Constructing binary decision trees for predicting Deep Venous Thrombosis

Christopher Nwosisi, Sung Hyuk Cha, Yoo Jung An, Charles C. Tappert, Evan Lipsitz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep Venous Thrombosis (DVT) is an intrinsic disease where blood clots form in a deep vein in the body. Since DVT has a high mortality rate, predicting it early is important. Decision trees are simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible. Here a genetic algorithm is used to construct decision trees of increased accuracy and efficiency compared to those constructed by the conventional ID3 or C4.5 decision tree building algorithms. Experimental results on two DVT datasets are presented and discussed.

Original languageEnglish (US)
Title of host publicationICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings
PagesV1121-V1124
DOIs
Publication statusPublished - Dec 16 2010
Event2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010 - San Juan, PR, United States
Duration: Oct 3 2010Oct 5 2010

Publication series

NameICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings
Volume1

Other

Other2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010
CountryUnited States
CitySan Juan, PR
Period10/3/1010/5/10

    Fingerprint

Keywords

  • Decision tree
  • Deep venous thrombosis
  • Genetic algorithm

ASJC Scopus subject areas

  • Software

Cite this

Nwosisi, C., Cha, S. H., An, Y. J., Tappert, C. C., & Lipsitz, E. (2010). Constructing binary decision trees for predicting Deep Venous Thrombosis. In ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings (pp. V1121-V1124). [5608901] (ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings; Vol. 1). https://doi.org/10.1109/ICSTE.2010.5608901