PREDICTION OF ISCHEMIC HEART DISEASE RISK BASED ON NONLINEAR ANALYSIS OF HEART RATE VARIABILITY FROM WEARABLE DEVICE DATA

Introduction. Ischemic heart disease is one of the leading causes of mortality worldwide, highlighting the importance of implementing accessible and non-invasive screening tools at the population level. This study aimed to assess the feasibility of using heart rate variability parameters obtained from a wearable photoplethysmography-based device to evaluate the risk of ischemic heart disease.

Materials and methods. A finger-worn IoT device called «Zhurek» was developed, based on photoplethysmography technology and capable of calculating real-time heart rate variability indices. The measurements obtained from «Zhurek» were compared with data from three‑lead Holter electrocardiographic monitoring, and machine learning algorithms were applied to datasets collected from angiographically confirmed patients and healthy volunteers.

Results. The deviations between the new device measurements and Holter electrocardiography remained within clinically acceptable limits; heart rate variability parameters, particularly low-frequency power, and patient age were identified as key diagnostic indicators for detecting ischemic heart disease.

Conclusion. The «Zhurek» device is suitable for large-scale ischemic heart disease risk stratification and may facilitate a shift in healthcare from a reactive, symptom-driven approach to a proactive, prevention-oriented model.

1. World Health Organization. (2024). Cardiovascular diseases (CVDs) [Electronic resource]. Retrieved June 11, 2024, from https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds).

2. Khan, M. A., et al. (2020). Global epidemiology of ischemic heart disease: Results from the Global Burden of Disease Study. Cureus, 12(7), e9349. DOI: https://doi.org/10.7759/cureus.9349.

3. Severino, P., et al. (2020). Ischemic heart disease pathophysiology paradigms overview: From plaque activation to microvascular dysfunction. International Journal of Molecular Sciences, 21(21), 8118. DOI: https://doi.org/10.3390/ijms21218118.

4. Janicki, Ł. J., et al. (2022). Comparative analysis of the diagnostic effectiveness of SATRO ECG in the diagnosis of ischemia diagnosed in myocardial perfusion scintigraphy performed using the SPECT method. Diagnostics, 12(2), 297. DOI: https://doi.org/10.3390/diagnostics12020297

5. Duca, Ș.-T., et al. (2024). Enhancing comprehensive assessments in chronic heart failure caused by ischemic heart disease: The diagnostic utility of Holter ECG parameters. Medicina, 60(8), 1315. DOI: https://doi.org/10.3390/medicina60081315.

6. Banerjee, R., Ghose, A., & Muthana Mandana, K. (2020). A hybrid CNN–LSTM architecture for detection of coronary artery disease from ECG. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). Glasgow, UK. DOI: https://doi.org/10.1109/IJCNN48605.2020.9207044.

7. Wang, L., et al. (2024). Heart diseases recognition model based on HRV feature extraction over 12-lead ECG signals. Sensors, 24(16), 5296. DOI: https://doi.org/10.3390/s24165296.

8. Verma, L., & Srivastava, S. (2016). A data mining model for coronary artery disease detection using noninvasive clinical parameters. Indian Journal of Science and Technology, 9(11), 1-6. DOI: https://doi.org/10.17485/ijst/2016/v9i11/82653.

9. Gaine, S. P., et al. (2022). Multimodality imaging in the detection of ischemic heart disease in women. Journal of Cardiovascular Development and Disease, 9(10), 350. DOI: https://doi.org/10.3390/jcdd9100350.

10. Doolub, G., et al. (2023). Artificial intelligence as a diagnostic tool in non-invasive imaging in the assessment of coronary artery disease. Medical Sciences, 11(1), 20. DOI: https://doi.org/10.3390/medsci11010020.

11. Sayadi, M., et al. (2022). A machine learning model for detection of coronary artery disease using noninvasive clinical parameters. Life, 12(11), 1933. DOI: https://doi.org/10.3390/life12111933.

12. Ribeiro, P., et al. (2024). Cardiovascular diseases diagnosis using an ECG multi-band non-linear machine learning framework analysis. Bioengineering, 11(1), 58. DOI: https://doi.org/10.3390/bioengineering11010058.

13. Moraes, J. L., et al. (2018). Advances in photoplethysmography signal analysis for biomedical applications. Sensors, 18(6), 1894. DOI: https://doi.org/10.3390/s18061894.

14. Elgendi, M., et al. (2019). The use of photoplethysmography for assessing hypertension. NPJ Digital Medicine, 2, 60. DOI: https://doi.org/10.1038/s41746-019-0136-7.

15. Almarshad, M. A., et al. (2022). Diagnostic features and potential applications of PPG signal in healthcare: A systematic review. Healthcare, 10(3), 547. DOI: https://doi.org/10.3390/healthcare10030547.

16. Kim, K. B., & Baek, H. J. (2023). Photoplethysmography in wearable devices: A comprehensive review of technological advances, current challenges, and future directions. Electronics, 12(13), 2923. DOI: https://doi.org/10.3390/electronics12132923.

17. Shabaan, M., et al. (2020). Survey: Smartphone-based assessment of cardiovascular diseases using ECG and PPG analysis. BMC Medical Informatics and Decision Making, 20, 177. DOI: https://doi.org/10.1186/s12911-020-01199-7.

18. Shaffer, F., & Ginsberg, J. P. (2017). An overview of heart rate variability metrics and norms. Frontiers in Public Health, 5, 258. https://doi.org/10.3389/fpubh.2017.00258.

19. Zeng, J., et al. (2023). High vagally mediated resting-state heart rate variability is associated with superior working memory function. Frontiers in Neuroscience, 17, 1119405. DOI: https://doi.org/10.3389/fnins.2023.1119405.

20. Volpe, M., et al. (2023). How cardiologists can manage excess body weight and related cardiovascular risk: An expert opinion. International Journal of Cardiology, 381, 101–104. DOI: https://doi.org/10.1016/j.ijcard.2023.03.054.

21. Kathiresan, S., & Srivastava, D. (2012). Genetics of human cardiovascular disease. Cell, 148(6), 1242-1257. DOI: https://doi.org/10.1016/j.cell.2012.03.001.