Author commentary on Eduarda Almeida et al.

Eduarda Almeida et al. Artificial intelligence for endoscopic grading of gastric intestinal metaplasia: advancing risk stratification for gastric cancer

In this study, an artificial intelligence (AI) approach for assessment of gastric intestinal metaplasia using the Endoscopic Grading of Gastric Intestinal Metaplasia (EGGIM) classification was developed and evaluated. Two datasets with 1280 narrow-band images were used. In 88%, an accurate indication for gastric surveillance (EGGIM ≥5) was achieved, with 85% specificity and no false-negative results. Positive and negative predictive values were 62% and 100%. AI tools for EGGIM assessment may contribute to improving the identification of patients at risk of gastric cancer.

Download Video

Publication History

Article published online:
28 October 2025