Decision Support for the Initial Triage of Patients with Acute Myocardial Infarction
(2006) In Clinical Physiology and Functional Imaging 26(3). p.151-156- Abstract
- Objectives:
To develop an automated tool for the analysis of electrocardiograms (ECG) with respect to changes that make the patient a candidate for reperfusion therapy. An additional aim was to assess the influence of the tool on the ECG classifications of three interns.
Methods and Results:
An artificial neural network was trained to interpret ECGs regarding changes making the patient a candidate for reperfusion therapy. The ECG measurements used as input to the network were obtained from the measurement program of the ECG recorders. The network was trained using a database of 3000 ECGs recorded at an emergency department. In the second step three interns classified 1000 test ECGs twice at different... (More) - Objectives:
To develop an automated tool for the analysis of electrocardiograms (ECG) with respect to changes that make the patient a candidate for reperfusion therapy. An additional aim was to assess the influence of the tool on the ECG classifications of three interns.
Methods and Results:
An artificial neural network was trained to interpret ECGs regarding changes making the patient a candidate for reperfusion therapy. The ECG measurements used as input to the network were obtained from the measurement program of the ECG recorders. The network was trained using a database of 3000 ECGs recorded at an emergency department. In the second step three interns classified 1000 test ECGs twice at different occasions, first without and thereafter with the advice of the neural network. The gold standard of the training and test ECGs was the classification of two experienced cardiologists. The three interns showed on average a sensitivity of 68% at a specificity of 92% without the advice of the neural network and a sensitivity of 93% at a specificity of 87% with the advice. The neural network itself showed a sensitivity of 95% at a specificity of 88%. The increase in sensitivity of 23-26% was highly significant (p<0.001) for all three interns.
Conclusion:
Artificial neural networks can be trained to gain a performance in the interpretation of ST-segment changes in accordance to experienced cardiologists. The neural networks offers a reliably support to physicians with lesser experience in the interpretation of ECG with respect to changes that make the patient a candidate for reperfusion therapy. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/766393
- author
- Olsson, Sven-Erik
LU
; Ohlsson, Mattias
LU
; Öhlin, Hans LU ; Dzaferagic, Samir ; Nilsson, Marie-Louise ; Sandkull, Per and Edenbrandt, Lars LU
- organization
- publishing date
- 2006
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Clinical Physiology and Functional Imaging
- volume
- 26
- issue
- 3
- pages
- 151 - 156
- publisher
- John Wiley & Sons Inc.
- external identifiers
-
- wos:000237093900003
- pmid:16640509
- scopus:33646035478
- pmid:16640509
- ISSN
- 1475-0961
- DOI
- 10.1111/j.1475-097X.2006.00669.x
- language
- English
- LU publication?
- yes
- id
- d22fa8b3-8d00-4c03-9872-7b6ecc3b7378 (old id 766393)
- alternative location
- http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=16640509&dopt=Abstract
- date added to LUP
- 2016-04-01 12:37:30
- date last changed
- 2024-01-09 03:07:17
@article{d22fa8b3-8d00-4c03-9872-7b6ecc3b7378, abstract = {{Objectives: <br/><br> To develop an automated tool for the analysis of electrocardiograms (ECG) with respect to changes that make the patient a candidate for reperfusion therapy. An additional aim was to assess the influence of the tool on the ECG classifications of three interns. <br/><br> <br/><br> Methods and Results: <br/><br> An artificial neural network was trained to interpret ECGs regarding changes making the patient a candidate for reperfusion therapy. The ECG measurements used as input to the network were obtained from the measurement program of the ECG recorders. The network was trained using a database of 3000 ECGs recorded at an emergency department. In the second step three interns classified 1000 test ECGs twice at different occasions, first without and thereafter with the advice of the neural network. The gold standard of the training and test ECGs was the classification of two experienced cardiologists. The three interns showed on average a sensitivity of 68% at a specificity of 92% without the advice of the neural network and a sensitivity of 93% at a specificity of 87% with the advice. The neural network itself showed a sensitivity of 95% at a specificity of 88%. The increase in sensitivity of 23-26% was highly significant (p<0.001) for all three interns. <br/><br> <br/><br> Conclusion: <br/><br> Artificial neural networks can be trained to gain a performance in the interpretation of ST-segment changes in accordance to experienced cardiologists. The neural networks offers a reliably support to physicians with lesser experience in the interpretation of ECG with respect to changes that make the patient a candidate for reperfusion therapy.}}, author = {{Olsson, Sven-Erik and Ohlsson, Mattias and Öhlin, Hans and Dzaferagic, Samir and Nilsson, Marie-Louise and Sandkull, Per and Edenbrandt, Lars}}, issn = {{1475-0961}}, language = {{eng}}, number = {{3}}, pages = {{151--156}}, publisher = {{John Wiley & Sons Inc.}}, series = {{Clinical Physiology and Functional Imaging}}, title = {{Decision Support for the Initial Triage of Patients with Acute Myocardial Infarction}}, url = {{http://dx.doi.org/10.1111/j.1475-097X.2006.00669.x}}, doi = {{10.1111/j.1475-097X.2006.00669.x}}, volume = {{26}}, year = {{2006}}, }