Effective use of FibroTest to generate decision trees in hepatitis C

Dana Lau-Corona, Luís Alberto Pineda, Héctor Hugo Avilés, Gabriela Gutiérrez-Reyes, Blanca Eugenia Farfan-Labonne, Rafael Núñez-Nateras, Alan Bonder, Rosalinda Martínez-García, Clara Corona-Lau, Marco A Olivera-Martinez, Maria Concepción Gutiérrez-Ruiz, Guillermo Robles-Díaz, David Kershenobich

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Aim: To assess the usefulness of FibroTest to forecast scores by constructing decision trees in patients with chronic hepatitis C. Methods: We used the C4.5 classification algorithm to construct decision trees with data from 261 patients with chronic hepatitis C without a liver biopsy. The FibroTest attributes of age, gender, bilirubin, apolipo-protein, haptoglobin, α2 macroglobulin, and γ-glutamyl transpeptidase were used as predictors, and the FibroTest score as the target. For testing, a 10-fold cross validation was used. Results: The overall classification error was 14.9% (accuracy 85.1%). FibroTest's cases with true scores of F0 and F4 were classified with very high accuracy (18/20 for F0, 9/9 for F0-1 and 92/96 for F4) and the largest confusion centered on F3. The algorithm produced a set of compound rules out of the ten classification trees and was used to classify the 261 patients. The rules for the classification of patients in F0 and F4 were effective in more than 75% of the cases in which they were tested. Conclusion: The recognition of clinical subgroups should help to enhance our ability to assess differences in fibrosis scores in clinical studies and improve our understanding of fibrosis progression.

Original languageEnglish (US)
Pages (from-to)2617-2622
Number of pages6
JournalWorld Journal of Gastroenterology
Volume15
Issue number21
DOIs
StatePublished - Jun 7 2009

Fingerprint

Decision Trees
Hepatitis C
Chronic Hepatitis C
Fibrosis
Macroglobulins
Haptoglobins
gamma-Glutamyltransferase
Bilirubin
Biopsy
Liver
Proteins

Keywords

  • C4.5 algorithm
  • Decision trees
  • FibroTest
  • Hepatitis C
  • Non-invasive biomarkers

ASJC Scopus subject areas

  • Gastroenterology

Cite this

Lau-Corona, D., Pineda, L. A., Avilés, H. H., Gutiérrez-Reyes, G., Farfan-Labonne, B. E., Núñez-Nateras, R., ... Kershenobich, D. (2009). Effective use of FibroTest to generate decision trees in hepatitis C. World Journal of Gastroenterology, 15(21), 2617-2622. https://doi.org/10.3748/wjg.15.2617

Effective use of FibroTest to generate decision trees in hepatitis C. / Lau-Corona, Dana; Pineda, Luís Alberto; Avilés, Héctor Hugo; Gutiérrez-Reyes, Gabriela; Farfan-Labonne, Blanca Eugenia; Núñez-Nateras, Rafael; Bonder, Alan; Martínez-García, Rosalinda; Corona-Lau, Clara; Olivera-Martinez, Marco A; Gutiérrez-Ruiz, Maria Concepción; Robles-Díaz, Guillermo; Kershenobich, David.

In: World Journal of Gastroenterology, Vol. 15, No. 21, 07.06.2009, p. 2617-2622.

Research output: Contribution to journalArticle

Lau-Corona, D, Pineda, LA, Avilés, HH, Gutiérrez-Reyes, G, Farfan-Labonne, BE, Núñez-Nateras, R, Bonder, A, Martínez-García, R, Corona-Lau, C, Olivera-Martinez, MA, Gutiérrez-Ruiz, MC, Robles-Díaz, G & Kershenobich, D 2009, 'Effective use of FibroTest to generate decision trees in hepatitis C', World Journal of Gastroenterology, vol. 15, no. 21, pp. 2617-2622. https://doi.org/10.3748/wjg.15.2617
Lau-Corona D, Pineda LA, Avilés HH, Gutiérrez-Reyes G, Farfan-Labonne BE, Núñez-Nateras R et al. Effective use of FibroTest to generate decision trees in hepatitis C. World Journal of Gastroenterology. 2009 Jun 7;15(21):2617-2622. https://doi.org/10.3748/wjg.15.2617
Lau-Corona, Dana ; Pineda, Luís Alberto ; Avilés, Héctor Hugo ; Gutiérrez-Reyes, Gabriela ; Farfan-Labonne, Blanca Eugenia ; Núñez-Nateras, Rafael ; Bonder, Alan ; Martínez-García, Rosalinda ; Corona-Lau, Clara ; Olivera-Martinez, Marco A ; Gutiérrez-Ruiz, Maria Concepción ; Robles-Díaz, Guillermo ; Kershenobich, David. / Effective use of FibroTest to generate decision trees in hepatitis C. In: World Journal of Gastroenterology. 2009 ; Vol. 15, No. 21. pp. 2617-2622.
@article{86c1f92ff30a46f6b92238a4dd1e8a3e,
title = "Effective use of FibroTest to generate decision trees in hepatitis C",
abstract = "Aim: To assess the usefulness of FibroTest to forecast scores by constructing decision trees in patients with chronic hepatitis C. Methods: We used the C4.5 classification algorithm to construct decision trees with data from 261 patients with chronic hepatitis C without a liver biopsy. The FibroTest attributes of age, gender, bilirubin, apolipo-protein, haptoglobin, α2 macroglobulin, and γ-glutamyl transpeptidase were used as predictors, and the FibroTest score as the target. For testing, a 10-fold cross validation was used. Results: The overall classification error was 14.9{\%} (accuracy 85.1{\%}). FibroTest's cases with true scores of F0 and F4 were classified with very high accuracy (18/20 for F0, 9/9 for F0-1 and 92/96 for F4) and the largest confusion centered on F3. The algorithm produced a set of compound rules out of the ten classification trees and was used to classify the 261 patients. The rules for the classification of patients in F0 and F4 were effective in more than 75{\%} of the cases in which they were tested. Conclusion: The recognition of clinical subgroups should help to enhance our ability to assess differences in fibrosis scores in clinical studies and improve our understanding of fibrosis progression.",
keywords = "C4.5 algorithm, Decision trees, FibroTest, Hepatitis C, Non-invasive biomarkers",
author = "Dana Lau-Corona and Pineda, {Lu{\'i}s Alberto} and Avil{\'e}s, {H{\'e}ctor Hugo} and Gabriela Guti{\'e}rrez-Reyes and Farfan-Labonne, {Blanca Eugenia} and Rafael N{\'u}{\~n}ez-Nateras and Alan Bonder and Rosalinda Mart{\'i}nez-Garc{\'i}a and Clara Corona-Lau and Olivera-Martinez, {Marco A} and Guti{\'e}rrez-Ruiz, {Maria Concepci{\'o}n} and Guillermo Robles-D{\'i}az and David Kershenobich",
year = "2009",
month = "6",
day = "7",
doi = "10.3748/wjg.15.2617",
language = "English (US)",
volume = "15",
pages = "2617--2622",
journal = "World Journal of Gastroenterology",
issn = "1007-9327",
publisher = "WJG Press",
number = "21",

}

TY - JOUR

T1 - Effective use of FibroTest to generate decision trees in hepatitis C

AU - Lau-Corona, Dana

AU - Pineda, Luís Alberto

AU - Avilés, Héctor Hugo

AU - Gutiérrez-Reyes, Gabriela

AU - Farfan-Labonne, Blanca Eugenia

AU - Núñez-Nateras, Rafael

AU - Bonder, Alan

AU - Martínez-García, Rosalinda

AU - Corona-Lau, Clara

AU - Olivera-Martinez, Marco A

AU - Gutiérrez-Ruiz, Maria Concepción

AU - Robles-Díaz, Guillermo

AU - Kershenobich, David

PY - 2009/6/7

Y1 - 2009/6/7

N2 - Aim: To assess the usefulness of FibroTest to forecast scores by constructing decision trees in patients with chronic hepatitis C. Methods: We used the C4.5 classification algorithm to construct decision trees with data from 261 patients with chronic hepatitis C without a liver biopsy. The FibroTest attributes of age, gender, bilirubin, apolipo-protein, haptoglobin, α2 macroglobulin, and γ-glutamyl transpeptidase were used as predictors, and the FibroTest score as the target. For testing, a 10-fold cross validation was used. Results: The overall classification error was 14.9% (accuracy 85.1%). FibroTest's cases with true scores of F0 and F4 were classified with very high accuracy (18/20 for F0, 9/9 for F0-1 and 92/96 for F4) and the largest confusion centered on F3. The algorithm produced a set of compound rules out of the ten classification trees and was used to classify the 261 patients. The rules for the classification of patients in F0 and F4 were effective in more than 75% of the cases in which they were tested. Conclusion: The recognition of clinical subgroups should help to enhance our ability to assess differences in fibrosis scores in clinical studies and improve our understanding of fibrosis progression.

AB - Aim: To assess the usefulness of FibroTest to forecast scores by constructing decision trees in patients with chronic hepatitis C. Methods: We used the C4.5 classification algorithm to construct decision trees with data from 261 patients with chronic hepatitis C without a liver biopsy. The FibroTest attributes of age, gender, bilirubin, apolipo-protein, haptoglobin, α2 macroglobulin, and γ-glutamyl transpeptidase were used as predictors, and the FibroTest score as the target. For testing, a 10-fold cross validation was used. Results: The overall classification error was 14.9% (accuracy 85.1%). FibroTest's cases with true scores of F0 and F4 were classified with very high accuracy (18/20 for F0, 9/9 for F0-1 and 92/96 for F4) and the largest confusion centered on F3. The algorithm produced a set of compound rules out of the ten classification trees and was used to classify the 261 patients. The rules for the classification of patients in F0 and F4 were effective in more than 75% of the cases in which they were tested. Conclusion: The recognition of clinical subgroups should help to enhance our ability to assess differences in fibrosis scores in clinical studies and improve our understanding of fibrosis progression.

KW - C4.5 algorithm

KW - Decision trees

KW - FibroTest

KW - Hepatitis C

KW - Non-invasive biomarkers

UR - http://www.scopus.com/inward/record.url?scp=67651152849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67651152849&partnerID=8YFLogxK

U2 - 10.3748/wjg.15.2617

DO - 10.3748/wjg.15.2617

M3 - Article

VL - 15

SP - 2617

EP - 2622

JO - World Journal of Gastroenterology

JF - World Journal of Gastroenterology

SN - 1007-9327

IS - 21

ER -