Reference Hub2
Variable Interaction Networks in Medical Data

Variable Interaction Networks in Medical Data

Stephan M. Winkler, Gabriel Kronberger, Michael Affenzeller, Herbert Stekel
Copyright: © 2013 |Volume: 1 |Issue: 2 |Pages: 16
ISSN: 2155-5621|EISSN: 2155-563X|EISBN13: 9781466634688|DOI: 10.4018/ijphim.2013070101
Cite Article Cite Article

MLA

Winkler, Stephan M., et al. "Variable Interaction Networks in Medical Data." IJPHIM vol.1, no.2 2013: pp.1-16. http://doi.org/10.4018/ijphim.2013070101

APA

Winkler, S. M., Kronberger, G., Affenzeller, M., & Stekel, H. (2013). Variable Interaction Networks in Medical Data. International Journal of Privacy and Health Information Management (IJPHIM), 1(2), 1-16. http://doi.org/10.4018/ijphim.2013070101

Chicago

Winkler, Stephan M., et al. "Variable Interaction Networks in Medical Data," International Journal of Privacy and Health Information Management (IJPHIM) 1, no.2: 1-16. http://doi.org/10.4018/ijphim.2013070101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this paper the authors describe the identification of variable interaction networks based on the analysis of medical data. The main goal is to generate mathematical models for medical parameters using other available parameters in this data set. For each variable the authors identify those features that are most relevant for modeling it; the relevance of a variable can in this context be defined via the frequency of its occurrence in models identified by evolutionary machine learning methods or via the decrease in modeling quality after removing it from the data set. Several data based modeling approaches implemented in HeuristicLab have been applied for identifying estimators for selected continuous as well as discrete medical variables and cancer diagnoses: Genetic programming, linear regression, k-nearest-neighbor regression, support vector machines (optimized using evolutionary algorithms), and random forests. In the empirical section of this paper the authors describe interaction networks identified for a medical data base storing data of more than 600 patients. The authors see that whatever modeling approach is used, it is possible to identify the most important influence factors and display those in interaction networks which can be interpreted without domain knowledge in machine learning or informatics in general.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.