Applicability of graded prognostic assessment of lung cancer using molecular markers to lung adenocarcinoma patients with brain metastases

Several scoring systems are available to estimate prognosis and assist in selecting treatment methods for non-small cell lung cancer (NSCLC) patients with brain metastasis, including recursive partitioning analysis (RPA), basic score for brain metastases (BSBM), and diagnosis-specific graded prognostic assessment (DS-GPA). Lung-molGPA is an update of the DS-GPA that incorporates EGFR and/or ALK mutation status. The present study tested the applicability of these four indexes in 361 lung adenocarcinoma patients with brain metastasis. Potential predictive factors in our independent multivariate analysis included patient age, Karnofsky performance status, EGFR and ALK mutation status, and use of targeted therapy. In the log-rank test, all four systems predicted overall survival (OS) (P < 0.001). Harrell's C indexes were 0.732, 0.724, 0.729, and 0.747 for RPA, BS-BM, DS-GPA, and Lung-molGPA, respectively. Our results confirmed that the Lung-molGPA index was useful for estimating OS in our patient cohort, and appeared to provide the most accurate predictions. However, the independent prognostic factors identified in our study were not entirely in agreement with the Lung-molGPA factors. In an era of targeted therapy, Lung-molGPA must be further updated to incorporate more specific prognostic factors based on additional patient data.