FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Cardiovasc Digit Health J / Detecting paroxysmal atrial fibrillation from normal sinus r...
Cardiovascular digital health journal2022; 3(2); 96-106; doi: 10.1016/j.cvdhj.2022.02.001

Detecting paroxysmal atrial fibrillation from normal sinus rhythm in equine athletes using Symmetric Projection Attractor Reconstruction and machine learning.

Abstract: Atrial fibrillation (AF) is a common cardiac arrhythmia in both human and equine populations. It is associated with adverse outcomes in humans and decreased athletic performance in both populations. Paroxysmal atrial fibrillation (PAF) presents with intermittent, self-terminating AF episodes, and is difficult to diagnose once sinus rhythm resumes. Unassigned: We aimed to detect PAF subjects from normal sinus rhythm equine electrocardiograms (ECGs) using the Symmetric Projection Attractor Reconstruction (SPAR) method to encapsulate the waveform morphology and variability as the basis of a machine learning classification. Unassigned: We obtained ECG signals from 139 active equine athletes (120 control, 19 with a PAF diagnosis). The SPAR method was applied to 9 short (20-second) ECG strips for each subject. An optimal SPAR feature set was determined by forward feature selection for input to a machine learning model ensemble of 3 different classifiers (k-nearest neighbors, linear support vector machine, and radial basis function kernel support vector machine). Imbalanced data were handled by upsampling the minority (PAF) class. A final subject classification was made by taking a majority vote over results from the 9 ECG strips. Unassigned: Our final cross-validated classification for a subject gave an accuracy of 89.0%, sensitivity of 94.8%, specificity of 87.1%, and receiver operating characteristic area under the curve of 0.98, taking PAF as the positive class. Unassigned: The SPAR method and machine learning generated a final model with high sensitivity, suggesting that PAF can be discriminated from short equine ECG strips. This preliminary study indicated that SPAR analysis of human ECG could support patient monitoring, risk stratification, and clinical decision-making.
© 2022 Heart Rhythm Society.
Get Full Text
Publication Date: 2022-02-14 PubMed ID: 35493267PubMed Central: PMC9043370DOI: 10.1016/j.cvdhj.2022.02.001Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

The research article focused on the application of Symmetric Projection Attractor Reconstruction (SPAR) and machine learning to detect paroxysmal atrial fibrillation (an intermittent form of irregular heart rhythm) in horses. The study involved analyzing electrocardiograms of equine athletes and demonstrated high accuracy in differentiating horses with and without this heart condition.

Objective of the Study

  • The aim of the research was to differentiate horses with paroxysmal atrial fibrillation (PAF) from their healthy counterparts. The focus area was to develop a reliable machine learning model using the Symmetric Projection Attractor Reconstruction (SPAR) method, which maps waveform shapes and variations to identify PAF instances from short electrocardiogram (ECG) strips.

Methodology

  • The researchers sourced ECG recordings from 139 active equine athletes consisting of 120 control (healthy) and 19 diagnosed with PAF.
  • Each of the subjects had their heart’s electrical activity captured in nine short (20-second) ECG recordings, which were subsequently analyzed via the SPAR technique.
  • The team identified the most valuable SPAR features for the machine learning model through a forward feature selection process. The model created was an ensemble of three different classifiers, namely k-nearest neighbors, linear support vector machine, and radial basis function kernel support vector machine.
  • As the dataset was imbalanced (more healthy horses than those diagnosed with PAF), the researchers handled this by upsampling the minority (PAF) class to balance it with the majority class.
  • The final classification for each horse was achieved by taking the majority vote from the results of the nine ECG strips.

Results of the Study

  • The researchers were quite successful in their endeavor, with the final cross-validated model showing an accuracy rate of 89.0%. The machine learning model’s sensitivity and specificity were 94.8% and 87.1%, respectively, with a receiver operating characteristic area under the curve of 0.98, taking PAF as the positive class.
  • This suggests that the SPAR method combined with machine learning can accurately distinguish PAF from short equine ECG strips.

Potential Applications

  • The results of the study suggest that the SPAR technique has potential applications beyond veterinary science. It could be used to analyze human ECG readings to improve patient monitoring, risk stratification, and clinical decision-making processes.

Cite This Article

APA
Huang YH, Lyle JV, Ab Razak AS, Nandi M, Marr CM, Huang CL, Aston PJ, Jeevaratnam K. (2022). Detecting paroxysmal atrial fibrillation from normal sinus rhythm in equine athletes using Symmetric Projection Attractor Reconstruction and machine learning. Cardiovasc Digit Health J, 3(2), 96-106. https://doi.org/10.1016/j.cvdhj.2022.02.001

Publication

Cardiovascular digital health journal
ISSN: 2666-6936
NlmUniqueID: 101771268
Country: United States
Language: English
Volume: 3
Issue: 2
Pages: 96-106

Researcher Affiliations

Huang, Ying H
  • Faculty of Health and Medical Sciences, University of Surrey, Guildford, United Kingdom.
  • Department of Mathematics, University of Surrey, Guildford, United Kingdom.
Lyle, Jane V
  • Department of Mathematics, University of Surrey, Guildford, United Kingdom.
Ab Razak, Anisa Shahira
  • Department of Veterinary Medicine, University of Cambridge, Madingley Rd, Cambridge, United Kingdom.
Nandi, Manasi
  • School of Cancer and Pharmaceutical Sciences, Faculty of Life Sciences & Medicine, King's College London, London, United Kingdom.
Marr, Celia M
  • Rossdales Equine Hospital and Diagnostic Centre, Newmarket, United Kingdom.
Huang, Christopher L-H
  • Faculty of Health and Medical Sciences, University of Surrey, Guildford, United Kingdom.
  • Physiological Laboratory, University of Cambridge, Cambridge, United Kingdom.
Aston, Philip J
  • Department of Mathematics, University of Surrey, Guildford, United Kingdom.
Jeevaratnam, Kamalan
  • Faculty of Health and Medical Sciences, University of Surrey, Guildford, United Kingdom.

References

This article includes 41 references
  1. Rao P, Shipon D M. Atrial fibrillation in competitive athletes.. Am Coll Cardiol 2019.
  2. Hindricks G, Potpara T, Dagres N. 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS). Eur Heart J 2020;42:373–498.
    pubmed: 32860505
  3. Reef V B, Levitan C W, Spencer P A. Factors affecting prognosis and conversion in equine atrial fibrillation.. J Vet Intern Med 1988;2:1–6.
    pubmed: 3221350
  4. McGurrin K. The diagnosis and management of atrial fibrillation in the horse.. Vet Med (Auckl) 2015;6:83–90.
    pmc: PMC6067668pubmed: 30101098
  5. Buhl R, Carstensen H, Hesselkilde E Z. Effect of induced chronic atrial fibrillation on exercise performance in Standardbred trotters.. J Vet Intern Med 2018;32:1410–1419.
    pmc: PMC6060327pubmed: 29749082
  6. van Loon G. Cardiac arrhythmias in horses.. Vet Clin North Am Equine Pract 2019;35:85–102.
    pubmed: 30871832
  7. Verheyen T, Decloedt A, van der Vekens N, Sys S, De Clercq D, van Loon G. Ventricular response during lungeing exercise in horses with lone atrial fibrillation.. Equine Vet J 2013;45:309–314.
    pubmed: 23094848
  8. Reef V B, Bonagura J, Buhl R. Recommendations for management of equine athletes with cardiovascular abnormalities.. J Vet Intern Med 2014;28:749–761.
    pmc: PMC4895474pubmed: 24628586
  9. Pillarisetti J, Patel A, Boc K. Evolution of paroxysmal atrial fibrillation to persistent or permanent atrial fibrillation: predictors of progression.. J Atr Fibrillation 2009;1:388–394.
    pmc: PMC5398837pubmed: 28496630
  10. Ogawa H, An Y, Ikeda S. Progression from paroxysmal to sustained atrial fibrillation is associated with increased adverse events.. Stroke 2018;49:2301–2308.
    pubmed: 30355097
  11. Friberg L, Hammar N, Rosenqvist M. Stroke in paroxysmal atrial fibrillation: report from the Stockholm Cohort of Atrial Fibrillation.. Eur Heart J 2010;31:967–975.
    pubmed: 19176537
  12. Rabinstein A A. Prolonged cardiac monitoring for detection of paroxysmal atrial fibrillation after cerebral ischemia.. Stroke 2014;45:1208–1214.
    pubmed: 24619396
  13. Frustaci A, Chimenti C, Bellocci F, Morgante E, Russo M A, Maseri A. Histological substrate of atrial biopsies in patients with lone atrial fibrillation.. Circulation 1997;96:1180–1184.
    pubmed: 9286947
  14. De Jong A M, Maass A H, Oberdorf-Maass S U, Van Veldhuisen D J, Van Gilst W H, Van Gelder I C. Mechanisms of atrial structural changes caused by stretch occurring before and during early atrial fibrillation.. Cardiovasc Res 2011;89:754–765.
    pubmed: 21075756
  15. Decloedt A, Verheyen T, Van Der Vekens N, Sys S, De Clercq D, Van Loon G. Long-term follow-up of atrial function after cardioversion of atrial fibrillation in horses.. Vet J 2013;197:583–588.
    pubmed: 23823082
  16. Hesselkilde E Z, Carstensen H, Flethøj M. Longitudinal study of electrical, functional and structural remodelling in an equine model of atrial fibrillation.. BMC Cardiovasc Disord 2019;19:1–12.
    pmc: PMC6805623pubmed: 31638896
  17. Xin Y, Zhao Y. Paroxysmal atrial fibrillation recognition based on multi-scale wavelet α-entropy.. Biomed Eng Online 2017;16:1–12.
    pmc: PMC5654099pubmed: 29061181
  18. Olier I, Ortega-Martorell S, Pieroni M, Lip G Y H. How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management.. Cardiovasc Res 2021;117:1700–1717.
    pmc: PMC8477792pubmed: 33982064
  19. Alexeenko V, Fraser J A, Bowen M, Huang C L H, Marr C M, Jeevaratnam K. The complexity of clinically-normal sinus-rhythm ECGs is decreased in equine athletes with a diagnosis of paroxysmal atrial fibrillation.. Sci Rep 2020;10:1–10.
    pmc: PMC7176685pubmed: 32321950
  20. Huang Y H, Alexeenko V, Tse G, Huang C L-H, Marr C M, Jeevaratnam K. ECG restitution analysis and machine learning to detect paroxysmal atrial fibrillation: insight from the equine athlete as a model for human athletes.. Function 2020;2:1–10.
    pmc: PMC8788737pubmed: 35330977
  21. Aston P J, Christie M I, Huang Y H, Nandi M. Beyond HRV: attractor reconstruction using the entire cardiovascular waveform data for novel feature extraction.. Physiol Meas 2018;39.
    pmc: PMC5831644pubmed: 29350622
  22. Nandi M, Venton J, Aston P J. A novel method to quantify arterial pulse waveform morphology: attractor reconstruction for physiologists and clinicians.. Physiol Meas 2018;39:104008.
    pmc: PMC6372136pubmed: 30256216
  23. Nandi M, Aston P J. Extracting new information from old waveforms: symmetric projection attractor reconstruction: where maths meets medicine.. Exp Physiol 2020;105:1444–1451.
    pubmed: 32347611
  24. Bonet-Luz E, Lyle J V, Huang C L H. Symmetric Projection Attractor Reconstruction analysis of murine electrocardiograms: retrospective prediction of Scn5a+/- genetic mutation attributable to Brugada syndrome.. Heart Rhythm O2 2020;1:368–375.
    pmc: PMC7962089pubmed: 33748801
  25. Lyle J V, Aston P J, Nandi M. Investigating the response to dofetilide with Symmetric Projection Attractor Reconstruction of the electrocardiogram.. Comput Cardiol 2019;46:73.
  26. Lyle J V, Nandi M, Aston P J. Symmetric Projection Attractor Reconstruction: sex differences in the ECG.. Front Cardiovasc Med 2021;8:709457.
    pmc: PMC8495026pubmed: 34631814
  27. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning.. Springer 2nd edition. 2008.
  28. He H, Garcia E A. Learning from imbalanced data.. IEEE Trans Knowl Data Eng 2009;21:1263–1284.
  29. Nekooeimehr I, Lai-Yuen S K. Adaptive semi-unsupervised weighted oversampling (A-SUWO) for imbalanced datasets.. Expert Syst Appl 2016;46:405–416.
  30. Kuhn M, Johnson K. Over-fitting and model tuning.. Applied Predictive Modeling 2016:61–92.
  31. Blum A L, Langley P. Selection of relevant features and examples in machine learning.. Artif Intell 1997;97:245–271.
  32. Guyon I, Elisseeff A. An introduction to variable and feature selection.. J Mach Learn Res 2003;3:1157–1182.
  33. Powers D M W. Evaluation: from precision, recall and F-factor to ROC, informedness, markedness and correlation.. J Mach Learn Technol 2011;2:37–63.
  34. Aston P J, Lyle J V, Bonet-Luz E. Deep learning applied to attractor images derived from ECG signals for detection of genetic mutation.. Comput Cardiol 2019;46:97.
  35. Venton J, Harris P M, Sundar A, Smith N A S, Aston P J. Robustness of convolutional neural networks to physiological ECG noise.. Philos Trans R Soc A Math Phys Eng Sci 2021;379:20200262.
    pmc: PMC8543045pubmed: 34689617
  36. Faust O, Kareem M, Ali A, Ciaccio E J, Acharya U R. Automated arrhythmia detection based on RR intervals.. Diagnostics 2021;11:1–18.
    pmc: PMC8391893pubmed: 34441380
  37. Bashar S K, Han D, Zieneddin F. Novel density Poincaré plot based machine learning method to detect atrial fibrillation from premature atrial / ventricular contractions.. IEEE Trans Biomed Eng 2021;68:448–460.
    pmc: PMC7863548pubmed: 32746035
  38. Alexeenko V, Fraser J A, Dolgoborodov A. The application of Lempel-Ziv and Titchener complexity analysis for equine telemetric electrocardiographic recordings.. Sci Rep 2019;9:1–7.
    pmc: PMC6385502pubmed: 30796330
  39. Lyle J V, Nandi M, Aston P J. Symmetric Projection Attractor Reconstruction: inter-individual differences in the ECG.. Comput Cardiol 2021;48:123.
    pmc: PMC8495026pubmed: 34631814
  40. Attia Z I, Noseworthy P A, Lopez-Jimenez F. 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;394:861–867.
    pubmed: 31378392
  41. Alexeenko V, Howlett P J, Fraser J A. Prediction of paroxysmal atrial fibrillation from complexity analysis of the sinus rhythm ECG: a retrospective case/control pilot study.. Front Physiol 2021;12:1–12.
    pmc: PMC7933455pubmed: 33679427

Citations

This article has been cited 3 times.
  1. Kapusniak A, Lara NM, Hitchens PL, Bailey S, Nath L, Franklin S. Use of Artificial Intelligence to Detect Cardiac Rhythm Disturbances in Athletes: A Scoping Review. J Vet Intern Med 2025 Nov-Dec;39(6):e70257.
    doi: 10.1111/jvim.70257pubmed: 41017277google scholar: lookup
  2. Akbarein H, Taaghi MH, Mohebbi M, Soufizadeh P. Applications and Considerations of Artificial Intelligence in Veterinary Sciences: A Narrative Review. Vet Med Sci 2025 May;11(3):e70315.
    doi: 10.1002/vms3.70315pubmed: 40173266google scholar: lookup
  3. Zhang Z, Hirose K, Yamada K, Sato D, Uchida K, Umezu S. A periodic split attractor reconstruction method facilitates cardiovascular signal diagnoses and obstructive sleep apnea syndrome monitoring. Heliyon 2024 Aug 15;10(15):e35623.
    doi: 10.1016/j.heliyon.2024.e35623pubmed: 39170365google scholar: lookup
Subscribe to our newsletter
Join 99,357 horse owners like you who receive our email updates on horse health and nutrition.