Abstract
The development of a decision aid for the early diagnosis of myocardial infarction is described. The system uses a connectionist system or neural network called the multilayer Perceptron. It is shown that the performance of the network can exceed that of the admitting clinicians, a panel of senior physicians in a large teaching hospital and a protocol derived using conventional statistical methods, over a wide range of performance measures. In particular, the network demonstrates the highly specific behaviour necessary when making the decision whether or not to administer thrombolytic therapy. This therapy reduces mortality but only if given in the few hours after the onset of symptoms and long before confirmatory laboratory test results are available.
The network is compact and has been implemented on a portable computer. In operation it responds very quickly, giving its diagnosis and recommendations (taking account of clinical opinion) in a fraction of the time taken to input the patient’s symptoms. An additional novel feature of the system is the use of “contribution analysis” to give an indication of the relative importance of individual data items in the decision making process.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Boissel, J and Vanarie, R (1977) Système d’aide à la phase aigué de l’infarctus du myocarde Proc Int Symposium on Medical Informatics, Toulouse (London: Taylor & Francis) 571–583.
Emerson, P et al (1988) The development of ACORN, an expert system enabling nurses to make admission decisions about patients with chest pain in an accident and emergency department Medical Informatics: Computers in Clinical Medicine, Nottingham, UK (London: British Med. Inf. Soc.) 37–40.
Fattu, J, Blomberg, D and Patrick, E (1987) CONSULT learning system applied to early diagnosis of chest pain Proc 11th Annual Symposium on Computer Applications in Medical Care 71–77.
Fuchs, R and Scheidt, S (1981) Improved criteria for admission to cardiac care units J Am Med Assoc 426 2037–2041.
Goldman, L et al (1982) A computer-derived protocol to aid the diagnosis of emergency room patients with acute chest pain New England J Med 307 588–596.
Goldman, L et al (1988) A computer protocol to predict myocardial infarction in emergency department patients with chest pain New England J Med 318 797–803.
Gutierrez, M, Wang, J and Grondin, R, O (1989) Estimating hidden units for two-layer Perceptrons Proc IEE 1st Int Conf on Artificial Neural Networks, London (IEE 313) 120–124.
Hart, A and Wyatt, J (1989) Connectionist models in medicine: an investigation of their potential Proc European Conf on AI in Medicine, London 115–124.
ISIS-2 (Second International Study of Infarct Survival) Collaborative Group (1988) Randomized trial of intravenous streptokinase, oral aspirin, both or neither, among 17,187 cases of suspected acute myocardial infarction Lancet ii 349–360.
Kereiakes, D et al (1990) Time delays in the diagnosis and treatment of acute myocardial infarction: a tale of eight cities Am Heart J 120 773–780.
Pozen, M et al (1984) A predictive instrument to improve coronary care unit admission practices in acute ischaemic heart disease: a prospective multi-centre clinical trial New England J Med 310 1273–1278.
Rumelhart, D, Hinton, G and Williams, R (1986) Learning representations by back-propagating errors Nature 323 533–536.
Verheugt, F et al (1989) Emergency room infusion of intravenous streptokinase in acute myocardial infarction: feasibility, safety and haemodynamic consequences Am Heart J 117 1018–1022.
Widrow, B, Gupta, N and Maitra, S (1973) Punish/reward: learning with a critic in adaptive threshold systems IEEE Trans on Systems, Man and Cybernetics SMC 3 455–465.
Wilcox, R et al (1988) Trial of tissue plasminogen activator for mortality reduction in acute myocardial infarction. Anglo-Scandinavian Study of Early Thrombolysis (ASSET). Lancet ii 525–533.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Harrison, R.F., Marshall, S.J., Kennedy, R.L. (1991). A Connectionist Aid to the Early Diagnosis of Myocardial Infarction. In: Stefanelli, M., Hasman, A., Fieschi, M., Talmon, J. (eds) AIME 91. Lecture Notes in Medical Informatics, vol 44. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-48650-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-48650-0_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54144-8
Online ISBN: 978-3-642-48650-0
eBook Packages: Springer Book Archive