Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients

Hsiang Yin Chen, Ta Cheng Chen, David I. Min, Gary W. Fischer, You Min Wu

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

The neural network (NN) is a technique using an artificial intelligent concept in predicting outcomes by using various input variables. Tacrolimus pharmacokinetics has wide inter- and intra-subject variability and it is often difficult to predict its blood concentrations by dose alone. The objectives of this study are to select the clinically significant variables and to predict the blood concentration of tacrolimus in liver transplant patients by NN combined with genetic algorithm (GA). A total of thirty-two adult liver transplant patients from the University of Iowa Hospitals and Clinics were selected and the patients' data were retrospectively collected. These patient were randomly assigned into two groups: either the training group (n = 10), or testing group (n = 22). A back propagation (BP) NN was developed which contained two hidden layers. A dynamic BP NN based on the time series concept was trained by using the current and previous data sets to predict the trough levels of tacrolimus. The mean of the NN prediction for tacrolimus blood levels was not significantly different from the observed value by a paired t-test comparison (12.05 ± 2.67 ng/ml vs. 12.14 ± 2.64 ng/ml, p = 0.80). The average difference of the testing sets between the observed and predicted levels was 1.74 ng/ml with a range from 0.08 to 5.26 ng/ml which is clinically acceptable range. Thirty-seven out of 44 data sets (84%) in the testing group were within 3.0 ng/ml of the observed values. This study demonstrated that tacrolimus blood concentrations are precisely predictable in liver transplant patients using patients variables by NN.

Original languageEnglish
Pages (from-to)50-56
Number of pages7
JournalTherapeutic Drug Monitoring
Volume21
Issue number1
DOIs
Publication statusPublished - Feb 1999

Fingerprint

Tacrolimus
Liver
Liver Transplantation
Blood
Genetic algorithms
Neural networks
Transplants
Backpropagation
Testing
Pharmacokinetics
Time series

Keywords

  • Neural network
  • Tacrolimus
  • Transplantation

ASJC Scopus subject areas

  • Toxicology
  • Health, Toxicology and Mutagenesis
  • Pharmacology
  • Biochemistry
  • Biochemistry, Genetics and Molecular Biology(all)
  • Pharmacology (medical)
  • Public Health, Environmental and Occupational Health

Cite this

Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients. / Chen, Hsiang Yin; Chen, Ta Cheng; Min, David I.; Fischer, Gary W.; Wu, You Min.

In: Therapeutic Drug Monitoring, Vol. 21, No. 1, 02.1999, p. 50-56.

Research output: Contribution to journalArticle

Chen, Hsiang Yin ; Chen, Ta Cheng ; Min, David I. ; Fischer, Gary W. ; Wu, You Min. / Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients. In: Therapeutic Drug Monitoring. 1999 ; Vol. 21, No. 1. pp. 50-56.
@article{694af8fb3dd7436981c978d11c6f1e5b,
title = "Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients",
abstract = "The neural network (NN) is a technique using an artificial intelligent concept in predicting outcomes by using various input variables. Tacrolimus pharmacokinetics has wide inter- and intra-subject variability and it is often difficult to predict its blood concentrations by dose alone. The objectives of this study are to select the clinically significant variables and to predict the blood concentration of tacrolimus in liver transplant patients by NN combined with genetic algorithm (GA). A total of thirty-two adult liver transplant patients from the University of Iowa Hospitals and Clinics were selected and the patients' data were retrospectively collected. These patient were randomly assigned into two groups: either the training group (n = 10), or testing group (n = 22). A back propagation (BP) NN was developed which contained two hidden layers. A dynamic BP NN based on the time series concept was trained by using the current and previous data sets to predict the trough levels of tacrolimus. The mean of the NN prediction for tacrolimus blood levels was not significantly different from the observed value by a paired t-test comparison (12.05 ± 2.67 ng/ml vs. 12.14 ± 2.64 ng/ml, p = 0.80). The average difference of the testing sets between the observed and predicted levels was 1.74 ng/ml with a range from 0.08 to 5.26 ng/ml which is clinically acceptable range. Thirty-seven out of 44 data sets (84{\%}) in the testing group were within 3.0 ng/ml of the observed values. This study demonstrated that tacrolimus blood concentrations are precisely predictable in liver transplant patients using patients variables by NN.",
keywords = "Neural network, Tacrolimus, Transplantation",
author = "Chen, {Hsiang Yin} and Chen, {Ta Cheng} and Min, {David I.} and Fischer, {Gary W.} and Wu, {You Min}",
year = "1999",
month = "2",
doi = "10.1097/00007691-199902000-00008",
language = "English",
volume = "21",
pages = "50--56",
journal = "Therapeutic Drug Monitoring",
issn = "0163-4356",
publisher = "Lippincott Williams and Wilkins",
number = "1",

}

TY - JOUR

T1 - Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients

AU - Chen, Hsiang Yin

AU - Chen, Ta Cheng

AU - Min, David I.

AU - Fischer, Gary W.

AU - Wu, You Min

PY - 1999/2

Y1 - 1999/2

N2 - The neural network (NN) is a technique using an artificial intelligent concept in predicting outcomes by using various input variables. Tacrolimus pharmacokinetics has wide inter- and intra-subject variability and it is often difficult to predict its blood concentrations by dose alone. The objectives of this study are to select the clinically significant variables and to predict the blood concentration of tacrolimus in liver transplant patients by NN combined with genetic algorithm (GA). A total of thirty-two adult liver transplant patients from the University of Iowa Hospitals and Clinics were selected and the patients' data were retrospectively collected. These patient were randomly assigned into two groups: either the training group (n = 10), or testing group (n = 22). A back propagation (BP) NN was developed which contained two hidden layers. A dynamic BP NN based on the time series concept was trained by using the current and previous data sets to predict the trough levels of tacrolimus. The mean of the NN prediction for tacrolimus blood levels was not significantly different from the observed value by a paired t-test comparison (12.05 ± 2.67 ng/ml vs. 12.14 ± 2.64 ng/ml, p = 0.80). The average difference of the testing sets between the observed and predicted levels was 1.74 ng/ml with a range from 0.08 to 5.26 ng/ml which is clinically acceptable range. Thirty-seven out of 44 data sets (84%) in the testing group were within 3.0 ng/ml of the observed values. This study demonstrated that tacrolimus blood concentrations are precisely predictable in liver transplant patients using patients variables by NN.

AB - The neural network (NN) is a technique using an artificial intelligent concept in predicting outcomes by using various input variables. Tacrolimus pharmacokinetics has wide inter- and intra-subject variability and it is often difficult to predict its blood concentrations by dose alone. The objectives of this study are to select the clinically significant variables and to predict the blood concentration of tacrolimus in liver transplant patients by NN combined with genetic algorithm (GA). A total of thirty-two adult liver transplant patients from the University of Iowa Hospitals and Clinics were selected and the patients' data were retrospectively collected. These patient were randomly assigned into two groups: either the training group (n = 10), or testing group (n = 22). A back propagation (BP) NN was developed which contained two hidden layers. A dynamic BP NN based on the time series concept was trained by using the current and previous data sets to predict the trough levels of tacrolimus. The mean of the NN prediction for tacrolimus blood levels was not significantly different from the observed value by a paired t-test comparison (12.05 ± 2.67 ng/ml vs. 12.14 ± 2.64 ng/ml, p = 0.80). The average difference of the testing sets between the observed and predicted levels was 1.74 ng/ml with a range from 0.08 to 5.26 ng/ml which is clinically acceptable range. Thirty-seven out of 44 data sets (84%) in the testing group were within 3.0 ng/ml of the observed values. This study demonstrated that tacrolimus blood concentrations are precisely predictable in liver transplant patients using patients variables by NN.

KW - Neural network

KW - Tacrolimus

KW - Transplantation

UR - http://www.scopus.com/inward/record.url?scp=0032987305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032987305&partnerID=8YFLogxK

U2 - 10.1097/00007691-199902000-00008

DO - 10.1097/00007691-199902000-00008

M3 - Article

C2 - 10051054

AN - SCOPUS:0032987305

VL - 21

SP - 50

EP - 56

JO - Therapeutic Drug Monitoring

JF - Therapeutic Drug Monitoring

SN - 0163-4356

IS - 1

ER -