Document Detail


Intelligent computer reporting 'lack of experience': a confidence measure for decision support systems.
MedLine Citation:
PMID:  9568353     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
The purpose of this study was to explore the feasibility of developing artificial neural networks that are able to provide confidence measures for their diagnostic advice. Computer-aided decision making can improve physician performance, but many physicians hesitate to use these 'black boxes'. If we are to rely upon decision support systems for such tasks as medical diagnosis it is essential that the computers indicate when the advice given is based on experience, i.e. give a confidence measure. An artificial neural network was trained to diagnose healed anterior myocardial infarction and to indicate 'lack of experience' when test electrocardiograms were different from the electrocardiograms of the training set. A database of 1249 electrocardiograms from patients who had undergone cardiac catheterization was used to train and test the neural network. Thereafter, the ability of the network to indicate 'lack of experience' was assessed using 100 left bundle branch block electrocardiograms, an electrocardiographic pattern that was excluded from the training set. The network indicated that 83% of the left bundle branch block electrocardiograms and 1% of the test electrocardiograms from catheterized patients were different from the electrocardiograms of the training set. All but one of the left bundle branch block electrocardiograms would otherwise be falsely classified as anterior myocardial infarction by the network. Artificial neural networks can be trained to indicate 'lack of experience', and this ability increases the possibility for neural networks to be accepted as reliable decision support systems in clinical practice.
Authors:
H Holst; M Ohlsson; C Peterson; L Edenbrandt
Related Documents :
7113753 - Correlation of electrophysiology and morphology in myocardial sarcoidosis. a case report.
6192403 - An unusual mechanism of initiation of circus movement tachycardia in a patient with con...
19560703 - Incidence of ventricular arrhythmias in patients on long-term support with a continuous...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Clinical physiology (Oxford, England)     Volume:  18     ISSN:  0144-5979     ISO Abbreviation:  Clin Physiol     Publication Date:  1998 Mar 
Date Detail:
Created Date:  1998-06-15     Completed Date:  1998-06-15     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  8309768     Medline TA:  Clin Physiol     Country:  ENGLAND    
Other Details:
Languages:  eng     Pagination:  139-47     Citation Subset:  IM    
Affiliation:
Department of Clinical Physiology, Lund University, Sweden.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Bundle-Branch Block / diagnosis
Confidence Intervals
Diagnosis, Computer-Assisted / standards*
Electrocardiography / methods*,  standards*
Humans
Myocardial Infarction / diagnosis
Neural Networks (Computer)*
Reproducibility of Results

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


Previous Document:  Pulmonary venous blood flow pattern in patients with univentricular hearts following total cavo-pulm...
Next Document:  Menopause is associated with the stiffness of the common carotid artery in 50-year-old women.