Document Detail


Use of artificial neural networks within deterministic logic for the computer ECG diagnosis of inferior myocardial infarction.
MedLine Citation:
PMID:  7884359     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
An investigation into the use of software-based artificial neural networks for the electrocardiographic (ECG) detection of inferior myocardial infarction was made. A total of 592 clinically validated subjects, including 208 with inferior myocardial infarction, 300 normal subjects, and 84 left ventricular hypertrophy cases, were used in this study. A total of 200 ECGs (100 from patients with inferior myocardial infarction and 100 from normal subjects) were fed to 66 supervised feedforward neural networks for training using a back-propagation algorithm. QRS and ST-T wave measurements were used as the input parameters for the neural networks. The best performing network using QRS measurements only and the best using QRS and ST-T data were selected by assessing a test set of 292 ECGs (108 from patients with inferior myocardial infarction, 84 from patients with left ventricular hypertrophy, and 100 from normal subjects). These two networks were then implanted separately into the deterministic Glasgow program for further study. After the implementation, it was found necessary to include a small inferior Q criterion to improve the specificity of reporting inferior myocardial infarction, thereby producing a small loss of sensitivity as compared with use of the network alone. The use of an artificial neural network within the deterministic logic performed better than either alone in the diagnosis of inferior myocardial infarction, producing a 20% gain in sensitivity with 2% loss in overall specificity compared with the original deterministic logic.
Authors:
T F Yang; B Devine; P W Macfarlane
Related Documents :
2975319 - False-positive posterior myocardial infarct criteria during left anterior descending co...
24044509 - Impact of left anterior line on left atrial appendage contractility in patients who und...
14975469 - Ischemic and viable myocardium in patients with non-q-wave or q-wave myocardial infarct...
560139 - Effect of halothane on systolic time intervals.
165909 - Technetium stannous pyrophosphate myocardial scintigrams in patients with chest pain of...
24685689 - Drug-eluting versus bare-metal stents in large coronary arteries of patients with st-se...
10888209 - Predictive value of remnant-like particle cholesterol as an indicator of coronary arter...
11096509 - Unstable angina.
19463339 - Utility of cardiac biomarkers in predicting infarct size, left ventricular function, an...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of electrocardiology     Volume:  27 Suppl     ISSN:  0022-0736     ISO Abbreviation:  J Electrocardiol     Publication Date:  1994  
Date Detail:
Created Date:  1995-04-13     Completed Date:  1995-04-13     Revised Date:  2009-11-11    
Medline Journal Info:
Nlm Unique ID:  0153605     Medline TA:  J Electrocardiol     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  188-93     Citation Subset:  IM    
Affiliation:
Department of Medical Cardiology, Glasgow Royal Infirmary, Scotland.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Diagnosis, Computer-Assisted*
Electrocardiography*
Humans
Myocardial Infarction / diagnosis*
Neural Networks (Computer)*
Sensitivity and Specificity
Software

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Smoothing techniques for improving the repeatability of the automated diagnosis of inferior myocardi...
Next Document:  Time-domain and frequency-domain analyses of the signal-averaged ECG in patients with sustained vent...