Neonatal Infection Diagnosis Using Constructive Induction in Data Mining

  • Authors:

  • Jerzy W. Grzymala-Busse;Zdzislaw S. Hippe;Agnieszka Kordek;Teresa Mroczek;Wojciech Podraza

  • Affiliations:

  • Department of Electrical Engineering and Computer Science, University of Kansas, Lawrence, KS 66045, USA, and Institute of Computer Science, Polish Academy of Sciences, 01-237 Warsaw, Poland;Department of Expert Systems and Artificial Intelligence, University of Information Technology and Management, 35-225 Rzeszow, Poland;Department of Obstetrics and Perinatology, Pomeranian Medical University, 70-111 Szczecin, Poland;Department of Expert Systems and Artificial Intelligence, University of Information Technology and Management, 35-225 Rzeszow, Poland;Department of Medical Physics, Pomeranian Medical University, 70-111 Szczecin, Poland

  • Venue:
  • RSFDGrC '07 Proceedings of the 11th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents the results of our experiments on a data set describing neonatal infection. We used two main tools: the MLEM2 algorithm of rule induction and BeliefSEEKER system for generation of Bayesian nets and rule sets. Both systems are based on rough set theory. Our main objective was to compare the quality of diagnosis of cases from two testing data sets: with an additional attribute called PCT and without this attribute. The PCT attribute was computed using constructive induction. The best results were associated with the rule set induced by the MLEM2 algorithm and testing data set enhanced by constructive induction.