# Development and Validation of the Early Gastric Carcinoma Prediction Model in Post-Eradication Patients with Intestinal Metaplasia

## TL;DR

This study developed a machine learning model to predict early stomach cancer risk in patients who have been treated for a common stomach bacterium but still have abnormal stomach lining changes.

## Contribution

The study introduces a validated machine learning model and web-based tool for predicting early gastric cancer in post-eradication patients with intestinal metaplasia.

## Key findings

- The CatBoost algorithm achieved high accuracy in predicting early gastric cancer with an AUC of 0.905 in external validation.
- The model outperformed traditional inflammatory biomarkers like NLR and PLR in risk discrimination.
- A web-based calculator was developed to help doctors assess patient risk and improve early detection.

## Abstract

Gastric cancer is one of the leading causes of cancer deaths worldwide. Although a common stomach bacterium can be treated with medicine, some patients still develop cancer even after treatment. This is especially true for people whose stomach lining has already changed in harmful ways. In this study, we used computer models to analyze medical records and endoscopy images from two hospitals to find patterns that might predict who is more likely to develop early stomach cancer. We created a simple online tool that doctors can use to calculate a patient’s risk. This can help identify high-risk patients earlier and make sure they receive the right follow-up care. Our goal is to improve early detection and save lives through better screening.

Background: Gastric cancer (GC) remains a major global health challenge, with rising incidence among patients post-Helicobacter pylori (H. pylori) eradication, particularly those with persistent intestinal metaplasia (IM). Current risk stratification tools are limited in this high-risk population. Aim: To develop, validate, and externally test a machine learning-based prediction model—termed the Early Gastric Cancer Model (EGCM)—for identifying early gastric cancer (EGC) risk in H. pylori-eradicated patients with IM, and to implement it as a web-based clinical tool. Methods: This retrospective, dual-center study enrolled 214 H. pylori-eradicated patients with histologically confirmed IM from 900 Hospital and Fujian Provincial People’s Hospital. The dataset was split into a training cohort (70%) and an internal validation cohort (30%), with an external test cohort from the second center. A total of 21 machine learning algorithms were screened using cross-validation and hyperparameter optimization. Boruta and SHAP analyses were employed for feature selection, and the final EGCM was constructed using the top five predictors: atrophy range, xanthoma, map-like redness (MLR), MLR range, and age. Model performance was evaluated via ROC curves, precision–recall curves, calibration plots, and decision curve analysis (DCA), and compared against conventional inflammatory biomarkers such as NLR and PLR. Results: The CatBoost algorithm demonstrated the best overall performance, achieving an AUC of 0.743 (95% CI: 0.70–0.80) in internal validation and 0.905 in the external test set. The EGCM exhibited superior discrimination compared to individual inflammatory markers (p < 0.01). Calibration analysis confirmed strong agreement between predicted and observed outcomes. DCA showed the EGCM yielded greater net clinical benefit. A web calculator was developed to facilitate clinical application. Conclusions: The EGCM is a validated, interpretable, and practical tool for stratifying EGC risk in H. pylori-eradicated IM patients across multiple centers. Its integration into clinical practice could improve surveillance precision and early cancer detection.