Terms

Conditions

Stomach Neoplasms

Condition Hierarchy (Ancestors)

Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Stomach Diseases

Study Officials

• Chang Seok Bang, MD, PhD

  HALLYM UNIVERSITY COLLEGE OF MEDICINE, Korea

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: PI

Study Record Dates

• First Submitted: April 25, 2025
• First Posted: May 14, 2025
• Study Start: July 1, 2023
• Primary Completion: August 1, 2023
• Study Completion: August 17, 2023
• Last Updated: May 14, 2025

Record last verified: 2025-05

Locations

KR (1)