膀胱癌术后复发危险因素分析及模型构建

Analysis of risk factors for recurrence and prediction model of bladder cancer

目的回顾分析手术治疗膀胱癌患者术后复发的独立危险因素,构建膀胱癌复发模型。方法选取240例经手术治疗的膀胱癌患者,进行不少于1年的随访,将患者分为复发组(n=54)和非复发组(n=186)。将患者一般资料对比分析后进行ROC曲线分析,将差异有统计学意义的数据纳入Logistic多因素分析。在筛选出的危险因素的基础上构建预测模型,通过模型校正曲线及临床净收益评估,得到可用于膀胱癌患者术后复发的预测模型。结果ROC曲线结果显示:预后营养指数(PNI)、膀胱癌特异性核基质蛋白(BLCA-4)、膀胱肿瘤抗原(BTA)、尿核基质蛋白22(NMP22)、癌胚抗原(CEA)的AUC分别为0.932、0.979、0.998、0.677、0.981;最佳截断值分别为:≤40.18%、>140.04 ng/mg、≤7.22 U/mg、>7.68μg/mg、>1.99 ng/mg。Logistic结果显示:PNI≤40.18%、BLCA-4>140.04 ng/mg、BTA≤7.22 U/mg、NMP22>7.68μg/mg是膀胱癌患者出现复发的危险因素。将PNI、BLCA-4、BTA、NMP22纳入复发模型的构建,作为膀胱癌患者病情复发的因子。对模型校正曲线及临床净收益分析,内部验证结果显示,模型膀胱癌复发的一致性指数为0.296(95%CI:0.078~1.329)。校准曲线显示观测值与值之间保持较好一致性。模型膀胱癌患者复发的风险阈值>0.128,模型提供临床净收益;此外,模型临床净收益均高于PNI、BLCA-4、BTA、NMP22。结论模型校正曲线及临床净收益分析,内部验证结果显示成功构建了膀胱癌复发模型。

Objective Review the independent risk factors of postoperative recurrence in surgical treatment of bladder cancer patients to construct a model of bladder cancer recurrence.Methods A total of 240 surgically treated bladder cancer patients were followed up for at least 1 year and divided into recurrence(n=54)and non-recurrence(n=186).The general data of patients were comparative analyzed,and the different and statistically significant data were further analyzed by ROC curve,and the statistically significant data were included in the multivariate analysis after logistic obtaining univariate analysis results.Risk factors were included in the model construction,and the model correction curve and clinical net benefit analysis were analyzed.The model could be used to predict postoperative recurrence in bladder cancer patients.Results The ROC curves of the statistically significant continuous variables were analyzed in the general data,and the results showed that the AUC of PNI,BLCA-4,BTA,NMP22 and CEA were 0.932,0.979,0.998,0.677 and 0.981,respectively,and the optimal truncation values were≤40.18%,>140.04 ng/mg,≤7.22 U/mg,>7.68μg/mg,and>1.99 ng/mg,respectively.Statistically significant data from univariate analysis were incorporated into the logistic regression model,and the results showed that PNI≤40.18%,BLCA-4>140.04 ng/mg,BTA≤7.22 U/mg,NMP22>7.68μg/mg was a risk factor for recurrence in patients with bladder cancer.Subsequently,PNI,BLCA-4,BTA,and NMP22 were incorporated into the construction of the model as predictors of recurrence in patients with bladder cancer.Based on the model correction curve and clinical net benefit analysis,the internal verification results showed that the C-index of the model predicting bladder cancer recurrence was 0.296(95%CI:0.078-1.329).The calibration curve showed good consistency between the observed and predicted values.The model predicted a risk threshold>0.128 for patients with bladder cancer,and the model provided a clinical net benefit;in addition,the model had a higher clinical net benefit than PNI,BLCA-4,BTA,and NMP22.Conclusion The model correction curve and clinical net benefit analysis,the results of internal verification show that the model can be used to predict recurrence in patients with bladder cancer.