skip to main content

SciTech ConnectSciTech Connect

Title: Support Vector Machine-Based Prediction of Local Tumor Control After Stereotactic Body Radiation Therapy for Early-Stage Non-Small Cell Lung Cancer

Background: Several prognostic factors for local tumor control probability (TCP) after stereotactic body radiation therapy (SBRT) for early stage non-small cell lung cancer (NSCLC) have been described, but no attempts have been undertaken to explore whether a nonlinear combination of potential factors might synergistically improve the prediction of local control. Methods and Materials: We investigated a support vector machine (SVM) for predicting TCP in a cohort of 399 patients treated at 13 German and Austrian institutions. Among 7 potential input features for the SVM we selected those most important on the basis of forward feature selection, thereby evaluating classifier performance by using 10-fold cross-validation and computing the area under the ROC curve (AUC). The final SVM classifier was built by repeating the feature selection 10 times with different splitting of the data for cross-validation and finally choosing only those features that were selected at least 5 out of 10 times. It was compared with a multivariate logistic model that was built by forward feature selection. Results: Local failure occurred in 12% of patients. Biologically effective dose (BED) at the isocenter (BED{sub ISO}) was the strongest predictor of TCP in the logistic model and also the most frequently selected input featuremore » for the SVM. A bivariate logistic function of BED{sub ISO} and the pulmonary function indicator forced expiratory volume in 1 second (FEV1) yielded the best description of the data but resulted in a significantly smaller AUC than the final SVM classifier with the input features BED{sub ISO}, age, baseline Karnofsky index, and FEV1 (0.696 ± 0.040 vs 0.789 ± 0.001, P<.03). The final SVM resulted in sensitivity and specificity of 67.0% ± 0.5% and 78.7% ± 0.3%, respectively. Conclusions: These results confirm that machine learning techniques like SVMs can be successfully applied to predict treatment outcome after SBRT. Improvements over traditional TCP modeling are expected through a nonlinear combination of multiple features, eventually helping in the task of personalized treatment planning.« less
 [1] ;  [2] ;  [3] ;  [4] ;  [5] ;  [6] ;  [7] ;  [8] ;  [9] ;  [10] ;  [11] ;  [12] ;  [13] ;  [14] ;  [1]
  1. Department of Radiation Oncology, University of Würzburg (Germany)
  2. (Germany)
  3. Department of Radiotherapy, Barmherzige Brüder Regensburg, Regensburg (Germany)
  4. Department of Radiation Oncology, Technische Universität Dresden (Germany)
  5. Department of Radiotherapy, Medical University of Vienna (Austria)
  6. Department of Radiotherapy, University Hospital Münster (Germany)
  7. Department of Radiation Oncology, Ludwigs-Maximilians-University Munich, München (Germany)
  8. Department of Radiation Oncology, RWTH Aachen University, Aachen (Germany)
  9. Department of Radiation Oncology, University Hospital Freiburg, Freiburg i Br (Germany)
  10. Department of Therapeutic Radiology and Oncology, Innsbruck Medical University (Austria)
  11. Department of Radiation Oncology, Friedrich-Alexander University Erlangen-Nuremberg, Erlangen (Germany)
  12. Department of Radiation Oncology, University Hospital Heidelberg (Germany)
  13. Department of Radiotherapy and Radiation Oncology, Philipps-University Marburg (Germany)
  14. Department of Radiation Oncology, Technische Universität München (Germany)
Publication Date:
OSTI Identifier:
Resource Type:
Journal Article
Resource Relation:
Journal Name: International Journal of Radiation Oncology, Biology and Physics; Journal Volume: 88; Journal Issue: 3; Other Information: Copyright (c) 2014 Elsevier Science B.V., Amsterdam, The Netherlands, All rights reserved.; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States