Development of automated system for diagnosing liver cirrhosis and selecting the optimal treatment option

Authors

  • Олена Костянтинівна Носовець National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056, Ukraine https://orcid.org/0000-0003-1288-3528
  • Олена Володимирівна Яценко National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056, Ukraine https://orcid.org/0000-0001-9447-6787
  • Роман Юрійович Древко National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056, Ukraine https://orcid.org/0000-0002-4943-2504

DOI:

https://doi.org/10.15587/2312-8372.2016.70228

Keywords:

liver cirrhosis, automated system, forecasting, logistic regression

Abstract

This research is devoted to developing the automated system of diagnosing liver cirrhosis, the number of which according to WHO data increases every year.

Despite the large number of existing achievements in the field of mathematical simulation of liver disease, creation of diagnostic models based on simple laboratory evidence is still relevant, because most of them don’t consider the possibility of qualitative signs or require complex laboratory tests.

The object of research is the process of identifying and analyzing the course of liver cirrhosis treatment using information technologies.

The aim of research is development of information system for diagnosing and analyzing the course of liver cirrhosis treatment on the basis of mathematical simulation.

An array of observations in 412 patients was applied as the clinical material, in the presence of informative consent of patients, who were divided into two groups according to the degree of liver damage. The analysis of general information about the patients, the results of biochemical blood tests and prescribed treatment was allocated a number of informative signs used in the simulation. The correctness of the chosen informative signs confirmed literature data and high accuracy of the mathematical models. It was determined that the indicators included in the stage of developing models affect the availability of liver disease with high degrees (p <0,001).

The mathematical models estimate the probability of liver disease with high degree (including liver cirrhosis) and probability of liver disease with high degree (including liver cirrhosis) in the remote period after treatment.

The automated system developed for the practical implementation of obtained mathematical models and designed to the diagnosing and selecting an optimal treatment of liver diseases.

Validity of an automated system that implements mathematical models was confirmed by testing of the independent test sample. The total classification accuracy was 84,9 %.

Author Biographies

Олена Костянтинівна Носовець, National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056

Candidate of Technical Science, Associate Professor

Department of Biomedical Cybernetics

Олена Володимирівна Яценко, National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056

Senior Lecturer

Department of Biomedical Cybernetics

Роман Юрійович Древко, National Technical University of Ukraine «Kyiv Polytechnic Institute», Pr. Pobedi, 37, Kyiv, 03056

Department of Biomedical Cybernetics

References

  1. World Health Organization. Health statistics and information systems. (2016). World Health Organization. Available: http://www.who.int/about/en/
  2. Satarkar, S. L., Ali, M. S. (2015). Fuzzy expert system for the diagnosis of common liver disease. International Engineering Journal For Research & Development, Vol. 1, № 1, 2–7.
  3. Neshat, M., Yaghobi, M., Naghibi, M. B., Esmaelzadeh, A. (2008, December). Fuzzy Expert System Design for Diagnosis of Liver Disorders. 2008 International Symposium on Knowledge Acquisition and Modeling. Institute of Electrical & Electronics Engineers (IEEE), 252–256. doi:10.1109/kam.2008.43
  4. Remien, C. H., Adler, F. R., Waddoups, L., Box, T. D., Sussman, N. L. (2012, July 6). Mathematical modeling of liver injury and dysfunction after acetaminophen overdose: Early discrimination between survival and death. Hepatology, Vol. 56, № 2, 727–734. doi:10.1002/hep.25656
  5. Huo, T.-I., Lee, S.-D., Lin, H.-C. (2008, April 10). Selecting an optimal prognostic system for liver cirrhosis: the model for end-stage liver disease and beyond. Liver International, Vol. 28, № 5, 606–613. doi:10.1111/j.1478-3231.2008.01727.x
  6. Lifshchits, V. B., Sernov, S. P. (2010). Matematicheskoe modelirovanie v diagnostike alkogol'noi bolesni pecheni. Vestnik sovremennoi klinicheskoi meditsiny, 3, 106–108.
  7. Fraser, P. M., Franklin, D. A. (1974). Mathematical models for the diagnosis of liver disease. Problems arising in the use of conditional probability theory. The Quarterly Journal of Medicine, 43 (169), 73–88.
  8. Abdeldayem, H., Allam, N. (2012). Liver Transplantation – Basic Issues. Rijeka, Croatia: InTech, 428. doi:10.5772/1473
  9. Di Martino, V., Weil, D., Cervoni, J., Thevenot, T. (2015). New prognostic markers in liver cirrhosis. World Journal of Hepatology, Vol. 7, № 9, 1244–1250. doi:10.4254/wjh.v7.i9.1244
  10. Peduzzi, P., Concato, J., Kemper, E., Holford, T. R., Feinstein, A. R. (1996, December). A simulation study of the number of events per variable in logistic regression analysis. Journal of Clinical Epidemiology, Vol. 49, № 12, 1373–1379. doi:10.1016/s0895-4356(96)00236-3

Downloads

Published

2016-05-26

How to Cite

Носовець, О. К., Яценко, О. В., & Древко, Р. Ю. (2016). Development of automated system for diagnosing liver cirrhosis and selecting the optimal treatment option. Technology Audit and Production Reserves, 3(1(29), 4–8. https://doi.org/10.15587/2312-8372.2016.70228

Issue

Vol. 3 No. 1(29) (2016): Mathematical modeling. Mechanical engineering and machine building. Information technologies

Section

Mathematical Modeling: Original Research

License

Copyright (c) 2016 Олена Костянтинівна Носовець, Олена Володимирівна Яценко, Роман Юрійович Древко

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.