Background: Autoimmune gastritis (AIG) can lead to hypergastrinemia and enterochromaffin ⁃ like cell hyperplasia, thereby increasing the risk of gastric neuroendocrine neoplasms and gastric adenocarcinoma. However, research on the association between AIG and gastric polyps is limited. Aims: To investigate the risk factors for the development of gastric polyps in AIG patients. Methods: The clinical data of 103 AIG patients visited the Chinese People’s Armed Police Force Sichuan Provincial Corps Hospital from June 2019 to June 2023 was collected retrospectively. The parameters analyzed included gender, age, anti⁃parietal cell antibody, anti⁃intrinsic factor antibody, pepsinogen (PG)I, PGII, ratio for PGI/ II, gastrin ⁃ 17 (G ⁃ 17), OLGA and OLGIM staging, size, location and pathological types of gastric polyps, vitamin B12, Helicobacter pylori infection and presence of anemia at the year AIG diagnosed. Univariate and multivariate Logistic regression analyses were performed to identify the risk factors for gastric polyps in AIG patients. The predictive performance of the variables was assessed by ROC curve analysis. Results: Among the 103 AIG patients enrolled in the study, 67 (65.05%) were females, and the median age was 58 years old. Fourteen (13.59%) patients had gastric polyps. Compared to patients without gastric polyps, those with gastric polyps had significantly higher levels of serum G ⁃ 17 (P< 0.000 1). Multivariate Logistic regression analysis indicated that G⁃ 17 was an independent risk factor for gastric polyps in AIG patients (OR=1.047, 95% CI: 1.017 ⁃ 1.078, P=0.002). The area under the curve (AUC) of G ⁃ 17 and the Logistic regression model in predicting the gastric polyp formation in AIG patients was 0.811 and 0.884, respectively. The optimal cutoff value of G⁃17 was 69.50 pmol/L, with the sensitivity and specificity of 92.9% and 67.4%, respectively. Conclusions: Serum G⁃17 is a potential prognostic factor for AIG. The optimal cutoff value for predicting the development of gastric polyp is 69.50 pmol/L.