Development and validation of a blood-based genomic mutation signature for predicting the risk of brain metastases in non-small cell lung cancer

Abstract Purpose Available research indicates that the mammalian target of rapamycin complex 1 (mTORC1) signaling pathway is significantly correlated with lung cancer brain metastasis (BM). This study established a clinical predictive model for assessing the risk of BM based on the mTORC1-related single nucleotide polymorphisms (SNPs). Methods The clinical data of 395 patients with non-small cell lung cancer (NSCLC) were retrospectively analyzed. Variables associated with the risk of BM were identified by the least absolute shrinkage and selection operator (Lasso) regression and included to establish a logistic model (Model A). These variables were further combined with SNPs from the peripheral blood samples to construct another logistic model (Model B). The predictive performance of both models was compared and the internal validation of the models was performed based on 1,000 bootstrap samples. Results Model A incorporated histology, clinical N stage, CEA, neutrophil to lymphocyte ratio, and lymphocyte-to-monocyte ratio. Model A and B showed an arear under the curve of 0.841 and 0.848 in the training set, and of 0.796 and 0.798 in the internal validation, respectively. The calibration curves and Hosmer-Lemeshow tests reported a good fit for both models. The continuous net reclassification improvement (NRI), integrated discrimination improvement (IDI) tests, and decision curve analysis (DCA) revealed a superior predictive performance for Model B when compared with Model A. Conclusion The mTORC1-related SNPs in the peripheral blood can greatly facilitate the prediction of NSCLC brain metastasis, signifying its promising clinical value for an early detection and intervention for the NSCLC population.