胃癌肝转移患者预后特征及列线图的建立与验证

Construction and validation of a prognostic nomogram model for gastric cancer liver metastasis

目的基于SEER数据库分析胃癌肝转移(GCLM)患者预后的重要风险因素,建立其1、3、5年生存率的预测模型。方法从SEER数据库中获得591例2010—2015年间诊断为GCLM患者的临床病理学资料。按照7∶3的比例将人群随机分为建模队列和内部验证队列。使用单因素和多因素Cox回归分析GCLM预后的独立预测因子,并构建列线图。通过校准曲线、ROC曲线、C指数验证模型的准确性,并使用决策曲线分析模型的临床实用性。结果肿瘤组织学分化等级、手术、化疗这3个因素与GCLM患者预后显著相关,将这3个因素纳入构建预后模型并绘制列线图。建模队列集和校验集的列线图C指数分别为0.706[95%CI(0.677,0.735)]和0.749[95%CI(0.710,0.788)]。ROC曲线分析结果表示训练集和校验集的1、3、5年曲线下面积(AUC)均超过0.7。结论基于肿瘤组织学分化等级、手术、化疗这3个因素构建的GCLM患者预后的预测模型具有良好的预测准确性,有助于GCLM患者术后的临床决策和个体化治疗。

Objective To establish a prediction model for the 1-,3-,and 5-year survival rates in patients with gastric cancer liver metastases(GCLM)by analyzing prognostic factors based on the Surveillance,Epidemiology,and End Results(SEER)database.Methods Clinical and pathological data from 591 patients diagnosed with GCLM between2010 and 2015 were obtained from the SEER database.The population was randomly divided into a training cohort and an internal validation cohort at a 7 to 3 ratio.Independent predictors of GCLM were analyzed using univariate and multifactorial Cox regression.Consequently,nomograms were constructed.The model’s accuracy was verified by calibration curve,ROC curve,and the C-index,and the clinical utility of the model was analyzed through decision curve analysis.Results Tumor differentiation grade,surgical status,and chemotherapy were significantly associated with the prognosis of GCLM patients,and these three factors were included in constructing the prognostic model and plotting the nomogram.The C-index was 0.706(95%CI 0.677 to 0.735)and 0.749(95%CI 0.710 to 0.788)for the training set and the internal validation cohort,respectively.The results of the ROC curve analysis indicated that the area under the curve(AUC)was over 0.7 at 1,3,and 5 years for both the training and validation cohorts.Conclusion The prediction model of the GCLM is developed based on the 3 factors,i.e.,tumor differentiation grade,surgery,and chemotherapy,and shows good prediction accuracy and thus may promote clinical decision making and individualized treatment of GCLM patients.