RESUMO
Objective:To assess the effectiveness of a model created using clinical features and preoperative chest CT imaging features in predicting the chronic obstructive pulmonary disease (COPD) among patients diagnosed with lung cancer.Methods:A retrospective analysis was conducted on clinical (age, gender, smoking history, smoking index, etc.) and imaging (lesion size, location, density, lobulation sign, etc.) data from 444 lung cancer patients confirmed by pathology at the Second Affiliated Hospital of Naval Medical University between June 2014 and March 2021. These patients were randomly divided into a training set (310 patients) and an internal test set (134 patients) using a 7∶3 ratio through the random function in Python. Based on the results of pulmonary function tests, the patients were further categorized into two groups: lung cancer combined with COPD and lung cancer non-COPD. Initially, univariate analysis was performed to identify statistically significant differences in clinical characteristics between the two groups. The variables showing significance were then included in the logistic regression analysis to determine the independent factors predicting lung cancer combined with COPD, thereby constructing the clinical model. The image features underwent a filtering process using the minimum absolute value convergence and selection operator. The reliability of these features was assessed through leave-P groups-out cross-validation repeated five times. Subsequently, a radiological model was developed. Finally, a combined model was established by combining the radiological signature with the clinical features. Receiver operating characteristic (ROC) curves and decision curve analysis (DCA) curves were plotted to evaluate the predictive capability and clinical applicability of the model. The area under the curve (AUC) for each model in predicting lung cancer combined with COPD was compared using the DeLong test.Results:In the training set, there were 182 cases in the lung cancer combined with COPD group and 128 cases in the lung cancer non-COPD group. The combined model demonstrated an AUC of 0.89 for predicting lung cancer combined with COPD, while the clinical model achieved an AUC of 0.82 and the radiological model had an AUC of 0.85. In the test set, there were 78 cases in the lung cancer combined with COPD group and 56 cases in the lung cancer non-COPD group. The combined model yielded an AUC of 0.85 for predicting lung cancer combined with COPD, compared to 0.77 for the clinical model and 0.83 for the radiological model. The difference in AUC between the radiological model and the clinical model was not statistically significant ( Z=1.40, P=0.163). However, there were statistically significant differences in the AUC values between the combined model and the clinical model ( Z=-4.01, P=0.010), as well as between the combined model and the radiological model ( Z=-2.57, P<0.001). DCA showed the maximum net benifit of the combined model. Conclusion:The developed synthetic diagnostic combined model, incorporating both radiological signature and clinical features, demonstrates the ability to predict COPD in patients with lung cancer.