NCOG-05. A BRAIN METASTASES SURVIVAL MODEL USING AN ENSEMBLE TREE APPROACH

Abstract

Abstract PURPOSE/OBJECTIVE(S) The primary purpose of this study is to determine whether a machine learning approach can estimate survival in patients with brain metastases undergoing stereotactic radiosurgery or fractionated stereotactic radiotherapy (SRS/SRT). The secondary purpose is to identify covariates of importance. MATERIALS/METHODS Data were collected for 377 SRS/SRT treatments in 291 patients done between the years 2008-2021. If a patient was treated with more than one course of SRS/SRT within 30 days, they were counted only once. Twenty-five clinically-relevant variables were identified as covariates and the primary outcome of time from brain metastasis diagnoses to death was used to build a random survival forest model. Brain metastasis location was categorized as infratentorial, supratentorial, or both. An 80/20 split was used for training (n = 302) and test (n = 75) sets. Missing data points were imputed using a just-in-time adaptive tree approach. Minimal depth and variable importance (VIMP) approaches were used to identify prognostic factors. Model performance was assessed using time-dependent area under the receiver operating characteristics curve (tAUC). RESULTS Median survival time was 16 months. The most important variables according to minimal depth analysis (depth threshold 5.23) were Karnofsky Performance Status (KPS), extracranial status, age, insurance status, metastases volume, histology, number of metastases, and location. Error rate on the test set was 0.38. tAUC was found to increase continuously over time and at 6, 12, 24, and 36 months was 0.56, 0.63, 0.74, and 0.84 respectively. CONCLUSION An ensemble tree approach can provide good survival prediction for patients with brain metastases undergoing SRS/SRT. Model performance, as measured by tAUC, increases over time suggesting better predictive capability at longer time intervals. Future directions include collecting more data to increase model performance, comparing to other models, and validating with external data.