Discrimination of malignant neutrophils of chronic myelogenous leukemia from normal neutrophils by support vector machine

Comput Biol Med. 2013 Sep;43(9):1192-5. doi: 10.1016/j.compbiomed.2013.06.004. Epub 2013 Jun 13.

Abstract

Malignant neutrophils of chronic myelogenous leukemia (CML) have similar antigen expression patterns compared to their normal counterparts, thus making the cells difficult to distinguish by clinical flow cytometry. In this study, we applied the support vector machine method to build a malignant neutrophil prediction model based on nine CML patients and nine healthy donors. This approach effectively differentiated between malignant and normal neutrophils with high specificity and sensitivity (≤95.80% and ≤95.30%, respectively). This approach may broaden the application of flow cytometry for differentiation between CML and normal neutrophils and become an important diagnostic tool in CML.

Keywords: ABL; Abelson murine leukemia; BCR; CML; FCS; Flow cytometry; Immunophenotyping; LIBLINEAR; Mature neutrophils; PCR; ROC; SVM; Support vector machine; breakpoint cluster region; chronic myelogenous leukemia; flow cytometry standard; polymerase chain reaction; receiver operating characteristic; support vector machine.

Publication types

  • Randomized Controlled Trial
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adult
  • Aged
  • Antigens, Neoplasm / biosynthesis*
  • Female
  • Flow Cytometry / methods*
  • Gene Expression Regulation, Leukemic*
  • Humans
  • Leukemia, Myelogenous, Chronic, BCR-ABL Positive* / blood
  • Leukemia, Myelogenous, Chronic, BCR-ABL Positive* / diagnosis
  • Leukemia, Myelogenous, Chronic, BCR-ABL Positive* / pathology
  • Male
  • Middle Aged
  • Neutrophils* / metabolism
  • Neutrophils* / pathology
  • Support Vector Machine*

Substances

  • Antigens, Neoplasm