Nomogram based on computed tomography radiomics features and clinicopathological factors to predict the prognosis of patients with non-small cell lung cancer receiving immune checkpoint inhibitor rechallenge.

Abstract

Background: Whether patients with advanced non-small cell lung cancer (NSCLC) who experience progressive disease (PD) after the initial immunotherapy treatment benefit from subsequent immunotherapy remains unclear. In this study, we aimed to identify predictive factors and develop a nomogram to predict successful immunotherapy rechallenge for such patients with NSCLC to guide clinical treatment and improve prognosis.

Methods: Between January 2019 and December 2022, 352 patients with advanced NSCLC who received immunotherapy rechallenge after experiencing PD were divided into the training (n=246) and validation (n=106) cohorts. Clinicopathological factors and radiomics features were included in the univariate and multivariate analyses, with significant predictive factors being used to develop the nomogram.

Results: Univariate and multivariate analyses showed that time from the initial immunotherapy to PD occurrence (duration), clinical N stage, liver metastasis, treatment after PD following the first immunotherapy (post-PD treatment), and radiomics features were independent predictive factors for progression-free survival (PFS). In addition, age, duration, clinical N stage, post-PD treatment, and radiomics were independent predictive factors for overall survival (OS). Accordingly, these predictive factors were used to develop a nomogram. The area under the curves (AUCs) of the nomogram for predicting 6-, 12-, and 18-month PFS and 12-, 18-, and 24-month OS were 0.731, 0.809, 0.878, 0.742, 0.782, and 0.868, respectively, in the training cohorts, whereas the corresponding values in the validation cohort were 0.672, 0.774, 0.826, 0.833, 0.705, and 0.762. This indicated good discrimination.

Conclusions: We developed and validated a predictive nomogram based on clinicopathological factors and radiomics features for the prognosis of patients with advanced NSCLC who received immunotherapy rechallenge following PD after the first immunotherapy. The nomogram showed strong predictive utility and can be a suitable tool for such patients with advanced NSCLC.