Variable Interaction Networks in Medical Data

Variable Interaction Networks in Medical Data

Stephan M. Winkler (Heuristic and Evolutionary Algorithms Laboratory, Bioinformatics Research Group, University of Applied Sciences Upper Austria, Hagenberg, Austria), Gabriel Kronberger (Heuristic and Evolutionary Algorithms Laboratory, Bioinformatics Research Group, University of Applied Sciences Upper Austria, Hagenberg, Austria), Michael Affenzeller (Heuristic and Evolutionary Algorithms Laboratory, Bioinformatics Research Group, University of Applied Sciences Upper Austria, Hagenberg, Austria) and Herbert Stekel (Central Laboratory, General Hospital Linz, Linz, Austria)
DOI: 10.4018/ijphim.2013070101
OnDemand PDF Download:
$30.00
List Price: $37.50

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.
Article Preview

2. Machine Learning Methods Applied

In this section we describe the modeling methods applied for identifying estimation models for medical variables and cancer diagnoses: On the one hand we apply hybrid modeling using machine learning algorithms and evolutionary algorithms for parameter optimization and feature selection (as described in Section 2.1), on the other hand we use genetic programming (as described in Section 2.2). In Winkler et al. (2011), for example, these methods have also been described in detail.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 2 Issues (2017)
Volume 4: 2 Issues (2016)
Volume 3: 2 Issues (2015)
Volume 2: 2 Issues (2014)
Volume 1: 2 Issues (2013)
View Complete Journal Contents Listing