S.Yu. Zhuleva1, A.V. Kroshilin2, S.V. Kroshilina3

1–3 Ryazan State Radio Engineering University named after V.F. Utkin (Ryazan, Russia)

The article deals with the problems associated with the presentation of knowledge in medical subject areas that require elaboration in the automation of medical decision support. There are certain stages of decision support, but they need to be clarified and specified for medical use cases. In the medical subject area, each stage is focused on a specific patient, since the same approaches do not provide a positive result for different patients. The algorithm of actions of the person making the medical decision will determine the main trajectories of the behavior of specialists when compiling the user manual and consulting medical personnel in the information system.

Managerial medical decisions and methods of obtaining medical information are different in conditions of certainty and uncertainty. In the first case, the probabilities of alternative outcomes of the situation (recommendations) are uniquely determined (deterministic), in the second case, there is a unique set of values for each variant of the outcome sets. The decision in the medical field requires clarification and additional detail. To support the adoption of a medical decision, it is necessary to have information on the problem situation, for which three main information flows can be distinguished in the medical subject area: materialized knowledge, professional knowledge of medical staff (of all categories), information about the practical solution of problems.

To obtain, process and store information and knowledge, as well as to attract additional information and new knowledge, medical information systems are used in management medical decisions, which contain the following main elements: a medical database, a medical expert system and a medical decision support system. The algorithm for the formation of a managerial medical decision in this case should be focused on the medical subject area and take into account its features and additional requirements.

There are several criteria for classifying fuzzy information, one of which is the domain of definition of fuzzy sets. In accordance with it, there are two types. The first type of fuzzy information is the sets that are defined on the numerical set X (the interval of real numbers). In this case, the set X is described using a numerical scale, and fuzzy sets are fuzzy quantities represented on this scale. Fuzzy numbers and intervals can be cited as an example of fuzzy quantities. The second type of fuzzy information is fuzzy sets defined on a non-numeric scale (facts, rules of the expert system, alternatives and goals on elements of the binary relation of objects to each other, etc.), with this approach, a fuzzy set is a set of "fuzzy objects". The representation of knowledge based on the theory of fuzzy sets in medical subject areas is based on the following definitions: "fuzziness", "inaccuracy", "uncertainty" and "fuzzy sets", "degree of proximity" and "degree of belonging", which are used in the construction of a semantic network. The classical construction of a semantic network implementing a medical domain model requires additional detail and elaboration. The theory of fuzzy sets makes it possible to model poorly defined processes, to the class of which medical and technological processes can be attributed.

Zhuleva S.Yu., Kroshilin A.V., Kroshilina S.V. Knowledge representation based on fuzzy set theory in medical subject areas. Biomedicine Radioengineering. 2022. V. 25. № 4. Р. 62-70. DOI: https://doi.org/10.18127/j15604136-202204-08 (In Russian)

1. Zhuleva S.Yu., Kroshilin A.V., Kroshilina S.V. Podderzhka prinyatiya upravlencheskikh meditsinskikh resheniy i priroda neopredelennosti v nikh. Biomeditsinskaya radioelektronika. 2021. T. 24. № 4. S. 89–96. (in Russian).
2. Zade L. Ponyatiye lingvisticheskoy peremennoy i eye primeneniye k prinyatiyu priblizhennykh resheniy: per. s angl. N.I. Ringo. M.: Mir. 1976. 168 s. (in Russian).
3. Kroshilina S.V., Zhuleva S.Yu., Kroshilin A.V. Realizatsiya modeli dinamiki raspredeleniya materialnykh potokov v meditsinskom uchrezhdenii. Biomeditsinskaya radioelektronika. 2020. T. 23. № 3. S. 53–60. (in Russian).
4. Kroshilin A.V., Kroshilina S.V. Ispolzovaniye metodov matematicheskogo modelirovaniya dlya postroyeniya sistemy informatsionnoy bezopasnosti. Problemy i metody upravleniya ekonomicheskoy bezopasnostyu regionov: Materialy mezhvuz. nauch. konf. prof.-prepod. sostava. Kolomna: KGPI. 2006. 256 s. (in Russian).
5. Kroshilin A., Kroshilina S., Pylkin A., Ovechkin G. Managerial medical decisions and methods of obtaining medical information in conditionsof uncertainty. 2021 10th Mediterranean Conference On Embedded Computing (Meco2021), 7-10 June 2021, Budva, Montenegro, 864 p, P. 500-503.
6. Pylkin A.N., Kroshilin A.V., Kroshilina S.V. Primeneniya nechetkoy logiki dlya podderzhki prinyatiya upravlencheskikh resheniy v meditsinskikh ekspertnykh sistemakh / pod nauch. red. V.I. Levina. Matematicheskiye i kompyuternyye metody v meditsine. biologii i ekologii: Kollektivnaya monografiya. Penza: Privolzhskiy dom znaniy; M.: MIEMP. 2012. S. 29–44. (in Russian).
7. Alekseyev A.V., Borisov A.N., Vilyums E.R., Slyadz N.N., Fomin S.A. Intellektualnyye sistemy prinyatiya proyektnykh resheniy. Riga: Zinatne. 1997. 320 s. (in Russian).
8. Gorodetskiy V.I., Tulupyev A.L. Neprotivorechivost baz znaniy s kolichestvennymi merami neopredelennosti. Shestaya natsionalnaya konferentsiya po iskusstvennomu intellektu s mezhdunarodnym uchastiyem KII’98: cb. nauch. tr. v 3-kh tomakh. T. 1. Pushchino. 1998. S. 100–107. (in Russian).
9. Kozlov V.N. Sistemnyy analiz. optimizatsiya i prinyatiye resheniy. M.: Prospekt. 2010. 176 s. (in Russian).