Predict the prognosis of patients with non-small cell lung cancer based on CT radiomics and clinical pathological factors

Background This study aims to investigate the use of computed tomography (CT) radiomics features combined with clinicopathological factors to establish and validate a radiomics nomogram for predicting overall survival (OS) in patients with non-small cell lung cancer (NSCLC). Methods This study included 177 patients with NSCLC, from whom CT images and clinicopathological data were collected (124 patients in the training set and 53 in the validation set). A total of 1,688 radiomics features were extracted from the volume of interest (VOI) of the tumors. Spearman correlation analysis and univariate Cox analysis were used for preliminary screening, followed by LASSO-COX regression combined with ten-fold cross-validation to further identify key radiomics features. Meanwhile, independent clinical risk factors were identified through Cox regression analysis. A nomogram was constructed based on the radiomics score (Radscore) combined with the independent clinical risk factors. The predictive performance of the model was evaluated using the C-index and calibration curves. Results Among the 177 patients with NSCLC, there were 107 males (60.45%)and 70 females (39.55%). In total, 16 key radiomics features were identified, and an OS nomogram was established based on the Radscore and clinical independent risk factors. The area under the curve(AUC) of the training and validation sets were 0.892 and 0.838, respectively. The calibration curve showed that the predicted OS values demonstrated good consistency with the actual values. Conclusion The construction of a nomogram based on CT radiomics features combined with clinicopathological factors demonstrates good efficacy in predicting OS in patients with NSCLC and can provide valuable guidance for individualized treatment strategies.