Abstract
A connectionist method is used in order to produce decision making limits for clinician from example patent data. A clinical patient material with symptoms and signs typical for Nephropathia epidemica (NE) is used as an example material. A single layer neural net was built using Minsky-Papert’s perceptron algorithm. Half of the material was used for learning and half for testing. The performance of the net was measured as a correctness rate for the classification of test material. A clear improvement was detected in the performance after the optimal cut-off points were searched using the connectionist method. We conclude that with connectionist algorithm we can imitate the learning process of a clinician and produce from example cases decision making limits which correlate more or less to those learned by clinician in their work.
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
Minsky ML and Papert S. Perceptrons: An Essay in Computational Geometry, (The MIT Press 1969).
Lahdevirta J. Nephropathia epidemica in Finland: A clinical, histological and epidemiological study. Ann Clin Res 3 (Suppl 8) 1971. pp. 1–154.
Lahdevirta J. Clinical features of HFRS in Scandinavia as compared with East Asia. Scand J Infect Dis Suppl 36 1982, 93–95.
Settergren B, Juto P, Trollfors B, Wadell G and Norrby SR. Clinical characteristics of Nephropathia Epidemica in Sweden: prospective study of 74 cases, Rev Infect Dis 1989; 11: 921–927.
Cosgriff T. Hemorrhagic fever with renal syndrome: four decades of research. Annals od Internal Medicine 1989; 110: 313–316.
Lahdevirta J, Savola J, Brummer-Korvenkontio M, Berndt R, Illikainer, R and Vaheri A. Clinical and serological diagnosis of Nephropathia epidemica, the mild type of hemorrhagic fever with renal syndrome. J Infect 1984; 9: 230–238.
Eklund P, Forsstrom J. Diagnosis of Nephropathia Epidemica by Adaptation through Lukasiewicz inference. Computational Intelligence 90, Milano, September 24–28, 1990, in press.
Forsstrom J, Eklund P, Virtanen H, Waxlax J, Lahdevirta J. DIAGAID: A connectionist approach to determine the information value of clinical data. Artificial Intelligence in Medicine. 1991; 3: XXX–XXX (in press).
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
Forsström, J., Fogström, M. (1991). Using Connectionist Approach for Finding Ideal Cut-Off Values for Quantitative Laboratory Tests. In: Adlassnig, KP., Grabner, G., Bengtsson, S., Hansen, R. (eds) Medical Informatics Europe 1991. Lecture Notes in Medical Informatics, vol 45. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-93503-9_63
Download citation
DOI: https://doi.org/10.1007/978-3-642-93503-9_63
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54392-3
Online ISBN: 978-3-642-93503-9
eBook Packages: Springer Book Archive