Show simple item record

dc.contributor.authorGarde Martínez, Ainara
dc.contributor.authorVoss, Andreas
dc.contributor.authorCaminal Magrans, Pere
dc.contributor.authorBenito Vales, Salvador
dc.contributor.authorGiraldo Giraldo, Beatriz
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.contributor.otherInstitut de Bioenginyeria de Catalunya
dc.date.accessioned2013-04-25T11:51:52Z
dc.date.created2013
dc.date.issued2013
dc.identifier.citationGarde, A. [et al.]. SVM-based feature selection to optimize sensitivity–specificity balance applied to weaning. "Computers in biology and medicine", 2013, vol. 43, p. 533-540.
dc.identifier.issn0010-4825
dc.identifier.urihttp://hdl.handle.net/2117/18985
dc.description.abstractClassification algorithms with unbalanced data sets tend to produce high predictive accuracy over the majority class, but poor predictive accuracy over the minority class. This problem is very common in biomedical data mining. This paper introduces a Support Vector Machine(SVM)-based optimized features election method, to select the most relevant features and maintain an accurate and well-balanced sensitivity–specificity result between unbalanced groups. A new metric called the balance index(B) is defined to implement this optimization. The balance index measures the difference between the misclassified data within each class. The proposed optimized feature selection is applied to the classification of patients’ weaning trials from mechanical ventilation: patients with successful trials who were able to maintain spontaneous breathing after 48 h and patients who failed to maintain spontaneous breathing and were reconnected to mechanical ventilation after 30min. Patients are characterized through cardiac and respiratory signals, applying joint symbolic dynamic (JSD) analys is to cardiac interbeat and breath durations. First, the most suitable parameters (C þ ,C ,s)are selected to define the appropriate SVM. Then, the features election process is carried out with this SVM, to maintain B lower than 40%. The best result is obtained using 6 features with an accuracy of 80%, a B of 18.64%, a sensitivity of 74.36% and a specificity of 82.42%.
dc.format.extent8 p.
dc.language.isoeng
dc.publisherElsevier
dc.subjectÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
dc.subject.lcshBioinformatics
dc.subject.otherSupport vectormachines Balance index Sensitivity–specificity balance Cardiorespiratory interaction Joint symbolicdynamics Feature selection Weaning procedure
dc.titleSVM-based feature selection to optimize sensitivity–specificity balance applied to weaning
dc.typeArticle
dc.subject.lemacBioinformàtica
dc.contributor.groupUniversitat Politècnica de Catalunya. SISBIO - Senyals i Sistemes Biomèdics
dc.relation.publisherversionhttp://dx.doi.org/10.1016/j.compbiomed.2013.01.014
dc.rights.accessRestricted access - publisher's policy
drac.iddocument11882380
dc.description.versionPostprint (published version)
dc.date.lift10000-01-01
upcommons.citation.authorGarde, A.; Voss, A.; Caminal, P.; Benito, S.; Giraldo, B.
upcommons.citation.publishedtrue
upcommons.citation.publicationNameComputers in biology and medicine
upcommons.citation.volume43
upcommons.citation.startingPage533
upcommons.citation.endingPage540


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder