Acute leukemia diagnosis aid using multicriteria fuzzy assignment methodology

N. Belacel, Ph Vincke, J. M. Scheiff, M. R. Boulassel

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

We recently developed a new multicriteria classification method called PROAFTN to help medical diagnosis. The aim of this paper is to present the application of the proposed method for the diagnosis of acute leukemia (AL). The implementation of PROAFTN was carried out on cytological data of 108 cases of AL, using the classification rules of French, American and British hematologists, and was then applied on an independent test set of 83 cases of AL. Forty-seven features, obtained by examining patients' bone-marrow smears with light microscope, defined each case. In order to determine the percentage of correct classifications for each subtype of AL, we compared our results with the clinical diagnosis given previously by the hematologist. 96.4% of the cases were correctly classified by the program, suggesting that the method yields good results in terms of discrimination between AL subtypes.

Original languageEnglish
Pages (from-to)145-151
Number of pages7
JournalComputer Methods and Programs in Biomedicine
Volume64
Issue number2
DOIs
Publication statusPublished - Feb 2001

    Fingerprint

Keywords

  • Acute leukemia
  • Classification
  • Computer-aided diagnosis
  • Fuzzy relations
  • Fuzzy sets

ASJC Scopus subject areas

  • Software

Cite this