Applicability of the adjusted graded prognostic assessment for lung cancer with brain metastases using molecular markers (Lung‐molGPA) in a Chinese cohort: A retrospective study of multiple institutions

BACKGROUND: In this era of precision medicine, prognostic heterogeneity is an important feature of patients with non‐small cell lung cancer (NSCLC) with brain metastases (BM). This multi‐institutional study is aimed to verify the applicability of the adjusted Lung‐molGPA model for NSCLC with BM in a Chinese cohort. METHODS: This retrospective study included 1903 patients at three hospitals in Southwest China. The performance of the Lung‐molGPA model was compared with that of the adjusted DS‐GPA model in terms of estimating the survival of NSCLC with BM. RESULTS: The median OS of this patient cohort was 27.0 months, and the adenocarcinoma survived longer than the non‐adenocarcinoma (28.0 months vs 18.7 months, p < 0.001). The adjusted Lung‐molGPA model was more accurate in predicting survival of adenocarcinoma patients than the adjusted DS‐GPA model (C‐index: 0.615 vs 0.571), and it was not suitable for predicting survival of non‐adenocarcinoma patients (p = 0.286, 1.5‐2.0 vs 2.5‐3.0; p = 0.410, 2.5‐3.0 vs 3.5‐4.0). CONCLUSIONS: The adjusted Lung‐molGPA model is better than the DS‐GPA model in predicting the prognosis of adenocarcinoma patients. However, it failed to estimate the prognosis for non‐adenocarcinoma patients.