HOMEPRODUCTSCOMPANYCONTACTFAQResearchDictionaryPharmaSign Up FREE or Login

Impact of statistical learning methods on the predictive power of multivariate normal tissue complication probability models.

AbstractPURPOSE:
To study the impact of different statistical learning methods on the prediction performance of multivariate normal tissue complication probability (NTCP) models.
METHODS AND MATERIALS:
In this study, three learning methods, stepwise selection, least absolute shrinkage and selection operator (LASSO), and Bayesian model averaging (BMA), were used to build NTCP models of xerostomia following radiotherapy treatment for head and neck cancer. Performance of each learning method was evaluated by a repeated cross-validation scheme in order to obtain a fair comparison among methods.
RESULTS:
It was found that the LASSO and BMA methods produced models with significantly better predictive power than that of the stepwise selection method. Furthermore, the LASSO method yields an easily interpretable model as the stepwise method does, in contrast to the less intuitive BMA method.
CONCLUSIONS:
The commonly used stepwise selection method, which is simple to execute, may be insufficient for NTCP modeling. The LASSO method is recommended.
AuthorsCheng-Jian Xu, Arjen van der Schaaf, Cornelis Schilstra, Johannes A Langendijk, Aart A van't Veld
JournalInternational journal of radiation oncology, biology, physics (Int J Radiat Oncol Biol Phys) Vol. 82 Issue 4 Pg. e677-84 (Mar 15 2012) ISSN: 1879-355X [Electronic] United States
PMID22245199 (Publication Type: Journal Article, Research Support, Non-U.S. Gov't)
CopyrightCopyright © 2012 Elsevier Inc. All rights reserved.
Topics
  • Adult
  • Aged
  • Aged, 80 and over
  • Algorithms
  • Bayes Theorem
  • Confounding Factors, Epidemiologic
  • Female
  • Head and Neck Neoplasms (radiotherapy)
  • Humans
  • Logistic Models
  • Male
  • Middle Aged
  • Models, Statistical
  • Organs at Risk (radiation effects)
  • Probability Learning
  • Radiotherapy, Conformal (methods)
  • Xerostomia (etiology)

Join CureHunter, for free Research Interface BASIC access!

Take advantage of free CureHunter research engine access to explore the best drug and treatment options for any disease. Find out why thousands of doctors, pharma researchers and patient activists around the world use CureHunter every day.
Realize the full power of the drug-disease research graph!


Choose Username:
Email:
Password:
Verify Password:
Enter Code Shown: