Combination of artificial intelligence endoscopic diagnosis and Kimura-Takemoto classification determined by endoscopic experts may effectively evaluate the stratification of gastric atrophy in post-eradication status

Abstract

Background: Since it is difficult for expert endoscopists to diagnose early gastric cancer in post-eradication status, it may be critical to evaluate the stratification of high-risk groups using the advance of gastric atrophy or intestinal metaplasia. We tried to determine whether the combination of endoscopic artificial intelligence (AI) diagnosis for the evaluation of gastric atrophy could be a useful tool in both pre- and post-eradication status.

Methods: 270 Helicobacter pylori-positive outpatients (Study I) were enrolled and Study II was planned to compare patients (n = 72) with pre-eradication therapy with post-eradication therapy. Assessment of endoscopic appearance was evaluated by the Kyoto classification and Kimura-Takemoto classification. The trained neural network generated a continuous number between 0 and 1 for gastric atrophy.

Results: There were significant associations between the severity of gastric atrophy determined by AI endoscopic diagnosis and not having a regular arrangement of collecting venules in angle, visibility of vascular pattern, and mucus using Kyoto classification in H. pylori-positive gastritis. There were significant differences (p = 0.037 and p = 0.014) in the severity of gastric atrophy between the high-risk group and low-risk group based on the combination of Kimura-Takemoto classification and endoscopic AI diagnosis in pre- and post-eradication status. The area under the curve values of the severity of gastric atrophy (0.674) determined by the combination of Kimura-Takemoto classification and gastric atrophy determined by AI diagnosis was higher than that determined by Kimura-Takemoto classification alone in post-eradication status.

Conclusion: A combination of gastric atrophy determined by AI endoscopic diagnosis and Kimura-Takemoto classification may be a useful tool for the prediction of high-risk groups in post-eradication status.

Keywords: Helicobacter pylori; Kyoto Classification; artificial intelligence; atrophic gastritis; gastric cancer.

FIGURE 1

Study design.

FIGURE 2

(a) Comparison of area under the curve (AUC) values in pre‐eradication status in Study II. Receiver operating characteristic (ROC) curves. The AUC values were 0.703 for Kimura‐Takemoto Classification ——, 0.647 for combination of Kimura‐Takemoto Classification and Artificial Intelligence (AI) score ——, Reference line ——. ROC curves were created by plotting sensitivity, as a proportion, versus (1‐specificity), as a proportion, using SPSS. The sensitivity/specificity of AUC data was following as the Kimura‐Takemoto classification alone in pre‐eradication status (0.938/0.482) and the combination of Kimura‐Takemoto classification and gastric atrophy determined by AI endoscopic diagnosis (0.688/0.607) in pre‐eradication status. (b) Comparison of area under the curve (AUC) values in post‐eradication status in Study II. Receiver operating characteristic (ROC) curves. The AUC values were 0.661 for Kimura‐Takemoto Classification ——, 0.674 for combination of Kimura‐Takemoto Classification and Artificial Intelligence (AI) score ——, Reference line ——. ROC curves were created by plotting sensitivity, as a proportion, versus (1‐specificity), as a proportion, using SPSS. The sensitivity/specificity of AUC data was following as the Kimura‐Takemoto classification alone in post‐eradication status (0.813/0.500), and the combination of Kimura‐Takemoto classification and gastric atrophy determined by AI endoscopic diagnosis in post‐eradication status (0.813/0.536).