Markov Chains Pattern Recognition Approach Applied to the Medical Diagnosis Tasks
In many medical decision problems there exist dependencies between subsequent diagnosis of the same patient. Among the different concepts and methods of using “contextual” information in pattern recognition, the approach through Bayes compound decision theory is both attractive and efficient from the theoretical and practical point of view. Paper presents the probabilistic approach (based on expert rules and learning set) to the problem of recognition of state of acid-base balance and to the problem of computer-aided anti-hypertension drug therapy. The quality of obtained classifier are compared to the frquencies of correct classification of three neural nets.
KeywordsPosterior Probability Learning Sequence Pattern Recognition Algorithm Decision Area Conditional Density Function
Unable to display preview. Download preview PDF.
- 2.Haralick, R.M.: Decision Making in Context. IEEE Trans. on Pattern Anal. Machine Intell., PAMI-5 (1983)Google Scholar
- 4.Giakoumakis, E., Papakonstantiou, G., Skordalakis, E.: Rule-based systems and pattern recognition. Pattern Recognition Letters 5 (1987)Google Scholar
- 5.Jackowski, K., Kurzynski, M., Wozniak, M., Zolnierek, A.: Different approaches to the sequential diagnosis problem: a comparative study. Computers in Medicine 1, 220–225 (1997)Google Scholar
- 7.Lin, T.Y., Wildberger, A. (red.), Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery, San Diego, Simulation Councils Inc. (1995)Google Scholar
- 13.Burduk, R.: Decision Rules for Bayesian Hierarchical Classifier with Fuzzy Factor. Soft Methodology and Random Information Systems. In: Advances in Soft Computing, pp. 519–526. Springer, Berlin (2004)Google Scholar