Analysis Of Risk Factors For Lung Cancer In Patients With Chronic Obstructive Pulmonary Disease And Construction And Verification Of Prediction Model

Objective:The aim of this study was to investigate the occurrence of lung cancer in patients with COPD and analyze its risk factors,and to develop an easy-to-use prediction model based on these risk factors.This model can provide a certain predictive value for the occurrence of lung cancer in patients with COPD in clinical practice,and screen out high-risk groups of lung cancer,so as to provide theoretical basis for individualized secondary prevention and the formulation of corresponding prevention and treatment measures.Methods:This study retrospectively included 1952 patients diagnosed with COPD at the Affiliated People’s Hospital of Jiangsu University from January 2015 to January 2023 according to the Guidelines for the Diagnosis and Treatment of Chronic Obstructive Pulmonary Disease(2021Revision).The COPD patients were divided into COPD group(Chronic Obstructive Pulmonary Disease,COPD)and COPD with lung cancer group(Pulmonary Disease Complicated With Lung Cancer,COPD+LC)according to the Chinese Medical Association Guidelines for the Clinical Diagnosis and Treatment of Lung Cancer(2022 edition).Among them,164 patients with COPD developed LC and 1788 patients with COPD did not develop LC by reviewing patient electronic medical records and pathological examination.The subjects were randomly divided into the training set(70%;N=1370)and validation set(30%;N=582).The general epidemiological data,hematological indexes and pulmonary function indexes of COPD group and COPD+LC group were collected.Univariate and multivariate logistic regression methods were used to screen the independent risk factors of LC in COPD patients,and a clinical prediction model was constructed and verified based on the above independent risk factors.The Receiver operating characteristic(ROC)curve,calibration curve and Decision curve analysis were used for statistical analysis DCA)was used to evaluate the discrimination ability,calibration and clinical validity of the clinical prediction model.Results:The clinical prediction model including the following four variables was constructed: static lung hyperinflation(Odds Ratio(OR):2.048),Platelet To Lymphocyte Ratio(PLR)(OR:1.056),and platelet to lymphocyte ratio(PLR)(OR:1.056).Neutrophil To Lymphocyte Ratio(NLR)(OR:1.516),Systemic Immune Inflammation Index(Systemic Immune Inflammation Index,SII)(OR:2.875).The areas of ROC of the training set and the validation set were 0.805 and 0.776,respectively,indicating that the prediction model had good predictive value.In addition,the calibration curve showed good agreement between the predicted values and the observed values in the training and validation sets.DCA also confirmed that the clinical prediction model had good clinical application value.Conclusion:The clinical prediction model for LC in COPD patients established based on independent risk factors has an ideal efficacy evaluation,which has a certain predictive value for the occurrence of LC in COPD patients,so as to screen out high-risk groups prone to LC,and provide a scientific reference for the secondary prevention of LC in COPD patients and the formulation of corresponding prevention and treatment measures.