Advertisement

Medical & Biological Engineering & Computing

, Volume 56, Issue 7, pp 1253–1270 | Cite as

A time local subset feature selection for prediction of sudden cardiac death from ECG signal

  • Elias Ebrahimzadeh
  • Mohammad Sajad Manuchehri
  • Sana Amoozegar
  • Babak Nadjar Araabi
  • Hamid Soltanian-Zadeh
Original Article

Abstract

Prediction of sudden cardiac death continues to gain universal attention as a promising approach to saving millions of lives threatened by sudden cardiac death (SCD). This study attempts to promote the literature from mere feature extraction analysis to developing strategies for manipulating the extracted features to target improvement of classification accuracy. To this end, a novel approach to local feature subset selection is applied using meticulous methodologies developed in previous studies of this team for extracting features from non-linear, time-frequency, and classical processes. We are therefore enabled to select features that differ from one another in each 1-min interval before the incident. Using the proposed algorithm, SCD can be predicted 12 min before the onset; thus, more propitious results are achieved. Additionally, through defining a utility function and employing statistical analysis, the alarm threshold has effectively been determined as 83%. Having selected the best combination of features, the two classes are classified using the multilayer perceptron (MLP) classifier. The most effective features would subsequently be discussed considering their prevalence in the rank-based selection. The results indicate the significant capacity of the proposed method for predicting SCD as well as selecting the appropriate processing method at any time before the incident.

Graphical abstract

Keywords

Sudden cardiac death Heart rate variability Feature reduction Time local subset feature selection 

Notes

Acknowledgements

We would like to show our gratitude to Ms. Farahnaz Fayaz (School of Electrical Engineering, Payam Noor University, Tehran, Iran) for sharing her pearls of wisdom with us during the course of this research and writing it. We are also immensely grateful to Dr. Morteza Zanganeh Soroush and Dr. Mohammad Hassan Zokaei Ashtiani for their comments on the earlier version of the manuscript, although any errors are of our own and should not tarnish the reputation of these esteemed persons.

References

  1. 1.
    Tamil EBM, Kamarudin N, Salleh R, Tamil AM. A review on feature extraction & classification techniques for biosignal processing (Part I: Electrocardiogram); 2008. Springer. pp. 107–112Google Scholar
  2. 2.
    Lloyd-Jones D, Adams RJ, Brown TM, Carnethon M, Dai S et al (2010) Heart disease and stroke statistics—2010 update. A report from the American Heart Association. Circulation 121(7):e46–e215.  https://doi.org/10.1161/CIRCULATIONAHA.109.192667 CrossRefPubMedGoogle Scholar
  3. 3.
    Kong MH, Fonarow GC, Peterson ED, Curtis AB, Hernandez AF, Sanders GD, Thomas KL, Hayes DL, SM a-K (2011) Systematic review of the incidence of sudden cardiac death in the United States. J Am Coll Cardiol 57(7):794–801.  https://doi.org/10.1016/j.jacc.2010.09.064 CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Pagidipati NJ, Gaziano TA (2013) Estimating deaths from cardiovascular disease: a review of global methodologies of mortality measurement. Circulation 127(6):749–756.  https://doi.org/10.1161/CIRCULATIONAHA.112.128413 CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    Passman R, Goldberger JJ (2012) Predicting the future risk stratification for sudden cardiac death in patients with left ventricular dysfunction. Circulation 125(24):3031–3037.  https://doi.org/10.1161/CIRCULATIONAHA.111.023879 CrossRefPubMedGoogle Scholar
  6. 6.
    Huikuri HV, Castellanos A, Myerburg RJ (2001) Sudden death due to cardiac arrhythmias. N Engl J Med 345(20):1473–1482.  https://doi.org/10.1056/NEJMra000650 CrossRefPubMedGoogle Scholar
  7. 7.
    Wever E, Hauer R, Oomen A, Peters R, Bakker P et al (1993) Unfavorable outcome in patients with primary electrical disease who survived an episode of ventricular fibrillation. Circulation 88(3):1021–1029.  https://doi.org/10.1161/01.CIR.88.3.1021 CrossRefPubMedGoogle Scholar
  8. 8.
    Zipes DP, Wellens HJ (1998) Sudden cardiac death. Circulation 98(21):2334–2351.  https://doi.org/10.1161/01.CIR.98.21.2334 CrossRefPubMedGoogle Scholar
  9. 9.
    Priori SG (1997) Survivors of out-of-hospital cardiac arrest with apparently normal heart. Circulation 95:265–272CrossRefGoogle Scholar
  10. 10.
    Chugh SS, Kelly KL, Titus JL (2000) Sudden cardiac death with apparently normal heart. Circulation 102(6):649–654.  https://doi.org/10.1161/01.CIR.102.6.649 CrossRefPubMedGoogle Scholar
  11. 11.
    Chugh SS (2001) Sudden cardiac death with apparently normal heart. Card Electrophysiol Rev 5(4):394–402.  https://doi.org/10.1023/A:1013254132689 CrossRefGoogle Scholar
  12. 12.
    Shen TW, Shen H-P, Lin CH, Ou YL. Detection and prediction of sudden cardiac death (SCD) for personal healthcare; 2007. IEEE. pp. 2575–2578.  https://doi.org/10.1109/IEMBS.2007.4352855
  13. 13.
    Smith WM (1997) Cardiac defibrillation. IEEE-EMBC and CMBEC: 249–250Google Scholar
  14. 14.
    Myerburg RJ (1992) Cardiac arrest and sudden cardiac death. Heart disease, a textbook of cardiovascular. Medicine 1:756–789Google Scholar
  15. 15.
    Nichol G, Thomas E, Callaway CW, Hedges J, Powell JL, Aufderheide TP, Rea T, Lowe R, Brown T, Dreyer J, Davis D, Idris A, Stiell I, Resuscitation Outcomes Consortium Investigators (2008) Regional variation in out-of-hospital cardiac arrest incidence and outcome. JAMA 300(12):1423–1431.  https://doi.org/10.1001/jama.300.12.1423 CrossRefPubMedPubMedCentralGoogle Scholar
  16. 16.
    Fishman GI, Chugh SS, DiMarco JP, Albert CM, Anderson ME, Bonow RO, Buxton AE, Chen PS, Estes M, Jouven X, Kwong R, Lathrop DA, Mascette AM, Nerbonne JM, O’Rourke B, Page RL, Roden DM, Rosenbaum DS, Sotoodehnia N, Trayanova NA, Zheng ZJ (2010) Sudden cardiac death prediction and prevention report from a National Heart, Lung, and Blood Institute and Heart Rhythm Society workshop. Circulation 122(22):2335–2348.  https://doi.org/10.1161/CIRCULATIONAHA.110.976092 CrossRefPubMedPubMedCentralGoogle Scholar
  17. 17.
    Jones JL, Tovar OH (1996) The mechanism of defibrillation and cardioversion. Proc IEEE 84(3):392–403.  https://doi.org/10.1109/5.486742 CrossRefGoogle Scholar
  18. 18.
    Lee H, Seo M, Joo S. Early prediction of ventricular tachyarrhythmias based on heart rate variability analysis; 2015. IEEE. pp. 1041–1044.  https://doi.org/10.1109/CIC.2015.7411092
  19. 19.
    Suszko AM, Dalvi R, Das M, Chauhan VS. Quantifying abnormal QRS peaks using a novel time-domain peak detection algorithm: application in patients with cardiomyopathy at risk of sudden death; 2015. IEEE. pp. 020–024.  https://doi.org/10.1109/EIT.2015.7293317
  20. 20.
    Imam MH, Karmakar C, Khandoker A, Palaniswami M. A novel technique for analysing beat-to-beat dynamical changes of QT-RR distribution for arrhythmia prediction; 2015. IEEE. pp. 1157–1160.  https://doi.org/10.1109/CIC.2015.7411121
  21. 21.
    Fang Z, Lai D, Ge X, Wu X. Successive ECG telemetry monitoring for preventing sudden cardiac death; 2009. IEEE. pp. 1738-1741.  https://doi.org/10.1109/IEMBS.2009.5333088
  22. 22.
    Huikuri HV, Tapanainen JM, Lindgren K, Raatikainen P, Mäkikallio TH, Juhani Airaksinen KE, Myerburg RJ (2003) Prediction of sudden cardiac death after myocardial infarction in the beta-blocking era. J Am Coll Cardiol 42(4):652–658.  https://doi.org/10.1016/S0735-1097(03)00783-6 CrossRefPubMedGoogle Scholar
  23. 23.
    Acharya UR, Fujita H, Sudarshan VK, Sree VS, Eugene LWJ, Ghista DN, Tan RS (2015) An integrated index for detection of sudden cardiac death using discrete wavelet transform and nonlinear features. Knowl-Based Syst 83:149–158.  https://doi.org/10.1016/j.knosys.2015.03.015 CrossRefGoogle Scholar
  24. 24.
    Al-Khatib SM, Sanders GD, Bigger JT, Buxton AE, Califf RM, Carlson M, Curtis A, Curtis J, Fain E, Gersh BJ, Gold MR, Haghighi-Mood A, Hammill SC, Healey J, Hlatky M, Hohnloser S, Kim RJ, Lee K, Mark D, Mianulli M, Mitchell B, Prystowsky EN, Smith J, Steinhaus D, Zareba W, Expert panel participating in a Duke’s Center for the Prevention of Sudden Cardiac Death conference (2007) Preventing tomorrow’s sudden cardiac death today: part I: current data on risk stratification for sudden cardiac death. Am Heart J 153(6):941–950.  https://doi.org/10.1016/j.ahj.2007.03.003 CrossRefPubMedGoogle Scholar
  25. 25.
    Kuck K-H, Cappato R, Siebels J, Rüppel R, Investigators C (2000) Randomized comparison of antiarrhythmic drug therapy with implantable defibrillators in patients resuscitated from cardiac arrest the Cardiac Arrest Study Hamburg (CASH). Circulation 102(7):748–754.  https://doi.org/10.1161/01.CIR.102.7.748 CrossRefPubMedGoogle Scholar
  26. 26.
    Braunschweig F, Boriani G, Bauer A, Hatala R, Herrmann-Lingen C, Kautzner J, Pedersen SS, Pehrson S, Ricci R, Schalij MJ (2010) Management of patients receiving implantable cardiac defibrillator shocks. Europace 12(12):1673–1690.  https://doi.org/10.1093/europace/euq316 CrossRefPubMedGoogle Scholar
  27. 27.
    Lombardi F, Mäkikallio TH, Myerburg RJ, Huikuri HV (2001) Sudden cardiac death: role of heart rate variability to identify patients at risk. Cardiovasc Res 50(2):210–217.  https://doi.org/10.1016/S0008-6363(01)00221-8 CrossRefPubMedGoogle Scholar
  28. 28.
    Huikuri HV, Mäkikallio TH, Raatikainen MP, Perkiömäki J, Castellanos A et al (2003) Prediction of sudden cardiac death appraisal of the studies and methods assessing the risk of sudden arrhythmic death. Circulation 108(1):110–115.  https://doi.org/10.1161/01.CIR.0000077519.18416.43 CrossRefPubMedGoogle Scholar
  29. 29.
    Statters DJ, Malik M, Ward DE, CAMM A (1994) QT dispersion: problems of methodology and clinical significance. J Cardiovasc Electrophysiol 5(8):672–685.  https://doi.org/10.1111/j.1540-8167.1994.tb01190.x CrossRefPubMedGoogle Scholar
  30. 30.
    Ebrahimzadeh E, Pooyan M (2011) Early detection of sudden cardiac death by using classical linear techniques and time-frequency methods on electrocardiogram signals. J Biomed Sci Eng 4(11):699–706.  https://doi.org/10.4236/jbise.2011.411087 CrossRefGoogle Scholar
  31. 31.
    Ebrahimzadeh E, Pooyan M (2013) Prediction of sudden cardiac death (SCD) using time-frequency analysis of ECG signals. Computational Intelligence Electr Eng 3:15–26Google Scholar
  32. 32.
    Ebrahimzadeh E, Pooyan M, Bijar A (2014) A novel approach to predict sudden cardiac death (SCD) using nonlinear and time-frequency analyses from HRV signals. PLoS One 9(2):e81896.  https://doi.org/10.1371/journal.pone.0081896 CrossRefPubMedPubMedCentralGoogle Scholar
  33. 33.
    Mirhoseini SR, JahedMotlagh MR, Pooyan M (2016) Improve accuracy of early detection sudden cardiac deaths (SCD) using decision forest and SVM. International Conference on Robotics and Artificial Intelligence (ICRAI), USAGoogle Scholar
  34. 34.
    Acharya R, Kumar A, Bhat P, Lim C, Kannathal N et al (2004) Classification of cardiac abnormalities using heart rate signals. Medical Biological Engineering Computing 42:288–293CrossRefPubMedGoogle Scholar
  35. 35.
    Malik M, Cardiology TFotESo (1996) the North American Society of Pacing and Electrophysiology. Heart rate variability: standards of measurement, physiological interpretation, and clinical use. Circulation 93:1043–1065CrossRefGoogle Scholar
  36. 36.
    Kurths J, Voss A, Saparin P, Witt A, Kleiner H et al (1995) Quantitative analysis of heart rate variability. Chaos: An Interdisciplinary J Nonlinear Sci 5(1):88–94.  https://doi.org/10.1063/1.166090 CrossRefGoogle Scholar
  37. 37.
    VanHoogenhuyze D, Martin G, Weiss J, Schaad J, Singer D. Spectrum of heart rate variability; 1989. IEEE pp 65.  https://doi.org/10.1109/CIC.1989.130482
  38. 38.
    Ichimaru Y, Kodama Y, Yanaga T. Circadian changes of heart rate variability; 1988. IEEE. pp. 315–318.  https://doi.org/10.1109/CIC.1988.72625
  39. 39.
    Murukesan L, Murugappan M, Iqbal M, Saravanan K (2014) Machine learning approach for sudden cardiac arrest prediction based on optimal heart rate variability features. J Medical Imaging Health Informatics 4(4):521–532.  https://doi.org/10.1166/jmihi.2014.1287 CrossRefGoogle Scholar
  40. 40.
    Murukesan L, Murugappan M, Iqbal M. Sudden cardiac death prediction using ECG signal derivative (heart rate variability): a review; 2013. IEEE. pp. 269–274.  https://doi.org/10.1109/CSPA.2013.6530054
  41. 41.
    Siwindarto P, Wardana I, Indra MR, Widodo MA (2015) Sudden cardiac death prediction using Poincaré plot of RR interval differences (PORRID). Appl Math Sci 9:2515–2524Google Scholar
  42. 42.
    Manis G, Nikolopoulos S, Arsenos P, Gatzoulis K, Dilaveris P, et al. Risk stratification for arrhythmic sudden cardiac death in heart failure patients using machine learning techniques; 2013. IEEE. pp. 141–144Google Scholar
  43. 43.
    Acharya UR, Fujita H, Sudarshan VK, Ghista DN, Lim WJE, et al. Automated prediction of sudden cardiac death risk using Kolmogorov complexity and recurrence quantification analysis features extracted from HRV signals; 2015. IEEE. pp. 1110–1115.  https://doi.org/10.1109/SMC.2015.199
  44. 44.
    Sheela CJ, Vanitha L. Prediction of sudden cardiac death using support vector machine; 2014. IEEE. pp. 377–381Google Scholar
  45. 45.
    Vanitha L, Suresh G, JenefarSheela C. Sudden cardiac death prediction system using Hybrid classifier; 2014. IEEE. pp. 1–5.  https://doi.org/10.1109/ECS.2014.6892677
  46. 46.
    Casas M, Avitia R, Reyna M, Cárdenas A Evaluation of three machine learning algorithms as classifiers of premature ventricular contractions on ECG beatsGoogle Scholar
  47. 47.
    Arjmandi MK, Pooyan M, Mikail M, Vali M, Moqarehzadeh AR (2011) Identification of voice disorders using long-time features and support vector machine with different feature reduction methods. J Voice 25:275–289CrossRefGoogle Scholar
  48. 48.
    http://www.physionet.org/PhysioBank/Signal Archives/ ECG/Sudden Cardiac Death Holter Database
  49. 49.
    http://www.physionet.org/PhysioBank/Signal Archives/ ECG/ Normal Sinus Rhythm database
  50. 50.
    Ebrahimzadeh E, Pooyan M, Jahani S, Bijar A, Setaredan SK (2015) ECG signals noise removal: selection and optimization of the best adaptive filtering algorithm based on various algorithms comparison. Biomedical eEngineering: aApplications, bBasis and. Biomedical Engineering: Applications, Basis Communications 27:1550038Google Scholar
  51. 51.
    Pola S, Macerata A, Emdin M, Marchesi C (1996) Estimation of the power spectral density in nonstationary cardiovascular time series: assessing the role of the time-frequency representations (TFR). IEEE Trans Biomed Eng 43(1):46–59.  https://doi.org/10.1109/10.477700 CrossRefPubMedGoogle Scholar
  52. 52.
    Ebrahimzadeh E, Alavi SM, Bijar A, Pakkhesal A (2013) A novel approach for detection of deception using smoothed pseudo Wigner-Ville distribution (SPWVD). J Biomed Sci Eng 6(01):8–18.  https://doi.org/10.4236/jbise.2013.61002 CrossRefGoogle Scholar
  53. 53.
    Mainardi L, Montano N, Cerutti S (2004) Automatic decomposition of Wigner distribution and its application to heart rate variability. Methods Inf Med 43(1):17–21CrossRefPubMedGoogle Scholar
  54. 54.
    Kamen PW, Krum H, Tonkin AM (1996) Poincare plot of heart rate variability allows quantitative display of parasympathetic nervous activity in humans. Clin Sci (Lond) 91(2):201–208.  https://doi.org/10.1042/cs0910201 CrossRefGoogle Scholar
  55. 55.
    Brennan M, Palaniswami M, Kamen P (2001) Do existing measures of Poincare plot geometry reflect nonlinear features of heart rate variability? IEEE Trans Biomed Eng 48(11):1342–1347.  https://doi.org/10.1109/10.959330 CrossRefPubMedGoogle Scholar
  56. 56.
    Voss A, Schroeder R, Heitmann A, Peters A, Perz S (2015) Short-term heart rate variability—influence of gender and age in healthy subjects. PLoS One 10(3):e0118308.  https://doi.org/10.1371/journal.pone.0118308 CrossRefPubMedPubMedCentralGoogle Scholar
  57. 57.
    Peng CK, Havlin S, Stanley HE, Goldberger AL (1995) Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos 5(1):82–87.  https://doi.org/10.1063/1.166141 CrossRefPubMedPubMedCentralGoogle Scholar
  58. 58.
    Ashtiani M-HZ, Ahmadabadi MN, Araabi BN (2014) Bandit-based local feature subset selection. Neurocomputing 138:371–382.  https://doi.org/10.1016/j.neucom.2014.02.001 CrossRefGoogle Scholar
  59. 59.
    Arjmandi MK, Dilley L, Ireland Z (2017) Applying pattern recognition to formant trajectories: a useful tool for understanding African American English (AAE) dialect variation. J Acoustical Society Am 141(5):3980–3980.  https://doi.org/10.1121/1.4989084 CrossRefGoogle Scholar
  60. 60.
    Fujita H, Acharya UR, Sudarshan VK, Ghista DN, Sree SV, Eugene LWJ, Koh JEW (2016) Sudden cardiac death (SCD) prediction based on nonlinear heart rate variability features and SCD index. Appl Soft Comput 43:510–519.  https://doi.org/10.1016/j.asoc.2016.02.049 CrossRefGoogle Scholar
  61. 61.
    Amoozegar S, Pooyan M, Ebrahimzadeh E (2013) Classification of brain signals in normal subjects and patients with epilepsy using mixture of experts. Computational Intelligence in. Computational Intelligence Electr Eng 4:1–8Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2017

Authors and Affiliations

  1. 1.School of Electrical and Computer Engineering, College of EngineeringUniversity of TehranTehranIran
  2. 2.Department of Biomedical Engineering, Faculty of EngineeringShahed UniversityTehranIran
  3. 3.Image Analysis Laboratory, Department of RadiologyHenry Ford HospitalDetroitUSA

Personalised recommendations