A Comparative Study of ECG Sampling Rates in Predicting Cardiac Arrhythmias Using a Deep Learning Approach

Rodrigo Alexandre Dos Santos

doi:10.70454/IJMRE.2025.50408

Authors

Rodrigo Alexandre Dos Santos Department of Software Development, CPQD Foundation, Campinas, SP, Brazil Author

DOI:

https://doi.org/10.70454/IJMRE.2025.50408

Keywords:

cardiac arrhythmias, electrocardiogram, sampling rates, deep learning

Abstract

Cardiac arrhythmias are a group of conditions that have caused great concern among healthcare professionals because they have a high incidence and prevalence worldwide, and their early diagnosis and effective treatment are essential to alleviate the negative impacts they can have on people’s quality of life. In recent years, many studies have suggested Deep Learning models for diagnosing cardiac arrhythmias by analysing data from electrocardiograms (ECG). The heart’s electrical activity can be measured using different ECG sampling rates, and the chosen rate can impact the model’s prediction accuracy and associated computational costs. This study presents a comparative analysis of various sampling rates for predicting cardiac arrhythmias using a Deep Learning model and a large public dataset. The findings can serve as a guideline for doctors and researchers to select the most appropriate sampling rates to achieve greater efficiency when using the ECG and better outcomes in predicting cardiac arrhythmias.

References

[1] H. Li, X. Song, Y. Liang, X. Bai, W. Liu-Huo, C. Tang, W. Chen, and L. Zhao, "Global, regional, and national burden of disease study of atrial fibrillation/flutter, 1990–2019: results from a global burden of disease study," BMC Public Health, vol. 22, no. 1, 2015, 2022. doi: 10.1186/s12889-022-14403-2

[2] iMotions, "Electrocardiography (ECG): the complete pocket guide," [Online]. Available: https://imotions.com/support/document-library/

[3] C. Bloe, "The role of single-use ECG leads in reducing healthcare-associated infections," British Journal of Nursing, vol. 30, no. 11, 2021. doi: 10.12968/bjon.2021.30.11.628

[4] G. Singh, C. Agarwal, I. Kaur, and P. Gupta, "Machine Learning for cardiac arrhythmia detection: a systematic survey," Journal of Physics: Conference Series, vol. 2570, no. 1, 012028, 2023. doi:10.1088/1742-6596/2570/1/012028

[5] V. D. Nagarajan, S. Lee, J. Robertus, C. A. Nienaber, N. A. Trayanova, and S. Ernst, "Artificial intelligence in the diagnosis and management of arrhythmias," European Heart Journal, vol. 42, no. 38, pp. 3904–3914, 2021. doi:10.1093/eurheartj/ehab544

[6] Y. Zhou et al., "Sampling rate requirement for accurate calculation of heart rate and its variability based on the electrocardiogram," Physiological Measurement, vol. 45, no. 2, 025007, 2024. doi:10.1088/1361-6579/ad252d

[7] S. Mahdiani, V. Jeyhani, M. Peltokangas, and A. Vehkaoja, "Is 50 Hz High Enough ECG Sampling Frequency for Accurate HRV Analysis?," in Proc. 37th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Milan, Italy, 2015, pp. 5948–5951. doi:10.1109/EMBC.2015.7319746

[8] J. Kingma, C. Simard, and B. Drolet, "Overview of cardiac arrhythmias and treatment strategies," Pharmaceuticals, vol. 16, no. 6, 844, 2023. doi:10.3390/ph16060844

[9] S. Chakrabarti and A. G. Stuart, "Understanding cardiac arrhythmias," Archives of Disease in Childhood, vol. 90, no. 10, pp. 1086–1090, 2005. doi:10.1136/adc.2005.076984

[10] P. R. Patil, A. Sait, and D. R. Patil, "A study of the risk factors of various arrhythmias in patients with coronary heart disease," International Journal of Advances in Medicine, vol. 4, no. 5, pp. 1369–1373, 2017. doi:10.18203/2349-3933.ijam20174285

[11] J. W. Mason, E. W. Hancock, and L. S. Gettes, "Recommendations for the standardization and interpretation of the electrocardiogram," Circulation, vol. 115, no. 10, pp. 1325–1332, 2007. doi:10.1161/circulationaha.106.180201

[12] T. Stracina, M. Ronzhina, R. Redina, and M. Novakova, "Golden standard or obsolete method? Review of ECG applications in clinical and experimental context," Frontiers in Physiology, vol. 13, no. 1, 867033, 2022. doi:10.3389/fphys.2022.867033

[13] D. E. Becker, “Fundamentals of electrocardiography interpretation,” Anesthesia Progress, vol. 53, no. 2, pp. 53–64, 2006. doi:10.2344/0003-3006(2006)53[53:FOEI]2.0.CO;2

[14] O. Kwon et al., "Electrocardiogram sampling frequency range acceptable for heart rate variability analysis," Healthcare Informatics Research, vol. 24, no. 3, pp. 198–206, 2018. doi:10.4258/hir.2018.24.3.198

[15] A. P. Wibawa, A. B. P. Utama, H. Elmunsyah, U. Pujianto, F. A. Dwiyanto, and L. Hernandez, "Time-series analysis with smoothed Convolutional Neural Network," Journal of Big Data, vol. 9, no. 1, 44, 2022. doi:10.1186/s40537-022-00599-y

[16] H. Liu et al., "A large-scale multi-label 12-lead electrocardiogram database with standardized diagnostic statements," Scientific Data, vol. 9, no. 1, 272, 2022. doi:10.1038/s41597-022-01403-5

[17] R. A. Dos Santos, "A comparative study of ECG leads in predicting cardiac arrhythmias using Deep Learning models," European Journal of Engineering Science and Technology, vol. 8, no. 1, pp. 1–12, 2025. doi:10.33422/ejest.v8i1.1472