Multiclassifier systems applied to the computer-aided sequential medical diagnosis

• Autorzy: Kurzyński M. , Majak M. , Żołnierek A.

Identyfikatory

DOI

10.1016/j.bbe.2016.08.001

• Języki publikacji: EN

Abstrakty

EN

The diagnosis of patient's state based on results of successive examinations is common task in the medicine. In computer-aided algorithms taking into account the patient's history in order to improve the quality of classification seems to be very reasonable solution. In this study, two original multiclassifier systems (MC) for the computer-aided sequential diagnosis are developed, which differ with decision scheme and the methods of combining of base classifiers. The first MC system is based on dynamic ensemble selection scheme and works in two-level structure. The second MC system in combining procedure uses original concept of meta-Bayes classifier and produces decision according to the Bayes rule. Both MC systems were practically applied to the diagnosis of human acid–base equilibrium states and compared with some state-of-the-art sequential diagnosis methods. Results obtained in experimental investigations imply that MC system is effective approach, which improves recognition accuracy in sequential diagnosis scheme.

Słowa kluczowe

EN

multiclassifier system; sequential medical diagnosis; dynamic ensemble selection; meta-Bayes classifier; acid base equilibrium states

PL

sekwencyjna diagnoza medyczna; wybór zespołu dynamiczny; klasyfikator Bayesa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2016
• Tom: Vol. 36, no. 4
• Strony: 619--625
• Opis fizyczny: Bibliogr. 23 poz., rys., tab.

Twórcy

autor

Kurzyński M.

• Department of Systems and Computer Networks, Wrocław University of Science and Technology, Wyb. Wyspiańskiego 27, 50-370 Wrocław, Poland

autor

Majak M.

• Department of Systems and Computer Networks, Wrocław University of Science and Technology, Wyb. Wyspiańskiego 27, 50-370 Wrocław, Poland

autor

Żołnierek A.

• Department of Systems and Computer Networks, Wrocław University of Science and Technology, Wyb. Wyspiańskiego 27, 50-370 Wrocław, Poland

Bibliografia

• [1] Wozniak M. Markov chains pattern recognition approach applied to the medical diagnosis tasks. Biological and Medical Data Analysis, LNBI 3745. Springer Verlag; 2005. p. 231–41.
• [2] Tarik Al-Ani T, Hamam Y. A stochastic learning based approach for automatic medical diagnosis using HMM toolbox in Scilab environment. Proc. of the IEEE Conference on Control Applications. 2005. pp. 28–31.
• [3] Bourgani E, Stylios Ch, Manis G, Georgopoulos V. Time dependent fuzzy cognitive maps for medical diagnosis. Proc. of 8th Hellenic Conference on Artificial Intelligence. Springer Verlag (LNAI 8445); 2014. p. 544–52.
• [4] Xue J, Wauwautosa W, Krajnak M. Fuzzy expert systems for sequential pattern recognition for patient status monitoring in operating room. Proc. of Annual International Conference of Engineering in Medicine and Biology Society. 2006. pp. 4671–4.
• [5] Kurzynski M. Benchmark of approaches to sequential diagnosis. In: Lisboa P, Ifeachor E, editors. Artificial neural networks in biomedicine. London: Springer; 2000. p. 129–40.
• [6] Kurzynski M, Zolnierek A. Sequential classification via fuzzy relations. Lecture Notes in Artificial Intelligence, vol. 4029. 2006;p. 1165–70.
• [7] Kurzynski M, Zołnierek A, Wolczowski A. Control of bio-prosthetic hand via sequential recognition of EMG signals using rough sets. Computer Recognition Systems 3. Berlin/ Heidelberg: Springer Verlag; 2009. p. 455–62.
• [8] Kuncheva L. Combining pattern classifiers: methods and algorithms. Wiley-Interscience; 2004.
• [9] Rokach L. Ensemble-based classifiers. Artif Intell Rev 2010;33:1–39.
• [10] Kamali T, Boostani R, Parsaei H. A multi-classifier approach to MUAP classification for diagnosis of neuromuscular disorders. IEEE Trans Neural Syst Rehabil Eng 2014;22:191–200.
• [11] Antonelli M, Cococcioni M, Lazzerini B, Marcelloni F, Stefanescu D. A multiclassifier system for pulmonary nodule classification. Proc. of IEEE International Symposium on Computer-Based Medical Systems. IEEE Computer Society Press; 2008. p. 587–9.
• [12] Davidsen S, Padmavathamma M. Multi-modal evolutionary ensemble classification in medical diagnosis problems. Proc. of International Conference on Advances in Computing, Communications and Informatics. 2015. pp. 1366–70.
• [13] Wołoszynski T, Kurzynski M. A probabilistic model of classifier competence for dynamic ensemble selection. Pattern Recogn 2011;44:2656–68.
• [14] Łysiak R, Kurzynski M, Woloszynski T. Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers. Neurocomputing 2014;126: 29–35.
• [15] Wołoszyński T, Kurzynski M, Podsiadlo P, Stachowiak G. A measure of competence based on random classification for dynamic ensemble selection. Inf Fusion 2012;13(3):207–13.
• [16] Woloszynski T. Classifier competence based on probabilistic modeling (ccprmod.m) at Matlab central file exchange; 2010, http://www.mathworks.com/matlabcentral/fileexchange/ 28391-classifier-competence-based-on-probabilistic- modeling.
• [17] Meisel W. Potential functions in mathematical pattern recognition. IEEE Trans Comput 1969;C-18:911–8.
• [18] Kurzynski M, Zołnierek A. Sequential pattern recognition: naive Bayes versus fuzzy relation method. Proc of International Conference on Computational Intelligence for Modelling Control & Automation CIMCA, vol. 1. IEEE Computer Society Press; 2005. p. 1165–70.
• [19] Duin R, Juszczak P. PRTools4. A Matlab Toolbox for Pattern Recognition. Delft University of Technology; 2007, http://prtools.org/.
• [20] Wolpert DH. Stacked generalization. Neural Netw 1992;5:214–59.
• [21] Duda R, Hart P, Stork D. Pattern classification. New York: John Wiley and Sons; 2000.
• [22] Ghahramani Z. An introduction to hidden Markov models and Bayesian networks. J Pattern Recogn Artif Intell 2001;15 (1):9–42.
• [23] Alpaydin E. Combined 5 _ 2 cv F test for comparing supervised classification learning algorithms. Neural Comput 1999;11(8):1885–92.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.