Skip to main content
SpringerLink
Log in

Explanation of HRV Features for Detecting Atrial Fibrillation

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Atrial fibrillation is a heart condition that is known to be affecting approximately 33 million people in the world and cause a wide range of complications, that may at times be fatal if not properly treated. Many studies try to address this condition by either training highly accurate artificial intelligence detector models or by explaining the physiological significance of certain features used to train these detector models. However, the problem with these kind of studies is that it leaves its users to either blindly trust the calls of a black box model, or merely inform themselves of various features. In this study, we try to address this problem by revealing which features are most frequently chosen by artificial intelligence models to detect atrial fibrillation and also try to explain why they might be so significant. To achieve this, heart rate variability features are extracted from the ‘PhysioNet/Computing in Cardiology (CinC) Challenge 2017’ dataset and are used to train machine learning models like Random Forest and XGBoost, with Recursive Feature Elimination. We find that many machine learning algorithms find the ‘hr_std’, ‘sd_ratio’, ‘nni_mean’, and ‘pnn20’ features to be most important in detecting atrial fibrillation. We achieve a mean F\(_1\)-score of 98.13% and 95.18% for Random Forest and Support Vector Machine with a Linear Kernel, respectively, using K-Fold Cross-Validation with five-folds.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Nattel S. New ideas about atrial fibrillation 50 years on. Nature. 2002;415:219–26.

    Article  Google Scholar 

  2. Rahman F, Kwan GF, Benjamin EJ. Global epidemiology of atrial fibrillation. Nat Rev Cardiol. 2014;11:639–54.

    Article  Google Scholar 

  3. Savelieva I, Camm AJ. Clinical relevance of silent atrial fibrillation: prevalence, prognosis, quality of life, and management. J Interv Card Electrophysiol. 2000;4:369–82.

    Article  Google Scholar 

  4. Chiang CE, Naditch-Brûlé L, Murin J, Goethals M, Inoue M, O’Neill J, Silva-Cardoso J, Zharinov O, Gamra H, Alam S, Ponikowski P, Lewalter T, Rosenqvist M, Steg PG. Distribution and risk profile of paroxysmal. Persistent, and permanent atrial fibrillation in routine clinical practice: insight from the real-life global survey evaluating patients with atrial fibrillation international registry. Circ Arrhythm Electrophysiol. 2012;5:632–9.

    Article  Google Scholar 

  5. Nieuwlaat R, Prins MH, Le Heuzey J-Y, Vardas PE, Aliot E, Santini M, Cobbe SM, Widdershoven JW, Baur LH, Lévy S, Crijns HJ. Prognosis, disease progression, and treatment of atrial fibrillation patients during 1 year: follow-up of the Euro Heart Survey on Atrial Fibrillation. Eur Heart J. 2008;29:1181–9.

    Article  Google Scholar 

  6. Atrial fibrillation - living with | NHLBI, NIH. https://www.nhlbi.nih.gov/health/atrial-fibrillation/living-with. Accessed 22 Apr 2022.

  7. Alpert JS, Petersen P, Godtfredsen J. Atrial fibrillation: natural history, complications, and management. Annu Rev Med. 1988;39(1):41–52.

    Article  Google Scholar 

  8. Lee Y, Pham V, Chung TM. Innovative way of detecting atrial fibrillation based on HRV features using AI-techniques. In: Dang TK, Küng J, Chung TM, Takizawa M, editors. Future data and security engineering. Big data, security and privacy smart city and industry 40 applications. Singapore: Springer; 2021. p. 363–74.

    Google Scholar 

  9. Tsipouras MG, Fotiadis DI. Automatic arrhythmia detection based on time and time–frequency analysis of heart rate variability. Comput Methods Programs Biomed. 2004;74:95–108.

    Article  Google Scholar 

  10. Attia ZI, Noseworthy PA, Lopez-Jimenez F, Asirvatham SJ, Deshmukh AJ, Gersh BJ, Carter RE, Yao X, Rabinstein AA, Erickson BJ, Kapa S, Friedman PA. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: A retrospective analysis of outcome prediction. Lancet. 2019;394:861–7.

    Article  Google Scholar 

  11. Hirsch G, Jensen SH, Poulsen ES, Puthusserypady S. Atrial fibrillation detection using heart rate variability and atrial activity: a hybrid approach. Expert Syst Appl. 2021;169: 114452.

    Article  Google Scholar 

  12. Liaqat S, Dashtipour K, Zahid A, Assaleh K, Arshad K, Ramzan N. Detection of atrial fibrillation using a machine learning approach. Information. 2020;11:549.

    Article  Google Scholar 

  13. Shaffer F, Ginsberg JP. An overview of heart rate variability metrics and norms. Front Public Health. 2017;5:258.

    Article  Google Scholar 

  14. Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. 2000;101:E215-220.

    Article  Google Scholar 

  15. Clifford GD, Liu C, Moody B, Lehman LwH LehmaLwH, Silva I, Li Q, Johnson AE. AF classification from a short single lead ECG recording: the physionet/computing in cardiology challenge 2017. Comput Cardiol. 2017. https://doi.org/10.22489/CinC.2017.065-469.

    Article  Google Scholar 

  16. Lemaître G, Nogueira F, Aridas CK. Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J Mach Learn Res. 2017;18(17):1–5.

    Google Scholar 

  17. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–30.

    MathSciNet  MATH  Google Scholar 

  18. Gomes P, Margaritoff P, Silva H. pyHRV: “Development and evaluation of an open-source python toolbox for heart rate variability (HRV)” in Proc. Electronic and Computing Engineering (IcETRAN): Int’l Conf. on Electrical; 2019. p. 822–8.

  19. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321–57.

    Article  MATH  Google Scholar 

  20. Highlights—pyHRV - OpenSource python toolbox for heart rate variability 0.4 Documentation. https://pyhrv.readthedocs.io/en/latest/. Accessed 13 Apr 2022.

  21. van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(86):2579–605.

    MATH  Google Scholar 

  22. Tipping ME, Bishop CM. Probabilistic principal component analysis. J R Stat Soc. 1999;61(3):611–22.

    Article  MathSciNet  MATH  Google Scholar 

  23. Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments. Philos Trans R Soc A. 2016;374:20150202.

    Article  MathSciNet  MATH  Google Scholar 

  24. MacQueen J. Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics. 1967;5(1):281–98.

    MathSciNet  MATH  Google Scholar 

  25. Carrara M, Carozzi L, Moss TJ, de Pasquale M, Cerutti S, Ferrario M, Lake DE, Moorman JR. Heart rate dynamics distinguish among atrial fibrillation, normal sinus rhythm and sinus rhythm with frequent ectopy. Physiol Meas. 2015;36:1873–88.

    Article  Google Scholar 

  26. Chen S-A, Hsieh M-H, Tai C-T, Tsai C-F, Prakash VS, Yu W-C, Hsu T-L, Ding Y-A, Chang M-S. Initiation of atrial fibrillation by ectopic beats originating from the pulmonary veins. Circulation. 1999;100:1879–86.

    Article  Google Scholar 

  27. Ewing DJ, Neilson JM, Travis P. New method for assessing cardiac parasympathetic activity using 24 hour electrocardiograms. Heart. 1984;52:396–402.

    Article  Google Scholar 

  28. Bigger JT, Kleiger RE, Fleiss JL, Rolnitzky LM, Steinman RC, Miller JP. Components of heart rate variability measured during healing of acute myocardial infarction. Am J Cardiol. 1988;61:208–15.

    Article  Google Scholar 

  29. Chakko S, Mulingtapang RF, Huikuri HV, Kessler KM, Materson BJ, Myerburg RJ. Alterations in heart rate variability and its circadian rhythm in hypertensive patients with left ventricular hypertrophy free of coronary artery disease. Am Heart J. 1993;126:1364–72.

    Article  Google Scholar 

  30. Mietus JE, Peng C-K, Henry I, Goldsmith RL, Goldberger AL. The pNNx files: re-examining a widely used heart rate variability measure. Heart. 2002;88:378–80.

    Article  Google Scholar 

  31. Behbahani S, Dabanloo NJ, Nasrabadi AM. Ictal heart rate variability assessment with focus on secondary generalized and complex partial epileptic seizures. Adv Biores. 2013;4(1):50–8.

    Google Scholar 

  32. Guzik P, Piskorski J, Krauze T, Schneider R, Wesseling KH, Wykretowicz A, Wysocki H. Correlations between poincaré plot and conventional heart rate variability parameters assessed during paced breathing. J Physiol Sci. 2007. https://doi.org/10.2170/physiolsci.RP005506.

    Article  Google Scholar 

Download references

Funding

This work was supported by the Technology Innovation Program (or Industrial Strategic Technology Development Program-Source Technology Development and Commercialization of Digital Therapeutics) (20014967, Development of Digital Therapeutics for Depression from COVID19) funded By the Ministry of Trade, Industry & Energy (MOTIE, Korea).

Author information

Authors and Affiliations

  1. College of International Studies, Kyung Hee University, Yongin, Republic of Korea

    Yongho Lee

  2. Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea

    Vinh Pham & Tai-Myoung Chung

  3. Hippo T&C, Inc., Suwon, Republic of Korea

    Yongho Lee & Tai-Myoung Chung

Authors
  1. Yongho Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vinh Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tai-Myoung Chung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yongho Lee or Tai-Myoung Chung.

Ethics declarations

Conflict of Interest

Yongho Lee is an employee of Hippo T&C, Inc. And Dr. Tai-Myoung Chung is the Chief Executive Officer of Hippo T&C, Inc. Business interest did not influence this research, and neither financial nor material gains were made as a result of it.

Informed Consent

As the authors are not the entity which engaged in the direct collection or distribution of human originating data, used to conduct experiments in this research, they have nothing to declare concerning informed consent. The authors are authorized per the Open Data Commons Attribution License (ODC-By) v1.0 to use the relevant dataset for this research. The authors, in good faith, believe that they are in compliance with the relevant ethical standards.

Research Involving Human Participants and/or Animals

Data originating from human participants, used in this research, were acquired from PhysioNet. PhysioNet, in turn, explicitly authorizes anyone to utilize the relevant datasets under the condition that the terms specified under the Open Data Commons Attribution License (ODC-By) v1.0 is complied with. The authors, in good faith, believe that they are in compliance with the relevant ethical standards.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Future Data and Security Engineering 2021” guest edited by Tran Khanh Dang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, Y., Pham, V. & Chung, TM. Explanation of HRV Features for Detecting Atrial Fibrillation. SN COMPUT. SCI. 3, 424 (2022). https://doi.org/10.1007/s42979-022-01309-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01309-4

Keywords

Search

Navigation