Introduction: KRAS mutation is the most frequent molecular alteration found in advanced NSCLC; it is associated with a poor prognosis without available targeted therapy. Treatment options for NSCLC have been recently enriched by the development of immune checkpoint inhibitors (ICIs), and data about its efficacy in patients with KRAS-mutant NSCLC are discordant. This study assessed the routine efficacy of ICIs in advanced KRAS-mutant NSCLC. Methods: In this retrospective study, clinical data were extracted from the medical records of patients with advanced NSCLC treated with ICIs and with available molecular analysis between April 2013 and June 2017. Analysis of programmed death ligand 1 (PD-L1) expression was performed if exploitable tumor material was available. Results: A total of 282 patients with ICI-treated (in the first line or more) advanced NSCLC (all histological subgroups) who were treated with ICIs (anti-programmed death 1, anti-PD-L1, or anti-cytotoxic T-lymphocyte associated protein 4 antibodies), including 162 (57.4%) with KRAS mutation, 27 (9.6%) with other mutations, and 93 (33%) with a wild-type phenotype, were identified. PD-L1 analysis was available for 128 patients (45.4%), of whom 45.3% and 19.5% had PD-L1 expression of 1% or more and 50%, respectively (49.5% and 21.2%, respectively, in the case of the 85 patients with KRAS-mutant NSCLC). No significant difference was seen in terms of objective response rates, progression-free survival, or overall survival between KRAS-mutant NSCLC and other NSCLC. No significant differences in overall survival or progressionfree survival were observed between the major KRAS mutation subtypes (G12A, G12C, G12D, G12V, and G13C). In KRAS-mutant NSCLC, unlike in non-KRAS-mutant NSCLC, the efficacy of ICIs is consistently higher, even though not statistically significant, for patients with PD-L1 expression in 1% or more of tumor cells than for those

No abstract

Background: Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs. Methods: Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response. Results: Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, p < 0.0001; OR 1.8, p < 0.001). These variables were also associated with PFS and OS and ranked top in random forest-based feature importance. Neutrophil-to-lymphocyte ratio was also associated with DCR, PFS and OS. The best ML algorithm was a random forest. It could predict DCR with satisfactory efficacy based on these three variables. Ten-fold cross-validated performances were: accuracy 0.68 ± 0.04, sensitivity 0.58 ± 0.08; specificity 0.78 ± 0.06; positive predictive value 0.70 ± 0.08; negative predictive value 0.68 ± 0.06; AUC 0.74 ± 0.03. Conclusion: Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.