Modeling the Symptom-Disease Relationship by Using Rough Set Theory and Formal Concept Analysis

Medical Decision Support Systems (MDSSs) are sophisticated, intelligent systems that can provide inference due to lack of information and uncertainty. In such systems, to model the uncertainty various soft computing methods such as Bayesian networks, rough sets, artificial neural networks, fuzzy logic, inductive logic programming and genetic algorithms and hybrid methods that formed from the combination of the few mentioned methods are used. In this study, symptom-disease relationships are presented by a framework which is modeled with a formal concept analysis and theory, as diseases, objects and attributes of symptoms. After a concept lattice is formed, Bayes theorem can be used to determine the relationships between attributes and objects. A discernibility relation that forms the base of the rough sets can be applied to attribute data sets in order to reduce attributes and decrease the complexity of computation.

• Mert Bal
• Hayri Sever
• Oya Kalıpsız

• Formal Concept Analysis
• Rough Set Theory
• Granular Computing
• Medical Decision Support System.

[1] C. Zhang, S. Zhang, Association Rule Mining. Berlin: Springer-Verlag,
2002, ch. 1.
[2] S. Pal, P. Mitra, Pattern Recognition Algorithms for Data Mining, Boca
Raton: Chapman Hall, Boca Raton, 2004, ch.1.
[3] H. S. Nguyen, D. Slezak, "Approximate reducts and association rules
correspondence and complexity results", Lecture Notes in Computer
Science, vol. 1711, pp. 137-145, November 1999.
[4] Z. Pawlak, "Rough sets and intelligent data analysis", Information
Sciences, vol. 147, pp. 1-12, November 2002.
[5] J. Komorowski, L. Polkowski, A. Skowron. (1998). Rough sets: a
tutorial (Online). Available:
http://citeseer.ist.psu.edu/komorowski98rough.html
[6] S. Hui. (2002), Rough set classification of gene expression data
(Online). Available:
http://www.cs.uwaterloo.ca/~s2hui/RoughSetProject.pdf
[7] J. Komorowski, Z. Pawlak, L. Polkowski. (1999). A rough set
perspective on data and knowledge (Online). Available:
http://citeseer.ist.psu.edu/336073.html
[8] H. S. Binay, "Rough set approaches in investment decisions", Ph.D.
dissertation, Dept. Business Adm., Ankara Univ., Ankara, 2002.
[9] Intelligent Decision Support: Handbook of Advance and Applications of
the Rough Set Theory", Kluwer Academic Publishers, 1992, pp, 311-
362.
[10] J. M. Saquer, "Formal concept analysis and applications", Ph.D.
dissertation, Dept. Comp. Sci. and Eng. Univ. of Nebraska, Lincoln,
2000.
[11] J. M. Saquer, J. S. Deogun, "Concept approximations based on rough
sets and similarity measures", Int. Journal App. Math. Computer
Science, vol. 11, pp. 655-674, 2001.
[12] J. S. Deogun, J. M. Saquer, "Monotone concepts for formal concept
analysis", Discrete Applied Mathematics, vol. 144, pp. 70-78.
[13] W. Ganter, R. Wille, Formal Concept Analysis: Mathematical
Foundation. Berlin: Springer-Verlag, 2002, ch.1.
[14] J. S. Deogun, V. V. Raghavan, H. Sever, "Association mining and
formal concept analysis", in Proc. 6th Int. Workshop on Rough Set,
Data Mining and Granular Computing", North Carolina, 1998, pp. 335-
338.
[15] B. Oğuz, H. Sever, M. Tolun, "Eşleştirme Sorgularının Modellenmesi",
in The 9th Turkish Symposium on Artificial Intelligence and Neural
Networks", Izmir, 2000, pp. 381-390.