Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension

Bogdan Procopet, Vasile Mircea Cristea, Marie Angele Robic, Mircea Grigorescu, Paul Serban Agachi, Sophie Metivier, Jean Marie Peron, Janick Selves, Horia Stefanescu, Annalisa Berzigotti, Jean Pierre Vinel, Christophe Bureau

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Background: The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. Aims: To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. Methods: 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. Results: The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics. = 0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy. >. 80%), but were not statistically superior to liver stiffness alone. Conclusions: Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.

Original languageEnglish
Pages (from-to)411-416
Number of pages6
JournalDigestive and Liver Disease
Volume47
Issue number5
DOIs
Publication statusPublished - May 1 2015

Fingerprint

Artificial Liver
Portal Hypertension
Fibrosis
Esophageal and Gastric Varices
Liver
Serum
Elasticity Imaging Techniques
Neural Networks (Computer)
Venous Pressure

All Science Journal Classification (ASJC) codes

  • Hepatology
  • Gastroenterology

Cite this

Procopet, Bogdan ; Cristea, Vasile Mircea ; Robic, Marie Angele ; Grigorescu, Mircea ; Agachi, Paul Serban ; Metivier, Sophie ; Peron, Jean Marie ; Selves, Janick ; Stefanescu, Horia ; Berzigotti, Annalisa ; Vinel, Jean Pierre ; Bureau, Christophe. / Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension. In: Digestive and Liver Disease. 2015 ; Vol. 47, No. 5. pp. 411-416.
@article{8e7f7012fd214980b43ff99af4657973,
title = "Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension",
abstract = "Background: The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. Aims: To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. Methods: 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. Results: The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics. = 0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy. >. 80{\%}), but were not statistically superior to liver stiffness alone. Conclusions: Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.",
author = "Bogdan Procopet and Cristea, {Vasile Mircea} and Robic, {Marie Angele} and Mircea Grigorescu and Agachi, {Paul Serban} and Sophie Metivier and Peron, {Jean Marie} and Janick Selves and Horia Stefanescu and Annalisa Berzigotti and Vinel, {Jean Pierre} and Christophe Bureau",
year = "2015",
month = "5",
day = "1",
doi = "10.1016/j.dld.2015.02.001",
language = "English",
volume = "47",
pages = "411--416",
journal = "Digestive and Liver Disease",
issn = "1590-8658",
publisher = "Elsevier",
number = "5",

}

Procopet, B, Cristea, VM, Robic, MA, Grigorescu, M, Agachi, PS, Metivier, S, Peron, JM, Selves, J, Stefanescu, H, Berzigotti, A, Vinel, JP & Bureau, C 2015, 'Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension', Digestive and Liver Disease, vol. 47, no. 5, pp. 411-416. https://doi.org/10.1016/j.dld.2015.02.001

Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension. / Procopet, Bogdan; Cristea, Vasile Mircea; Robic, Marie Angele; Grigorescu, Mircea; Agachi, Paul Serban; Metivier, Sophie; Peron, Jean Marie; Selves, Janick; Stefanescu, Horia; Berzigotti, Annalisa; Vinel, Jean Pierre; Bureau, Christophe.

In: Digestive and Liver Disease, Vol. 47, No. 5, 01.05.2015, p. 411-416.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension

AU - Procopet, Bogdan

AU - Cristea, Vasile Mircea

AU - Robic, Marie Angele

AU - Grigorescu, Mircea

AU - Agachi, Paul Serban

AU - Metivier, Sophie

AU - Peron, Jean Marie

AU - Selves, Janick

AU - Stefanescu, Horia

AU - Berzigotti, Annalisa

AU - Vinel, Jean Pierre

AU - Bureau, Christophe

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Background: The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. Aims: To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. Methods: 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. Results: The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics. = 0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy. >. 80%), but were not statistically superior to liver stiffness alone. Conclusions: Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.

AB - Background: The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. Aims: To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. Methods: 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. Results: The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics. = 0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy. >. 80%), but were not statistically superior to liver stiffness alone. Conclusions: Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.

UR - http://www.scopus.com/inward/record.url?scp=84928824918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928824918&partnerID=8YFLogxK

U2 - 10.1016/j.dld.2015.02.001

DO - 10.1016/j.dld.2015.02.001

M3 - Article

VL - 47

SP - 411

EP - 416

JO - Digestive and Liver Disease

JF - Digestive and Liver Disease

SN - 1590-8658

IS - 5

ER -