AUTOMATED CLASSIFICATION OF HEMODYNAMICALLY SIGNIFICANT ARRHYTHMIAS BASED ON ECG FEATURES

This paper presents an automated method for the classification of hemodynamically significant arrhythmias (HSA) based solely on electrocardiographic (ECG) features, without the use of additional imaging diagnostic techniques. The proposed approach relies on key ECG parameters, including QRS complex duration, RR intervals, and heart rate (HR). The study is based on data from the open-access MIT-BIH Arrhythmia Database, which contains multiple types of cardiac rhythm disturbances. A comparative analysis of arrhythmia classes was conducted, leading to the identification of diagnostically significant predictors associated with hemodynamic instability. Logical decision rules and a decision tree model were developed to enable automatic recognition of HSA and clinical risk stratification. The proposed algorithm demonstrates high interpretability and practical applicability for real-time monitoring systems. The results confirm that ECG-based features alone can be effectively used for preliminary detection of dangerous arrhythmias. The developed approach is especially valuable for telemedicine systems and healthcare facilities with limited access to expensive diagnostic equipment.

1. Moody G.B. The impact of the MIT-BIH Arrhythmia Database / G.B. Moody, R.G. Mark // IEEE Engineering in Medicine and Biology Magazine. – 2001. https://doi.org/10.1109/51.932724.

2. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals / A.L. Goldberger et al // Circulation. – 2000. – № 101(23). – Р. e215-e220. https://doi.org/10.1161/01.CIR.101.23.e215.

3. Cardiologist-level arrhythmia detection with convolutional neural networks / Р. Rajpurkar et al // arXiv preprint. – 2017. https://arxiv.org/abs/1707.01836.

4. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm / Z.I. Attia et al // The Lancet. – 2019. – № 394(10201). – Р. 861-867. https://doi.org/10.1016/S0140-6736(19)31721-0.

5. Automatic diagnosis of the 12-lead ECG using a deep neural network / А.Н. Ribeiro et al // Nature Communications. – 2020. – № 11. – Р. 1760. https://doi.org/10.1038/s41467-020-15432-4.

6. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network / A.Y. Hannun et al // Nature Medicine. – 2019. – № 25(1). – Р. 65-69. https://doi.org/10.1038/s41591-018-0268-3.

7. Recommendations for physical activity and recreational sports participation in young patients with genetic cardiovascular diseases / B.J. Maron et al // Circulation. – 2004. – № 109(23). – Р. 2807-2816. https://doi.org/10.1161/01.CIR.0000128363.85581.E1.

8. Deep learning-based stacked denoising autoencoder for ECG heartbeat classification / S. Nurmaini et al // Electronics. – 2020. – № 9(1). – Р. 135. https://doi.org/10.3390/electronics9010135.

9. AF Classification from a Short Single Lead ECG Recording: The PhysioNet / G.D. Clifford et al // Computing in Cardiology Challenge 2017. Computing in Cardiology. – 2017. – № 44. https://doi.org/10.22489/CinC.2017.065-469.

10. Passive detection of atrial fibrillation using a commercially available smartwatch / G.H. Tison et al // JAMA Cardiology. – 2018. – № 3(5). – Р. 409-416. https://doi.org/10.1001/jamacardio.2018.0136.

11. Yildirim Ö. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification / Ö. Yildirim // Computers in Biology and Medicine. – 2018. – № 96. – Р. 189-202. https://doi.org/10.1016/j.compbiomed.2018.03.016.

12. Wu Zhenyan Deep learning and electrocardiography: systematic review of current techniques in cardiovascular disease diagnosis and management / Wu Zhenyan, Guo, Caixia // BioMedical Engineering OnLine. – 2025. – № 24. – Р. 23. https://doi.org/10.1186/s12938-025-01349-w.

13. CVPhysiology.com. (n.d.). Hemodynamic consequences of cardiac arrhythmias. Retrieved from https://cvphysiology.com/cad/cad007.

14. Translational challenges in atrial fibrillation / J. Heijman et al // Circulation Research. – 2018. – № 122(5). – Р. 752-773. https://doi.org/10.1161/CIRCRESAHA.117.311081.

15. MedElement. (n.d.). Ventricular arrhythmias and prevention of sudden cardiac death. Retrieved from https://diseases.medelement.com.

16. Deep learning for healthcare applications based on physiological signals: A review / О. Faust et al // Computer Methods and Programs in Biomedicine. – 2018. – № 161. – Р. 1-13. https://doi.org/10.1016/j.cmpb.2018.04.005.

17. Shen W.K. 2017 ACC/AHA/HRS Guideline for the Evaluation and Management of Patients With Syncope / W.K. Shen et al // Journal of the American College of Cardiology. – 2017. – № 70(5). – Р. e39-e110. https://doi.org/10.1016/j.jacc.2017.03.003.

18. Heart State Monitoring Using Multi-Agent Technology / А. Bekbay et al // In 2019 8th Mediterranean Conference on Embedded Computing (MECO)/ – 2019. – Р. 691-694. https://doi.org/10.1109/MECO.2019.8760007.

19. Deep learning-based algorithm for detecting aortic stenosis using electrocardiography / J.-M. Kwon et al // Journal of the American Heart Association. – 2020. – № 9(7). – Р. e014717. https://doi.org/10.1161/JAHA.119.014717.

20. Large-scale assessment of a smartwatch to identify atrial fibrillation (Apple Heart Study) / M.V. Perez et al // New England Journal of Medicine. – 2019. – № 381(20). – Р. 1909-1917. https://doi.org/10.1056/NEJMoa1901183.