{"id":{"repo_id":"wustl","oai_identifier":"oai:openscholarship.wustl.edu:etd-1931"},"canonical_url":"https://search.dev.ndltd.org/etd/wustl/oai:openscholarship.wustl.edu:etd-1931","repository":{"repo_id":"wustl","name":"Washington University in St. Louis","base_url":"https://openscholarship.wustl.edu/do/oai/"},"display":{"title":"Ensemble Support Vector Machine Models of Radiation-Induced Lung Injury Risk","abstract":"Patients undergoing radiation therapy can develop a potentially fatal inflammation of the lungs known as radiation pneumonitis: RP). In practice, modeling RP factors is difficult because existing data are under-sampled and imbalanced. Support vector machines: SVMs), a class of statistical learning methods that implicitly maps data into a higher dimensional space, is one machine learning method that recently has been applied to the RP problem with encouraging results. In this thesis, we present and evaluate an ensemble SVM method of modeling radiation pneumonitis. The method internalizes kernel/model parameter selection into model building and enables feature scaling via Olivier Chapelle's method. We show that the ensemble method provides statistically significant increases to the cross-folded area under the receiver operating characteristic curve while maintaining model parsimony. Finally, we extend our model with John C. Platt's method to support non-binary outcomes in order to augment clinical relevancy.","abstract_html":"Patients undergoing radiation therapy can develop a potentially fatal inflammation of the lungs known as radiation pneumonitis: RP). In practice, modeling RP factors is difficult because existing data are under-sampled and imbalanced. Support vector machines: SVMs), a class of statistical learning methods that implicitly maps data into a higher dimensional space, is one machine learning method that recently has been applied to the RP problem with encouraging results. In this thesis, we present and evaluate an ensemble SVM method of modeling radiation pneumonitis. The method internalizes kernel/model parameter selection into model building and enables feature scaling via Olivier Chapelle's method. We show that the ensemble method provides statistically significant increases to the cross-folded area under the receiver operating characteristic curve while maintaining model parsimony. Finally, we extend our model with John C. Platt's method to support non-binary outcomes in order to augment clinical relevancy.","abstract_has_math":false,"creators":["Schiller, Todd"],"institution":null,"degree_name":"Master of Arts (MA)","degree_level":"Thesis","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Yixin Chen"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2009,"date_issued":"2009-01-01T08:00:00Z","date_published":"2009-01-01T08:00:00Z","updated_at":"2026-07-24T06:12:58Z","subjects":["support vector machine","radiation pneumonitis","feature selection","ensemble classifier","data imbalance"],"languages":["English (en)"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7936/K7XK8CKP"],"render_values":[{"text":"https://doi.org/10.7936/K7XK8CKP","href":"https://doi.org/10.7936/K7XK8CKP","code":true}]}]},"links":{"outbound_url":"https://openscholarship.wustl.edu/etd/932","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Yixin Chen"]},{"key":"dc:creator","label":"Author","values":["Schiller, Todd"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2013-05-25T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Arts (MA)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["support vector machine","radiation pneumonitis","feature selection","ensemble classifier","data imbalance"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English (en)"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openscholarship.wustl.edu/etd/932"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7936/K7XK8CKP"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Patients undergoing radiation therapy can develop a potentially fatal inflammation of the lungs known as radiation pneumonitis: RP). In practice, modeling RP factors is difficult because existing data are under-sampled and imbalanced. Support vector machines: SVMs), a class of statistical learning methods that implicitly maps data into a higher dimensional space, is one machine learning method that recently has been applied to the RP problem with encouraging results. In this thesis, we present and evaluate an ensemble SVM method of modeling radiation pneumonitis. The method internalizes kernel/model parameter selection into model building and enables feature scaling via Olivier Chapelle's method. We show that the ensemble method provides statistically significant increases to the cross-folded area under the receiver operating characteristic curve while maintaining model parsimony. Finally, we extend our model with John C. Platt's method to support non-binary outcomes in order to augment clinical relevancy."]},{"key":"dc:title","label":"Title","values":["Ensemble Support Vector Machine Models of Radiation-Induced Lung Injury Risk"]}]}],"canonical_facts":{"dc:contributor":["Yixin Chen"],"dc:creator":["Schiller, Todd"],"dc:date.available":["2013-05-25T07:00:00Z"],"dc:description.abstract":["Patients undergoing radiation therapy can develop a potentially fatal inflammation of the lungs known as radiation pneumonitis: RP). In practice, modeling RP factors is difficult because existing data are under-sampled and imbalanced. Support vector machines: SVMs), a class of statistical learning methods that implicitly maps data into a higher dimensional space, is one machine learning method that recently has been applied to the RP problem with encouraging results. In this thesis, we present and evaluate an ensemble SVM method of modeling radiation pneumonitis. The method internalizes kernel/model parameter selection into model building and enables feature scaling via Olivier Chapelle's method. We show that the ensemble method provides statistically significant increases to the cross-folded area under the receiver operating characteristic curve while maintaining model parsimony. Finally, we extend our model with John C. Platt's method to support non-binary outcomes in order to augment clinical relevancy."],"dc:identifier":["https://openscholarship.wustl.edu/etd/932"],"dc:identifier.doi":["https://doi.org/10.7936/K7XK8CKP"],"dc:language":["English (en)"],"dc:subject":["support vector machine","radiation pneumonitis","feature selection","ensemble classifier","data imbalance"],"dc:title":["Ensemble Support Vector Machine Models of Radiation-Induced Lung Injury Risk"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Arts (MA)"]},"updated_at":"2026-07-24T06:12:58Z"}