A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis

Jae Youn Cheong, Soon-Ho Um, Yeon Seok Seo, Seung Soo Shin, Rae Woong Park, Dong Joon Kim, Seong Gyu Hwang, Youn Jae Lee, Mong Cho, Jin Mo Yang, Young Bae Kim, Young Nyun Park, Sung Won Cho

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Background/Aims: The purpose of the current study was to develop a simple model for predicting cirrhosis in chronic viral hepatitis patients and to evaluate the usefulness of decision tree algorithms. Methodology: Serum markers of fibrosis were compared with the stage of fibrosis in liver biopsy specimens prospectively obtained from 526 subjects with chronic HBV and HCV infections (estimation set, 367; validation set, 159). Results: Univariate analysis revealed that age, bilirubin, platelet count, APRI, ALP, hyaluronic acid (HA), α2-macroglobulin, MMP-2, TIMP-1, and procollagen III N-terminal peptide (PIIINP) were significantly different between patients with (F4) and without cirrhosis (F0123). Multivariate logistic regression analysis identified platelet count, HA and PIIINP as independent predictors of cirrhosis. We categorized the individual variable into the most appropriate cut-off value by calculating the likelihood ratio for predicting cirrhosis and constructed a score system expressed by the following simple formula: PHP index = platelet score + HA score + PIIINP score. For predicting cirrhosis, the area under the receiver operating characteristic curve (AUROC) was 0.824 and 0.759 in the estimation and validation set, respectively. Using a cut-off score of 4, the presence of cirrhosis was predicted with high accuracy. The diagnostic performance of the PHP index was similar to decision tree algorithms (AUROC=0.819) for predicting liver cirrhosis, but more useful in clinical situations. Conclusions: Compared to a decision tree model, a simple score system using a categorized value based on a combination of platelet count, HA and PIIINP identified patients with liver cirrhosis with a higher clinical usability.

Original languageEnglish
Pages (from-to)2592-2597
Number of pages6
JournalHepato-Gastroenterology
Volume59
Issue number120
DOIs
Publication statusPublished - 2012 Nov 1

Fingerprint

Chronic Hepatitis
Fibrosis
Procollagen
Hyaluronic Acid
Decision Trees
Platelet Count
Liver Cirrhosis
Peptides
ROC Curve
Macroglobulins
Tissue Inhibitor of Metalloproteinase-1
Matrix Metalloproteinases
Bilirubin
Blood Platelets
Biomarkers
Logistic Models
Regression Analysis
Biopsy
Infection

Keywords

  • Chronic hepatitis
  • Decision tree algorithm
  • Hyaluronic acid
  • Liver fibrosis
  • Procollagen iii N-terminal peptide

ASJC Scopus subject areas

  • Hepatology
  • Gastroenterology

Cite this

A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis. / Cheong, Jae Youn; Um, Soon-Ho; Seo, Yeon Seok; Shin, Seung Soo; Park, Rae Woong; Kim, Dong Joon; Hwang, Seong Gyu; Lee, Youn Jae; Cho, Mong; Yang, Jin Mo; Kim, Young Bae; Park, Young Nyun; Cho, Sung Won.

In: Hepato-Gastroenterology, Vol. 59, No. 120, 01.11.2012, p. 2592-2597.

Research output: Contribution to journalArticle

Cheong, JY, Um, S-H, Seo, YS, Shin, SS, Park, RW, Kim, DJ, Hwang, SG, Lee, YJ, Cho, M, Yang, JM, Kim, YB, Park, YN & Cho, SW 2012, 'A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis', Hepato-Gastroenterology, vol. 59, no. 120, pp. 2592-2597. https://doi.org/10.5754/hge10157
Cheong, Jae Youn ; Um, Soon-Ho ; Seo, Yeon Seok ; Shin, Seung Soo ; Park, Rae Woong ; Kim, Dong Joon ; Hwang, Seong Gyu ; Lee, Youn Jae ; Cho, Mong ; Yang, Jin Mo ; Kim, Young Bae ; Park, Young Nyun ; Cho, Sung Won. / A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis. In: Hepato-Gastroenterology. 2012 ; Vol. 59, No. 120. pp. 2592-2597.
@article{7438380c8f8448ebb6f88c7a8a0de5be,
title = "A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis",
abstract = "Background/Aims: The purpose of the current study was to develop a simple model for predicting cirrhosis in chronic viral hepatitis patients and to evaluate the usefulness of decision tree algorithms. Methodology: Serum markers of fibrosis were compared with the stage of fibrosis in liver biopsy specimens prospectively obtained from 526 subjects with chronic HBV and HCV infections (estimation set, 367; validation set, 159). Results: Univariate analysis revealed that age, bilirubin, platelet count, APRI, ALP, hyaluronic acid (HA), α2-macroglobulin, MMP-2, TIMP-1, and procollagen III N-terminal peptide (PIIINP) were significantly different between patients with (F4) and without cirrhosis (F0123). Multivariate logistic regression analysis identified platelet count, HA and PIIINP as independent predictors of cirrhosis. We categorized the individual variable into the most appropriate cut-off value by calculating the likelihood ratio for predicting cirrhosis and constructed a score system expressed by the following simple formula: PHP index = platelet score + HA score + PIIINP score. For predicting cirrhosis, the area under the receiver operating characteristic curve (AUROC) was 0.824 and 0.759 in the estimation and validation set, respectively. Using a cut-off score of 4, the presence of cirrhosis was predicted with high accuracy. The diagnostic performance of the PHP index was similar to decision tree algorithms (AUROC=0.819) for predicting liver cirrhosis, but more useful in clinical situations. Conclusions: Compared to a decision tree model, a simple score system using a categorized value based on a combination of platelet count, HA and PIIINP identified patients with liver cirrhosis with a higher clinical usability.",
keywords = "Chronic hepatitis, Decision tree algorithm, Hyaluronic acid, Liver fibrosis, Procollagen iii N-terminal peptide",
author = "Cheong, {Jae Youn} and Soon-Ho Um and Seo, {Yeon Seok} and Shin, {Seung Soo} and Park, {Rae Woong} and Kim, {Dong Joon} and Hwang, {Seong Gyu} and Lee, {Youn Jae} and Mong Cho and Yang, {Jin Mo} and Kim, {Young Bae} and Park, {Young Nyun} and Cho, {Sung Won}",
year = "2012",
month = "11",
day = "1",
doi = "10.5754/hge10157",
language = "English",
volume = "59",
pages = "2592--2597",
journal = "Hepato-Gastroenterology",
issn = "0172-6390",
publisher = "H.G.E. Update Medical Publishing Ltd.",
number = "120",

}

TY - JOUR

T1 - A practical scoring system for predicting cirrhosis in patients with chronic viral hepatitis

AU - Cheong, Jae Youn

AU - Um, Soon-Ho

AU - Seo, Yeon Seok

AU - Shin, Seung Soo

AU - Park, Rae Woong

AU - Kim, Dong Joon

AU - Hwang, Seong Gyu

AU - Lee, Youn Jae

AU - Cho, Mong

AU - Yang, Jin Mo

AU - Kim, Young Bae

AU - Park, Young Nyun

AU - Cho, Sung Won

PY - 2012/11/1

Y1 - 2012/11/1

N2 - Background/Aims: The purpose of the current study was to develop a simple model for predicting cirrhosis in chronic viral hepatitis patients and to evaluate the usefulness of decision tree algorithms. Methodology: Serum markers of fibrosis were compared with the stage of fibrosis in liver biopsy specimens prospectively obtained from 526 subjects with chronic HBV and HCV infections (estimation set, 367; validation set, 159). Results: Univariate analysis revealed that age, bilirubin, platelet count, APRI, ALP, hyaluronic acid (HA), α2-macroglobulin, MMP-2, TIMP-1, and procollagen III N-terminal peptide (PIIINP) were significantly different between patients with (F4) and without cirrhosis (F0123). Multivariate logistic regression analysis identified platelet count, HA and PIIINP as independent predictors of cirrhosis. We categorized the individual variable into the most appropriate cut-off value by calculating the likelihood ratio for predicting cirrhosis and constructed a score system expressed by the following simple formula: PHP index = platelet score + HA score + PIIINP score. For predicting cirrhosis, the area under the receiver operating characteristic curve (AUROC) was 0.824 and 0.759 in the estimation and validation set, respectively. Using a cut-off score of 4, the presence of cirrhosis was predicted with high accuracy. The diagnostic performance of the PHP index was similar to decision tree algorithms (AUROC=0.819) for predicting liver cirrhosis, but more useful in clinical situations. Conclusions: Compared to a decision tree model, a simple score system using a categorized value based on a combination of platelet count, HA and PIIINP identified patients with liver cirrhosis with a higher clinical usability.

AB - Background/Aims: The purpose of the current study was to develop a simple model for predicting cirrhosis in chronic viral hepatitis patients and to evaluate the usefulness of decision tree algorithms. Methodology: Serum markers of fibrosis were compared with the stage of fibrosis in liver biopsy specimens prospectively obtained from 526 subjects with chronic HBV and HCV infections (estimation set, 367; validation set, 159). Results: Univariate analysis revealed that age, bilirubin, platelet count, APRI, ALP, hyaluronic acid (HA), α2-macroglobulin, MMP-2, TIMP-1, and procollagen III N-terminal peptide (PIIINP) were significantly different between patients with (F4) and without cirrhosis (F0123). Multivariate logistic regression analysis identified platelet count, HA and PIIINP as independent predictors of cirrhosis. We categorized the individual variable into the most appropriate cut-off value by calculating the likelihood ratio for predicting cirrhosis and constructed a score system expressed by the following simple formula: PHP index = platelet score + HA score + PIIINP score. For predicting cirrhosis, the area under the receiver operating characteristic curve (AUROC) was 0.824 and 0.759 in the estimation and validation set, respectively. Using a cut-off score of 4, the presence of cirrhosis was predicted with high accuracy. The diagnostic performance of the PHP index was similar to decision tree algorithms (AUROC=0.819) for predicting liver cirrhosis, but more useful in clinical situations. Conclusions: Compared to a decision tree model, a simple score system using a categorized value based on a combination of platelet count, HA and PIIINP identified patients with liver cirrhosis with a higher clinical usability.

KW - Chronic hepatitis

KW - Decision tree algorithm

KW - Hyaluronic acid

KW - Liver fibrosis

KW - Procollagen iii N-terminal peptide

UR - http://www.scopus.com/inward/record.url?scp=84872092331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872092331&partnerID=8YFLogxK

U2 - 10.5754/hge10157

DO - 10.5754/hge10157

M3 - Article

C2 - 23178625

AN - SCOPUS:84872092331

VL - 59

SP - 2592

EP - 2597

JO - Hepato-Gastroenterology

JF - Hepato-Gastroenterology

SN - 0172-6390

IS - 120

ER -