Use of neural networks for prediction of graft failure following liver transplantation

Sherri Matis, Howard Doyle, Ignazio Marino, Richard Mural, Edward Uberbacher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Clinical information was gathered prospectively for 295 patients who underwent liver transplantation at the University of Pittsburgh Medical Center, and was divided into sets. The feedforward, fully connected, neural networks had 7 or 8 inputs, a single hidden layer consisting of 3 nodes and a single output node. Using a standard back propagation algorithm, the networks were trained with data from a randomly selected subset of 240 patients while the remaining 55 patients made up the test set. Training was assessed by testing the ability of the network to correctly predict the outcome of the 55 patients in the test set. The accuracy of prediction by the neural network improved each day and so by day 5, 98% of the graft survivors in the test set were correctly predicted while 88% of graft failures in the test set were correctly predicted.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Symposium on Computer-Based Medical Systems
Editors Anon
PublisherIEEE
Pages133-140
Number of pages8
StatePublished - 1995
Externally publishedYes
EventProceedings of the 8th IEEE Symposium on Computer-Based Medical Systems - Lubbock, TX, USA
Duration: Jun 9 1995Jun 10 1995

Other

OtherProceedings of the 8th IEEE Symposium on Computer-Based Medical Systems
CityLubbock, TX, USA
Period6/9/956/10/95

Fingerprint

Transplantation (surgical)
Grafts
Liver
Neural networks
Backpropagation algorithms
Testing

ASJC Scopus subject areas

  • Software

Cite this

Matis, S., Doyle, H., Marino, I., Mural, R., & Uberbacher, E. (1995). Use of neural networks for prediction of graft failure following liver transplantation. In Anon (Ed.), Proceedings of the IEEE Symposium on Computer-Based Medical Systems (pp. 133-140). IEEE.

Use of neural networks for prediction of graft failure following liver transplantation. / Matis, Sherri; Doyle, Howard; Marino, Ignazio; Mural, Richard; Uberbacher, Edward.

Proceedings of the IEEE Symposium on Computer-Based Medical Systems. ed. / Anon. IEEE, 1995. p. 133-140.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Matis, S, Doyle, H, Marino, I, Mural, R & Uberbacher, E 1995, Use of neural networks for prediction of graft failure following liver transplantation. in Anon (ed.), Proceedings of the IEEE Symposium on Computer-Based Medical Systems. IEEE, pp. 133-140, Proceedings of the 8th IEEE Symposium on Computer-Based Medical Systems, Lubbock, TX, USA, 6/9/95.
Matis S, Doyle H, Marino I, Mural R, Uberbacher E. Use of neural networks for prediction of graft failure following liver transplantation. In Anon, editor, Proceedings of the IEEE Symposium on Computer-Based Medical Systems. IEEE. 1995. p. 133-140
Matis, Sherri ; Doyle, Howard ; Marino, Ignazio ; Mural, Richard ; Uberbacher, Edward. / Use of neural networks for prediction of graft failure following liver transplantation. Proceedings of the IEEE Symposium on Computer-Based Medical Systems. editor / Anon. IEEE, 1995. pp. 133-140
@inproceedings{fb3a973deb76473a93e0c6ae848a66cc,
title = "Use of neural networks for prediction of graft failure following liver transplantation",
abstract = "Clinical information was gathered prospectively for 295 patients who underwent liver transplantation at the University of Pittsburgh Medical Center, and was divided into sets. The feedforward, fully connected, neural networks had 7 or 8 inputs, a single hidden layer consisting of 3 nodes and a single output node. Using a standard back propagation algorithm, the networks were trained with data from a randomly selected subset of 240 patients while the remaining 55 patients made up the test set. Training was assessed by testing the ability of the network to correctly predict the outcome of the 55 patients in the test set. The accuracy of prediction by the neural network improved each day and so by day 5, 98{\%} of the graft survivors in the test set were correctly predicted while 88{\%} of graft failures in the test set were correctly predicted.",
author = "Sherri Matis and Howard Doyle and Ignazio Marino and Richard Mural and Edward Uberbacher",
year = "1995",
language = "English (US)",
pages = "133--140",
editor = "Anon",
booktitle = "Proceedings of the IEEE Symposium on Computer-Based Medical Systems",
publisher = "IEEE",

}

TY - GEN

T1 - Use of neural networks for prediction of graft failure following liver transplantation

AU - Matis, Sherri

AU - Doyle, Howard

AU - Marino, Ignazio

AU - Mural, Richard

AU - Uberbacher, Edward

PY - 1995

Y1 - 1995

N2 - Clinical information was gathered prospectively for 295 patients who underwent liver transplantation at the University of Pittsburgh Medical Center, and was divided into sets. The feedforward, fully connected, neural networks had 7 or 8 inputs, a single hidden layer consisting of 3 nodes and a single output node. Using a standard back propagation algorithm, the networks were trained with data from a randomly selected subset of 240 patients while the remaining 55 patients made up the test set. Training was assessed by testing the ability of the network to correctly predict the outcome of the 55 patients in the test set. The accuracy of prediction by the neural network improved each day and so by day 5, 98% of the graft survivors in the test set were correctly predicted while 88% of graft failures in the test set were correctly predicted.

AB - Clinical information was gathered prospectively for 295 patients who underwent liver transplantation at the University of Pittsburgh Medical Center, and was divided into sets. The feedforward, fully connected, neural networks had 7 or 8 inputs, a single hidden layer consisting of 3 nodes and a single output node. Using a standard back propagation algorithm, the networks were trained with data from a randomly selected subset of 240 patients while the remaining 55 patients made up the test set. Training was assessed by testing the ability of the network to correctly predict the outcome of the 55 patients in the test set. The accuracy of prediction by the neural network improved each day and so by day 5, 98% of the graft survivors in the test set were correctly predicted while 88% of graft failures in the test set were correctly predicted.

UR - http://www.scopus.com/inward/record.url?scp=0029222724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029222724&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029222724

SP - 133

EP - 140

BT - Proceedings of the IEEE Symposium on Computer-Based Medical Systems

A2 - Anon, null

PB - IEEE

ER -