建立诺曼图预测Ⅳ期年轻非小细胞肺癌预后

Establishing a Norman diagram to predict the prognosis of stageⅣyoung non-small cell lung cancer

目的以诺曼图模型预测Ⅳ期年轻非小细胞肺癌的生存及预后。方法选取2010年至2016年美国国立癌症研究所(Surveillance Epidemiology and End Results,SEER)数据库年龄≤45岁Ⅳ期非小细胞肺癌患者,3∶1随机分为训练组584例和验证组195例。使用COX比例风险回归模型探究影响生存的独立因素,再建立预后诺曼图模型。以C指数和校准曲线评估诺曼图预测效果。结果多因素分析发现年龄、种族、手术、化疗、肿瘤分化程度、T分期、N分期为预后独立因素,分化程度所占比重最大,其次为化疗以及手术。训练组C指数为:0.70(95%CI:0.67~0.73);验证组C指数为:0.68(95%CI:0.63~0.73)。校准曲线显示诺曼图预测肿瘤生存和肿瘤实际生存有良好一致性。结论所构建的诺曼图模型可用于预测年轻Ⅳ期非小细胞肺癌患者预后。

Objective To predict stage IV young non-small cell lung cancer with Norman diagram model(non-small cell lung cancer,NSCLC)survival and prognosis.Methods Select the 2010-2016 National Cancer Institute(Surveillance Epidemiology and End Results,SEER)database age≤45 years old stage IV non-small cell lung cancer patients,3:1 randomly divided into training group 584 cases and verification group 195 cases.Use the COX proportional hazard regression model to explore the independent factors that affect survival,and then establish a prognostic Norman chart model.Evaluate the prediction effect of Norman diagram with C index and calibration curve.Results Multivariate analysis found that age,race,surgery,chemotherapy,tumor differentiation,T staging,and N staging were independent prognostic factors,and differentiation accounted for the largest proportion,followed by chemotherapy and surgery.The C index of the training group was 0.70(95%CI:0.67~0.73);the C index of the validation group was 0.68(95%CI:0.63~0.73).The calibration curve shows that the Norman chart predicts tumor survival and the actual tumor survival is in good agreement.Conclusion The constructed Norman diagram model can be used to predict the prognosis of young patients with stage IV non-small cell lung cancer.