Advanced

In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department.

Forberg, Jakob L; Green, Michael LU ; Björk, Jonas LU ; Ohlsson, Mattias LU ; Edenbrandt, Lars LU ; Öhlin, Hans LU and Ekelund, Ulf LU (2009) In Journal of Electrocardiology 42(1). p.58-63
Abstract
INTRODUCTION: The aim of this study was to compare different methods to predict acute coronary syndrome (ACS) using only data from a single electrocardiogram (ECG) in the emergency department (ED). METHOD: We compared the ACS prediction abilities of classical ECG criteria, human expert ECG interpretation, a logistic regression model and an artificial neural network ensemble (ANN). The ED ECG and discharge diagnoses were retrieved for 861 patient visits to the ED for chest pain. Cross-validation was used to estimate the generalization performance of the logistic regression and the ANN model. RESULTS: The logistic regression model had the overall best performance in predicting ACS with an area under the receiver operating characteristic... (More)
INTRODUCTION: The aim of this study was to compare different methods to predict acute coronary syndrome (ACS) using only data from a single electrocardiogram (ECG) in the emergency department (ED). METHOD: We compared the ACS prediction abilities of classical ECG criteria, human expert ECG interpretation, a logistic regression model and an artificial neural network ensemble (ANN). The ED ECG and discharge diagnoses were retrieved for 861 patient visits to the ED for chest pain. Cross-validation was used to estimate the generalization performance of the logistic regression and the ANN model. RESULTS: The logistic regression model had the overall best performance in predicting ACS with an area under the receiver operating characteristic curve of 0.88. The sensitivities of logistic regression, ANN, expert physicians, and classical ECG criteria were 95%, 95%, 82%, and 75%, respectively, and the specificities were 54%, 44%, 63%, and 69%. CONCLUSION: Our logistic regression model was the best overall method to predict ACS, followed by our ANN. Decision support models have the potential to improve even experienced ECG readers' ability to predict ACS in the ED. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Neural network ensembles, Myocardial infarction, Acute coronary syndrome, Diagnosis, Unstable angina pectoris, Electrocardiography
in
Journal of Electrocardiology
volume
42
issue
1
pages
58 - 63
publisher
Elsevier
external identifiers
  • wos:000262231800011
  • pmid:18804783
  • scopus:57349180665
ISSN
1532-8430
DOI
10.1016/j.jelectrocard.2008.07.010
language
English
LU publication?
yes
id
bcde56e0-a412-4424-aca8-51ab5393c5ba (old id 1242829)
alternative location
http://www.ncbi.nlm.nih.gov/pubmed/18804783?dopt=Abstract
date added to LUP
2008-10-03 17:36:36
date last changed
2017-11-12 03:20:33
@article{bcde56e0-a412-4424-aca8-51ab5393c5ba,
  abstract     = {INTRODUCTION: The aim of this study was to compare different methods to predict acute coronary syndrome (ACS) using only data from a single electrocardiogram (ECG) in the emergency department (ED). METHOD: We compared the ACS prediction abilities of classical ECG criteria, human expert ECG interpretation, a logistic regression model and an artificial neural network ensemble (ANN). The ED ECG and discharge diagnoses were retrieved for 861 patient visits to the ED for chest pain. Cross-validation was used to estimate the generalization performance of the logistic regression and the ANN model. RESULTS: The logistic regression model had the overall best performance in predicting ACS with an area under the receiver operating characteristic curve of 0.88. The sensitivities of logistic regression, ANN, expert physicians, and classical ECG criteria were 95%, 95%, 82%, and 75%, respectively, and the specificities were 54%, 44%, 63%, and 69%. CONCLUSION: Our logistic regression model was the best overall method to predict ACS, followed by our ANN. Decision support models have the potential to improve even experienced ECG readers' ability to predict ACS in the ED.},
  author       = {Forberg, Jakob L and Green, Michael and Björk, Jonas and Ohlsson, Mattias and Edenbrandt, Lars and Öhlin, Hans and Ekelund, Ulf},
  issn         = {1532-8430},
  keyword      = {Neural network ensembles,Myocardial infarction,Acute coronary syndrome,Diagnosis,Unstable angina pectoris,Electrocardiography},
  language     = {eng},
  number       = {1},
  pages        = {58--63},
  publisher    = {Elsevier},
  series       = {Journal of Electrocardiology},
  title        = {In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department.},
  url          = {http://dx.doi.org/10.1016/j.jelectrocard.2008.07.010},
  volume       = {42},
  year         = {2009},
}