Use of artificial neural networks in improving renal transplantation outcomes

Nikolai Petrovsky, Soh Khum Tam, Vladimir Brusic, Graeme Russ, Luis Socha, Vladimir B. Bajic

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Recent advances in renal transplantation, including the matching of major histocompatibility complex or new immunosuppressants, have improved 1-year survival of cadaver kidney grafts to more than 85%. Further optimization of kidney transplant outcomes is necessary to enhance both the graft survival time and the quality of life. Techniques derived from the artificial intelligence enable better prediction of graft outcomes by using donor and recipient data. The authors used an artificial neural network (ANN) to model kidney graft rejection and trained it with data on 1542 kidney transplants. The ANN correctly predicted 85% of successful and 72% of failed transplants. Also, ANN correctly predicted the type of rejection (hyperacute, acute, subacute, and chronic) for approximately 60% of the failed transplants. These results indicate that the ANN-based approach is useful for prediction of both the general outcomes of kidney transplants and the prediction of the type of rejection.

Original languageEnglish
Pages (from-to)6-13
Number of pages8
JournalGraft
Volume5
Issue number1
Publication statusPublished - 2002
Externally publishedYes

Fingerprint

Kidney Transplantation
Transplants
Kidney
Graft Rejection
Neural Networks (Computer)
Artificial Intelligence
Graft Survival
Immunosuppressive Agents
Major Histocompatibility Complex
Cadaver
Quality of Life

ASJC Scopus subject areas

  • Transplantation

Cite this

Petrovsky, N., Tam, S. K., Brusic, V., Russ, G., Socha, L., & Bajic, V. B. (2002). Use of artificial neural networks in improving renal transplantation outcomes. Graft, 5(1), 6-13.

Use of artificial neural networks in improving renal transplantation outcomes. / Petrovsky, Nikolai; Tam, Soh Khum; Brusic, Vladimir; Russ, Graeme; Socha, Luis; Bajic, Vladimir B.

In: Graft, Vol. 5, No. 1, 2002, p. 6-13.

Research output: Contribution to journalArticle

Petrovsky, N, Tam, SK, Brusic, V, Russ, G, Socha, L & Bajic, VB 2002, 'Use of artificial neural networks in improving renal transplantation outcomes', Graft, vol. 5, no. 1, pp. 6-13.
Petrovsky N, Tam SK, Brusic V, Russ G, Socha L, Bajic VB. Use of artificial neural networks in improving renal transplantation outcomes. Graft. 2002;5(1):6-13.
Petrovsky, Nikolai ; Tam, Soh Khum ; Brusic, Vladimir ; Russ, Graeme ; Socha, Luis ; Bajic, Vladimir B. / Use of artificial neural networks in improving renal transplantation outcomes. In: Graft. 2002 ; Vol. 5, No. 1. pp. 6-13.
@article{64ece04eebfa476195634f846f593504,
title = "Use of artificial neural networks in improving renal transplantation outcomes",
abstract = "Recent advances in renal transplantation, including the matching of major histocompatibility complex or new immunosuppressants, have improved 1-year survival of cadaver kidney grafts to more than 85{\%}. Further optimization of kidney transplant outcomes is necessary to enhance both the graft survival time and the quality of life. Techniques derived from the artificial intelligence enable better prediction of graft outcomes by using donor and recipient data. The authors used an artificial neural network (ANN) to model kidney graft rejection and trained it with data on 1542 kidney transplants. The ANN correctly predicted 85{\%} of successful and 72{\%} of failed transplants. Also, ANN correctly predicted the type of rejection (hyperacute, acute, subacute, and chronic) for approximately 60{\%} of the failed transplants. These results indicate that the ANN-based approach is useful for prediction of both the general outcomes of kidney transplants and the prediction of the type of rejection.",
author = "Nikolai Petrovsky and Tam, {Soh Khum} and Vladimir Brusic and Graeme Russ and Luis Socha and Bajic, {Vladimir B.}",
year = "2002",
language = "English",
volume = "5",
pages = "6--13",
journal = "Graft",
issn = "1522-1628",
publisher = "SAGE Publications Inc.",
number = "1",

}

TY - JOUR

T1 - Use of artificial neural networks in improving renal transplantation outcomes

AU - Petrovsky, Nikolai

AU - Tam, Soh Khum

AU - Brusic, Vladimir

AU - Russ, Graeme

AU - Socha, Luis

AU - Bajic, Vladimir B.

PY - 2002

Y1 - 2002

N2 - Recent advances in renal transplantation, including the matching of major histocompatibility complex or new immunosuppressants, have improved 1-year survival of cadaver kidney grafts to more than 85%. Further optimization of kidney transplant outcomes is necessary to enhance both the graft survival time and the quality of life. Techniques derived from the artificial intelligence enable better prediction of graft outcomes by using donor and recipient data. The authors used an artificial neural network (ANN) to model kidney graft rejection and trained it with data on 1542 kidney transplants. The ANN correctly predicted 85% of successful and 72% of failed transplants. Also, ANN correctly predicted the type of rejection (hyperacute, acute, subacute, and chronic) for approximately 60% of the failed transplants. These results indicate that the ANN-based approach is useful for prediction of both the general outcomes of kidney transplants and the prediction of the type of rejection.

AB - Recent advances in renal transplantation, including the matching of major histocompatibility complex or new immunosuppressants, have improved 1-year survival of cadaver kidney grafts to more than 85%. Further optimization of kidney transplant outcomes is necessary to enhance both the graft survival time and the quality of life. Techniques derived from the artificial intelligence enable better prediction of graft outcomes by using donor and recipient data. The authors used an artificial neural network (ANN) to model kidney graft rejection and trained it with data on 1542 kidney transplants. The ANN correctly predicted 85% of successful and 72% of failed transplants. Also, ANN correctly predicted the type of rejection (hyperacute, acute, subacute, and chronic) for approximately 60% of the failed transplants. These results indicate that the ANN-based approach is useful for prediction of both the general outcomes of kidney transplants and the prediction of the type of rejection.

UR - http://www.scopus.com/inward/record.url?scp=0036212695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036212695&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036212695

VL - 5

SP - 6

EP - 13

JO - Graft

JF - Graft

SN - 1522-1628

IS - 1

ER -