Zhang Xing-Qi, Huang Ze-Ning, Wu Ju, Liu Xiao-Dong, Xie Rong-Zhen, Wu Ying-Xin, Zheng Chang-Yue, Zheng Chao-Hui, Li Ping, Xie Jian-Wei, Wang Jia-Bin, He Qi-Chen, Qiu Wen-Wu, Tang Yi-Hui, Zhang Hao-Xiang, Zhou Yan-Bing, Lin Jian-Xian, Huang Chang-Ming
Department of Gastric Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, China.
Department of General Surgery, Fujian Medical University Union Hospital, Fuzhou, China.
Ann Surg Oncol. 2025 Apr;32(4):2637-2650. doi: 10.1245/s10434-024-16701-y. Epub 2024 Dec 30.
Patients with gastric cancer (GC) who experience early recurrence (ER) within 2 years postoperatively have poor prognoses. This study aimed to analyze and predict ER after curative surgery for patients with GC using machine learning (ML) methods.
This multicenter population-based cohort study included data from ten large tertiary regional medical centers in China. The clinical, pathological, and laboratory parameters were retrospectively collected from the records of 11,615 patients. The patients were randomly divided into training (70%) and test (30%) cohorts. A total of ten ML models were developed and validated to predict the ER. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), calibration plots, and Brier score (BS). SHapley Additive exPlanations (SHAP) was used to rank the input features and interpret predictions.
ER was reported in 1794 patients (15%) during follow-up. The stacking ensemble model achieved AUCs of 1.0 and 0.8 in the training and testing cohorts, respectively, with a BS of 0.113. SHAP dependency plots revealed that tumor staging, elevated tumor marker levels, lymphovascular invasion, perineural invasion, and tumor size > 5 cm were associated with higher ER risk. The impact of age and the number of lymph nodes harvested on ER risk exhibited a "U-shaped distribution." Additionally, an online prediction tool based on the best model was developed to facilitate clinical applications.
We developed a robust clinical model for predicting the risk of ER after surgery for GC, which may aid in individualized clinical decision-making.
胃癌（GC）患者术后2年内出现早期复发（ER），其预后较差。本研究旨在使用机器学习（ML）方法分析和预测GC患者根治性手术后的ER情况。
这项基于人群的多中心队列研究纳入了中国十个大型三级区域医疗中心的数据。从11615例患者的记录中回顾性收集临床、病理和实验室参数。患者被随机分为训练组（70%）和测试组（30%）。共开发并验证了十个ML模型以预测ER。使用受试者工作特征曲线下面积（AUC）、校准图和Brier评分（BS）评估模型性能。使用SHapley加性解释（SHAP）对输入特征进行排序并解释预测结果。
随访期间，1794例患者（15%）出现ER。堆叠集成模型在训练组和测试组中的AUC分别为1.0和0.8，BS为0.113。SHAP依赖图显示，肿瘤分期、肿瘤标志物水平升高、淋巴管侵犯、神经周围侵犯以及肿瘤大小>5 cm与较高的ER风险相关。年龄和清扫淋巴结数量对ER风险的影响呈“U形分布”。此外，还开发了一种基于最佳模型的在线预测工具，以促进临床应用。
我们开发了一种强大的临床模型，用于预测GC手术后的ER风险，这可能有助于个体化临床决策。
