基于SEER数据库分析放疗对宫颈癌患者生存的影响

Analysis on effect of radiotherapy on the survival of cervical cancer based on SEER database

目的分析基于SEER数据库下放疗对宫颈癌患者生存的影响。方法采用SEER数据库搜索1973—2016年宫颈癌患者数据并筛选出有效数据10 920例,对其病历资料(10 748例接受放疗,172例未接受放疗)进行回顾性分析。构建多因素Cox回归模型,分析临床病理因素对宫颈癌患者预后的影响。绘制列线图评估多指标联合预测疾病进展的价值。采用一致性指数(C-index)、受试者工作特征(ROC)曲线及校准图评价模型的预测精度及判别能力。采用Kaplan-Meier曲线进行生存分析。结果多因素回归分析结果显示,放疗是宫颈癌患者预后的独立影响因素(P=0. 001)。Cox模型多因素分析结果显示,年龄、放疗、TNM分期均是影响宫颈癌患者总生存期的重要因素,其中≥60岁(P=0. 001)、T_4期(P=0. 019)、N_1期(P=0. 001)、N_X期(P=0. 001)、M_1期(P=0. 001)、未接受放疗(P=0. 001)的患者预后较差。列线图结果显示,年龄≥80岁、未接受放疗、肿瘤原发灶进展达到T_3期、远处转移发展至M_1期均可作为影响宫颈癌预后的独立危险因素。使用R软件计算得出C-index=0. 745,标准误(SE)=0. 004,表明预测模型具有中等准确度,预测结果可信。ROC曲线显示,3、5年的曲线下面积(AUC)分别为0. 759、0. 758,表明预测模型具有较好的敏感性和特异性。本研究校准曲线拟合线与参考线重合率极高,表明该预测模型准确可信。Kaplan-Meier生存分析显示,与未接受放疗者相比,接受放疗者80个月总体生存率明显较高,TNMⅠ~Ⅱ期患者的生存率明显高于Ⅲ~Ⅳ期宫颈癌患者,年龄小的患者生存率高于年龄大的患者。结论放疗可显著改善宫颈癌患者的总生存期。本研究在SEER大样本人群研究的基础上,建立了可信的列线图,在设计治疗方案和评估患者预后方面具有一定的价值。

Objective To investigate the impact of radiotherapy on the survival of patients with cervical cancer based on SEER database.Methods The data of cervical cancer patients from1973 through 2016 was searched in SEER database and 10920 valid data was screen out.The medical records of these patients were retrospectively analyzed,including 10748 patients with radiotherapy and172 without radiotherapy.Multivariate Cox regression model was constructed to evaluate the influence of different clinicopathological factors on the prognosis of patients with cervical cancer.Nomogram was plotted to evaluate the value of predicting disease progression by multiple indicators.The concordance index(C-index),receiver operating characteristic(ROC)curve and calibration chart are used to evaluate the prediction accuracy and discriminative ability of the model.Survival condition was analyzed by a Kaplan-Meier curve.Results Multivariate regression analysis showed that radiotherapy was an independent prognostic factor for cervical cancer patients(P=0.001).Multivariate regression analysis also showed that age,radiotherapy and TNM stage were all important factors affecting the overall survival of cervical cancer patients,and the factors including≥60 years(P=0.001),T4 staging(P=0.019),N1 staging(P=0.001),NXstaging(P=0.001),M1 staging(P=0.001)and receiving no radiotherapy(P=0.001)caused worse prognosis of patients.The results of nomogram showed that age≥80 years,no radiotherapy,tumor progression to T3 staging and distant metastasis to M1 staging were independent risk factors for prognosis of cervical cancer patients.The C-index calculated by R software was equaled to 0.745,and standard error(SE)was equaled to 0.004,indicating that the prediction model was moderately accurate and the prediction results is reliable.The ROC curves showed that area under the curve(AUC)at 3 and 5 year was 0.759 and 0.758,respectively,indicating better sensitivity and specificity of the predictive model.The calibration curve fit line in this study has an extremely high overlap with the reference line,indicating that the prediction model was accurate and reliable.Kaplan-Meier survival analysis showed that 80-month overall survival rate was significantly higher in patients who received radiotherapy compared to those who did not,and the survival rate was significantly higher inⅠorⅡstaging of TNM versusⅢorⅣstaging,in younger patients versus older ones.Conclusion Radiotherapy can significantly improve overall survival in patients with cervical cancer.Based on the SEER large-sample population study,this study establishes a plausible Nomogram,which is of value in designing treatment plans and assessing patient prognosis.