DOI:https://doi.org/10.15407/kvt204.02.064
Cybernetics and Computer Engineering, 2021, 2(204)
FAINZILBERG L.S.1, DSc. (Engineering), Professor,
Chief Researcher of the Department of Automatic Systems
ORCID: 0000-0002-3092-0794
e-mail: fainzilberg@gmail.com
SOLOVEY S.R.2, Student Faculty of Biomedical Engineering,
e-mail: maximum.lenovo.ml@gmail.com
1International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine,
40, Acad. Glushkova av., Kyiv, 03187, Ukraine,
2The National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»
37, Peremohy av., Kyiv, 03056, Ukraine
SELF-LEARNING INFORMATION TECHNOLOGY FOR DETECTING RESPIRATORY DISORDERS IN HOME CONDITION
Introduction. In connection with the COVID-19 pandemic, it is important to start treatment promptly in case of a threat of developing viral pneumonia in a patient. The solution to this problem requires the creation of new means for detecting respiratory disorders with a minimum probability of “missing the target”. At the same time, it is equally important to minimize visits to medical institutions by healthy patients because of the danger of their contact with possible carriers of coronavirus infections, that is, to minimize the likelihood of a «false alarm».
Purpose of the article is to develop a method that allows a patient to signal at home about the advisability of contacting a medical institution for an in-depth examination of the respiratory system, and to assess the possibility of implementing this method on a smartphone using a built-in microphone.
Methods. A distinctive feature of the proposed approach lies in the construction of a personalized standard of normal respiratory respiration for a particular patient based on self-learning from a finite sample of observations at home and in comparison, based on original computational algorithms of phonospirograms of sound signals of the following observations with the standard.
Results. A prototype of information technology has been developed that will provide home alarms about possible respiratory disorders, requiring consultation with a doctor and the need for an in-depth medical examination.
It is shown that the construction of a personalized standard of normal breathing can be carried out based on the use of a set of original computational procedures for a finite sample of realizations, independently registered by the user using a microphone built into a smartphone. The algorithm for constructing a standard is based on digital processing of a matrix of paired distances between phonospirograms of the final training sample of observations.
Findings. A software application that provides the implementation of the proposed computational procedures can be implemented on a smartphone of average performance running the Android operating system.
Keywords: respiratory noises, intelligent IT, computational procedures, smartphone.
REFERENCES
1. Piirila P., Sovijarvi A.R. Crackles: recording, analysis and clinical significance. European Respiratory Journal. 1995, no. 8(12), pp. 2139-2148.
https://doi.org/10.1183/09031936.95.08122139
2. Forgacs P. The functional basis of pulmonary sounds. Chest Journal. 1978, vol. 73,no 3, pp. 399-405. DOI: 10.1378/chest.73.3.399.
https://doi.org/10.1378/chest.73.3.399
3. Kosovets LI Experience of electronic registration and classification of breathing sounds of children with bronchopulmonary diseases. Collection of works of acoustic symposium “Consonance-2011”. 2011: Institute of Hydromechanics of the National Academy of Sciences of Ukraine, pp. 154-159. (In Russian).
4. Pasterkamp H., Carson C., Daien D., Oh Y. Digital respirosonography. New images of lung sounds. Chest Journal. 1989, vol. 96, no 6, pp. 1405-1412. DOI: 10.1378/chest.96.6.1405.
https://doi.org/10.1378/chest.96.6.1405
5. Pasterkamp H., Patel S., Wodicka G.R. Asymmetry of respiratory sounds and thoracic transmission. Medical and Biological Engineering and Computing. 1997, vol. 35, pp. 103-106.
https://doi.org/10.1007/BF02534138
6. Wodichka G.R., Kraman S.S., Zenk G.M., Pasterkamp H. Measurement of respiratory acoustic signals. Chest Journal. 1994. vol. 106, no. 4. pp. 1140-1144.
https://doi.org/10.1378/chest.106.4.1140
7. Murphy R.L.H., Vyshedskiy A. et all. Automated Lung Sound Analysis in Patients With Pneumonia. Respiratory Care. 2005, vol. 49, no. 12, pp. 1490-1497. DOI: 10.1378/chest.124.4_MeetingAbstracts.190S-b
https://doi.org/10.1378/chest.124.4_MeetingAbstracts.190S-b
8. Vovk I.V., Goncharova I.Yu. An analytical method for assessing the acoustic properties of stethoscopes. Acoustic bulletin. 2000, vol. 3, no. 2, pp. 10-16. (In Russian).
9. Goncharova Yu.O. Prospects for storing phonospirographic computer diagnostics in children with bronchogenic dysplasia. Bulletin of VDNZU “Ukrainian Medical Stomatological Academy”. 2013, vol. 13, issue 2 (42), pp. 85-88. (In Russian).
10. Gritsenko V.I., Fainzilberg L.S. Intelligent information technologies in digital medicine on the example of phase-graphy. Kyiv: Naukova Dumka, 2019. 423 p. (In Russian).
11. Cugell D.W. Lung sound nomenclature. The American Review of Respiratory Disease. 1987, vol. 136, no. 4, pp. 1016.
https://doi.org/10.1164/ajrccm/136.4.1016
12. Earis J. Lung sounds. Thorax. 1992, no, 47, pp. 671-672.
https://doi.org/10.1136/thx.47.9.671
13. Loudon R.G., Murphy R.L. 1984. Lung sounds. The American Review of Respiratory. 1984, Vol. 130, pp. 663-673.
14. Paciej R., Vyshedskiy A., Bana D. Squawks in pneumonia. Thorax. 2004, vol. 59, pp. 177-178.
https://doi.org/10.1136/thorax.2003.014415
15. Wilkins R.L., Dexter J.R., Murphy R.L., Belbono E.A. Lung sound nomenclature survey. Chest Journal. 1990, no. 98, pp. 886-889. DOI: 10.1378/chest.98.4.88.
https://doi.org/10.1378/chest.98.4.886
16. Sounds in human lungs download and listen online. URL:https://zvukipro.com/zvukiludei/1392-zvuki-v-legkih-cheloveka.html. (Last accessed: 24.12.2020) (In Russian).
17. Makarenkova A.A., Ermakova O.V. Preliminary studies of breathing sounds in patients with chronic obstructive pulmonary disease. Abstracts of the reports of the acoustic symposium “Consonance-2009”. 2009, Institute of Hydromechanics of the National Academy of Sciences of Ukraine, pp. 40-41. (In Russian).
18. Fainzilberg L.S. An approach to diagnostic personification decisions on the example of evaluation of cardiac activity. Kibernetika i vycislitel’naa tehnika. 2014, no. 178, p. 52-65. (In Russian).
19. Frigo M., Johnson S.G. FFTW: An adaptive software architecture for the FFT. Proc. of the IEEE Intern. Conf. on Acoustics, Speech, and Signal Processing, Seattle, 1998: WA, vol. 3, pp. 1381-1384.
20. Sejdic E. Djurovic I. JiangJ. Time-frequency feature representation using energy concentration: An overview of recent advances. Digital Signal Processin. 2009, vol. 19, no 1, pp. 153-183.
https://doi.org/10.1016/j.dsp.2007.12.004
21. Bureev A.S. Mathematic model for spectral characteristics of respiratory sounds registered in trachea region. Global Journal of Pure and Applied Mathematics. 2016, vol. 12, no 5. pp. 4569-4578.
22. Ghafarian P., Jamaati H., Hashemian S.M. A Review on human respiratory modeling. Tanaffos. 2016, vol.15, no. 2, pp. 61-69.
23. Harper P., Kraman S.S., Pasterkamp H., Wodicka R. An acoustic model of the respiratory tract. IEEE Transactions on Biomedical Engineering. 2001, vol. 48, no. 5, pp. 543-550.
https://doi.org/10.1109/10.918593
24. Harper P. Modeling and measurement of flow effects on tracheal sounds. IEEE Transactions on Biomedical Engineering. 2003, vol. 50, no 1, pp. 1-10.
https://doi.org/10.1109/TBME.2002.807327
25. Liu Y., So R.M.C., Zhang C.H. Modeling the bifurcating flow in an asymmetric human lung airway. Journal of Biomechanics. 2003, vol. 36, no. 7, pp. 951-959.
https://doi.org/10.1016/S0021-9290(03)00064-2
26. Venegas J.G. Self-organized patchiness in asthma as a prelude to catastrophic shifts. Nature. 2005, vol. 434, pp. 777-782.
https://doi.org/10.1038/nature03490
27. Xi J. Numerical study of dynamic glottis and tidal breathing on respiratory sounds in a human upper airway model. Sleep and Breathing. 2017, vol. 22, pp. 463-479.
https://doi.org/10.1007/s11325-017-1588-0
28. Gurung A. Computerized lung sound analysis as diagnostic aid for the detection of abnormal lung sounds: A systematic review and meta-analysis. Respiratory Medicine. 2011, vol. 105, no. 9, pp. 1396-1403.
https://doi.org/10.1016/j.rmed.2011.05.007
29. Schmidt A., Zidowitz S., Kriete A., Denhard T., Krass S., Peitgen H.O. A digital reference model of the human bronchial tree. Computerized Medical Imaging and Graphics. 2004, vol. 28, no. 4, pp. 203-211. DOI: 10.1016/j.compmedimag.2004.01.001.
https://doi.org/10.1016/j.compmedimag.2004.01.001
30. Korenbaum V.I. Acoustic diagnostics of the human respiratory system based on an objective analysis of respiratory sounds. Vestnik FEB RAS. 2004, no. 5, pp. 68-79. (In Russian).
31. Furman E.G., Sokolovsky V.L., Furman G.B. Mathematical model of respiratory noise propagation in the respiratory tract. Russian journal of biomechanics. 2018, vol. 22, no. 2b, pp. 166-177. (In Russian).
32. Dyachenko A.I., Mikhailovskaya A.N. Respiratory acoustics (Review). Proceedings of the Prokhorov General Physics Institute. 2012, vol. 68, pp. 136-181. (In Russian).
Received 02.03.2021