Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence

Thomas F. Heston, Douglas Norman, John Barry, William M. Bennett, Richard A. Wilson

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

The purpose of this study was to determine if an expert network, a form of artificial intelligence, could effectively stratify cardiac risk in candidates for renal transplant. Input into the expert network consisted of clinical risk factors and thallium-201 stress test data. Clinical risk factor screening alone identified 95 of 189 patients as high risk. These 95 patients underwent thallium-201 stress testing, and 53 had either reversible or fixed defects. The other 42 patients were classified as low risk. This algorithm made up the "expert system," and during the 4-year follow-up period had a sensitivity of 82%, specificity of 77%, and accuracy of 78%. An artificial neural network was added to the expert system, creating an expert network. Input into the neural network consisted of both clinical variables and thallium-201 stress test data. There were 5 hidden nodes and the output (end point) was cardiac death. The expert network increased the specificity of the expert system alone from 77% to 90% (p

Original languageEnglish (US)
Pages (from-to)415-417
Number of pages3
JournalAmerican Journal of Cardiology
Volume79
Issue number4
StatePublished - Feb 15 1997
Externally publishedYes

Fingerprint

Expert Systems
Thallium
Artificial Intelligence
Kidney Transplantation
Exercise Test
Transplants
Kidney
Sensitivity and Specificity

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence. / Heston, Thomas F.; Norman, Douglas; Barry, John; Bennett, William M.; Wilson, Richard A.

In: American Journal of Cardiology, Vol. 79, No. 4, 15.02.1997, p. 415-417.

Research output: Contribution to journalArticle

Heston, Thomas F. ; Norman, Douglas ; Barry, John ; Bennett, William M. ; Wilson, Richard A. / Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence. In: American Journal of Cardiology. 1997 ; Vol. 79, No. 4. pp. 415-417.
@article{dc646c904aae4fe7acb25cbaa15c28f9,
title = "Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence",
abstract = "The purpose of this study was to determine if an expert network, a form of artificial intelligence, could effectively stratify cardiac risk in candidates for renal transplant. Input into the expert network consisted of clinical risk factors and thallium-201 stress test data. Clinical risk factor screening alone identified 95 of 189 patients as high risk. These 95 patients underwent thallium-201 stress testing, and 53 had either reversible or fixed defects. The other 42 patients were classified as low risk. This algorithm made up the {"}expert system,{"} and during the 4-year follow-up period had a sensitivity of 82{\%}, specificity of 77{\%}, and accuracy of 78{\%}. An artificial neural network was added to the expert system, creating an expert network. Input into the neural network consisted of both clinical variables and thallium-201 stress test data. There were 5 hidden nodes and the output (end point) was cardiac death. The expert network increased the specificity of the expert system alone from 77{\%} to 90{\%} (p",
author = "Heston, {Thomas F.} and Douglas Norman and John Barry and Bennett, {William M.} and Wilson, {Richard A.}",
year = "1997",
month = "2",
day = "15",
language = "English (US)",
volume = "79",
pages = "415--417",
journal = "American Journal of Cardiology",
issn = "0002-9149",
publisher = "Elsevier Inc.",
number = "4",

}

TY - JOUR

T1 - Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence

AU - Heston, Thomas F.

AU - Norman, Douglas

AU - Barry, John

AU - Bennett, William M.

AU - Wilson, Richard A.

PY - 1997/2/15

Y1 - 1997/2/15

N2 - The purpose of this study was to determine if an expert network, a form of artificial intelligence, could effectively stratify cardiac risk in candidates for renal transplant. Input into the expert network consisted of clinical risk factors and thallium-201 stress test data. Clinical risk factor screening alone identified 95 of 189 patients as high risk. These 95 patients underwent thallium-201 stress testing, and 53 had either reversible or fixed defects. The other 42 patients were classified as low risk. This algorithm made up the "expert system," and during the 4-year follow-up period had a sensitivity of 82%, specificity of 77%, and accuracy of 78%. An artificial neural network was added to the expert system, creating an expert network. Input into the neural network consisted of both clinical variables and thallium-201 stress test data. There were 5 hidden nodes and the output (end point) was cardiac death. The expert network increased the specificity of the expert system alone from 77% to 90% (p

AB - The purpose of this study was to determine if an expert network, a form of artificial intelligence, could effectively stratify cardiac risk in candidates for renal transplant. Input into the expert network consisted of clinical risk factors and thallium-201 stress test data. Clinical risk factor screening alone identified 95 of 189 patients as high risk. These 95 patients underwent thallium-201 stress testing, and 53 had either reversible or fixed defects. The other 42 patients were classified as low risk. This algorithm made up the "expert system," and during the 4-year follow-up period had a sensitivity of 82%, specificity of 77%, and accuracy of 78%. An artificial neural network was added to the expert system, creating an expert network. Input into the neural network consisted of both clinical variables and thallium-201 stress test data. There were 5 hidden nodes and the output (end point) was cardiac death. The expert network increased the specificity of the expert system alone from 77% to 90% (p

UR - http://www.scopus.com/inward/record.url?scp=0031568673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031568673&partnerID=8YFLogxK

M3 - Article

VL - 79

SP - 415

EP - 417

JO - American Journal of Cardiology

JF - American Journal of Cardiology

SN - 0002-9149

IS - 4

ER -