Computing Importance Value of Medical Data Parameters in Classification Tasks and Its Evaluation Using Machine Learning Methods

  • Andrea Peterkova
  • Martin Nemeth
  • German Michalconok
  • Allan Bohm
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 763)

Abstract

This paper aims to evaluate the importance values of medical data parameters for further classification tasks. One of the steps of proposed methodology for analyzing medical data is initial data analysis. One part of the initial data analysis is to determine the importance rate of parameters in given data set. The reason behind this step is to provide overview of the parameters and the idea of choosing right predictors for classification task. Statistica 13 software provides a tool for determining the importance rate of each data parameter, which can be found in feature selection module. However, it is not always clear whether is the importance rate correct or not.

Keywords

Data analysis Classification Predictors 

Notes

Acknowledgments

This publication is the result of implementation of the project: “UNIVERSITY SCIENTIFIC PARK: CAMPUS MTF STU - CAMBO” (ITMS: 26220220179) supported by the Research & Development Operational Program funded by the EFRR.

This publication is the result of implementation of the project VEGA 1/0673/15: “Knowledge discovery for hierarchical control of technological and production processes” supported by the VEGA.

References

  1. 1.
    Geisser, S.: Predictive Inference: An Introduction. Chapman & Hall, New York (2016). ISBN 0-412-03471-9Google Scholar
  2. 2.
    Larose, D.T.: Discovering knowledge in data: an introduction to data mining. Wiley, Hoboken (2014)Google Scholar
  3. 3.
    Kotsiantis, S.B., Zaharakis, I., Pintelas, P.: Supervised machine learning: a review of classification techniques (2007)Google Scholar
  4. 4.
    Hernández, M.A., Stolfo, S.J.: Real-world data is dirty: data cleansing and the merge/purge problem. Data Mining Knowl. Disc. 2(1), 9–37 (1998)Google Scholar
  5. 5.
    Kim, W., et al.: A taxonomy of dirty data. Data Mining Knowl. Disc. 7(1), 81–99 (2003)Google Scholar
  6. 6.
    Meyer, D., Technikum Wien, F.H.: Support vector machines. The Interface to libsvm in package e1071 (2015)Google Scholar
  7. 7.
    Shmilovici, A.: Support vector machines. In: Data Mining and Knowledge Discovery Handbook, pp. 257–276. Springer (2005)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Andrea Peterkova
    • 1
  • Martin Nemeth
    • 1
  • German Michalconok
    • 1
  • Allan Bohm
    • 2
    • 3
  1. 1.Faculty of Materials Science and Technology in Trnava, Institute of Applied Informatics, Automation and MechatronicsSlovak University of Technology in BratislavaBratislavaSlovakia
  2. 2.Faculty of MedicineSlovak Medical University in BratislavaBratislavaSlovakia
  3. 3.Research Institute of AcademyBratislavaSlovakia

Personalised recommendations