Effects of SVM parameter optimization on discrimination and calibration for post-procedural PCI mortality

Authors:
Michael E. Matheny;Frederic S. Resnic;Nipun Arora;Lucila Ohno-Machado
Affiliations:
Decision Systems Group, Brigham & Women's Hospital, 75 Francis Street, Boston, MA 02115, USA and Harvard-MIT Division of Health Sciences & Technology, Cambridge, MA, USA and Division of General Me ...;Decision Systems Group, Brigham & Women's Hospital, 75 Francis Street, Boston, MA 02115, USA and Harvard-MIT Division of Health Sciences & Technology, Cambridge, MA, USA and Division of Cardiovasc ...;Division of Cardiovascular Medicine, Brigham & Women's Hospital, Boston, MA, USA;Decision Systems Group, Brigham & Women's Hospital, 75 Francis Street, Boston, MA 02115, USA and Harvard-MIT Division of Health Sciences & Technology, Cambridge, MA, USA
Venue:
Journal of Biomedical Informatics
Year:
2007

Citing 16
Cited 3

The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
Fast training of support vector machines using sequential minimal optimization

Advances in kernel methods
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Choosing Multiple Parameters for Support Vector Machines

Machine Learning
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
Radius margin bounds for support vector machines with the RBF kernel

Neural Computation
Bias-Variance Analysis of Support Vector Machines for the Development of SVM-Based Ensemble Methods

The Journal of Machine Learning Research
Support vector machine classification on the web

Bioinformatics
A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis

Bioinformatics
Gradient-Based Adaptation of General Gaussian Kernels

Neural Computation
Discrimination and calibration of mortality risk prediction models in interventional cardiology

Journal of Biomedical Informatics - Special issue: Clinical machine learning
2006 Special issue: Machine learning in soil classification

Neural Networks - 2006 special issue: Earth sciences and environmental applications of computational intelligence
Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers

Artificial Intelligence in Medicine
Evolutionary tuning of multiple SVM parameters

Neurocomputing
Comparing support vector machines with Gaussian kernels to radialbasis function classifiers

IEEE Transactions on Signal Processing

Guest Editorial: Intelligent data analysis in biomedicine

Journal of Biomedical Informatics
Predicting the probability of survival in intensive care unit patients from a small number of variables and training examples

Artificial Intelligence in Medicine
Learning predictive models that use pattern discovery-A bootstrap evaluative approach applied in organ functioning sequences

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Support vector machines (SVM) have become popular among machine learning researchers, but their applications in biomedicine have been somewhat limited. A number of methods, such as grid search and evolutionary algorithms, have been utilized to optimize model parameters of SVMs. The sensitivity of the results to changes in optimization methods has not been investigated in the context of medical applications. In this study, radial-basis kernel SVM and polynomial kernel SVM mortality prediction models for percutaneous coronary interventions were optimized using (a) mean-squared error, (b) mean cross-entropy error, (c) the area under the receiver operating characteristic, and (d) the Hosmer-Lemeshow goodness-of-fit test (HL @g^2). A threefold cross-validation inner and outer loop method was used to select the best models using the training data, and evaluations were based on previously unseen test data. The results were compared to those produced by logistic regression models optimized using the same indices. The choice of optimization parameters had a significant impact on performance in both SVM kernel types.