P78.02 A CT-Based Radiomics Approach to Predict Nivolumab Response in Advanced Non–Small-Cell Lung Cancer

Abstract

This study aims to develop a CT-based radiomics model to predict the clinical outcomes of advanced non-small-cell lung cancer (NSCLC) patients treated with nivolumab. Forty-six stage IIIB/IV NSCLC patients without EGFR mutation or ALK rearrangement who received nivolumab were enrolled between Apr 2016 and Jan 2019. After segmenting primary tumors depicting on the pre-anti-PD1 treatment CT images, 1106 high-dimensional quantitative imaging features were computed and extracted to decode the imaging phenotypes. A L1-based feature selection method was applied to remove redundant features and build an optimal feature pool. To predict the risk of progression-free survival (PFS) and overall survival (OS) for each patient, the selected radiomics features were used to train and test three machine-learning classifiers namely, support vector machine classifier, logistic regression classifier, and Gaussian Naïve Bayes classifier. The prediction scores obtained by three classifiers were used to stratify patients into high and low risk subgroups. Finally, we analyzed and compared the Kaplan–Meier survival estimators of the stratified subgroups with high and low risk for progression and death (Fig A). The median PFS was 3.0 months (95% CI, 1.9-4.1 months), the median OS was 17.0 months (95%CI, 7.3-26.7 months) (Fig B-C). To predict the risk of PFS and OS, three classifiers yielded the average area under a receiver operating characteristic curve (AUC) value of 0.73±0.07 and 0.61±0.08, respectively (Fig D). The corresponding average Harrell’s concordance indexes for three classifiers in predicting PFS and OS were 0.92 and 0.79 (Fig E-F). The average hazard ratios (HR) of three models for predicting PFS and OS were 6.22 and 3.54, suggesting the dramatic difference of the two subgroup’s PFS and OS in immune treatment (p<0.05) (Table 1).View Large Image Figure ViewerDownload Hi-res image Download (PPT) The pre-treatment CT-based radiomics model provided a promising way to predict clinical outcomes for advanced NSCLC patients treated with nivolumab.