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-Martínez MA, Gutiérrez-Ruiz MC, Robles-Díaz G, Kershenobich D. Effective use of FibroTest to generate decision trees in hepatitis C. World J Gastroenterol 2009; 15(21): 2617-2622 [PMID: 19496191 DOI: 10.3748/wjg.15.2617]
Corresponding Author of This Article
David Kershenobich, MD, PhD, Professor of Medicine, Chief, Department of Experimental Medicine, School of Medicine, UNAM, General Hospital of Mexico, Mexico City 06726, Mexico. kesdhipa@yahoo.com
Article-Type of This Article
Brief Articles
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
World J Gastroenterol. Jun 7, 2009; 15(21): 2617-2622 Published online Jun 7, 2009. doi: 10.3748/wjg.15.2617
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 Antonio Olivera-Martínez, Maria Concepción Gutiérrez-Ruiz, Guillermo Robles-Díaz, David Kershenobich
Dana Lau-Corona, Gabriela Gutiérrez-Reyes, Blanca Eugenia Farfan-Labonne, Rafael Núñez-Nateras, Alan Bonder, Rosalinda Martínez-García, Maria Concepción Gutiérrez-Ruiz, Guillermo Robles-Díaz, David Kershenobich, Department of Experimental Medicine, School of Medicine, Universidad Nacional Autonoma de Mexico, General Hospital of Mexico, Mexico City 06726, Mexico
Luís Alberto Pineda, Héctor Hugo Avilés, Department of Computer Sciences, Institute for Applied Mathematics and Systems, Universidad Nacional Autonoma de Mexico, Mexico City 01000, Mexico
Clara Corona-Lau, Marco Antonio Olivera-Martínez, Department of Gastroenterology, Lomas Altas Clinic, Mexico City 11950, Mexico
Author contributions: Lau-Corona D, Pineda LA, Gutiérrez-Reyes G, Farfan-Labonne BE, Gutiérrez-Ruiz MC, Robles-Díaz G and Kershenobich D designed the research; Pineda LA and Avilés HH performed and analyzed the decision trees; Olivera-Martínez MA and Kershenobich D were responsible for patient enrollment; Lau-Corona D, Núñez-Nateras R, Bonder A and Martínez-García R created and analyzed the patients database; Corona-Lau C performed the FibroTests; Lau-Corona D, Pineda LA and Kershenobich D wrote the manuscript.
Correspondence to: David Kershenobich, MD, PhD, Professor of Medicine, Chief, Department of Experimental Medicine, School of Medicine, UNAM, General Hospital of Mexico, Mexico City 06726, Mexico. kesdhipa@yahoo.com
Telephone: +52-55-56232673
Fax: +52-55-57617651
Received: March 17, 2009 Revised: May 6, 2009 Accepted: May 13, 2009 Published online: June 7, 2009
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, apolipoprotein, 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.
