Analysis Of Risk Factors Of Secondary Lung Cancer In ILD Patients And Establishment And Evaluation Of The Nomogram

Objective:Currently,lung cancer is one of the most common malignancies in China and one of the leading causes of cancer-related deaths worldwide.The incidence of interstitial lung disease is increasing year by year,but there is no nomogram of secondary lung cancer in ILD patients during disease progression.After successful model construction,it can be used to screen out the patients with high incidence of secondary lung cancer in ILD patients at an early stage,and follow up these patients closely in order to carry out early intervention in these patients.Methods:This study mainly included all ILD patients admitted to the Department of Respiratory and Critical Care Medicine of the Affiliated Hospital of Qingdao University from January 2015 to December 2018,with a total of 968 cases.Some patients were excluded due to incomplete data,incomplete medical records and other reasons,and a total of 601 cases were finally included.According to the ratio of 4:1,they were randomly divided into training group and test group.Follow-up to December 2020,45 ILD patients developed secondary lung cancer during the follow-up period.Inclusion indexes were mainly routine blood,blood biochemical,blood gas analysis,tumor markers of lung cancer,lung function,lung imaging findings and other common clinical indicators.We used Cox regression model to screen out some statistically significant risk factors through univariate analysis,and then carried out multivariate analysis on these significant factors screened out,and finally determined the risk factors related to secondary lung cancer in ILD patients in the course of disease development.Then,this nomogram was constructed using"R" software based on Cox analysis results,and the prediction model was verified and evaluated.The area under the ROC curve(AUC)of the prediction model was calculated,and the accuracy of the prediction model was verified with the data of the test group,and the consistency curve of the model was plotted.The utility of Nomogram was evaluated using C-index,Decision curve analysis,and Calibrate plot.Results:Cox regression showed lymphocytes(HR=1.191,95%CI=0.954-1.485,P=0.022),eosinophil(HR=2.204,95%CI=1.149-4.227,P=0.017),C-reactive protein(HR=0.987,95%CI=0.973-1.001,P=0.039),carcinoembryonic antigen(HR=1.049,95%CI=1.010-1.090,P=0.014),age>65 years(HR=1.508,95%CI=1.053-2.160,P=0.025)is an independent risk factor for secondary lung cancer in ILD patients.These indicators were incorporated into the Nomogram to construct a prediction model for secondary lung cancer in ILD patients.The area under the ROC curve(AUC)was 0.674,and the AUC of the test group was 0.735.The accuracy of this model was high combined with various indicators.Consistency curves were drawn against the model,and the results showed that the predicted secondary risk of lung cancer was in good agreement with the actual incidence of lung cancer.Conclusion:The results showed that lymphocytes,eosinophils,C-reactive protein,carcinoembryonic antigen and age>65 years were independent risk factors for secondary lung cancer in ILD patients.This study establishes a Nomogram prediction model for secondary lung cancer in ILD patients based on the statistical analysis results for the first time.This model has a good predictive ability and has important clinical significance for early detection of secondary lung cancer in ILD patients.