INTRODUCTION: This study compares four management paradigms for large brain metastasis (LMB): fractionated SRS (FSRS), staged SRS (SSRS), resection and postoperative-FSRS (postop-FSRS) or preoperative-SRS (preop-SRS). METHODS: Patients with LBM (≥ 2 cm) between July 2017 and January 2022 at a single tertiary institution were evaluated. Primary endpoints were local failure (LF), radiation necrosis (RN), leptomeningeal disease (LMD), a composite of these variables, and distant intracranial failure (DIF). Gray's test compared cumulative incidence, treating death as a competing risk with a random survival forests (RSF) machine-learning model also used to evaluate the data. RESULTS: 183 patients were treated to 234 LBMs: 31.6% for postop-FSRS, 28.2% for SSRS, 20.1% for FSRS, and 20.1% for preop-SRS. The overall 1-year composite endpoint rates were comparable (21 vs 20%) between nonoperative and operative strategies, but 1-year RN rate was 8 vs 4% (p = 0.012), 1-year overall survival (OS) was 48 vs. 69% (p = 0.001), and 1-year LMD rate was 5 vs 10% (p = 0.052). There were differences in the 1-year RN rates (7% FSRS, 3% postop-FSRS, 5% preop-SRS, 10% SSRS, p = 0.037). With RSF analysis, the out-of-bag error rate for the composite endpoint was 47%, with identified top-risk factors including widespread extracranial disease, > 5 total lesions, and breast cancer histology. CONCLUSION: This is the first study to conduct a head-to-head retrospective comparison of four SRS methods, addressing the lack of randomized data in LBM literature amongst treatment paradigms. Despite patient characteristic trends, no significant differences were found in LF, composite endpoint, and DIF rates between non-operative and operative approaches.
