Decision tree based fuzzy classifier of H1 magnetic resonance spectra from cerebrospinal fluid samples

https://doi.org/10.1016/j.fss.2011.01.003Get rights and content

Abstract

This paper presents a method for classifying cerebrospinal fluid (CSF) samples studied by proton magnetic resonance spectroscopy (H1 MRS) into clinical subgroups by means of a fuzzy classifier. The method focuses on the analysis of a low signal-to-noise region of the spectra and is designed to use a small number of samples because sampling can only be done through an invasive technique. The proposed method involves the fusion of classifiers based on decision trees designed using fuzzy techniques. The fusion step was carried out by ordered weighted averaging (OWA) operators. The quality of the proposed classifier was evaluated by efficiency and robustness quality indexes using a method based on a cross-validation technique. Results show excellent classification levels and satisfactory robustness in both training and test sets.

References (48)

  • J.D. Bell et al.

    NMR studies of body fluids

    NMR Biomed.

    (1989)
  • U.F.H. Engelke et al.

    NMR spectroscopy of aminoacylase 1 deficiency, a novel inborn error of metabolism

    NMR Biomed.

    (2008)
  • N.W. Lutz et al.

    Inflammatory multiple-sclerosis plaques generate characteristic metabolic profiles in cerebrospinal fluid

    PLoS ONE

    (2007)
  • M. Coen et al.

    Proton nuclear magnetic resonance-based metabonomics for rapid diagnosis of meningitis and ventriculitis

    Clin. Infect. Dis.

    (2005)
  • F.Y. Ghauri et al.

    NMR spectroscopy of human post mortem cerebrospinal fluid: distinction of Alzheimer's disease from control using pattern recognition and statistics

    NMR Biomed.

    (1993)
  • V.G. Dunne et al.

    Metabolites from cerebrospinal fluid in aneurysmal subarachnoid haemorrhage correlate with vasospasm and clinical outcome: a pattern-recognition 1H NMR study

    NMR Biomed.

    (2005)
  • R.A. Wevers et al.

    Standardized method for high-resolution 1H-NMR of cerebrospinal fluid

    Clin. Chem.

    (1995)
  • J. Luts et al.

    Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectra

    Magn. Reson. Med.

    (2008)
  • J.R. Quinlan

    Induction on decision trees

    Mach. Learn.

    (1986)
  • S.R. Safavian et al.

    A survey of decision tree classifier methodology

    IEEE Trans. Syst. Man Cybern.

    (1991)
  • X. Wu et al.

    Top 10 algorithms in data mining

    Knowl. Inf. Syst.

    (2008)
  • L. Rokach et al.

    Top-down induction of decision trees

    IEEE Trans. Syst Man Cybern. Part C Appl. Rev.

    (2005)
  • J.R. Quinlan

    C4.5: Programs for Machine Learning

    (1993)
  • L. Breiman et al.

    Classification and Regression Trees

    (1984)
  • Cited by (6)

    • NMR and pattern recognition methods in metabolomics: From data acquisition to biomarker discovery: A review

      2012, Analytica Chimica Acta
      Citation Excerpt :

      Several significant changes in metabolites concentration in MScl patients were found, namely elevated levels of 2-aminobutyrate, 1,3-dimethylurrate, glutamate and acetate, and reduced levels of oxaloacetate, citrate, alanine and 3-hydroxybutyrate. Another study applying pattern recognition, namely decision-tree-fuzzy classifier, by Aymerich et al. [246] investigated differences in metabolic profile of RR-MScl (8 patients), PP-MScl (7 patients) and patients with other neurological disease (7 individuals. They focus on spectral regions with poor signal-to-noise ratio (i.e. between 6.0 and 9.7 ppm).

    • IIVFDT: Ignorance functions based interval-valued fuzzy decision tree with genetic tuning

      2012, International Journal of Uncertainty, Fuzziness and Knowldege-Based Systems
    View full text