Hybrid Neuro-Fuzzy Classifier for Monitoring the Effectiveness of Treatment of Diseases of the Respiratory System, Taking into Account Comorbidity

The purpose of research is to develop a hybrid neuro-fuzzy classifier for remote monitoring of the severity of community-acquired pneumonia, taking into account the risk of concomitant diseases.

Methods. To assess the severity of community-acquired pneumonia and determine the effectiveness of its treatment plan, a hybrid neural network is included in the hybrid neuro-fuzzy classifier, which contains three macrolayers: PNNFNN-FNN*. The number of decisive blocks of the PNN macrolayer is equal to the number of segments allocated in the space of informative features, and the output of each PNN block produces risk and non-risk assessments of communityacquired pneumonia by severity clusters. Aggregation of decisions made over N segments of the space of informative features is carried out in the FNN layer, which has the structure of a fuzzy decision-making module. The aggregation of 2L PNN-FNN outputs occurs in the FNN* macrolayer. The same macrolayer takes into account the influence of comorbidity on the severity of community-acquired pneumonia.

Results. The testing of a hybrid neuro-fuzzy classifier of the severity of community-acquired pneumonia was carried out on an experimental group of patients with community-acquired pneumonia with comorbidity in the form of coronary heart disease. Indicators of the quality of classification of the severity of pneumonia taking into account the risk of comorbid disease using the example of coronary heart disease showed that the aggregation of the classifier of the severity of community-acquired pneumonia and the classifier of the risk of comorbid disease in the form of a hybrid neuro-fuzzy classifier makes it possible to improve the quality of assessing the severity of community-acquired pneumonia by more than 10% for all quality indicators.

Conclusion. A hybrid neuro-fuzzy classifier, built on different pattern recognition paradigms, makes it possible to identify clusters of disease severity and improve the quality indicators for classifying the severity of community-acquired pneumonia in the presence of comorbidity by an average of 12%.

1. Chuchalin A. G., Sinopal'nikov A. I., Kozlov R. S., eds. Vnebol'nichnaya pnevmoniya u vzroslyh: prakticheskie rekomendatsii po diagnostike, lecheniyu i profilaktike (Posobie dlya vrachej) [Community-acquired pneumonia in adults: practical recommendations for diagnosis, treatment and prevention (A manual for doctors)]. Klinicheskaya mikrobiologiya i antimikrobnaya himioterapiya = Clinical Microbiology and Antimicrobial Chemotherapy, 2010, vol. 12, no. 3, pp. 186‒225.

2. Chuchalin A. G., Sinopal'nikov A. I., Kozlov R. S., eds. Klinicheskie rekomendatsii po diagnostike, lecheniyu i profilaktike tyazheloj vnebol'nichnoj pnevmonii u vzroslyh [Clinical guidelines on diagnosis, treatment and prevention of severe community-acquired pneumonia in adults]. Pul'monologiya = Pulmonology, 2014, no. 4, pp. 13–48. https://doi.org/10.18093/0869-0189-2014-0-4

3. Rogozhkina Yu. A., Mishchenko T. A., Malishevskij L. M., eds. Sozdanie prognosticheskoj modeli dlya otsenki stepeni tyazhesti vnebol'nichnoj pnevmonii [The creation of predictive models forassessing the severity of community-acquired pneumonia]. Byulleten' fiziologii i patologii dyhaniya = Bulletin of Physiology and Pathology of Respiration, 2019, vol. 1, no. 71, pp. 45‒50. https://doi.org/10.12737/article_5c898b1674b5d2.31350435

4. Sirotko I. I., Samojlov R. G. Matematicheskie modeli vnebol'nichnoj pnevmonii [Mathematical models of predicting course of community-acquired pneumonia in young persons]. Sibirskij meditsinskij zhurnal = Siberian Medical Journal, 2007, no. 2, pp. 5‒10.

5. Kurochkin A. G., Zhilin V. V., Filist S. A., Surzhikova S. A. Ispol'zovanie gibridnyh nejrosetevyh modelej dlya mnogoagentnyh sistem klassifikatsii v geterogennom prostranstve informativnyh priznakov [Use of hybrid neural network models for multi-agent classification systems in heterogeneous space of informative signs]. Prikaspijskij zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Management and High Technologies, 2015, vol. 3, no. 31, pp. 85‒95.

6. Kurochkin A. G., Protasova V. V., Filist S. A., Shutkin A. N. Nejrosetevye modeli dlya metaanaliza mediko-ekologicheskih dannyh [Neural network models for metaanalysis of medical and environmental data]. Nejrokomp'yutery. Razrabotka, primenenie = Neurocomputers. Development, Application, 2015, no. 6, pp. 42‒48.

7. Petrova T. V., Kuz'min A. A., Savinov D. Yu., Serebrovskij V. V. Raspredelennye avtonomnye intellektual'nye agenty dlya monitoringa i meta-analiza effektivnosti upravleniya zhivymi sistemami [Distributed autonomous intellectual agents for monitoring and metaanalysis of living systems management effectiveness]. Prikaspijskij zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies, 2017, vol. 4, no. 40, pp. 61‒ 73.

8. Zhilin V. V., Filist S. A., Haled Abdul R. S., Shatalova O. V. Sposob modelirovaniya nechetkih modelej v pakete MATLAB dlya biomeditsinskih prilozhenij [A method for modeling fuzzy models in the MATLAB package for biomedical applications]. Meditsinskaya tekhnika = Medical Equipment, 2008, no. 2, pp. 15‒18.

9. Zhilin V. V., Filist S. A., Al'-Muaalemi V. A. Gibridnyj sposob klassifikatsii biosignalov na osnove tekhnologij nechetkoj logiki prinyatiya reshenij i nejronnyh setej [Hybrid method of classification of biosignals based on fuzzy decision logic and neural networks technologies]. Biomeditsinskaya Radioelektronika = Biomedicine Radioengineering, 2009, no. 5, pp. 77‒82.

10. Filist S. A., Petrova T. V., Podmaster'ev K. V., Shatalova O. V. [Intelligent information systems for monitoring the effectiveness of medicinal prescriptions and therapeutic procedures]. Nejrokomp'yutery i ih primenenie. Tezisy dokladov XVI Vserossijiskoj nauchnoj konferentsii (13 marta 2018 g.) [Neurocomputers and their application: Abstracts of the XVI All-Russian Scientific Conference (March 13, 2018)]. Moscow, Moscow State Psychological and Pedagogical University Publ., 2018, pp. 74–77. (In Russ.)

11. Kurochkin A. G., Protasova V. V, Filist S. A., eds. Nejrosetevye modeli dlya metaanaliza mediko-ekologicheskih dannyh [Neural network models for meta-analysis of medical and environmental data]. Nejrokomp'yutery: razrabotka, primenenie = Neurocomputers. Development, Application, 2015, no. 6, pp. 48‒53.

12. Butusov A. V., Kiselev A. V., Petrunina E. V., Safronov R. I., Pesok V. V., Pshenichnyj A. E. Algoritmy monitoringa effektivnosti terapevticheskih i reabilitatsionnyh protsedur po pokazatelyam klinicheskogo analiza krovi v sisteme podderzhki prinyatiya vrachebnyh reshenij [Algorithms for Monitoring the Effectiveness of Therapeutic and Rehabilitation Procedures Based on Clinical Blood Analysis Indicators in the Medical Decision Support System]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2023, vol. 13, no. 1, pp. 170‒190. https://doi.org/10.21869/2223-1536-2023-13-1-170-190.

13. Filist S. A., Shatalova O. V., Efremov M. A. Gibridnaya nejronnaya set' s makrosloyami dlya meditsinskih prilozhenij [Hybrid neural network with macro layers for medical applications]. Nejrokomp'yutery: razrabotka, primenenie = Neurocomputers. Development, Application, 2014, no. 6, pp. 35‒39.

14. Emel'yanov S. G., Rybochkin A. F., Filist S. A., Haled A. R. Nejrosetevoj reshayushchij modul' dlya issledovaniya zhivyh system [Neural network solving module for the study of living systems]. Izvestiya Kurskogo gosudarstvennogo tekhnicheskogo universiteta = Proceedings of the Kursk State Technical University, 2008, vol. 2, no. 23, pp. 77‒82.

15. Filist S. A., Shutkin A. N., Uvarova V. V. Strukturno-funktsional'naya model' metaanaliza mediko-ekologicheskih dannyh [Structural and functional model of meta-analysis of medical and environmental data]. Aktual'nye napravleniya nauchnyh issledovanij XXI veka: teoriya i praktika = Current Directions of Scientific Research of the XXI Century: Theory and Practice, 2015, vol. 3, no. 8‒1 (19‒1), pp. 364‒367. https://doi.org/10.12737/15449

16. Tomakova R. A., Filist S. A., Zhilin V. V., eds. Programmnoe obespechenie intellektual'noj sistemy klassifikatsii formennyh elementov krovi [Software intellectual system of classification of formed elements of blood]. Fundamental'nye issledovaniya = Fundamental Research, 2013, no. 10, pt. 2, pp. 303‒307.

17. Morosanova N. A., Solov'ev S. Yu. Formal'nye svojstva skhemy Shortliffa [Formal properties of the Shortlife scheme]. Upravlenie bol'shimi sistemami = Managing Large Systems, 2012, no. 36, pp. 5–38.

18. Piette J. D., List J., Rana G. K., eds. Mobile Health Devices as Tools for Worldwide Cardiovascular Risk Reduction and Disease Management. Circulation, 2015, vol. 132, no. 21, pp. 2012‒2027. https://doi.org/10.1161/CIRCULATIONAHA.114.008723

19. Fisenko O. V., Sinopal'nikov A. I. Tyazhelaya vnebol'nichnaya pnevmoniya i shkaly otsenki prognoza [Severe community-acquired pneumonia and prognosis assessment scales]. Prakticheskaya pul'monologiya = Practical Pulmonology, 2014, no. 2, pp. 20‒26.

20. Shishkina E. A., Hlynova O. V., Tuev A. V., eds. Vozmozhnosti prognozirovaniya povtornogo infarkta miokarda u bol'nyh trudosposobnogo vozrasta [Prediction of recurrent myocardial infarction in working-age patients]. Rossijskij kardiologicheskij zhurnal = Russian Journal of Cardiology, 2020, vol. 25, no. 8, pp. 69‒74. https://doi.org/10.15829/1560-4071-2020-3909

21. Korenevskij N. A., Filatova O. I., Lukashov M. I., Krupchatnikov R. A. Kompleksnaya otsenka urovnya psihoemotsional'nogo napryazheniya [Comprehensive assessment of the level of psycho-emotional stress]. Biomeditsinskaya radioelektronika = Biomedicine Radioengineering, 2009, no. 5, pp. 4‒9.

22. Ermakov S. A., Bolgov A. A. Otsenka riska s ispol'zovaniem nejro-nechetkoj sistemy [Risk assessment using a neuro-fuzzy system]. Informatsiya i bezopasnost' = Information and Security, 2022, vol. 25, no. 4, pp. 583‒592. https://doi.org/10.36622/VSTU.2022.25.4.012

23. Kiselev A. V., Savinov D. Yu., Filist S. A., Shatalova O. V., Zhilin V. V. Virtual'nye potoki v gibridnyh reshayushchih modulyah klassifikatsii slozhnostrukturiruemyh dannyh [Virtual flows in hybrid decision modules of classification of complex-structured data]. Prikaspijskij zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies, 2018, vol. 2, no. 42, pp. 137‒149.

24. Kiselev A. V., Shatalova O. V., Protasova Z. U., Filist S. A., Stadnichenko N. S. Modeli latentnyh prediktorov v intellektual'nyh sistemah prognozirovaniya sostoyaniya zhivyh sistem [Models of Latent Predictors in Intellectual Systems for Forecasting the State of Living Systems]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Serija: Upravlenie, vychislitel'naja tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2020, vol. 10, no. 1, pp. 114–133.

25. Kiselev A. V., Petrova T. V., Degtyarev S. V., Rybochkin A. F., Filist S. A., Shatalova O. V., Mishustin V. N. Nejrosetevye moduli s virtual'nymi potokami dlya klassifikatsii i prognozirovaniya funktsional'nogo sostoyaniya slozhnyh sistem [Hybrid Deciding Modules with Virtual Streams for Classification and Prediction of Functional State of Complex Systems]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2018, vol. 22, no. 4(79), pp. 123‒134. https://doi.org/10.21869/2223-1560-2018-22-4-123-134.

26. Kiselev A. V., Tomakov M. V., Petrunina E. V., eds. Slabye klassifikatory s virtual'nymi potokami v intellektual'nyh sistemah prognozirovaniya serdechno-sosudistyh oslozhnenij [The prediction of cardiovascular complications with the help of weak classifiers with virtual streams in intelligent systems]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2019, vol. 9, no. 1 (30), pp. 6‒19.