Mathematical models to automate diagnostic processes with patients in a pre-stroke condition
Authors: Sidnyaev N.I., Garazha V.V.
Published in issue: #8(152)/2024
DOI: 10.18698/2308-6033-2024-8-2377
Category: Mechanics | Chapter: Biomechanics and Bioengineering
This study objective is to define a mathematical model that could underlie automation of the diagnostic processes with patients in a pre-stroke condition. The paper proposes to use a “black box” representation of a person being diagnosed. It shows that this approach could be used to assess the patient's condition and accumulate information from several examinations. A diagnostic matrix is used to identify relationship between the diagnostic parameters and the person's physical condition. The work applied a number of stages to obtain a testing set and a localizing set, which implies reducing the distinguishability function using a table. After removing unnecessary lines according to the membership principle, the Boolean product of the remaining functions was obtained to determine the minimum diagnostic set. The considered diagnostic matrices are the deterministic models of objects of diagnosing patients in the pre-stroke condition, where each possible physical state is assigned with a well-defined rigid combination of the conditional parameter values. The paper considers advantages of the proposed analytical model, which includes obtaining specific numerical values of a person's physical state making it possible to identify the person’s function state for its further prediction. The diagnostic matrix provides an opportunity to receive a description of all types of relationships between the physical states of a person and the diagnostic parameters. The resulting model could be called illustrative and relatively simple, which helps in facilitating the diagnostics process. The Boolean function used systems are based on the diagnostic matrices and serve as the foundation in synthesizing logical automata for diagnostics capable of simplifying the diagnostics process and carrying it out not only in the clinical settings.
EDN LQSGXK
References
[1] Kalenova I.E., Shmyrev V.I., Boyartsev V.V., Chetkarev Yu.E., Ardashev V.N. Prognozirovanie vozniknoveniya ishemicheskogo insulta [Prognostication of the probability of ishemic stroke]. Klinicheskaya meditsina — Clinical Medicine, 2013, vol. 91, no. 9, pp. 48–52.
[2] Ozaltin O., Coskun O., Yeniay O., Subasi A. A Deep Learning Approach for Detecting Stroke from Brain CT Images Using OzNet. Bioengineering, 2022, vol. 9, no. 12, p. 783.
[3] Mukhametzianov A.M., Sharafutdinova N.Kh., Izhbuldina G.I., Usmanov Z.N. Pervichnaya profilaktika insulta v usloviyakh mnogoprofilnoy polikliniki [Primary prevention of stroke in multidisciplinary clinic]. Sovremennye problemy nauki i obrazovaniya — Modern Problems of Science and Education, 2015, no. 3, p. 213. Available at: https://s.science-education.ru/pdf/2015/3/459.pdf
[4] Martynev E.V. Differentsialnaya diagnostika insultov v molodom vozraste. Klinicheskiy sluchay [Differential diagnostics of strokes in young age. Clinical case]. Vselennaya mozga — Brain Universe, 2019, vol. 1, no. 2, pp. 27–29.
[5] Zihni E., Madai V.I., Livne M., Galinovic I., Khalil A.A., Fiebach J.B., Frey D. Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome. PLoS One, 2020, vol. 15, no. 4, p. e0231166.
[6] Fedorenko E.I., Sysoev O.M., Farmanian Kh.A. Profilaktika insulta v molodom vozraste [Stroke prevention at a young age]. Intellektualnyi i nauchnyi potentsial XXI veka: sbornik statei Mezhdunarodnoi nauchno-prakticheskoi konf. (mai 22, 2017 Volgograd) [Intellectual and scientific potential of the 21st century: Collection of papers of the Int. research and practical conf. (May 22, 2017, Volgograd)]. In 4 parts. Ufa, MTsII Omega Science, 2017, part 4, pp. 116–118.
[7] Lyashenko E.A. Rol kaliya i magniya v profilaktike insulta [The role of potassium and magnesium in stroke prevention]. RMZh — Russian Medical Inquiry, 2012, vol. 20, no. 19, pp. 960–962.
[8] Meshkova K.S., Gudkova V.V., Stakhovskaya L.V. Faktory riska i profilaktika insulta [Risk factors and prevention of stroke]. Zemskiy vrach, 2013, no. 2 (19), pp. 16–19.
[9] Gunkin A.M., Ponomarev I., Primachenko G.K. Razrabotka sistemy opovesheniya o predinsultnom sostoyanii cheloveka [Development of a system for warning about a person’s pre-stroke condition]. In: Gagarinskie chteniya [Gagarin Readings]. Moscow, MAI Publ., 2017, pp. 941–942.
[10] Xu W., Lin J., Gao M., Chen Y., Cao J., Pu J., Qian K. Rapid computer‐aided diagnosis of stroke by serum metabolic fingerprint based multi-modal recognition. Advanced Science, 2020, vol. 7, no. 21, p. 2002021.
[11] Yang C.C. Explainable artificial intelligence for predictive modeling in healthcare. Journal of healthcare informatics research, 2022, vol. 6, no. 2, pp. 228–239.
[12] Kychkin A.V. Intellektualnaya informatsionno-diagnosticheskaya sistema dlya issledovaniy krovenosnykh sosudov [Intelligent information and diagnostic system for examining blood vessels]. Izvestiya Rossiyskoy akademii nauk. Teoriya i sistemy upravleniya — Journal of Computer and Systems Sciences International, 2013, no. 3, p. 114.
[13] Bereznikov A.I., Shevyakin V.N., Soloshenko S.V., Kryukov A.A. Progno-zironanie, differentsialnaya diagnostika i upravlenie kombinirovannoy terapiey trombozov tsentralnoy veny setchatki i ee vetvey [Forecasting, differential diagnostics and management of combined therapy of thrombosis of the central retinal vein and its branches]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh — System Analysis and Management in Biomedical Systems, 2008, vol. 7, no. 4, pp. 999–1004.
[14] Kotov S.V., Isakova E.V. Insult: diagnostika, lechenie [Stroke: diagnostics, treatment]. Almanakh klinicheskoy meditsiny — Almanac of Clinical Medicine, 2004, no. 7, pp. 275–294.
[15] Kandyba D.V. Insult [Stroke]. Rossiyskiy semeynyi vrach — Russian Family Doctor, 2016, vol. 20, no. 3, pp. 5–15.
[16] Dzhaubaeva Z.K, Dzhanibekova T.T. Issledovanie matematicheskikh modeley [Research of mathematical models]. Sovremennye problemy matematicheskogo obrazovaniya: materialy III Vserossiyskoi nauchno-prakticheskoi konferentsii [Modern problems of mathematical education: materials of the III All-Russian. research and practical conf.]. Karachaevsk, 2018, pp. 110–113.
[17] Saylaubekov N.T. Printsipy razrabotki analiticheskikh modeley [Principles of development of analytical models]. Vestnik KazEU — Central Asian Economic Review, 2009, no. 1, pp. 291–294.
[18] Bratus А., Novozhilov A., Platonov A. Dinamicheskie sistemy i modeli v biologii [Dynamic systems and models in biology]. Мoscow, Litres Publ., 2022, 390 p.
[19] Gadalov V.N., Korenevskiy N.A., Snopkov V.N. Matematicheskie modeli reflektornykh sistem organizma cheloveka i ikh ispolzovanie dlya prognozirovaniya i diagnostiki zabolevaniy [Mathematical models of reflex systems the body uefa rights and use them for prediction and diagnosis of diseases]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh — System Analysis and Management in Biomedical Systems, 2012, vol. 11, no. 2, pp. 515–521.
[20] Kortuzov D.E., Gorbenko A.Yu., Pavlova A.I. Issledovanie operatsiy s nechetkimi mnozhestvami [Research of operations of fuzzy sets]. Sovremennye materialy, tekhnika i tekhnologii — Modern Materials, Equipment and Technologies, 2016, no. 1(4), pp. 98–103.
[21] Antonova G.M. Evoliutsiya terminov “chernyi yashchik” i “seryi yashchik” [The evolution of terms “black box” and “grey box”]. Vestnik Moskovskogo finansovo-yuridicheskogo universiteta — Bulletin of the MFUA, 2012, no. 1, pp. 16–19.
[22] Ermakov A.D., Evtushenko N.V. K sintezu adaptivnykh proveryayushchikh posledovatelnostey dlya nedeterminirovannykh avtomatov [Deriving adaptive checking sequence for nondeterministic Finite State Machines]. Trudy Instituta sistemnogo programmirovaniya RAN — Proceedings of the Institute for System Programming of the RAS, 2016, vol. 28, no. 3, pp. 123–144.
[23] Artemenko M.V. Sintez diagnosticheskikh matrits pri skrininge [Synthesis of diagnostic matrices in screening]. Uspekhi sovremennogo estestvoznaniya — Advances in current natural sciences, 2004, no. 12, pp. 33–34.
[24] Radzhabov A.G., Khaydarov A.Kh. Primenenie programmiruemykh logicheskikh matrits dlya meditsinskikh issledovaniy [Using programmable logic matrices in medical research]. Tsifrovoy region: opyt, kompetentsii, proekty — Digital region: experience, competences, projects, 2018, pp. 403–406.
[25] Shevelev S.S., Kobelev N.S., Kobelev V.N. Ustroystvo vypolneniya logicheskikh operatsiy [Device of the execution logical operation]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seria Upravleniye, vychislitelnaya tekhnika, informatika. Meditsinskoye priborostroyeniye — Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering, 2011, no. 2, pp. 50–56.