Using patient-reportable clinical history factors to predict myocardial infarction

Samuel Wang, Lucila Ohno-Machado, Hamish S F Fraser, R. Lee Kennedy

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Using a derivation data set of 1253 patients, we built several logistic regression and neural network models to estimate the likelihood of myocardial infarction based upon patient-reportable clinical history factors only. The best performing logistic regression model and neural network model had C-indices of 0.8444 and 0.8503, respectively, when validated on an independent data set of 500 patients. We conclude that both logistic regression and neural network models can be built that successfully predict the probability of myocardial infarction based on patient-reportable history factors alone. These models could have important utility in applications outside of a hospital setting when objective diagnostic test information is not yet be available. Copyright (C) 2001 Elsevier Science B.V.

Original languageEnglish (US)
Pages (from-to)1-13
Number of pages13
JournalComputers in Biology and Medicine
Volume31
Issue number1
DOIs
StatePublished - Jan 2001
Externally publishedYes

Fingerprint

Neural Networks (Computer)
Logistic Models
Myocardial Infarction
Logistics
Neural networks
Routine Diagnostic Tests
History
Datasets

Keywords

  • Artificial intelligence
  • Decision support techniques
  • Logistic models
  • Myocardial infarction
  • Neural networks (computer)
  • Regression analysis

ASJC Scopus subject areas

  • Computer Science Applications

Cite this

Using patient-reportable clinical history factors to predict myocardial infarction. / Wang, Samuel; Ohno-Machado, Lucila; Fraser, Hamish S F; Kennedy, R. Lee.

In: Computers in Biology and Medicine, Vol. 31, No. 1, 01.2001, p. 1-13.

Research output: Contribution to journalArticle

Wang, Samuel ; Ohno-Machado, Lucila ; Fraser, Hamish S F ; Kennedy, R. Lee. / Using patient-reportable clinical history factors to predict myocardial infarction. In: Computers in Biology and Medicine. 2001 ; Vol. 31, No. 1. pp. 1-13.
@article{6cca3d93502144209a9f65f30ed9628d,
title = "Using patient-reportable clinical history factors to predict myocardial infarction",
abstract = "Using a derivation data set of 1253 patients, we built several logistic regression and neural network models to estimate the likelihood of myocardial infarction based upon patient-reportable clinical history factors only. The best performing logistic regression model and neural network model had C-indices of 0.8444 and 0.8503, respectively, when validated on an independent data set of 500 patients. We conclude that both logistic regression and neural network models can be built that successfully predict the probability of myocardial infarction based on patient-reportable history factors alone. These models could have important utility in applications outside of a hospital setting when objective diagnostic test information is not yet be available. Copyright (C) 2001 Elsevier Science B.V.",
keywords = "Artificial intelligence, Decision support techniques, Logistic models, Myocardial infarction, Neural networks (computer), Regression analysis",
author = "Samuel Wang and Lucila Ohno-Machado and Fraser, {Hamish S F} and Kennedy, {R. Lee}",
year = "2001",
month = "1",
doi = "10.1016/S0010-4825(00)00022-6",
language = "English (US)",
volume = "31",
pages = "1--13",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Using patient-reportable clinical history factors to predict myocardial infarction

AU - Wang, Samuel

AU - Ohno-Machado, Lucila

AU - Fraser, Hamish S F

AU - Kennedy, R. Lee

PY - 2001/1

Y1 - 2001/1

N2 - Using a derivation data set of 1253 patients, we built several logistic regression and neural network models to estimate the likelihood of myocardial infarction based upon patient-reportable clinical history factors only. The best performing logistic regression model and neural network model had C-indices of 0.8444 and 0.8503, respectively, when validated on an independent data set of 500 patients. We conclude that both logistic regression and neural network models can be built that successfully predict the probability of myocardial infarction based on patient-reportable history factors alone. These models could have important utility in applications outside of a hospital setting when objective diagnostic test information is not yet be available. Copyright (C) 2001 Elsevier Science B.V.

AB - Using a derivation data set of 1253 patients, we built several logistic regression and neural network models to estimate the likelihood of myocardial infarction based upon patient-reportable clinical history factors only. The best performing logistic regression model and neural network model had C-indices of 0.8444 and 0.8503, respectively, when validated on an independent data set of 500 patients. We conclude that both logistic regression and neural network models can be built that successfully predict the probability of myocardial infarction based on patient-reportable history factors alone. These models could have important utility in applications outside of a hospital setting when objective diagnostic test information is not yet be available. Copyright (C) 2001 Elsevier Science B.V.

KW - Artificial intelligence

KW - Decision support techniques

KW - Logistic models

KW - Myocardial infarction

KW - Neural networks (computer)

KW - Regression analysis

UR - http://www.scopus.com/inward/record.url?scp=0035238940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035238940&partnerID=8YFLogxK

U2 - 10.1016/S0010-4825(00)00022-6

DO - 10.1016/S0010-4825(00)00022-6

M3 - Article

C2 - 11058690

AN - SCOPUS:0035238940

VL - 31

SP - 1

EP - 13

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 1

ER -