Variable interaction networks in medical data

Stephan Winkler, Michael Affenzeller, Gabriel Kronberger, Michael Kommenda, Stefan Wagner, Witold Jacak, Herbert Stekel

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

2 Citations (Scopus)


In this paper we describe the identification of variable interaction networks in a medical data set. The main goal is to generate mathematical models for standard blood parameters as well as tumor markers using other available parameters in this data set. For each variable we identify those variables that are most relevant for modeling it; 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 tumor markers and cancer diagnoses: Linear regression and support vector machines (optimized using evolutionary algorithms) as well as genetic programming.

Original languageEnglish
Title of host publication24th European Modeling and Simulation Symposium, EMSS 2012
Number of pages6
Publication statusPublished - 2012
Event24th European Modeling and Simulation Symposium, EMSS 2012 - Vienna, Austria
Duration: 19 Sept 201221 Sept 2012

Publication series

Name24th European Modeling and Simulation Symposium, EMSS 2012


Conference24th European Modeling and Simulation Symposium, EMSS 2012


  • Data mining
  • Evolutionary algorithms
  • Medical data analysis
  • Variable interaction networks


Dive into the research topics of 'Variable interaction networks in medical data'. Together they form a unique fingerprint.

Cite this