Formalized Information Description for a Medical Expert System

The purpose of research. The information description of the patient's health status is based on quantitative parameters and qualitative signs. It is proposed to formalize quantitative and qualitative information about the patient's state of health in order to use this information to build a medical expert system. The expert system built on the basis of this information will be able to make a more accurate diagnosis, which will reduce the time for diagnosis and ultimately increase the effectiveness of treatment.

Methods. On the basis of a formalized information description of the state of health of patients, it is possible to construct classes of states: the class of the current state (at the moment), the class of the reference (healthy) state of health of the patient. In the future, it is possible to build classes of patients' health conditions taking into account age and a number of features of diseases, for example, taking into account the area in which the patient lives, etc. In the future, these classes can be implemented in a medical expert system.

Results. As a result, a formalized information model of describing the patient's health status based on quantitative parameters and qualitative signs has been built, which can be the basis for a database and knowledge base of a medical expert diagnostic system.

Conclusion. As a result, a formalized description of the patient's state of health is proposed. For implementation, it is necessary to provide for the possibility of constructing a separate heuristic algorithm for the diagnosis of the disease, which will be associated with the reproduction in the form of operations of the process of developing a logical structure when reasoning by an expert (doctor) during the treatment of a patient.

1. Kanatov M., Atymtayeva L., Yagaliyeva B. Expert systems for Information Security Management and Audit. Implementation phase issues. 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS). Kitakyushu, Japan, IEEE Publ., 2014.

2. Kononenko W. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med., 2001, no. 23(1), pp. 89–109.

3. Computer-aided design of information and control systems. Designing expert systems based on system modeling [Computer-aided design of information and control systems. Designing expert systems based on system modeling]; ed. by G. G. Kulikov. Ufa, Ufa State Aviation Technical University Publ., 1999. 223 p.

4. Evlanov L. G., Kutuzov V. A. Ekspertnye ocenki v upravlenii [Expert assessments in management]. Moscow, Ekonomika Publ., 1978. 133 p.

5. Melikhov A. N., Berstein L. S., Korovin S. Ya. Situacionnye sovetuyushchie sistemy s nechetkoj logikoj [Situational advising systems with fuzzy logic]. Moscow, Nauka Publ., 1990. 272 p.

6. Sidorkina I. G. Sistemy iskusstvennogo intellekta [Artificial intelligence systems]. Moscow, KNORUS Publ., 2015. 248 p.

7. Averkin A. N., Batyrshin I. Z., Blishun A. F., Silov V. B., Tarasov V. B. Nechetkie mnozhestva v modelyah upravleniya i iskusstvennogo intellekta [Fuzzy sets in control and artificial intelligence models]; ed. by D. A. Pospelova. Moscow, Nauka Publ., 1986. 312 p.

8. Aliev R. A., Abdikeev N. M., Shakhnazarov M. M. Proizvodstvennye sistemy s iskusstvennym intellektom [Production systems with artificial intelligence]. Moscow, Radio and Communications Publ., 1990. 262 p.

9. Altunin A. E., Semukhin M. V. Modeli i algoritmy prinyatiya reshenij v nechetkih usloviyah [Models and algorithms of decision-making in fuzzy conditions]. Tyumen, Tyumen State University Publishing House, 2000. 352 p.

10. Beshelev C. D., Gurvich F. G. Matematiko-statisticheskie metody ekspertnyh ocenok [Mathematical and statistical methods of expert assessments]. Moscow, Statistics Publ., 1980. 263 p.

11. Dunin V. O., Egorov V. A. Problemy sozdaniya intellektual'nyh sredstv poiska, analiza i obrabotki biomedicinskoj informacii [Problems of creating intelligent means of searching, analyzing and processing biomedical information]. Inzhenernyj vestnik Dona = Engineering Bulletin of the Don, 2012, no. 4-1(22), p. 24.

12. Borisov A. N., Alekseev A. V., Krumberg O. A., eds. Modeli prinyatiya reshenij na osnove lingvisticheskoj peremennoj [Decision-making models based on a linguistic variable]. Riga, Zinatne Publ., 1982. 256 p.

13. Dolzhenko E. N., Pylkin A. N., Kroshilin A. V., Zhuleva S. Yu. Podderzhka prinyatiya reshenij na osnove nechetkoj logiki v sistemah medicinskogo naznacheniya [Decision support based on fuzzy logic in medical systems]. Biomedicinskaya radioelektronika = Biomedical Radioelectronics, 2015, no. 7, pp. 62‒68.

14. Zadeh L. A. Ponyatie lingvisticheskoj peremennoj i ego primenenie k prinya-tiyu priblizhennyh reshenij [The concept of a linguistic variable and its application to the adoption of approximate solutions]. Moscow, Mir Publ., 1976. 165 p.

15. Leonenko A. V. Nechetkoe modelirovanie v srede MATLAB i fuzzyTECH [Fuzzy modeling in MATLAB and fuzzyTECH]. St. Petersburg, BVH ‒ Petersburg Publ., 2005. 736 p.

16. Voronina E. I., Muravey L. A., Kostikov Yu. A. Matematiko-statisticheskie modeli prognozirovaniya effektivnosti operativnogo lecheniya nekotoryh zabolevanij [Mathematical and statistical models for predicting the effectiveness of surgical treatment of certain diseases]. Inzhenernyj vestnik Dona = Engineering Bulletin of the Don, 2013, no. 1(24), p. 64.

17. Gelrud Ya. D. Optimizaciya razvitiya holdingovoj struktury s ispol'zovaniem nechetkoj logiki [Optimization of the development of the holding structure using fuzzy logic]. Upravlenie proektami i programmami = Project and Program Management, 2007, no. 3, pp. 182‒190.

18. Dushkin R. V. Metody polucheniya, predstavleniya i obrabotki znanij s NE-faktorami [Methods of obtaining, presenting and processing knowledge with NON-factors]. Moscow, National Research University "MEI" Publ., 2011. 115 p.

19. Telnov Yu. F., eds. Inzhiniring informacionnyh i delovyh processov. Sbornik nauchnyh trudov [Engineering of information and business processes. Collection of scientific works]. Moscow, Moscow State University of Economics, Statistics and Informatics Publ., 1998. 137 p.

20. Popov E. V., Fomin I. B., Kisel E. B., Shapot M. D. Staticheskie i dinamicheskie ekspertnye sistemy [Static and dynamic expert systems]. Moscow, Finance and Statistics Publ., 1996. 318 p. 2

21. Rossiev D. A. Nejrosetevye samoobuchayushchiesya ekspertnye sistemy v medicine [Neural network self-learning expert systems in medicine]. Molodye uchenye – prakticheskomu zdravoohraneniyu [Young scientists ‒ practical healthcare]. Krasnoyarsk, 1994, p. 17.