Predicting Outcomes of Septic Shock Patients Using Feature Selection Based on Soft Computing Techniques

  • André S. Fialho
  • Federico Cismondi
  • Susana M. Vieira
  • João M. C. Sousa
  • Shane R. Reti
  • Michael D. Howell
  • Stan N. Finkelstein
Part of the Communications in Computer and Information Science book series (CCIS, volume 81)

Abstract

This paper proposes the application of new knowledge based methods to a septic shock patient database. It uses wrapper methods (bottom-up tree search or ant feature selection) to reduce the number of features. Fuzzy and neural modeling are used for classification. The goal is to estimate, as accurately as possible, the outcome (survived or deceased) of these septic shock patients. Results show that the approaches presented outperform any previous solutions, specifically in terms of sensitivity.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    American College of Chest Physicians/Society of Critical Care Medicine Consensus Conference: Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. Crit. Care Med. (20), 864–874 (1992)Google Scholar
  2. 2.
    Burchardi, H., Schneider, H.: Economic aspects of severe sepsis: a review of intensive care unit costs, cost of illness and cost effectiveness of therapy. Pharmacoeconomics 22(12), 793–813 (2004)CrossRefGoogle Scholar
  3. 3.
    Paetza, J., Arlt, B., Erz, K., Holzer, K., Brause, R., Hanisch, E.: Data quality aspects of a database for abdominal septic shock patients. Computer Methods and Programs in Biomedicine 75, 23–30 (2004)CrossRefGoogle Scholar
  4. 4.
    Paetza, J.: Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions. Artificial Intelligence in Medicine 28, 207–230 (2003)CrossRefGoogle Scholar
  5. 5.
    Mendonça, L.F., Vieira, S.M., Sousa, J.M.C.: Decision tree search methods in fuzzy modeling and classification. International Journal of Approximate Reasoning 44(2), 106–123 (2007)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Kuncheva, L.I.: Fuzzy Classifier Design. Springer, Heidelberg (2000)MATHGoogle Scholar
  7. 7.
    van den Berg, J., Kaymak, U., van den Bergh, W.M.: Fuzzy classification using probability-based rule weighting. In: Proceedings of the 2002 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2002, vol. 2, pp. 991–996 (2002)Google Scholar
  8. 8.
    Takagi, T., Sugeno, M.: Fuzzy identification of systems and its applications to modelling and control. IEEE Transactions on Systems, Man and Cybernetics 15(1), 116–132 (1985)MATHGoogle Scholar
  9. 9.
    Sugeno, M., Yasukawa, T.: A fuzzy-logic-based approach to qualitative modeling. IEEE Transactions on Fuzzy Systems 1(1), 7–31 (1993)CrossRefGoogle Scholar
  10. 10.
    Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice-Hall, Upper Saddle River (2008)Google Scholar
  11. 11.
    Jensen, R., Shen, Q.: Are more features better? a response to attributes reduction using fuzzy rough sets. IEEE Transactions on Fuzzy Systems 17(6), 1456–1458 (2009)CrossRefGoogle Scholar
  12. 12.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003)MATHCrossRefGoogle Scholar
  13. 13.
    Vieira, S.M., Mendonça, L., Sousa, J.M.C.: Modified regularity criterion in dynamic fuzzy modeling applied to industrial processes. In: Proc. of 2005 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2005, Reno, Nevada, May 2005, pp. 483–488 (2005)Google Scholar
  14. 14.
    Pekalska, E., Duin, R.P.W.: The Dissimilarity Representation for Pattern Recognition: Foundations And Applications (Machine Perception and Artificial Intelligence). World Scientific Publishing Co., Inc., River Edge (2005)MATHCrossRefGoogle Scholar
  15. 15.
    Dorigo, M., Birattari, M., Stützle, T.: Ant colony optimization. IEEE Computational Intelligence Magazine 1(4), 28–39 (2006)Google Scholar
  16. 16.
    Vieira, S.M., Sousa, J.M.C., Runkler, T.A.: Two cooperative ant colonies for feature selection using fuzzy models. Expert Systems with Applications 37(4), 2714–2723 (2010)CrossRefGoogle Scholar
  17. 17.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley–Interscience Publication, Chichester (2001)MATHGoogle Scholar
  18. 18.
    Hanisch, E., Brause, R., Arlt, B., Paetz, J., Holzer, K.: The MEDAN Database (2003), http://www.medan.de (accessed October 20, 2009)

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • André S. Fialho
    • 1
    • 2
    • 3
  • Federico Cismondi
    • 1
    • 2
    • 3
  • Susana M. Vieira
    • 1
    • 3
  • João M. C. Sousa
    • 1
    • 3
  • Shane R. Reti
    • 4
  • Michael D. Howell
    • 5
  • Stan N. Finkelstein
    • 1
    • 2
  1. 1.MIT–Portugal ProgramCambridgeUSA
  2. 2.Engineering Systems DivisionMassachusetts Institute of TechnologyCambridgeUSA
  3. 3.Instituto Superior Técnico, Dept. of Mechanical Engineering, CIS/IDMEC – LAETATechnical University of LisbonLisbonPortugal
  4. 4.Division of Clinical Informatics, Department of Medicine, Beth Israel Deaconess Medical CentreHarvard Medical SchoolBostonUSA
  5. 5.Silverman Institute for Healthcare Quality and Safety, Beth Israel Deaconess Medical CenterHarvard Medical SchoolBostonUSA

Personalised recommendations