Establishment And Validation Of Nomograms For Predicting Distant Metastasis And Prognosis In Patients With Invasive Lung Adenocarcinoma

ObjectiveTo investigate the clinical characteristics that influence the risk of distant metastasis and prognosis of invasive lung adenocarcinoma(IAC).And to establish and verify corresponding nomograms.Methods5742 patients with IAC diagnosis between 2010 and 2015 were retrospectively chosen from the surveillance,epidemiology,and end results(SEER)database,and they were at random split into training and verification groups in a 7:3 ratio.Tumor site,histological type,T stage,N stage,distant metastasis,surgical approach,whether lymph node dissection was performed,age at diagnosis,race,gender,as well as survival status and time were among the patients data that were gathered.By using univariate and multivariate logistic regression analysis,predictors associated with distant metastasis in patients with IAC were identified.The overall survival of IAC patients was predicted using a nomogram established using the R program.The predictive ability of the nomogram and AJCC staging system was compared using AUC and DCA.To analyze the effect of clinical information on the overall survival(OS)of patients with IAC using Kaplan-Meier survival curves.Prognostic factors in patients with IAC were screened by univariate and multivariate COX regression analysis.The R software was used to construct a nomogram to predict the overall survival of IAC patients,and AUC and DCA curves were also used to evaluate its predictive ability.In addition,in order to further evaluate the clinical effectiveness of the nomogram,the X-tile software was used to stratify the nomogram scores and draw the Kaplan-Meier survival curve about the overall survival to evaluate its differentiation ability.Results(1)The predictors of distant metastasis in IAC patients screened by Logistic regression analysis included histological type,age at diagnosis,T stage,N stage,surgical approach,and whether lymph node dissection was performed.Compared with AJCC staging system,the nomogram constructed by these factors has better performance in AUC and DCA.AUC showed that the nomogram has better predictive performance(training set:0.922 vs 0.790;verification set:0.919vs0.779),and DCA showed that the nomogram has higher net income.(2)Kaplan-Meier survival curve showed that the clinical characteristics of patients were related to the overall survival of IAC patients,and the overall difference was statistically significant.However,there were no meaningful differences in overall survival between certain subgroups within race and tumor location.The predictors of overall survival of IAC patients screened by univariate and multivariate COX regression analysis included histological type,age at diagnosis,gender,T stage,N stage,distant metastasis,surgical approach,and whether lymph node dissection was performed.The nomogram constructed by these factors also showed good predictive performance in AUC and DCA curves.The AUC of 1-year,3-year and 5-year survival rates in the training set were 0.843,0.839 and 0.841.The AUC of 1-year,3-year and 5-year survival rates in the validation set were 0.843,0.843 and 0.822.The nomogram score-based Kaplan-Meier survival curve for overall survival demonstrated that the prediction model has effective layering.Conclusion(1)Age at diagnosis,histological type,T stage,N stage,surgical approach,and whether lymph node dissection is performed are independent predictors of the risk of distant metastasis in IAC patients.The nomogram can more accurately predict the risk of distant metastasis,which will help doctors formulate appropriate adjuvant treatment plans.(2)Histological type,T stage,N stage,distant metastasis,age at diagnosis,gender,surgical approach,and whether lymph node dissection is performed are independent prognostic factors for IAC patients.The nomogram can be used for survival prediction of IAC patients,which helps in personalized treatment and prognosis assessment.