Nonlinear Kernel-Based Approaches for Predicting Normal Tissue Toxicities
ABSTRACT Since the early demonstration of the curative potential of radiation therapy for tumor sterilization, normal tissue toxicity continues to be dose limiting. Accurate prediction of patientÂ¿s complication risk would allow personalization of treatment planning decisions. Nonlinear kernel methods can provide a robust framework for learning complex interactions between observed toxicities and treatment, anatomical, and patient-related variables. However, proper application of these powerful methods would require better understanding of a high-dimensional feature space that is spanned by all these variables. In this work, we investigate methods for visualization of this high-dimensional space and compare different approaches for extracting discriminant features. Our preliminary results demonstrate that principle component analysis is a valuable tool for visualizing high dimensional data and for determining proper kernel type. In addition, variable selection based on resampling methods within the logistic regression framework seemed to yield improved prediction performance compared to the recursive-feature elimination method.
- SourceAvailable from: Joseph O Deasy[Show abstract] [Hide abstract]
ABSTRACT: Radiotherapy outcomes are determined by complex interactions between physical and biological factors, reflecting both treatment conditions and underlying genetics. Recent advances in radiotherapy and biotechnology provide new opportunities and challenges for predicting radiation-induced toxicities, particularly radiation pneumonitis (RP), in lung cancer patients. In this work, we utilize datamining methods based on machine learning to build a predictive model of lung injury by retrospective analysis of treatment planning archives. In addition, biomarkers for this model are extracted from a prospective clinical trial that collects blood serum samples at multiple time points. We utilize a 3-way proteomics methodology to screen for differentially expressed proteins that are related to RP. Our preliminary results demonstrate that kernel methods can capture nonlinear dose-volume interactions, but fail to address missing biological factors. Our proteomics strategy yielded promising protein candidates, but their role in RP as well as their interactions with dose-volume metrics remain to be determined.BioMed Research International 02/2009; 2009(1110-7243):892863. DOI:10.1155/2009/892863 · 2.71 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Radiation-induced lung injury, radiation pneumonitis (RP), is a potentially fatal side-effect of thoracic radiation therapy. In this work, using an ensemble of support vector machines (SVMs), we build a binary RP risk model from clinical and dosimetric parameters. Patient/treatment data is partitioned into balanced subsets to prevent model bias. Forward feature selection, maximizing the area under the curve (AUC) for a cross-validated receiver operating characteristic (ROC) curve, is performed on each subset. Model parameter selection and construction occurs concurrently via alternating SVM and gradient descent steps to minimize estimated generalization error. We show that an ensemble classifier with a mean fusion function, five component SVMs, and limit of five features per classifier exhibits a mean AUC of 0.818—an improvement over previous SVM models of RP risk.Neurocomputing 06/2010; 73(10-12-73):1861-1867. DOI:10.1016/j.neucom.2009.09.023 · 2.01 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Lung cancer patients who receive radiotherapy as part of their treatment are at risk radiation-induced lung injury known as radiation pneumonitis (RP). RP is a potentially fatal side effect to treatment. Hence, new methods are needed to guide physicians to prescribe targeted therapy dosage to patients at high risk of RP. Several predictive models based on traditional statistical methods and machine learning techniques have been reported, however, no guidance to variation in performance has not been provided to date. Therefore, in this study, we compare several widely used classification algorithms in the machine learning field are used to distinguish between different risk groups of RP. The performance of these classification algorithms is evaluated in conjunction with several feature selection strategy and the impact of the feature selection on performance is further evaluated.International Conference on Machine Learning and Applications, ICMLA 2009, Miami Beach, Florida, USA, December 13-15, 2009; 01/2009