Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C

P. A. Maiellaro, R. Cozzolongo, Pasquale Marino

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Combined therapy using Interferon alfa (IFN) and Ribavirin (RIB) represents the standard treatment in patients with chronic hepatitis C. However, the percentage of responders to this regimen is still low, while its cost and side effects are elevated. Therefore, the possibility to predict patient's response to the above treatment is of paramount importance. The progress in the field of informatics and its large use for decision making has led to the development of novel techniques related to the so-called Artificial Intelligence, even including artificial neural networks (ANNs). In chronic viral hepatitis data are lacking. By means of an artificial neural network (ANN), 300 patients treated with IFN plus RIB were retrospectively analyzed with the aim to predict the response to the treatment. One hundred patients resulted responders and 200 non-responders at the end of treatment and during the follow up. For evaluating the prediction of treatment response, six ANNs with 16 neurons of input, an hidden layer with 7 neurons and an output layer with one neuron were utilized. The ANN model generated a positive predictive value (i.e. posterior probability of treatment response) ranging from 57% to 75% while the negative one (i.e. posterior probability of no response to treatment) was comprised between 52% and 71%. The highest level of diagnostic accuracy was 70%. In conclusion, ANNs appear to be a promising tool in the prediction of treatment response in patients with chronic hepatitis C. However, additional prospective studies are necessary to ultimately validate this predictive method.

Original languageEnglish
Pages (from-to)2101-2109
Number of pages9
JournalCurrent Pharmaceutical Design
Volume10
Issue number17
DOIs
Publication statusPublished - 2004

Fingerprint

Ribavirin
Chronic Hepatitis C
Interferons
Therapeutics
Neurons
Interferon-alpha
Informatics
Neural Networks (Computer)
Artificial Intelligence
Chronic Hepatitis
Decision Making
Prospective Studies
Costs and Cost Analysis

Keywords

  • Artificial neural network
  • Hepatitis C
  • Interferon
  • Prediction
  • Ribavirin

ASJC Scopus subject areas

  • Molecular Medicine
  • Pharmacology, Toxicology and Pharmaceutics(all)

Cite this

Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C. / Maiellaro, P. A.; Cozzolongo, R.; Marino, Pasquale.

In: Current Pharmaceutical Design, Vol. 10, No. 17, 2004, p. 2101-2109.

Research output: Contribution to journalArticle

@article{345452ce72284086ac4fc133579a6985,
title = "Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C",
abstract = "Combined therapy using Interferon alfa (IFN) and Ribavirin (RIB) represents the standard treatment in patients with chronic hepatitis C. However, the percentage of responders to this regimen is still low, while its cost and side effects are elevated. Therefore, the possibility to predict patient's response to the above treatment is of paramount importance. The progress in the field of informatics and its large use for decision making has led to the development of novel techniques related to the so-called Artificial Intelligence, even including artificial neural networks (ANNs). In chronic viral hepatitis data are lacking. By means of an artificial neural network (ANN), 300 patients treated with IFN plus RIB were retrospectively analyzed with the aim to predict the response to the treatment. One hundred patients resulted responders and 200 non-responders at the end of treatment and during the follow up. For evaluating the prediction of treatment response, six ANNs with 16 neurons of input, an hidden layer with 7 neurons and an output layer with one neuron were utilized. The ANN model generated a positive predictive value (i.e. posterior probability of treatment response) ranging from 57{\%} to 75{\%} while the negative one (i.e. posterior probability of no response to treatment) was comprised between 52{\%} and 71{\%}. The highest level of diagnostic accuracy was 70{\%}. In conclusion, ANNs appear to be a promising tool in the prediction of treatment response in patients with chronic hepatitis C. However, additional prospective studies are necessary to ultimately validate this predictive method.",
keywords = "Artificial neural network, Hepatitis C, Interferon, Prediction, Ribavirin",
author = "Maiellaro, {P. A.} and R. Cozzolongo and Pasquale Marino",
year = "2004",
doi = "10.2174/1381612043384240",
language = "English",
volume = "10",
pages = "2101--2109",
journal = "Current Pharmaceutical Design",
issn = "1381-6128",
publisher = "Bentham Science Publishers B.V.",
number = "17",

}

TY - JOUR

T1 - Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C

AU - Maiellaro, P. A.

AU - Cozzolongo, R.

AU - Marino, Pasquale

PY - 2004

Y1 - 2004

N2 - Combined therapy using Interferon alfa (IFN) and Ribavirin (RIB) represents the standard treatment in patients with chronic hepatitis C. However, the percentage of responders to this regimen is still low, while its cost and side effects are elevated. Therefore, the possibility to predict patient's response to the above treatment is of paramount importance. The progress in the field of informatics and its large use for decision making has led to the development of novel techniques related to the so-called Artificial Intelligence, even including artificial neural networks (ANNs). In chronic viral hepatitis data are lacking. By means of an artificial neural network (ANN), 300 patients treated with IFN plus RIB were retrospectively analyzed with the aim to predict the response to the treatment. One hundred patients resulted responders and 200 non-responders at the end of treatment and during the follow up. For evaluating the prediction of treatment response, six ANNs with 16 neurons of input, an hidden layer with 7 neurons and an output layer with one neuron were utilized. The ANN model generated a positive predictive value (i.e. posterior probability of treatment response) ranging from 57% to 75% while the negative one (i.e. posterior probability of no response to treatment) was comprised between 52% and 71%. The highest level of diagnostic accuracy was 70%. In conclusion, ANNs appear to be a promising tool in the prediction of treatment response in patients with chronic hepatitis C. However, additional prospective studies are necessary to ultimately validate this predictive method.

AB - Combined therapy using Interferon alfa (IFN) and Ribavirin (RIB) represents the standard treatment in patients with chronic hepatitis C. However, the percentage of responders to this regimen is still low, while its cost and side effects are elevated. Therefore, the possibility to predict patient's response to the above treatment is of paramount importance. The progress in the field of informatics and its large use for decision making has led to the development of novel techniques related to the so-called Artificial Intelligence, even including artificial neural networks (ANNs). In chronic viral hepatitis data are lacking. By means of an artificial neural network (ANN), 300 patients treated with IFN plus RIB were retrospectively analyzed with the aim to predict the response to the treatment. One hundred patients resulted responders and 200 non-responders at the end of treatment and during the follow up. For evaluating the prediction of treatment response, six ANNs with 16 neurons of input, an hidden layer with 7 neurons and an output layer with one neuron were utilized. The ANN model generated a positive predictive value (i.e. posterior probability of treatment response) ranging from 57% to 75% while the negative one (i.e. posterior probability of no response to treatment) was comprised between 52% and 71%. The highest level of diagnostic accuracy was 70%. In conclusion, ANNs appear to be a promising tool in the prediction of treatment response in patients with chronic hepatitis C. However, additional prospective studies are necessary to ultimately validate this predictive method.

KW - Artificial neural network

KW - Hepatitis C

KW - Interferon

KW - Prediction

KW - Ribavirin

UR - http://www.scopus.com/inward/record.url?scp=3042684526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042684526&partnerID=8YFLogxK

U2 - 10.2174/1381612043384240

DO - 10.2174/1381612043384240

M3 - Article

VL - 10

SP - 2101

EP - 2109

JO - Current Pharmaceutical Design

JF - Current Pharmaceutical Design

SN - 1381-6128

IS - 17

ER -