Predicting the Prognosis of Lung Cancer Patients Treated with Intensitymodulated Radiotherapy based on Radiomic Features

Abstract

Aims: This study aimed to develop a method for predicting short-term outcomes of lung cancer patients treated with intensity-modulated radiotherapy (IMRT) using radiomic features detected through computed tomography images. Methods: A prediction model was developed based on a dataset of radiomic features obtained from 132 patients with lung cancer receiving IMRT. Dimension reduction was performed for the features using the maximum-relevance and minimum-redundancy (mRMR) algorithm, and the least absolute shrinkage and selection operator (LASSO) regression model was utilized to optimize feature selection for the IMRT-sensitivity prediction model. The model was constructed using binary logistic regression analysis and was evaluated using the concordance index (C-index), calibration plots, receiver operating characteristic curve, and decision curve analysis. Results: Fifty features were selected from 1348 radiomic features using the mRMR method. Of these, three radiomic features were selected by LASSO logistic regression to construct the radiomics nomogram. The C-index of the model was 0.776 (95% confidence interval: 0.689–0.862) and 0.791 (95% confidence interval: 0.607–0.974) in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful. Conclusion: Radiomic features have the potential to be applied to predict the short-term efficacy of IMRT in patients with inoperable lung cancer.