Recursive Partitioning Analysis for the Prediction of Stereotactic Radiosurgery Brain Metastases Lesion Control
Bibliographic record
Abstract
PURPOSE: The objective of this investigation was to identify independent pretreatment factors that predict for control of local brain metastases (BM) in a large single-institution series of patients receiving stereotactic radiosurgery (SRS). Recursive partitioning analysis was used to potentially identify a class of patients with durable lesion control characteristics. METHODS: A retrospective SRS database containing baseline characteristics, treatment details, and follow-up data of newly diagnosed patients with 1-3 BM (on magnetic resonance imaging) treated with linear accelerator-based SRS was created. Three study endpoints were used: time to progression (primary endpoint, individual lesion progression; n = 536), time to first progression (secondary endpoint, first lesion progression on an individual patient basis; n = 380), and overall survival (secondary endpoint; n = 380). Recursive partitioning analysis (RPA) was performed to identify predictors of time to progression. RESULTS: Multivariable analysis demonstrated that lesion aspect/phenotype and radiotherapy schedule were independent factors associated with both progression outcomes. Presence of tumor necrosis was found to be associated with a significant hazard of progression (hazard ratio >3), whereas use of the most intense radiotherapy fractionation schedule (21 Gy in one fraction) was associated with significant reductions in progression (hazard ratio <0.3). RPA using SRS dose and lesion aspect/phenotype was created and described three distinct prognostic groups. CONCLUSIONS: RPA of a large retrospective database of patients receiving SRS confirmed previous observations regarding the importance of SRS dose and lesion aspect/phenotype in lesion control and overall survival. The SRS lesion analysis may help to stratify future clinical trials and better define patient care options and prognosis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".