Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Usefulness of serial electrocardiograms for diagnosis of acute myocardial infarction

Ohlsson, Mattias LU orcid ; Öhlin, Hans LU ; Wallerstedt, Susanna Maria LU and Edenbrandt, Lars LU (2001) In American Journal of Cardiology 88(5). p.478-481
Abstract

The purpose of this study was to determine whether the automated detection of acute myocardial infarction (AMI) by utilizing artificial neural networks was improved by using a previous electrocardiogram (ECG) in addition to the current ECG. A total of 4,691 ECGs were recorded from patients admitted to an emergency department due to suspected AMI. Of these, 902 ECGs, in which diagnoses of AMI were later confirmed, formed the study group, whereas the remaining 3,789 ECGS comprised the control group. For each ECG recorded, a previous ECG of the same patient was selected from the clinical electrocardiographic database. Artificial neural networks were then programed to detect AMI based on either the current ECG only or on the combination of... (More)

The purpose of this study was to determine whether the automated detection of acute myocardial infarction (AMI) by utilizing artificial neural networks was improved by using a previous electrocardiogram (ECG) in addition to the current ECG. A total of 4,691 ECGs were recorded from patients admitted to an emergency department due to suspected AMI. Of these, 902 ECGs, in which diagnoses of AMI were later confirmed, formed the study group, whereas the remaining 3,789 ECGS comprised the control group. For each ECG recorded, a previous ECG of the same patient was selected from the clinical electrocardiographic database. Artificial neural networks were then programed to detect AMI based on either the current ECG only or on the combination of the previous and the current ECGs. On this basis, 3 assessors - a neural network, an experienced cardiologist, and an intern - separately classified the ECGs of the test group, with and without access to the previous ECG. The detection performance, as measured by the area under the receiver operating characteristic curve, showed an increase for all assessors with access to previous ECGs. The neural network improved from 0.85 to 0.88 (p = 0.02), the cardiologist from 0.79 to 0.81 (p = 0.36), and the intern from 0.71 to 0.78 (p <0.001). Thus, the performance of a neural network, detecting AMI in an ECG, is improved when a previous ECG is used as an additional input.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
American Journal of Cardiology
volume
88
issue
5
pages
4 pages
publisher
Excerpta Medica
external identifiers
  • scopus:0035451345
  • pmid:11524053
ISSN
0002-9149
DOI
10.1016/S0002-9149(01)01722-2
language
English
LU publication?
yes
id
7c84f371-fd9a-4290-ab3c-be978e99047c
date added to LUP
2017-05-19 08:07:45
date last changed
2024-02-12 19:30:48
@article{7c84f371-fd9a-4290-ab3c-be978e99047c,
  abstract     = {{<p>The purpose of this study was to determine whether the automated detection of acute myocardial infarction (AMI) by utilizing artificial neural networks was improved by using a previous electrocardiogram (ECG) in addition to the current ECG. A total of 4,691 ECGs were recorded from patients admitted to an emergency department due to suspected AMI. Of these, 902 ECGs, in which diagnoses of AMI were later confirmed, formed the study group, whereas the remaining 3,789 ECGS comprised the control group. For each ECG recorded, a previous ECG of the same patient was selected from the clinical electrocardiographic database. Artificial neural networks were then programed to detect AMI based on either the current ECG only or on the combination of the previous and the current ECGs. On this basis, 3 assessors - a neural network, an experienced cardiologist, and an intern - separately classified the ECGs of the test group, with and without access to the previous ECG. The detection performance, as measured by the area under the receiver operating characteristic curve, showed an increase for all assessors with access to previous ECGs. The neural network improved from 0.85 to 0.88 (p = 0.02), the cardiologist from 0.79 to 0.81 (p = 0.36), and the intern from 0.71 to 0.78 (p &lt;0.001). Thus, the performance of a neural network, detecting AMI in an ECG, is improved when a previous ECG is used as an additional input.</p>}},
  author       = {{Ohlsson, Mattias and Öhlin, Hans and Wallerstedt, Susanna Maria and Edenbrandt, Lars}},
  issn         = {{0002-9149}},
  language     = {{eng}},
  month        = {{09}},
  number       = {{5}},
  pages        = {{478--481}},
  publisher    = {{Excerpta Medica}},
  series       = {{American Journal of Cardiology}},
  title        = {{Usefulness of serial electrocardiograms for diagnosis of acute myocardial infarction}},
  url          = {{http://dx.doi.org/10.1016/S0002-9149(01)01722-2}},
  doi          = {{10.1016/S0002-9149(01)01722-2}},
  volume       = {{88}},
  year         = {{2001}},
}