PHOTOPLETHYSMOGRAPHY-BASED HEART RATE VARIABILITY ANALYSIS USING MACHINE LEARNING METHODS FOR NON-INVASIVE SCREENING OF CORONARY ARTERY DISEASE WITH THE ZHUREK IOT DEVICE

Cardiovascular diseases remain the leading cause of mortality worldwide; therefore, early-stage noninvasive risk assessment is crucial both for prevention and for the efficient allocation of healthcare resources. Heart rate variability (HRV) is a reliable indicator of autonomic balance, yet in clinical practice it still relies mainly on long-term ECG recordings, which limits large-scale application. Although photoplethysmography (PPG) is widely available, the effectiveness of PPG-derived HRV metrics for detecting ischemic heart disease (IHD) has not been fully established.
In this study, PPG signals obtained from a low-cost Zhurek device, combined with machine learning classifiers, enabled IHD detection with an accuracy of 90.82%. Comparison with three-channel Holter ECG showed satisfactory agreement. SHAP and mutual information analyses highlighted the dominant role of frequency-domain features (HF, LF). Data balancing using CTGAN improved training stability.
Overall, the results demonstrate that PPG-based HRV analysis offers a feasible, accessible, and interpretable approach for IHD screening. Future steps include multicenter validation, expansion of feature sets, and integration of the method into wearable devices.

1. World Health Organization. Cardiovascular Diseases (CVDs). Available online: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds (accessed on 11 June 2024).

2. Global Epidemiology of Ischemic Heart Disease: Results from the Global Burden of Disease Study / M.A. Khan et al // Cureus. – 2020. – № 12. – Р. e9349. https://doi.org/10.7759/cureus.9349.

3. Tengrinews.kz. The Most Common Disease among Kazakhstanis Has Been Named. Available online: https://tengrinews.kz/kazakhstan_news/nazvana-samaya-rasprostranennaya-bolezn-sredikazahstantsev-503527/ (accessed on 18 October 2022).

4. Smoking, Drinking, Diet and Physical Activity – Modifiable Lifestyle Risk Factors and Their Associations with Age to First Chronic Disease / R. Ng et al // Int. J. Epidemiol. – 2020. – № 49. – Р. 113-130. https://doi.org/10.1093/ije/dyz078.

5. Enhancing Comprehensive Assessments in Chronic Heart Failure Caused by Ischemic Heart Disease: The Diagnostic Utility of Holter ECG Parameters / Ș.-T. Duca et al // Medicina. – 2024. – № 60. – Р. 1315. https://doi.org/10.3390/medicina60081315.

6. Heart Rate Variability and Myocardial Infarction: Systematic Literature Review and Metanalysis / F. Buccelletti et al // Eur. Rev. Med. Pharmacol. Sci. – 2009. – № 13. – Р. 299-307.

7. Short-Term vs. Long-Term Heart Rate Variability in Ischemic Cardiomyopathy Risk Stratification / A. Voss et al // Front. Physiol. – 2013. – № 4. – Р. 364. https://doi.org/10.3389/fphys.2013.00364.

8. Advances in Photoplethysmography Signal Analysis for Biomedical Applications / J.L. Moraes et al // Sensors. – 2018. – № 18. – Р. 1894. https://doi.org/10.3390/s18061894.

9. The Use of Photoplethysmography for Assessing Hypertension / М. Elgendi et al // npj Digit. Med. – 2019. – № 2. – Р. 60. https://doi.org/10.1038/s41746-019-0136-7.

10. Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review / М.А. Almarshad et al // Healthcare. – 2022. – № 10. – Р. 547. https://doi.org/10.3390/healthcare10030547.

11. Kim K.B. Photoplethysmography in Wearable Devices: A Comprehensive Review of Technological Advances, Current Challenges, and Future Directions / K.B. Kim, H.J. Baek // Electronics. – 2023. – № 12. – Р. 2923. https://doi.org/10.3390/electronics12132923.

12. Survey: Smartphone-Based Assessment of Cardiovascular Diseases Using ECG and PPG Analysis / М. Shabaan et al // BMC Med. Inform. Decis. Mak. – 2020. – № 20. – Р. 177. https://doi.org/10.1186/s12911-020-01199-7.

13. Cardiovascular Disease Risk Prediction Using Automated Machine Learning: A Prospective Study of 423,604 UK Biobank Participants / А.М. Alaa et al // M. PLoS ONE. – 2019. – № 14. – Р. e0213653. https://doi.org/10.1371/journal.pone.0213653.

14. Exploring Relationships of Heart Rate Variability, Neurological Function, and Clinical Factors with Mortality and Behavioral Functional Outcome in Patients with Ischemic Stroke / M.-J. Wu et al // Diagnostics. – 2024. – № 14. – Р. 1304. https://doi.org/10.3390/diagnostics14121304.

15. Heart Rate Variability in Acute Myocardial Infarction: Results of the HeaRt-V-AMI Single-Center Cohort Study / С. Brinza et al // J. Cardiovasc. Dev. Dis. – 2024. – № 11. – Р. 254. https://doi.org/10.3390/jcdd11080254.

16. A Novel Wearable Device for Continuous Ambulatory ECG Recording: Proof of Concept and Assessment of Signal Quality / С. Steinberg et al // Biosensors. – 2019. – № 9. – Р. 17. https://doi.org/10.3390/bios9010017.

17. Holter ECG for Syncope Evaluation in the Internal Medicine Department—Choosing the Right Patients / О. Freund et al // J. Clin. Med. – 2022. – № 11. – Р. 4781. https://doi.org/10.3390/jcm11164781.

18. Self-Reporting Technique-Based Clinical-Trial Service Platform for Real-Time Arrhythmia Detection / Н. Kim et al // Appl. Sci. – 2022. – № 12. – Р. 4558. https://doi.org/10.3390/app12094558.

19. Heart Disease Diagnosis and Prediction Using Machine Learning and Data Mining Techniques: A Review / А. Hazra et al // Adv. Comput. Sci. Technol. – 2017. – № 10. – Р. 2137-2159.

20. Automated Detection of Coronary Artery Disease, Myocardial Infarction and Congestive Heart Failure Using GaborCNN Model with ECG Signals / V. Jahmunah et al // Comput. Biol. Med. – 2021. – № 134. – Р. 104457. https://doi.org/10.1016/j.compbiomed.2021.104457.

21. Trigka M. Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models / M. Trigka, E. Dritsas // Sensors. – 2023. – № 23. – Р. 1193. https://doi.org/10.3390/s23031193.

22. Roerecke M. Alcohol Consumption, Drinking Patterns, and Ischemic Heart Disease: A Narrative Review of Meta-Analyses and a Systematic Review and Meta-Analysis of the Impact of Heavy Drinking Occasions on Risk for Moderate Drinkers / M. Roerecke, J. Rehm // BMC Med. – 2014. – № 12. – Р. 182. https://doi.org/10.1186/s12916-014-0182-6.

23. Comparative Analysis of the Diagnostic Effectiveness of SATRO ECG in the Diagnosis of Ischemia Diagnosed in Myocardial Perfusion Scintigraphy Performed Using the SPECT Method / Ł.J. Janicki et al // Diagnostics. – 2022. – № 12. – Р. 297. https://doi.org/10.3390/diagnostics12020297.

24. Prognostic Role of Electrocardiographic Alternans in Ischemic Heart Disease / I. Marcantoni et al // J. Clin. Med. – 2025. – № 14. – Р. 2620. https://doi.org/10.3390/jcm14082620.

25. Exploring Relationships of Heart Rate Variability, Neurological Function, and Clinical Factors with Mortality and Behavioral Functional Outcome in Patients with Ischemic Stroke / M.-J. Wu et al // Diagnostics. – 2024. – № 14. – Р. 1304. https://doi.org/10.3390/diagnostics14121304.

26. The Influence of Physiological Noise Correction on Test–Retest Reliability of Resting-State Functional Connectivity / R.M. Birn et al // Brain Connect. – 2014. – № 4. – Р. 511-522. https://doi.org/10.1089/brain.2014.0284.

27. Reliability of Resting Metabolic Rate Measurements in Young Adults: Impact of Methods for Data Analysis / Y. Sanchez-Delgado et al // Clin. Nutr. – 2018. – № 37. – Р. 1618-1624. https://doi.org/10.1016/j.clnu.2017.07.026.

28. McDuff D. Remote Measurement of Cognitive Stress via Heart Rate Variability / D. McDuff, S. Gontarek, R. Picard // In Proceedings of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, USA. – 2014. – № 26-30. – Р. 2957-2960. https://doi.org/10.1109/EMBC.2014.6944243.

29. Validity of Ultra-Short-Term HRV Analysis Using PPG – A Preliminary Study / А. Taoum et al // Sensors. – 2022. – № 22. – Р. 7995. https://doi.org/10.3390/s22207995.

30. Accuracy of Heart Rate Variability Estimated with Reflective Wrist-PPG in Elderly Vascular Patients / С. Hoog Antink et al // Sci. Rep. – 2021. – № 11. – Р. 8123. https://doi.org/10.1038/s41598-021-87489-0.

31. Eom G. Searching for Optimal Oversampling to Process Imbalanced Data: Generative Adversarial Networks and Synthetic Minority Over-Sampling Technique / G. Eom, H. Byeon // Mathematics. – 2023. – № 11. – Р. 3605. https://doi.org/10.3390/math11163605.

32. Adiputra I.N.M. CTGAN-ENN: A Tabular GAN-Based Hybrid Sampling Method for Imbalanced and Overlapped Data in Customer Churn Prediction / I.N.M. Adiputra, P. Wanchai // J. Big Data. – 2024. – № 11. – Р. 121. https://doi.org/10.1186/s40537-024-00982-x.

33. Relationship Between Heart Rate Variability Traits and Stroke: A Mendelian Randomization Study / W. Liu et al // J. Stroke Cerebrovasc. Dis. – 2025. – № 34. – Р. 108251. https://doi.org/10.1016/j.jstrokecerebrovasdis.2025.108251.

34. The Hemisphere of the Brain in Which a Stroke Has Occurred Visible in the Heart Rate Variability / J. Aftyka et al // J. Life. – 2022. – № 12. – Р. 1659. https://doi.org/10.3390/life12101659.

35. Ischemic Stroke Risk Assessment by Multiscale Entropy Analysis of Heart Rate Variability in Patients with Persistent Atrial Fibrillation / G. Chairina et al // Entropy. – 2021, 23, 918. https://doi.org/10.3390/e23070918.

36. Baroreflex Sensitivity but Not Microvolt T-Wave Alternans Can Predict Major Adverse Cardiac Events in Ischemic Heart Failure / D.K. Kaufmann et al // Cardiol. J. – 2022. – № 29. – Р. 1004-1012. https://doi.org/10.5603/CJ.a2020.0129.

37. Accuracy of Physicians Interpreting Photoplethysmography and Electrocardiography Tracings to Detect Atrial Fibrillation: INTERPRET-AF / Н. Gruwez et al // Front. Cardiovasc. Med. – 2021. – № 8. – Р. 734737. https://doi.org/10.3389/fcvm.2021.734737.