A.V. Kiselev1, S.A. Filist2, Haider A.Н. Alawsi3, V.V. Pesok4, A.Ye. Pshenichniy5, O.V. Shatalova6

1–6 Southwest State University (Kursk, Russia)
1 Kiselevalexey1990@gmail.com, 2 SFilist@gmail.com, 3 book.hp.2015@gmail.com, 4 lera.pesok@mail.ru,
5 lera.pesok@mail.ru, 6 shatolg@mail.ru

The aim of the study is to improve the quality of diagnostics and prediction of the functional state of the cardiorespiratory system, in particular, the respiratory system, by using the artificial intelligence methodology in clinical decision support systems.

Cardiorespiratory synchronism was taken as a key predictor of the functional state of the respiratory system. The index of cardiorespiratory synchronism is proposed to be calculated on the basis of the synchronism of the spectrum variation of the respiratory muscle electromyosignal and the spectrum variation of the cardiosignal in the region of the respiratory rhythm. Since non-stationary signals are being studied, it was proposed to use wavelet analysis to determine their spectral characteristics. It was hypothesized that with a high rate of cardiorespiratory synchronism, the power spectrum of the electrical myosignal of the respiratory muscles and the power spectrum of the cardiosignal in the same frequency range change synchronously. This made it possible to construct a method for determining cardiorespiratory synchronism based on the calculation of the arguments of vectors built on the projections of the wavelet coefficients of the wavelet plane of the electromyosignal and the wavelet plane of the cardiosignal. Therefore, the functional state of the respiratory system can be determined by means of a trainable classifier. As its descriptors, indicators of cardiorespiratory synchronism are used, determined at specific points in time on a specific time aperture and on a specific frequency segment of the wavelet planes. A block diagram of the classifier of the functional state of the respiratory system is proposed. The classifier of the functional state of the respiratory system allows quantitatively interpreting cardiorespiratory synchronism and contains software and hardware for synchronous recording of surface electromyograms and cardiosignals, as well as their wavelet analysis and classification. The software and hardware includes a trainable neural network with a hierarchical structure designed to classify the medical risk of the respiratory system. A method for calculating the integral indicator of cardiorespiratory synchronism and a method for constructing a space of informative features for the classifier of the functional state of the respiratory system are proposed.

Experimental and statistical studies of the quality indicators of the classifier were carried out on the example of the risk of community-acquired pneumonia. The main statistical indicators of the quality of the classifier were comparable with the indicators of the quality of diagnosing X-ray studies on the same control sample, which makes it possible to recommend it for clinical practice.

Kiselev A.V., Filist S.A., Alawsi Haider A.Н., Pesok V.V., Pshenichniy A.Ye., Shatalova O.V. A method for classifying the functional state of the respiratory system based on the control of cardiorespiratory synchronism indicators. Science Intensive Technologies. 2024. V. 27. № 2. P. 5–12. DOI: https://doi.org/10.18127/j19998465-202402-01 (in Russian)

1. Huang Yu Chen, Ting Yu Lin, Hau Tieng. Cardiorespiratory Coupling is Associated with Exercise Capacity in Patients with Chronic Obstructive Pulmonary Disease. BMC Pulmonary Medicine. 2021; 21(1): 22 (1-10). DOI: 10.1186/s12890-021-01400-1
2. Filist S.A., Kuz'min A.A., Alavci Hajder A.H., Pesok V.V., Pshenichnyj A.E. Klassifikacii funkcional'nogo sostoyaniya sistemy dyhaniya na osnove analiza kardiorespiratornogo sinhronizma. International Journal of Open Information Technologies. 2023; 11 (4): 21–28. ISSN: 2307-8162.
3. Grishin O.V., Grishin V.G., Kovalenko Yu.V. Variabel'nost' legochnogo gazoobmena i dyhatel'nogo ritma. Fiziologiya cheloveka. 2012. T. 38. № 2. S. 87–93.
4. Petrova T.V., Filist S.A, Degtyarev S.V., Kiselev A.V., Shatalova O.V. Prediktory sinhronnosti sistemnyh ritmov zhivyh sistem dlya klassifikatorov ih funkcional'nyh sostoyanij. Sistemnyj analiz i upravlenie v biomedicinskih sistemah. 2018. T. 17. № 3. S. 693–700.
5. Ren Y., Zhang J. Increased Cardiorespiratory Synchronization Evoked by a Breath Controller Based on Heartbeat Detection. BioMed Eng OnLine. 2019; 18: 61. DOI:10.1186/s12938-019-0683-9
6. Myasnyankin M.B., Filist S.A., Kiselev A.V., Kuz'min A.A. Formirovanie deskriptorov dlya klassifikatorov funkcional'nogo sostoyaniya sistemy dyhaniya na osnove spektral'nogo analiza elektrokardiosignala. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2020. T. 10. № 3/4. S. 8–28.
7. Kiselev A.V., Kuz'min A.A., Myasnyankin M.B., Maslak A.A., Filist S.A., Rybochkin A.F. Klassifikaciya funkcional'nogo sostoyaniya sistemy dyhaniya na osnove analiza variabel'nosti medlennyh voln VLF diapazona. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2022. T. 12. № 1. S. 8–32. DOI: 10.21869/2223-1536-2022-12-1-8-32
8. Filist S.A., Al-Kasasbeh R.T., Shatalova O.V., Btoush M.H., Namazov M., Shaqadan A.A., Alshamasin M., Korenevskiy N., Aloqeili S., Myasnyankin M.B. Biotechnical Neural Network System for Predicting Cardiovascular Health State Using Processing of Bio-Signals [Electronic Resource]. International Journal of Medical Engineering and Informatics. 2022; 1. URL: https://www.scilit.net/journal/ 2329896. DOI:10.1504/IJMEI.2022.10047451 (date accessed 25.07.2023).
9. Filist S.A., Ali Kassim K.D., Kuz'min A.A., Shatalova O.V., Alyab'ev E.A. Formirovanie priznakovogo prostranstva dlya zadach klassifikacii slozhnostrukturiruemyh izobrazhenij na osnove spektral'nyh okon i nejrosetevyh struktur. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. 2016. № 4 (67). S. 56–68.
10. Filist S.A., Shashkova E.A., Shatalova O.V., Tomakova R.A. Analiz biomedicinskih izobrazhenij razlichnymi metodami segmentacii, osnovannymi na operatorah vychisleniya gradient. Perspektivy razvitiya informacionnyh tekhnologij. 2011. № 3-1. S. 146–150.
11. Efremov M.A., Starcev E.A., Rybochkin A.F., Shatalova O.V., Serebrovskij V.V. Modeli formirovaniya prostranstva in-formativnyh priznakov dlya prognozirovaniya insul'tov po rezul'tatam issledovaniya perekhodnyh processov v anomal'nyh zonah elektroprovodnosti v eksperimentah in vivo. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2017. T. 7. № 3 (24). S. 120–131.
12. Kurochkin A.G., Zhilin V.V., Surzhikova S.E., Filist S.A. Ispol'zovanie gibridnyh nejrosetevyh modelej dlya mnogoagentnyh sistem klassifikacii v geterogennom prostranstve informativnyh priznakov. Prikaspijskij zhurnal: upravlenie i vysokie tekhnologii. 2015. № 3 (31). S. 85–95.
13. Filist S.A., Shatalova O.V., Efremov M.A. Gibridnaya nejronnaya set' s makrosloyami dlya medicinskih prilozhenij. Nejrokomp'yutery. Razrabotka i primenenie. 2014. № 6. S. 35–39.
14. Khatatneh K., Filist S., Al-Kasasbeh R.T., Aikeyeva A.A., Namazov M., Shatalova O., Shaqadan A. and Miroshnikov A. Hybrid Neural Net­works with Virtual Flows in Medical Risk. Journal of Intelligent & Fuzzy Systems. 2022; 43 (1): 1621–1632. URL: https://www.elibrary.ru/ item.asp?id=48718437. DOI: 10.3233/JIFS-212617
15. Filist S.A., Salem H.A.R., Shatalova O.V., Rudenko V.V. Modeli nechetkih nejronnyh setej s trekhstabil'nym vyhodom v instrumentarii dlya psihologicheskih i fiziologicheskih issledovanij. Sistemnyj analiz i upravlenie v biomedicinskih sistemah. 2007. T. 6. № 2. S. 475–479.
16. Efremov M.A., Filist C.A., Shatalova O.V., Starcev E.A., Shul'ga L.V. Gibridnye nechetkie modeli dlya prognozirovaniya vozniknoveniya i oslozhnenij arterial'noj gipertenzii s uchetom energeticheskih harakteristik bioaktivnyh tochek. Izvestiya Yugo-Zapadnogo gosudars­tvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2018. T. 8. № 4 (29). S. 104–119.
17. Kiselev A.V., Petrova T.V., Shatalova O.V. Gibridnye reshayushchie moduli c virtual'nymi potokami v klassifikatorah funkcional'nogo sostoyaniya slozhnyh system. Nejroinformatika, eyo prilozheniya i analiz dannyh: materialy XXVI Vserossijskogo seminara (28–30 sen­tyabrya 2018 g.). Krasnoyarsk: Institut vychislitel'nogo modelirovaniya SO RAN, 2018. S. 79–85.
18. Komlev I.A., Shatalova O.V., Degtyarev S.V., Serebrovskij A.V. Prognozirovanie i ocenka stepeni tyazhesti ishemii serdca na osnove gibridnyh nechyotkih modelej. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2019. T. 9. № 1 (30). S. 133–145.
19. Surzhikova S.E., Shatalova O.V., Fedyanin V.V. Programmno-apparatnyj kompleks diagnostiki social'no znachimyh zabolevanij. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. 2015. № 2 (15). S. 79-87.
20. Mohammed Avad Ali, Shatalova O.V., Al'-Kdasi Adel Mohammed, Snopkov V.N. Modelirovanie vliyaniya elektrokardiosignala na ocenku dinamicheskoj sostavlyayushchej bioimpedansa. Medicinskaya tekhnika. 2013. № 4 (280). S. 30–32.
21. Shatalova O., Filist S., Korenevskiy N., Protasova Z., Taha Al-kasasbeh R., Shaqadan A., Ilyash M., Rybochkin A. Application of fuzzy neural network model and current-voltage analysis of biologically active points for prediction post-surgery risks // Computer Methods in Biomechanics and Biomedical Engineering. 2021. V. 24. No. 13. P. 1504–1516. DOI: https://doi.org/10.1080/10255842. 2021.1895128