Predicting Gastric Intestinal Metaplasia in a

Introduction: Gastric intestinal metaplasia (GIM) is a precancerous lesion. It has a low prevalence rate in the United States. However, GIM is more common among non-White and immigrant populations. Harlem Hospital serves a community that includes predominantly African Americans, Hispanics, and immigrants from West Africa and Spanish-speaking Caribbean countries. This study aims to define the factors predicting GIM in this high-risk group as well as help define screening strategies for vulnerable populations. Methods: A total of 1351 patients who underwent endoscopic gastroduodenoscopy (EGD) and biopsy in 2018 and 2019 for any indication at Harlem Hospital were included in this study. Gastric biopsy specimens taken during the procedure were assessed for GIM by histopathology. Baseline demographics were collected, including age, sex, and ethnicity. Other information collected included risk factors for GIM such as Helicobacter pylori infection, smoking status, and the use of alcohol. Descriptive analysis was done and the Wilcoxon rank sum test and chi-squared test were used to test for associations. Multiple logistic regressions were used to assess the odds of independent factors associated with increased risk of GIM. Results: Of the 1351 patients reviewed, 106 had GIM for a prevalence of 8.0% (CI: 6.7%-9.6%, p < 0.001). Univariate analysis revealed older patients, males, history of smoking, alcohol, and H. pylori infection were significantly associated with GIM. Using multiple logistic regressions and adjusting for underlying risk factors, smoking (OR: 1.61, 95% CI: 1.00-2.570) and H. pylori infection (OR: 3.35, 95% CI: 2.18-5.15) continued to be significantly associated with increased risk of GIM; however, alcohol use was not significant after adjusting for other risk factors (OR: 1.10, 95% CI: 0.68-1.78). Hispanic risk for GIM was slightly higher than African Americans (OR: 1.17, 95% CI: 0.74-1.83). The predicted marginal effect of age on the odds of GIM was significant from age 40 and increased exponentially at age 50. By age 70, the odds of GIM were as high as 11% (95% CI: 8.3-13.6). Conclusion: The prevalence of GIM in our population is significantly higher compared to reported cases in the United States. Age, male gender, H. pylori infection, and smoking significantly increase the risk of GIM. Given the high prevalence of GIM in our population, early endoscopic screening would play an important role in evaluating dyspepsia to diagnose GIM with or without H. pylori infection. We propose screening all at -risk ethnicities from age 40 years with EGD according to the Sydney System biopsy protocol. We believe this will ultimately decrease the incidence of gastric cancer death in these vulnerable populations of color.