Lin Wulian, Zhang Guanpo, Chen Hong, Huang Weidong, Xu Guilin, Zheng Yunmeng, Gao Chao, Zheng Jin, Li Dazhou, Wang Wen
Fuzong Clinical Medical College of Fujian Medical University, Fuzhou 350005, China.
Department of Gastroenterology, 900th Hospital of PLA Joint Logistic Support Force, Fuzhou 350025, China.
Cancers (Basel). 2025 Jun 26;17(13):2158. doi: 10.3390/cancers17132158.
: Gastric cancer (GC) remains a major global health challenge, with rising incidence among patients post- () eradication, particularly those with persistent intestinal metaplasia (IM). Current risk stratification tools are limited in this high-risk population. : 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. : 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. : 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 ( < 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. : 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.
胃癌（GC）仍然是一项重大的全球健康挑战，在幽门螺杆菌根除治疗后的患者中发病率呈上升趋势，尤其是那些存在持续性肠化生（IM）的患者。当前的风险分层工具在这一高风险人群中存在局限性。
为了开发、验证并对外测试一种基于机器学习的预测模型——早期胃癌模型（EGCM），用于识别幽门螺杆菌根除治疗后伴有IM的患者发生早期胃癌（EGC）的风险，并将其作为基于网络的临床工具来应用。
这项回顾性双中心研究纳入了来自900医院和福建省立医院的214例经组织学证实为IM且幽门螺杆菌已根除的患者。数据集被分为一个训练队列（70%）和一个内部验证队列（30%），另有来自第二个中心的外部测试队列。使用交叉验证和超参数优化筛选了总共21种机器学习算法。采用Boruta和SHAP分析进行特征选择，并使用前五个预测因子构建最终的EGCM：萎缩范围、黄色瘤、地图样发红（MLR）、MLR范围和年龄。通过ROC曲线、精确召回率曲线、校准图和决策曲线分析（DCA）评估模型性能，并与诸如中性粒细胞与淋巴细胞比值（NLR）和血小板与淋巴细胞比值（PLR）等传统炎症生物标志物进行比较。
CatBoost算法表现出最佳的总体性能，在内部验证中AUC为0.743（95%CI：0.70 - 0.80），在外部测试集中为0.905。与单个炎症标志物相比，EGCM表现出更好的区分能力（P < 0.01）。校准分析证实预测结果与观察结果之间具有高度一致性。DCA显示EGCM产生了更大的净临床效益。开发了一个网络计算器以方便临床应用。
EGCM是一种经过验证、可解释且实用的工具，用于对多个中心的幽门螺杆菌根除治疗后的IM患者进行EGC风险分层。将其整合到临床实践中可以提高监测精度和早期癌症检测能力。
