Abstract
Purpose: To determine whether a machine learning approach optimizes survival estimation for patients with symptomatic bone metastases (SBM), we developed the Bone Metastases Ensemble Trees for Survival (BMETS) to predict survival using 27 prognostic covariates. To establish its relative clinical utility, we compared BMETS with 2 simpler Cox regression models used in this setting. Methods and Materials: For 492 bone sites in 397 patients evaluated for palliative radiation therapy (RT) for SBM from January 2007 to January 2013, data for 27 clinical variables were collected. These covariates and the primary outcome of time from consultation to death were used to build BMETS using random survival forests. We then performed Cox regressions as per 2 validated models: Chow's 3-item (C-3) and Westhoff's 2-item (W-2) tools. Model performance was assessed using cross-validation procedures and measured by time-dependent area under the curve (tAUC) for all 3 models. For temporal validation, a separate data set comprised of 104 bone sites treated in 85 patients in 2018 was used to estimate tAUC from BMETS. Results: Median survival was 6.4 months. Variable importance was greatest for performance status, blood cell counts, recent systemic therapy type, and receipt of concurrent nonbone palliative RT. tAUC at 3, 6, and 12 months was 0.83, 0.81, and 0.81, respectively, suggesting excellent discrimination of BMETS across postconsultation time points. BMETS outperformed simpler models at each time, with respective tAUC at each time of 0.78, 0.76, and 0.74 for the C-3 model and 0.80, 0.78, and 0.77 for the W-2 model. For the temporal validation set, respective tAUC was similarly high at 0.86, 0.82, and 0.78. Conclusions: For patients with SBM, BMETS improved survival predictions versus simpler traditional models. Model performance was maintained when applied to a temporal validation set. To facilitate clinical use, we developed a web platform for data entry and display of BMETS-predicted survival probabilities.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 554-563 |
| Number of pages | 10 |
| Journal | International Journal of Radiation Oncology Biology Physics |
| Volume | 108 |
| Issue number | 3 |
| DOIs | |
| State | Published - Nov 1 2020 |
| Externally published | Yes |
Bibliographical note
Funding Information:Disclosures: S.A., J.W., T.S., T.M., and T.D. are employed by the Johns Hopkins School of Medicine and S.Z. by the School of Public Health. S.A. reports grant from Elekta, nonfinancial support from Angiodynamics, and personal fees from Allegheny Health Network (AHN), all outside the submitted work. J.W. reports personal fees from AHN and is an editor of the International Journal of Radiation Oncology, Biology, Physics, outside the submitted work. T.S. reports nonfinancial support from EMD Serono and personal fees from Allergan, outside the submitted work. T.M. reports a grant from the Radiation Oncology Institute and is chairman of the board and a stockholder of a health-related start-up, Oncospace, Inc., outside the submitted work. T.D. is president of the American Society for Radiation Oncology and reports nonfinancial support from Elekta, Sanofi-Aventis, and Varian, Inc; outside the submitted work.
Funding Information:
This work was supported by a grant from the National Institutes of Health ( 5KL2TR001077 ) to S.A.
Publisher Copyright:
© 2020 Elsevier Inc.
