青年胰腺癌患者疾病特异生存列线图的构建

Construction of nomogram for disease-specific survival in young patients with pancreatic cancer

目的:探讨青年胰腺癌患者预后的影响因素,构建列线图模型并进行验证.方法:从美国国家癌症研究所(SEER)数据库获取2010—2016年的808例青年胰腺癌患者临床资料,按7:3比例随机分为训练集(n=565)及验证集(n=243).使用LASSO回归及多因素Cox回归分析明确影响青年胰腺癌患者预后危险因素,构建预测1年、2年、3年疾病特异生存率(DSS)的列线图模型;计算C-index及绘制校准曲线对列线图模型进行验证并评估其预测效能.结果:共808例患者被纳入研究(训练集565例,验证集243例).训练集LASSO Cox回归分析结果显示,年龄、性别、肿瘤类型、肿瘤大小、肿瘤分化程度、手术、T、N、M分期与DSS独立相关(P<0.05).训练集及验证集C指数均大于0.7,校准曲线显示模型预测的疾病特异生存率与实际疾病生存率相近.结论:构建列线图模型可以较准确预测青年胰腺癌患者的预后.

Objective To investigate prognostic factors in young patients with pancreatic cancer,construct a nomogram model,and validate its accuracy.Methods Clinical data of 808 young patients with pancreatic cancer from the National Cancer Institute's Surveillance,Epidemiology,and End Results(SEER)database(2010–2016)were collected.The data were randomly divided into a training set(n=565)and a validation set(n=243)in a 7:3 ratio.Lasso regression and multivariate Cox regression were used to identify independent prognostic factors in young pancreatic cancer patients.A nomogram predicting 1,2 and 3-year disease-specific survival(DSS)rates were constructed.The C-index was calculated,and calibration curves were plotted to assess the predictive performance of the nomogram model.Results A total of 808 patients were included(565 in the training set,243 in the validation set).Multivariate regression analysis of the training set revealed that age,sex,tumor type,tumor size,tumor differentiation,surgery,T stage,N stage,and M stage were independently associated with DSS(P<0.05).The C-index of both the training and validation sets were greater than 0.7.The calibration curves showed close agreement between predicted and actual disease-specific survival rates.Conclusions The constructed nomogram model accurately predicts the prognosis of young patients with pancreatic cancer.