Classification of the Functional State of the Respiratory System Based on the Analysis of the Variability of Slow Waves

The purpose of research is development of a method for classifying the functional state of the respiratory system based on the analysis of the variability of slow waves of the VLF range for diagnosing the functional state of the respiratory system.

Methods. The proposed method is based on multimodal analysis of the rhythms of the cardiorespiratory system. To select slow waves of the second order, the wavelet transform of monitoring cardiac signals is used. The detector of slow waves of the second order is built on the basis of the Fourier analysis of each line of the wavelet plane belonging to the region of the breathing rhythm. This allows you to build a hierarchical structure of "weak" classifiers with their subsequent strengthening. When generating descriptors for such classifiers, the signals of slow waves reflecting variations in the breathing rhythm are extracted from the monitoring cardiosignal by means of exploratory analysis in the frequency range of the breathing rhythm and subsequent wavelet analysis in the frequency range corresponding to the frequency range of the breathing rhythm determined as a result of the exploratory analysis. The components of the relevant strings of the wavelet plane are used to calculate the descriptors of the trained neural network, which makes a decision on assigning the current state of the respiratory system to the tested state.

Results. The studies have shown that the functional state of the cardiorespiratory system is characterized by the dynamics of slow waves of the first and second order, which are associated both with the systemic rhythms of the autonomic nervous system and with the systemic rhythms of the central nervous system. In the course of experimental studies on the control sample, a comparative analysis of two methods of classification of the functional state of the respiratory system was carried out: the proposed one and the radiological one. The proposed research method is superior to radiological in specificity and somewhat inferior in sensitivity, which makes it possible to recommend them for clinical practice.

Conclusion. In the course of the study, it was revealed that for the identification of descriptors, on the basis of which classifiers of the functional state of the respiratory system are built, the correlation of wavelet-planes of the electrocardiosignal with the respiratory system using Fourier analysis can be used.

1. Chuchalin A. G., Aisanov Z. R. Narushenie funktsii dykhatel'nykh myshts pri khronicheskikh obstruktivnykh zabolevaniyakh legkikh [Violation of the function of the respiratory muscles in chronic obstructive pulmonary diseases]. Terapevticheskii arkhiv = Therapeutic Archive, 1988, vol. 60, no. 7, pp. 126-131.

2. Baevsky R. M., Berseneva A. P. Otsenka adaptatsionnykh vozmozhnostei organizma i risk razvitiya zabolevanii [Assessment of the adaptive capabilities of the body and the risk of developing diseases]. Moscow, Medicine Publ., 1997. 265 p.

3. Tetenev F. F., Ageeva T. S., Danilenk V. Yu., Dubakov A. V. Pikovaya skorost' vydokha i bronkhial'noe soprotivlenie u bol'nykh s vnebol'nichnoi pnevmoniei [Peak expiratory velocity and bronchial resistance in patients with community-acquired pneumonia]. Sibirskii meditsinskii zhurnal = Siberian Medical Journal, 2005, vol. 58, no. 8, pp. 43-45.

4. Ershov S. P., Perelman Yu. M. Elektrofiziologicheskaya kharakteristika dykhatel'nykh myshtsu bol'nykh khronicheskim bronkhitom [Electrophysiological characteristics of respiratory muscles in patients with chronic bronchitis]. Byulleten'fiziologii ipatologii dykhaniya = Bulletin of Physiology and Pathology of Respiration, 1999, is. 5, pp. 28-35.

5. Noskin L. A., Rubinsky A. V., Romanchuk A. P., Marchenko V. N., Pivovarov V. V., Cherepov A. B., Zarovkina L. A. Izuchenie serdechno-sosudistogo i dykhatel'nogo sinkhronizma pri razlichnykh rezhimakh dykhaniya [Study of cardiovascular and respiratory synchronism in different breathing modes]. Patogenez = Pathogenesis, 2018, vol. 16, no. 4, рр. 9096.

6. Kassim K. D. A., Filist S. A., Rybochkin A. F. Komp'yuternye tekhnologii obrabotki i analiza biomeditsinskikh signalov i dannykh [Computer technologies of processing and analysis of biomedical signals and data]. Kursk, Southwest State University Publ., 2016. 209 p.

7. Fleishman A. N. Variabel'nost' ritma serdtsa i medlennye kolebaniya gemodinamiki. Nelineinye fenomeny v klinicheskoi praktike [Heart rate variability and slow fluctuations of hemodynamics. Nonlinear phenomena in clinical practice]. Novosibirsk, Siberian Branch of the Russian Academy of Sciences Publishing House, 2009. 194 p.

8. Petrova T. V., Filist S. A., Degtyarev S. V., Kiselev A. V., Shatalova O. V. Prediktory sinkhronnosti sistemnykh ritmov zhivykh sistem dlya klassifikatorov ikh funktsional'nykh sostoyanii [Predictors of synchronicity of system rhythms of living systems for classifiers of their functional states]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh = System Analysis and Management in Biomedical Systems, 2018. vol. 17, no. 3, pp. 693-700.

9. Belobrov A. P., Kuzmin A. A., Filist S. A. Mnogomernaya chastotnaya selektsiya v zadachakh analiza medlennykh voln [Multidimensional frequency sequence in problems of analysis of slow waves]. Biomeditsinskaya radioelektronika = Biomedical Radioelectronics, 2010, no. 2, pp. 4-10.

10. Filist S. A., Tomakova R. A., Ya Z. D. Universal'nye setevye modeli dlya zadach klassifikatsii biomeditsinskikh dannykh [Universal network models for problems of classification of biomedical data]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceeding of the Southwest State University, 2012, no. 4 (43), pt. 2, pp. 44-50.

11. Ulyanychev N. V., Kilin E. V., Perelman Yu. M., Nakhamchen D. L. Sposob issledo- vaniya mekhaniki dykhaniya [Method for studying the mechanics of respiration]. Patent RF, no. 2009140655/14, 2011.

12. Maryanova O. V., Osnovina I. P., Kalinina O. V. Sposob diagnostiki sindroma utomleniya dykhatelnoi muskulatury u bolnykh bronkhialnoi astmoi [Method for diagnosing fatigue syndrome of respiratory muscles in patients with bronchial asthma]. Patent RF, no. 2000130701/14, 2000.

13. Shamsutdinova M. E., Miroshnichenko I. V., Ivanov K. M., Kunarbaeva A. K., Sidorova M. A., Sivozhelezova O. K. Sposob otsenki effektivnosti raboty dykhatelnykh myshts [Method for assessing the efficiency of the respiratory muscles]. Patent RF, no. 2016129437, 2017.

14. Grishin O. V., Grishin V. G., Kovalenko Yu. V. Variabel'nost' legochnogo gazoobmena i dykhatel'nogo ritma [Variability of pulmonary gas exchange and respiratory rhythm]. Fiziologiya cheloveka = Human Physiology, 2012, vol. 38, no. 2, pp. 87-93.

15. Shortliffe E. H., Sepulveda M. J. Clinical Decision Support in the Era of Artificial Intel16. ligence. JAMA. 2018, no. 320(21), рр. 2199-2200.

16. Hamet P., Tremblay J. Artificial intelligence in medicine. Metabolism. ArticlePubMed / NCBIGoogle Scholar. United States, 2017, рр. 36-40.

17. Tarnok A. Machine Learning, COVID-19 (2019-nCoV), and multi-OMICS. ArticleGoogle Scholar, 2020, no. 19, рр. 215-216.

18. Wynants L., Van Calster B., eds. Prediction models for diagnosis and prognosis of COVID-19 infection: systematic review and critical appraisal. B. M. J., 2020, no. 369, p. 1328.

19. Tomakova R. A., Yemelyanov S. G., Filist S. A. Intellektual'nye tekhnologii seg- mentatsii i klassifikatsii biomeditsinskikh izobrazhenii [Intellectual technologies of segmentation and classification of biomedical images]. Kursk, Southwest State University Publ., 2012. 222 p.

20. Grakhov A. A., Kuzmin A. A., Pihlap S. V., Filist S. A. Ispol'zovanie metoda adaptivnogo kvantovaniya mod pri issledovanii veivlet-izobrazhenii elektrokardiosignalov bol'nykh ishemicheskoi bolezn'yu serdtsa [Using the adaptive mode quantization method in the study of wavelet images of electrocardiosignals of patients with ischemic heart disease]. Izvestiya Yuzhnogo Federalnogo universiteta. Tekhnicheskie nauki. Tematicheskii vypusk "Meditsinskie informatsionnye sistemy" = Proceedings of the Southern Federal University. Technical Sciences. Thematic Issue "Medical Information Systems", 2008, no. 5 (82), pp. 7679.

21. Myasnyankin M. B, Filist S. A., Kiselev A. V., Kuzmin A. A. Formirovanie deskriptorov dlya klassifikatorov funktsionalnogo sostoyaniya sistemy dykhaniya na osnove spektralnogo analiza elektrokardiosignala [Formation of descriptors for classifiers of the functional state of the respiratory system based on the spectral analysis of the electrocardiosignal]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceeding of the Southwest State University, 2020, vol. 10, no. 3/4, рр. 8-28.

22. Filist S. A., Shatalova O. V., Efremov M. A. Gibridnaya neironnaya set' s makrosloyami dlya meditsinskikh prilozhenii [Hybrid neural network with macro-layers for medical applications]. Neirokomp'yutery. Razrabotka iprimenenie = Neurocomputers. Development and Application, 2014, no. 6, рр. 35-39.

23. Tomakova R. A., Efremov M. A., Filist S. A., eds. Gibridnye tekhnologii vydeleniya medlennykh voln iz kvaziperiodicheskikh signalov [Hybrid technologies for the isolation of slow waves from quasi-periodic signals ]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceeding of the Southwest State University, 2011, no. 1 (34), pp. 66-73.