Advanced

Intelligent computer reporting 'lack of experience' : A confidence measure for decision support systems

Holst, H.; Ohlsson, M. LU ; Peterson, C. LU and Edenbrandt, L. LU (1998) In Clinical Physiology 18(2). p.139-147
Abstract

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... (More)

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.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial intelligence, Computer-assisted, Diagnosis, Electrocardiography, Myocardial infarction
in
Clinical Physiology
volume
18
issue
2
pages
9 pages
publisher
Wiley-Blackwell
external identifiers
  • scopus:0031980916
ISSN
0144-5979
DOI
10.1046/j.1365-2281.1998.00087.x
language
English
LU publication?
yes
id
11fa8d3e-897d-4368-9114-80bf7e2db103
date added to LUP
2017-05-19 08:15:37
date last changed
2017-05-22 09:10:04
@article{11fa8d3e-897d-4368-9114-80bf7e2db103,
  abstract     = {<p>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.</p>},
  author       = {Holst, H. and Ohlsson, M. and Peterson, C. and Edenbrandt, L.},
  issn         = {0144-5979},
  keyword      = {Artificial intelligence,Computer-assisted,Diagnosis,Electrocardiography,Myocardial infarction},
  language     = {eng},
  number       = {2},
  pages        = {139--147},
  publisher    = {Wiley-Blackwell},
  series       = {Clinical Physiology},
  title        = {Intelligent computer reporting 'lack of experience' : A confidence measure for decision support systems},
  url          = {http://dx.doi.org/10.1046/j.1365-2281.1998.00087.x},
  volume       = {18},
  year         = {1998},
}