Artificial Intelligence, Endoscopy, Intestinal Metaplasia of Gastric Mucosa
Conditions
Brief summary
The endoscopic grading system (EGGIM) has been widely used to assess the extent of gastric intestinal metaplasia during endoscopy. Investigators developed an artificial intelligence (AI) system to automatically evaluate the extent of gastric intestinal metaplasia (GIM) and calculate the EGGIM scores in endoscopy examination. This study is a prospective, multi-center study aimed at exploring the performance and reliability of AI-EGGIM scoring. This is a prospective study designed to validate the AI-EGGIM system in a larger cohort. The study protocol was developed based on preliminary experience from a prior investigation (NCT05464108).
Detailed description
Gastric intestinal metaplasia (GIM) is an important precancerous stage in the gastric carcinogenesis cascade. The endoscopic grading system (EGGIM) has been proposed as a practical method to evaluate the extent of GIM during endoscopy. Investigators developed an artificial intelligence (AI) system to automatically assess the extent of GIM and calculate EGGIM scores from endoscopic examinations. This study is a prospective, multi-center study aimed at evaluating the accuracy, performance, and reliability of AI-assisted EGGIM scoring.
Interventions
DIAGNOSTIC_TESTThe diagnostic performance of AI system and endoscopists
Eligible patients will undergo independent EGGIM score assessment by both endoscopists and the AI system.
Sponsors
Qilu Hospital of Shandong University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
40 Years to 75 Years
Inclusion criteria
* patients aged 40-75 years who undergo the IEE examination * patients who voluntarily sign the informed consent form
Exclusion criteria
* patients with severe cardiac, cerebral, pulmonary or renal dysfunction or psychiatric disorders who cannot participate in gastroscopy * patients with previous surgical procedures on the stomach
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Performance of AI system to diagnose the grade of intestinal metaplasia by calculating the EGGIM score | 1 year | The performance of the AI system will be evaluated in diagnosing the grade of gastric intestinal metaplasia (IM) based on the Endoscopic Grading of Gastric Intestinal Metaplasia (EGGIM) system. EGGIM is a validated scoring method ranging from 0 to 10, reflecting the extent of IM across five gastric regions: two in the antrum, two in the corpus, and one at the incisura. Each region is scored as 0 (no IM), 1 (focal IM, ≤30% of the area), or 2 (extensive IM, \>30% of the area), with a total possible score of 10. Higher EGGIM scores correspond to more severe IM and greater gastric cancer risk. The AI-derived scores will be compared with expert' EGGIM scores, which serve as the gold standard, to assess diagnostic accuracy. |
Countries
China
Outcome results
None listed