L.A. Manilo1, A.A. Mekhonoshina2, A.P. Nemirko3, Z.M. Yuldashev4, D.A. Stepanov5

1–4 St. Petersburg State Electrotechnical University "LETI" (St. Petersburg, Russia)
5 Almazov National Medical Research Centre (St. Petersburg, Russia)
1 lmanilo@yandex.ru, 2 annmeh2003@yandex.ru, 3apn-bs@yandex.ru, 4yuld@mail.ru, 5daniel36611b@gmail.com

Sudden cardiac death is a leading cause of mortality in cardiovascular diseases, often occurring outside medical facilities, which limits timely intervention. Early prediction using non-invasive biomedical signals is therefore of great importance. Heart rate variability (HRV) is one of the most informative signals, reflecting the state of autonomic cardiovascular regulation. This paper proposes an algorithm for HRV signal processing, which includes preprocessing, ensemble empirical mode decomposition, and calculation of entropy indices fuzzy entropy and improved multiscale permutation entropy. Classification was performed using the k-nearest neighbors method. The best results were achieved for the first two-minute interval before sudden cardiac death onset, with accuracy of 94.74%, sensitivity of 90%, and specificity of 100% at k = 1. These findings demonstrate the potential of nonlinear entropy-based HRV analysis in predicting life-threatening cardiac conditions and could contribute to the development of intelligent monitoring systems.

Manilo L. A., Mekhonoshina A.A., Nemirko A.P., Yuldashev Z.M., Stepanov D.A. Prediction of sudden cardiac death by heart rate variability indicators. Biomedicine Radioengineering. 2026. V. 29. № 3. P. 8–17. DOI: https:// doi.org/10.18127/ j15604136-202603-02 (In Russian)

1. VOZ: kazhdyj god v mire umiraet ot serdechno-sosudistyh zabolevanij 17,9 mln chelovek [Elektronnyj resurs]. URL: https://www.vshouz.ru/news/analitika/wcs-19279/ (In Russian).
2. Kurdgeliya T.M., Kislicina O.N., Bazarsadaeva T.S. Vnezapnaya serdechnaya smert': epidemiologiya, faktory riska i profilaktika. Byulleten' medicinskih Internet‐konferencij. 2014. T. 4. № 3. S. 220–229 (In Russian).
3. Shi M., He H., Geng W., Wu R., Zhan C., Jin Y., Zhu F., Ren S. and Shen B. Early Detection of Sudden Cardiac Death by Using Ensemble Empirical Mode Decomposition-Based Entropy and Classical Linear Features From Heart Rate Variability Signals. Front. Physiol. 2020. V. 11. P. 118. https://doi.org/10.3389/fphys.2020.00118.
4. Bokeriya O.L., Ahobekov A.A. Vnezapnaya serdechnaya smert': mekhanizmy vozniknoveniya i stratifikaciya riska. Ann. aritm. 2012. № 3. S. 6‒7 (In Russian).
5. Manilo L.A., Men'shikova V.I., Nemirko A.P., Yuldashev Z.M., Tatarinova A.A., Stepanov D.A. Prognozirovanie vnezapnoj serdechnoj smerti po pokazatelyam variabel'nosti serdechnogo ritma. Biomedicinskaya radioelektronika. 2025. T. 28. № 2. S. 5–13. doi: https://doi.org/10.18127/j15604136-202502-01 (In Russian).
6. Manilo L., Menshikova V., Nemirko A., Yuldashev Z., Tatarinova A., Stepanov D. An Algorithm for Predicting Sudden Cardiac Death Using Heart Rate Variability Parameters, 2025 Systems and Technologies of the Digital HealthCare (STDH). Saint Petersburg, Russian Federation. 2025. P. 109–113. DOI: 10.1109/STDH66836.2025.11227247.
7. Jianli Yang, Zhiqiang Sun, Weiwei Zhu, Peng Xiong, Haiman Du, Xiuling Liu. Intelligent prediction of sudden cardiac death based on multi‑domain feature fusion of heart rate variability signals. EURASIP Journal on Advances in Signal Processing (2023) 2023. V. 32. https://doi.org/10.1186/s13634-023-00992-6.
8. Sudden Cardiac Death Holter Database. PhysioNet. URL: https://physionet.org/content/sddb/1.0.0/.
9. MIT-BIH Normal Sinus Rhythm Database. PhysioNet. URL: https://physionet.org/content/nsrdb/1.0.0/.
10. Azami H., Fernández A., Escudero J. Refined multiscale fuzzy entropy based on standard deviation for biomedical signal analysis. Med Biol Eng Comput. 2017. Nov. V. 55(11). P. 2037–2052. DOI: 10.1007/s11517-017-1647-5.
11. Azami H., Escudero Ja. Improved Multiscale Permutation Entropy for Biomedical Signal Analysis: Interpretation and Application to Electroencephalogram Recordings. Biomedical Signal Processing and Control. V. 23. № 1. P. 28–41. https://doi.org/10.1016/j.bspc.2015. 08.004.