A hybrid algorithm for medical diagnosis

Camelia Vidrighin Bratu, Cristina Savin, Rodica Potolea

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

Abstract

Medical diagnosis and prognosis is an emblematic example for classification problems. Machine learning could provide invaluable support for automatically inferring diagnostic rules from descriptions of past cases, making the diagnosis process more objective and reliable. Since the problem involves both test and misclassification costs, we have analyzed ICET, the most prominent approach in the literature for complex cost problems. The hybrid algorithm tries to avoid the pitfalls of traditional greedy induction by performing a heuristic search in the space of possible decision trees through evolutionary mechanisms. Our implementation solves some of the problems of the initial ICET algorithm, proving it to be a viable solution for the problem considered.

Original languageEnglish (US)
Title of host publicationEUROCON 2007 - The International Conference on Computer as a Tool
PublisherIEEE Computer Society
Pages668-673
Number of pages6
ISBN (Print)142440813X, 9781424408139
DOIs
StatePublished - 2007
EventEUROCON 2007 - The International Conference on Computer as a Tool - Warsaw, Poland
Duration: Sep 9 2007Sep 12 2007

Publication series

NameEUROCON 2007 - The International Conference on Computer as a Tool

Other

OtherEUROCON 2007 - The International Conference on Computer as a Tool
CountryPoland
CityWarsaw
Period9/9/079/12/07

Keywords

  • Cost-sensitive learning
  • Hybrid algorithm
  • Medical diagnosis

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A hybrid algorithm for medical diagnosis'. Together they form a unique fingerprint.

  • Cite this

    Bratu, C. V., Savin, C., & Potolea, R. (2007). A hybrid algorithm for medical diagnosis. In EUROCON 2007 - The International Conference on Computer as a Tool (pp. 668-673). [4400571] (EUROCON 2007 - The International Conference on Computer as a Tool). IEEE Computer Society. https://doi.org/10.1109/EURCON.2007.4400571