A Predictive Model of Noncardia Gastric Adenocarcinoma Risk Using Antibody Response to Helicobacter pylori Proteins and Pepsinogen

Abstract

Background: Blood-based biomarkers for gastric cancer risk stratification could facilitate targeting screening to people who will benefit from it most. The ABC Method, which stratifies individuals by their Helicobacter pylori infection and serum-diagnosed chronic atrophic gastritis status, is currently used in Japan for this purpose. Most gastric cancers are caused by chronic H. pylori infection, but few studies have explored the capability of antibody response to H. pylori proteins to predict gastric cancer risk in addition to established predictors.

Methods: We used the least absolute shrinkage and selection operator (Lasso) to build a predictive model of noncardia gastric adenocarcinoma risk from serum data on pepsinogen and antibody response to 13 H. pylori antigens as well as demographic and lifestyle factors from a large international study in East Asia.

Results: Our best model had a significantly (P < 0.001) higher AUC of 73.79% [95% confidence interval (CI), 70.86%-76.73%] than the ABC Method (68.75%; 95% CI, 65.91%-71.58%). At 75% specificity, the new model had greater sensitivity than the ABC Method (58.67% vs. 52.68%) as well as NPV (68.24% vs. 66.29%).

Conclusions: Along with serologically defined chronic atrophic gastritis, antibody response to the H. pylori proteins HP 0305, HP 1564, and UreA can improve the prediction of gastric cancer risk.

Impact: The new risk stratification model could help target more invasive gastric screening resources to individuals at high risk.

Figure 1:

Receiver-operating characteristic curve for classification of gastric cancer in a subset of the Helicobacter pylori Biomarker Cohort Consortium (n=1422). This figure compares the gastric cancer discrimination performance of the Lasso model (solid) to that of the ABC Method (dashed) within the training data set. Dots represent the threshold of gastric cancer risk score > 1 at which sensitivity and specificity were calculated for both models.

Figure 2:

Sensitivity analysis. Receiver-operating characteristic curve for classification of gastric cancer in a subset of the Helicobacter pylori Biomarker Cohort Consortium (n=1422). This figure compares the gastric cancer discrimination performance of the Lasso model including pepsinogen I (solid) to that of the ABC Method (dashed) and the Lasso model without pepsinogen I (dot-dashed) within the training data set. Points represent the threshold of gastric cancer risk score > 1 at which sensitivity and specificity were calculated for both models