A confident decision support system for interpreting electrocardiograms
Holst, Holger LU ; Ohlsson, Mattias LU
; Peterson, Carsten
LU
and Edenbrandt, Lars
LU
(1999)
In Clinical Physiology
19(5).
p.410-418
- Abstract
Computer-aided interpretation of electrocardiograms (ECGs) is widespread but many physicians hesitate to rely on the computer, because the advice is presented without information about the confidence of the advice. The purpose of this work was to develop a method to validate the advice of a computer by estimating the error of an artificial neural network output. A total of 1249 ECGs, recorded with computerized electrocardiographs, on patients who had undergone diagnostic cardiac catheterization were studied. The material consisted of two groups, 414 patients with and 835 without anterior myocardial infarction. The material was randomly divided into three data sets. The first set was used to train an artificial neural network for the... (More)
Computer-aided interpretation of electrocardiograms (ECGs) is widespread but many physicians hesitate to rely on the computer, because the advice is presented without information about the confidence of the advice. The purpose of this work was to develop a method to validate the advice of a computer by estimating the error of an artificial neural network output. A total of 1249 ECGs, recorded with computerized electrocardiographs, on patients who had undergone diagnostic cardiac catheterization were studied. The material consisted of two groups, 414 patients with and 835 without anterior myocardial infarction. The material was randomly divided into three data sets. The first set was used to train an artificial neural network for the diagnosis of anterior infarction. The second data set was used to calculate the error of the network outputs. The last data set was used to test the network performance and to estimate the error of the network outputs. The performance of the neural network, measured as the area under the receiver operating characteristic (ROC) curve, was 0.887 (0.845-0.922). The 25% test ECGs with the lowest error estimates had an area under the ROC curve as high as 0.995 (0.982-1.000), i.e. almost all of these ECGs were correctly classified. Neural networks can therefore be trained to diagnose myocardial infarction and to signal when the advice is given with great confidence or when it should be considered more carefully. This method increases the possibility that artificial neural networks will be accepted as reliable decision support systems in clinical practice.
(Less)
- author
- Holst, Holger
LU
; Ohlsson, Mattias
LU
; Peterson, Carsten
LU
and Edenbrandt, Lars
LU
- organization
- publishing date
- 1999-09
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Computer-assisted electrocardiography, Diagnosis, Myocardial infarction, Neural networks (computer)
- in
- Clinical Physiology
- volume
- 19
- issue
- 5
- pages
- 9 pages
- publisher
- John Wiley & Sons Inc.
- external identifiers
-
- scopus:0032878967
- pmid:10516892
- ISSN
- 0144-5979
- DOI
- 10.1046/j.1365-2281.1999.00195.x
- language
- English
- LU publication?
- yes
- id
- 2b0b78a0-e48d-4cca-830c-131c275a82f6
- date added to LUP
- 2017-05-19 08:12:57
- date last changed
- 2024-05-12 14:16:56
@article{2b0b78a0-e48d-4cca-830c-131c275a82f6,
abstract = {{<p>Computer-aided interpretation of electrocardiograms (ECGs) is widespread but many physicians hesitate to rely on the computer, because the advice is presented without information about the confidence of the advice. The purpose of this work was to develop a method to validate the advice of a computer by estimating the error of an artificial neural network output. A total of 1249 ECGs, recorded with computerized electrocardiographs, on patients who had undergone diagnostic cardiac catheterization were studied. The material consisted of two groups, 414 patients with and 835 without anterior myocardial infarction. The material was randomly divided into three data sets. The first set was used to train an artificial neural network for the diagnosis of anterior infarction. The second data set was used to calculate the error of the network outputs. The last data set was used to test the network performance and to estimate the error of the network outputs. The performance of the neural network, measured as the area under the receiver operating characteristic (ROC) curve, was 0.887 (0.845-0.922). The 25% test ECGs with the lowest error estimates had an area under the ROC curve as high as 0.995 (0.982-1.000), i.e. almost all of these ECGs were correctly classified. Neural networks can therefore be trained to diagnose myocardial infarction and to signal when the advice is given with great confidence or when it should be considered more carefully. This method increases the possibility that artificial neural networks will be accepted as reliable decision support systems in clinical practice.</p>}},
author = {{Holst, Holger and Ohlsson, Mattias and Peterson, Carsten and Edenbrandt, Lars}},
issn = {{0144-5979}},
keywords = {{Computer-assisted electrocardiography; Diagnosis; Myocardial infarction; Neural networks (computer)}},
language = {{eng}},
number = {{5}},
pages = {{410--418}},
publisher = {{John Wiley & Sons Inc.}},
series = {{Clinical Physiology}},
title = {{A confident decision support system for interpreting electrocardiograms}},
url = {{http://dx.doi.org/10.1046/j.1365-2281.1999.00195.x}},
doi = {{10.1046/j.1365-2281.1999.00195.x}},
volume = {{19}},
year = {{1999}},
}