L.A. Manilo1, D.U. Kholmatov2, A.P. Nemirko3

1–3 St. Petersburg State Electrotechnical University "LETI" (Saint Petersburg, Russia)
1 lmanilo@yandex.ru, 2 xolmatov.2000@mail.ru, 3 apn-bs@yandex.ru

In Russia, the number of patients with congestive heart failure is at least 12–14 million people. Heart failure has a high mortality rate and a high risk for patients over 65 years of age. The search for new tools for the analysis of heart failure is important to improve the efficiency of diagnosing pathology, especially in the early stages of heart failure, when the signs of the development of pathology may be outwardly invisible. The search for new methods of analysis is necessary to expand the functions of diagnostic systems capable of detecting pathology at the early stages of the development of the disease. The aim of the work is to develop a classifier using non-linear heart rhythm analysis to detect early congestive heart failure against the background of normal sinus rhythm and atrial fibrillation. As a result, with the help of non-linear heart rate indicators, supplemented with statistical parameters, it was possible to develop a classifier based on multiple linear discriminant analysis. Using the Fisher criterion, the decisive functions were obtained that can effectively separate three classes of rhythm: objects with congestive heart failure, atrial fibrillation, and normal sinus rhythm. The results obtained are important for the creation of autonomous diagnostic systems designed for early detection of congestive heart failure by ECG.

Manilo L.A., Kholmatov D.U., Nemirko A.P. Construction a classifier for the diagnosis of congestive heart failure using nonlinear parameters of the heart rate signal. Biomedicine Radioengineering. 2024. V. 27. № 2. P. 18–24. DOI: https://doi.org/10.18127/ j19998465-202402-03 (in Russian)

1. Yontz L. Congestive Heart Failure: Early Recognition of Congestive Heart Failure in the Primary Care Setting. Journal of the American Academy of Nurse Practitioners. 1994. V. 6 (6). P. 273–279.
2. Bokeriya O.L., Bakulaeva A.N. Resinhroniziruyushchaya terapiya pri prodolzhitel'noj serdechnoj nedostatochnosti – mnenie ekspertov i predvaritel'nye rezul'taty nedavnih randomizirovannyh issledovanij. Annaly aritmologii. 2006. № 1. S. 11–21.
3. Melekhov A.V., Ostrovskaya Yu.I. Hronicheskaya serdechnaya nedostatochnost' Atmosfera. Novosti kardiologii. 2017. T. 4. S. 30–35.
4. Fomin I.V. Hronicheskaya serdechnaya nedostatochnost' v Rossijskoj Federacii: chto segodnya my znaem i chto dolzhny delat'. Rossijskij kardiologicheskij zhurnal. 2016. №. 8. S. 7–13.
5. Baevskij R.M., Ivanov G.G. Variabel'nost' serdechnogo ritma: teoreticheskie aspekty i vozmozhnosti klinicheskogo primeneniya. Ul'trazvukovaya i funkcional'naya diagnostika. 2001. №3. S. 108–127.
6. Figueroa M., Peters J. Congestive heart failure: Diagnosis, pathophysiology, therapy, and implications for respiratory care. Respir Care. 2006. V. 51(4). P. 403–412.
7. Alejnikova T.V. Variabel'nost' serdechnogo ritma. Problemy zdorov'ya i ekologii. 2012. № 1 (31). S. 17–23.
8. Pobivanceva N.F. Nelinejnyj analiz variabel'nosti ritma serdca: prognosticheskie vozmozhnosti metoda u pacientov s hronicheskoj serdechnoj nedostatochnost'yu ishemicheskoj etiologii. Zhurnal Grodnenskogo gosudarstvennogo medicinskogo universiteta. 2013. №4. S. 37–40.
9. Casolo G., Balli E., Taddei T., Amuhasi J., Gori C. Decreased spontaneous heart rate variability in congestive heart failure. The American Journal of Cardiology. 1989. V. 64 (18). P. 1162–1167. ISSN 0002-9149, doi.org/10.1016/0002-9149(89)90871-0
10. Tereshchenko S.N., Galyavich A.S., Uskach T.M. Hronicheskaya serdechnaya nedostatochnost': klinicheskie rekomendacii 2020. Rossijskij kardiologicheskij zhurnal. 2020. № 25 (11). S. 311–374.
11. Pieske B., Tschöpe C., Boer de R., Fraser A., Anker S. and other. How to diagnose heart failure with preserved ejection fraction: the HFA–PEFF diagnostic algorithm: a consensus recommendation from the Heart Failure Association (HFA) of the European Society of Cardiology (ESC). European Heart Journal. 2019. V. 40 (40). P. 3297-3317. doi:10.1093/eurheartj/ehz641
12. Borisov S.N., Gendlin G.E. Primenenie natrijureticheskih peptidov v diagnostike hronicheskoj serdechnoj nedostatochnosti. Novosti kardiologii. Atmosfera. 2011. №. 2. S. 13–17.
13. Manilo L.A. Raspoznavanie mercatel'noj aritmii v kardiologicheskih sistemah diagnostiki i nablyudeniya. Biotekhnosfe-ra. 2009. T. 1 (2). S. 41–45.
14. Borisenko T.L., Snezhickij V.A., Frolov A.V. Klinicheskoe znachenie nelinejnyh parametrov variabel'nosti serdechnogo ritma u pacientov s serdechno-sosudistymi zabolevaniyami. Zhurnal Grodnenskogo gos. med. un-ta. 2020. №3. S. 223–228.
15. Krstacic G., Gamberger D., Krstacic A., Smuc T. and Milicic D. The Chaos Theory and Non-linear Dynamics in Heart Rate Variability in Patients with Heart Failure. Computers in Cardiology. 2008. P. 957–959. doi: 10.1109/CIC.2008.4749202
16. Stein K., Reddy A. Non-Linear Heart Rate Variability and Risk Stratification in Cardiovascular Disease. Indian Pacing and Electrophy­siology Journal. 2005. V. 5 (3). P. 210–220.
17. Karmakar C., Khandoker A., Gubbi J., Palaniswami M. Complex Correlation Measure: a novel descriptor for Poincar´e plot. Bio-Medical Engineering OnLine. 2009. Vol. 8 (17). P. 17–35. doi.org/10.1186/1475-925X-8-17
18. Manilo L.A., Kholmatov D.U. Recognition of Congestive Heart Failure Based on a Complex Correlation Measure of the Heart Rate Signal. Pattern Recognition and Image Analysis. 2022. V. 32(3). P. 586–590. doi: 10.1134/S1054661822030233
19. Akay M. Nonlinear biomedical signal processing. Dynamic analysis and modelling. New York: IEEE. 2001. V. 2. P. 341.
20. Orozco-Duque A., Novak D., Kremen V., Bustamante J. Multifractal analysis for grading complex fractionated electrograms in atrial fibrillation. Physiological Measurement. 2015. V. 36 (11). P. 2269–2284. doi:10.1088/0967-3334/36/11/2269
21. Osmolovskaya Yu.F., Romanova N.V., Zhirov I.V., Tereshchenko S.N. Epidemiologiya i osobennosti terapii hronicheskoj serdechnoj nedostatochnosti v sochetanii s fibrillyaciej predserdij. Klinicheskaya medicina. 2016. № 10. S. 93–97.
22. Goldberger A., Amaral L., Glass L., Hausdorff J., Ivanov P., Mark R., Stanley H. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. PCirculation. 2000. V. 101(23). P. 215–220.
23. Moody G., Mark R. A new method for detecting atrial fibrillation using R-R intervals. Computers in Cardiology. 1983. V. 10. P. 227–230.
24. Nemirko A.P., Manilo L.A., Kalinichenko A.N. Matematicheskij analiz biomedicinskih signalov i dannyh. M.: Fizmatlit, 2017.