Title | ||
---|---|---|
Modeling radiation-induced lung injury risk with an ensemble of support vector machines |
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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.neucom.2009.09.023 | Neurocomputing |
Keywords | Field | DocType |
feature selection,unbalanced data,support vector machine,mean auc,ensemble learning,component svms,binary rp risk model,radiation pneumonitis,model parameter selection,model bias,rp risk,radiation-induced lung injury risk,previous svm model,mean fusion function,ensemble classifier,roc curve,radiation therapy,receiver operator characteristic,generalization error,cross validation,side effect,gradient descent,area under the curve | Gradient descent,Receiver operating characteristic,Pattern recognition,Feature selection,Support vector machine,Artificial intelligence,Classifier (linguistics),Radiation-induced lung injury,Ensemble learning,Machine learning,Mathematics,Binary number | Journal |
Volume | Issue | ISSN |
73 | 10-12 | Neurocomputing |
Citations | PageRank | References |
2 | 0.45 | 24 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Todd W. Schiller | 1 | 47 | 3.16 |
Yixin Chen | 2 | 37 | 1.71 |
Issam El-Naqa | 3 | 528 | 36.31 |
Joseph O. Deasy | 4 | 105 | 14.98 |