| Nonlinear support vector machine visualization for risk factor analysis using nomograms and localized radial basis function kernels. | |
| | |
MedLine Citation:
|
PMID: 18348954 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
Nonlinear classifiers, e.g., support vector machines (SVMs) with radial basis function (RBF) kernels, have been used widely for automatic diagnosis of diseases because of their high accuracies. However, it is difficult to visualize the classifiers, and thus difficult to provide intuitive interpretation of results to physicians. We developed a new nonlinear kernel, the localized radial basis function (LRBF) kernel, and new visualization system visualization for risk factor analysis (VRIFA) that applies a nomogram and LRBF kernel to visualize the results of nonlinear SVMs and improve the interpretability of results while maintaining high prediction accuracy. Three representative medical datasets from the University of California, Irvine repository and Statlog dataset-breast cancer, diabetes, and heart disease datasets-were used to evaluate the system. The results showed that the classification performance of the LRBF is comparable with that of the RBF, and the LRBF is easy to visualize via a nomogram. Our study also showed that the LRBF kernel is less sensitive to noise features than the RBF kernel, whereas the LRBF kernel degrades the prediction accuracy more when important features are eliminated. We demonstrated the VRIFA system, which visualizes the results of linear and nonlinear SVMs with LRBF kernels, on the three datasets. |
| | |
Authors:
|
Baek Hwan Cho; Hwanjo Yu; Jongshill Lee; Young Joon Chee; In Young Kim; Sun I Kim |
Related Documents
:
|
18525094 - Use of magnetic resonance imaging for detecting clinically and mammographically occult ... 17693574 - A public-domain image processing tool for automated quantification of fluorescence in s... 2657974 - Imaging techniques in breast cancer. 10417974 - Precocious puberty in a patient with indicanuria. 3955174 - Contact x-ray microscopy. a new technique for imaging cellular fine structure. 23612384 - Sickle cell-related bone marrow complications: the utility of diffusion-weighted magnet... |
Publication Detail:
|
Type: Journal Article; Research Support, Non-U.S. Gov't |
Journal Detail:
|
Title: IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society Volume: 12 ISSN: 1089-7771 ISO Abbreviation: IEEE Trans Inf Technol Biomed Publication Date: 2008 Mar |
Date Detail:
|
Created Date: 2008-03-19 Completed Date: 2008-05-14 Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9712259 Medline TA: IEEE Trans Inf Technol Biomed Country: United States |
Other Details:
|
Languages: eng Pagination: 247-56 Citation Subset: IM |
Affiliation:
|
Department of Biomedical Engineering, Hanyang University, Seoul 133-605, Korea. uranus@bme.hanyang.ac.kr |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Artificial Intelligence* Computer Graphics Diagnosis, Computer-Assisted / methods* Nonlinear Dynamics Pattern Recognition, Automated / methods* Prognosis Proportional Hazards Models* Risk Assessment / methods* Risk Factors User-Computer Interface* |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Interoperability of GADU in using heterogeneous grid resources for bioinformatics applications.
Next Document: Modeling real-time 3-d lung deformations for medical visualization.