Abstract
The statement advocated here is that a trainable scheme resembling some elements of physician's decision making process could lead to an increased classification accuracy. Problems are considered which are difficult to cope with from both pattern recognition and AI point of view. A combination scheme is proposed which consists of an AI preprocessing part and a pattern recognition part delivering the final decision. The idea is to detect and then to aggregate the strengths of positive and negative evidence for a given medical hypothesis through a trainable nonlinear function. A possibility for application to CADIAG-2 is considered. An example from aviation medicine is presented which demonstrates the classification accuracy of 76.6 % of the proposed scheme versus 64.1 % obtained with linear discriminant analysis.
This work was partially supported by the Research Contract HИ-M-2-ИH/93 with the Young Scientists Foundation.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Gelsema E.S. (Ed.) Pattern recognition and Artificial Intelligence in medical research and clinical practice, Methods of Information in Medicine, 28, 1989, 63–65.
Chandrasekaran B., A. Goel. From numbers to symbols to knowledge structures: Artificial intelligence perspectives on the classification task, IEEE Transactions on Systems, Man, and Cybernetics, 18, 1988, 415–424.
Kuncheva L. Fuzzy multi-level classifier for medical applications, Computers in Biology and Medicine, 20, 1990, 421–431.
Kissiov V., S. Hadjitodorov, L. Kuncheva. Using key features in pattern classification, Pattern Recognition Letters, 11, 1990, 1–5.
Kuncheva L., R. Zlatev, V. Raicheva. A decision making system in aviation medicine, Proc. MIE'91, in: Lecture Notes in Medical Informatics, 45, 1991, 418–422.
Umeyama S. The complementary process of fuzzy medical diagnosis and its properties, Information Sciences, 38, 1986, 229–242.
Adlassnig K.-P. Fuzzy set theory in medical diagnosis, IEEE Transactions on Systems, Man, and Cybernetics, SMC-16, 1986, 260–265.
Adlassnig K.-P., W. Scheithauer, G. Kolarz. Fuzzy medical diagnosis in a hospital, In: H. Prade and C. Negoita (eds.) Fuzzy Logic in Knowledge Engineering, Verlag TUV Rheinland, Germany, 1986, 275–294.
Adlassnig K.-P. Uniform representation of vagueness and imprecision in patient's medical findings using fuzzy sets, in: R. Trappl (ed.) Cybernetics and Systems'88, Kluwer Academic Publishers, 1988, 685–692.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuncheva, L.I., Zlatev, R.Z., Neshkova, S.N., Gamper, H. (1993). A combination scheme of artificial intelligence and fuzzy pattern recognition in medical diagnosis. In: Klement, E.P., Slany, W. (eds) Fuzzy Logic in Artificial Intelligence. FLAI 1993. Lecture Notes in Computer Science, vol 695. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56920-0_17
Download citation
DOI: https://doi.org/10.1007/3-540-56920-0_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56920-6
Online ISBN: 978-3-540-47782-2
eBook Packages: Springer Book Archive