Advertisement

Detection of shockable ventricular arrhythmia using optimal orthogonal wavelet filters

  • Manish SharmaEmail author
  • Ru-San Tan
  • U. Rajendra Acharya
Recent Advances in Deep Learning for Medical Image Processing

Abstract

Sudden cardiac death (SCD) is caused by lethal arrhythmia. Ventricular fibrillation (VF) and ventricular tachycardia (VT) are amenable to defibrillation or electrical shock therapy (“shockable” arrhythmia) that can abolish the VF/VT and restore normal electrical and mechanical heart function. The challenge is to differentiate between shockable and non-shockable arrhythmia during the emergency response to SCD. When it comes to saving the life, accurate electrocardiogram (ECG) diagnosis and fast delivery of appropriate treatment is imperative. Automated systems to differentiate shockable from non-shockable arrhythmia have been developed to overcome the difficulty, and possible errors due to the manual inspection. In the present work, we have devised an efficient, effective and robust automated system to detect shockable and non-shockable arrhythmia using an optimal wavelet-based features extracted from ECG epochs of 2 s durations. We employed optimal two-channel frequency selective orthogonal wavelet filter bank to diagnose shockable ventricular arrhythmia. The optimization was carried out by minimizing the stop band ripple energy of the wavelet filter. The optimal orthogonal wavelet filter has been designed using a semi-definite programming (SDP) formulation without the use of any parameterization. The SDP solution gave us the desired optimal orthogonal wavelet filter bank with minimum stop band energy and the desired degree of regularity for the given length of filter. Fuzzy entropy and Renyi entropy features were extracted from the 2-s ECG epochs. These extracted features were then fed into the classifiers for discrimination of shockable arrhythmia rhythms and non-shockable arrhythmia rhythms. The best results were obtained from support vector machine. Accuracy of 97.8%, sensitivity of 93.42%, and specificity of 98.35% were obtained using a tenfold cross validation scheme. The developed automated system is accurate and robust; therefore, it can be integrated in automated external defibrillators that can be deployed for hospitals as well as out-of-hospital emergency resuscitation of SCD.

Keywords

Electrocardiogram ECG Shockable rhythms Non-shockable rhythms Biorthogonal filter bank Stopband energy SVM 

Notes

Compliance with ethical standards

Conflict of interest

None of the authors have any conflict of interest. We also would like to declare that we do not have any competing interests.

References

  1. 1.
    Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M (2017) Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci 415:190–198Google Scholar
  2. 2.
    Acharya UR, Fujita H, Oh SL, Raghavendra U, Tan JH, Adam M, Gertych A, Hagiwara Y (2018) Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network. Future Gener Comput Syst 79:952–959Google Scholar
  3. 3.
    Acharya UR, Molinari F, Sree SV, Chattopadhyay S, Ng KH, Suri JS (2012) Automated diagnosis of epileptic eeg using entropies. Biomed Signal Process Control 7(4):401–408Google Scholar
  4. 4.
    Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, San Tan R (2017) A deep convolutional neural network model to classify heartbeats. Comput Biol Med 89:389–396Google Scholar
  5. 5.
    Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H (2017) Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 100:270–278Google Scholar
  6. 6.
    Alonso-Atienza F, Morgado E, Fernandez-Martinez L, García-Alberola A, Rojo-Alvarez JL (2014) Detection of life-threatening arrhythmias using feature selection and support vector machines. IEEE Trans Biom Eng 61(3):832–840Google Scholar
  7. 7.
    Amann A, Tratnig R, Unterkofler K (2007) Detecting ventricular fibrillation by time-delay methods. IEEE Trans Biomed Eng 54(1):174–177Google Scholar
  8. 8.
    Barro S, Ruiz R, Cabello D, Mira J (1989) Algorithmic sequential decision-making in the frequency domain for life threatening ventricular arrhythmias and imitative artefacts: a diagnostic system. J Biomed Eng 11(4):320–328Google Scholar
  9. 9.
    Bhati D, Sharma M, Pachori RB, Gadre VM (2017) Time-frequency localized three-band biorthogonal wavelet filter bank using semidefinite relaxation and nonlinear least squares with epileptic seizure EEG signal classification. Digit Signal Process 62:259–273Google Scholar
  10. 10.
    Bhattacharyya A, Sharma M, Pachori RB, Sircar P, Acharya UR (2018) A novel approach for automated detection of focal EEG signals using empirical wavelet transform. Neural Comput Appl 29(8):47–57Google Scholar
  11. 11.
    Caglar H, Liu Y, Akansu AN (1991) Statistically optimized PR-QMF design. In: Proceedings of SPIE, vol 1605, pp 86–94Google Scholar
  12. 12.
    Chandrasekhar E, Dimri V, Gadre VM (2013) Wavelets and fractals in earth system sciences. Taylor & Francis, LondonzbMATHGoogle Scholar
  13. 13.
    Chen S, Thakor N, Mower M (1987) Ventricular fibrillation detection by a regression test on the autocorrelation function. Med Biol Eng Comput 25(3):241–249Google Scholar
  14. 14.
    Chen W, Wang Z, Xie H, Yu W (2007) Characterization of surface emg signal based on fuzzy entropy. IEEE Trans Neural Syst Rehabil Eng 15(2):266–272Google Scholar
  15. 15.
    Daubechies I (1992) Ten lectures on wavelets, vol 61. SIAM, PhiladelphiazbMATHGoogle Scholar
  16. 16.
    Dumitrescu B, Tabus I, Stoica P (2001) On the parameterization of positive real sequences and ma parameter estimation. IEEE Trans Signal Process 49(11):2630–2639.  https://doi.org/10.1109/78.960409 MathSciNetzbMATHGoogle Scholar
  17. 17.
    Dumitrescu B, Tabus I, Stoica P (2001) On the parameterization of positive real sequences and MA parameter estimation. IEEE Trans Signal Process 49(11):2630–2639MathSciNetzbMATHGoogle Scholar
  18. 18.
    Fan A, Han P, Liu B (2012) Shockable rhythm detection algorithms for electrocardiograph rhythm in automated defibrillators. AASRI Proc 1:21–26Google Scholar
  19. 19.
    Fokkenrood S, Leijdekkers P, Gay V (2007) Ventricular tachycardia/fibrillation detection algorithm for 24/7 personal wireless heart monitoring. In: International conference on smart homes and health telematics, pp 110–120. SpringerGoogle Scholar
  20. 20.
    Gaziano TA (2005) Cardiovascular disease in the developing world and its cost-effective management. Circulation 112(23):3547–3553Google Scholar
  21. 21.
    Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE (2000) Physiobank, physiotoolkit, and physionet. Circulation 101(23):e215–e220Google Scholar
  22. 22.
    Grant M, Boyd S (2012) CVX: Matlab software for disciplined convex programming, version 2.0 beta. http://cvxr.com/cvx. Accessed 12 Jan 2015
  23. 23.
    Greenwald SD (1986) The development and analysis of a ventricular fibrillation detector. PhD thesis, Massachusetts Institute of TechnologyGoogle Scholar
  24. 24.
    Hitz L, Anderson B (1969) Discrete positive-real functions and their application to system stability. In: Proceedings of the Institution of Electrical Engineers, vol 116, pp 153–155. IETGoogle Scholar
  25. 25.
    Jekova I (2000) Comparison of five algorithms for the detection of ventricular fibrillation from the surface ECG. Physiol Meas 21(4):429Google Scholar
  26. 26.
    Jekova I (2007) Shock advisory tool: detection of life-threatening cardiac arrhythmias and shock success prediction by means of a common parameter set. Biomed Signal Process Control 2(1):25–33Google Scholar
  27. 27.
    Jekova I, Krasteva V (2004) Real time detection of ventricular fibrillation and tachycardia. Physiol Meas 25(5):1167Google Scholar
  28. 28.
    Karmakar A, Kumar A, Patney R (2007) Design of an optimal two-channel orthogonal filterbank using semidefinite programming. IEEE Signal Process Lett 14(10):692–694Google Scholar
  29. 29.
    Kuo S (1978) Computer detection of ventricular fibrillation. In: Proceedings of computers in cardiology. IEEE Comupter Society, pp 347–349Google Scholar
  30. 30.
    Kutsogiannis DJ, Bagshaw SM, Laing B, Brindley PG (2011) Predictors of survival after cardiac or respiratory arrest in critical care units. Can Med Assoc J 183(14):1589–1595.  https://doi.org/10.1503/cmaj.100034 Google Scholar
  31. 31.
    Laslett LJ, Alagona P, Clark BA, Drozda JP, Saldivar F, Wilson SR, Poe C, Hart M (2012) The worldwide environment of cardiovascular disease: prevalence, diagnosis, therapy, and policy issues: a report from the american college of cardiology. J Am Coll Cardiol 60(25):S1–S49Google Scholar
  32. 32.
    Li Q, Rajagopalan C, Clifford GD (2014) Ventricular fibrillation and tachycardia classification using a machine learning approach. IEEE Trans Biomed Eng 61(6):1607–1613Google Scholar
  33. 33.
    Moody GB, Mark RG (2001) The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag 20(3):45–50Google Scholar
  34. 34.
    Moulin P, Anitescu M, Kortanek KO, Potra FA (1997) The role of linear semi-infinite programming in signal-adapted QMF bank design. IEEE Trans Signal Process 45(9):2160–2174Google Scholar
  35. 35.
    Muthuvel A, Makur A (2000) Design of two-channel linear-phase FIR PR filter banks with even length filters using convolution matrices. IEEE Trans Circuits Syst II Analog Digit Signal Process 47(12):1413–1418Google Scholar
  36. 36.
    Nolle F, Badura F, Catlett J, Bowser R, Sketch M (1986) CREI-GARD, a new concept in computerized arrhythmia monitoring systems. Comput Cardiol 13:515–518Google Scholar
  37. 37.
    Padmavati S (1962) Epidemiology of cardiovascular disease in India: Ii. Ischemic heart disease. Circulation 25(4):711–717Google Scholar
  38. 38.
    Plawiak P (2018) Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals. Swarm Evol Comput 39:192–208.  https://doi.org/10.1016/j.swevo.2017.10.002 Google Scholar
  39. 39.
    Plawiak P (2018) Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system. Expert Syst with Appl 92:334–349.  https://doi.org/10.1016/j.eswa.2017.09.022 Google Scholar
  40. 40.
    Plawiak P, Acharya UR (2018) Novel deep genetic ensemble of classifiers for arrhythmia detection using ECG signals. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-03980-2 Google Scholar
  41. 41.
    Renner R, Wolf S (2004) Smooth rényi entropy and applications. In: ISIT 2004. Proceedings. International symposium on information theory, 2004, p 233. IEEEGoogle Scholar
  42. 42.
    Roth GA, Johnson C, Abajobir A, Abd-Allah F, Abera SF, Abyu G, Ahmed M, Aksut B (2017) Global, regional, and national burden of cardiovascular diseases for 10 causes, 1990 to 2015. J Am Coll Cardiol 70:1–25Google Scholar
  43. 43.
    Sharma M, Acharya UR (2018) Analysis of knee-joint vibroarthographic signals using bandwidth-duration localized three-channel filter bank. Comput Electr Eng 72:191–202Google Scholar
  44. 44.
    Sharma M, Pachori RB, Acharya UR (2017) A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recogn Lett 94:172–179.  https://doi.org/10.1016/j.patrec.2017.03.023 Google Scholar
  45. 45.
    Sharma M, Achuth P, Deb D, Puthankattil SD, Acharya UR (2018) An automated diagnosis of depression using three-channel bandwidth-duration localized wavelet filter bank with EEG signals. Cogn Syst Res 52:508–520Google Scholar
  46. 46.
    Sharma M, Achuth PV, Pachori RB, Gadre VM (2017) A parametrization technique to design joint time-frequency optimized discrete-time biorthogonal wavelet bases. Signal Process 135:107–120Google Scholar
  47. 47.
    Sharma M, Agarwal S, Acharya UR (2018) Application of an optimal class of antisymmetric wavelet filter banks for obstructive sleep apnea diagnosis using ECG signals. Comput Biol Med 100:100–113.  https://doi.org/10.1016/j.compbiomed.2018.06.011 Google Scholar
  48. 48.
    Sharma M, Bhati D, Pillai S, Pachori RB, Gadre VM (2016) Design of time-frequency localized filter banks: transforming non-convex problem into convex via semidefinite relaxation technique. Circuits Syst Signal Process 35(10):3716–3733MathSciNetGoogle Scholar
  49. 49.
    Sharma M, Bhurane AA, Acharya UR (2018) MMSFL-OWFB: a novel class of orthogonal wavelet filters for epileptic seizure detection. Knowl Based Syst 160:265–277.  https://doi.org/10.1016/j.knosys.2018.07.019 Google Scholar
  50. 50.
    Sharma M, Deb D, Acharya UR (2017) A novel three-band orthogonal wavelet filter bank method for an automated identification of alcoholic EEG signals. Appl Intell 48:1368Google Scholar
  51. 51.
    Sharma M, Dhere A, Pachori RB, Acharya UR (2017) An automatic detection of focal EEG signals using new class of time-frequency localized orthogonal wavelet filter banks. Knowl Based Syst 118:217–227Google Scholar
  52. 52.
    Sharma M, Dhere A, Pachori RB, Gadre VM (2017) Optimal duration-bandwidth localized antisymmetric biorthogonal wavelet filters. Signal Process 134:87–99Google Scholar
  53. 53.
    Sharma M, Gadre VM, Porwal S (2015) An eigenfilter-based approach to the design of time-frequency localization optimized two-channel linear phase biorthogonal filter banks. Circuits Syst Signal Process 34(3):931–959Google Scholar
  54. 54.
    Sharma M, Goyal D, Achuth P, Acharya UR (2018) An accurate sleep stages classification system using a new class of optimally time-frequency localized three-band wavelet filter bank. Comput Biol Med 98:58–75.  https://doi.org/10.1016/j.compbiomed.2018.04.025 Google Scholar
  55. 55.
    Sharma M, Sharma P, Pachori RB, Acharya UR (2018) Dual-tree complex wavelet transform-based features for automated alcoholism identification. Int J Fuzzy Syst 20(5):1297–1308Google Scholar
  56. 56.
    Sharma M, Sharma P, Pachori RB, Gadre VM (2019) Double density dual-tree complex wavelet transform based features for automated screening of knee-joint vibroarthrographic signals. In: 2019 international conference on machine intelligence and signal analysis, advances in intelligent systems and computing, vol 748. Springer, Singapore, pp 279–290.  https://doi.org/10.1007/978-981-13-0923-6_24
  57. 57.
    Sharma M, Kolte R, Patwardhan P, Gadre V (2010) Time-frequency localization optimized biorthogonal wavelets. In: International conference on signal processing and communications (SPCOM), pp 1–5Google Scholar
  58. 58.
    Sharma M, Singh T, Bhati D, Gadre V (2014) Design of two-channel linear phase biorthogonal wavelet filter banks via convex optimization. In: 2014 international conference on signal processing and communications (SPCOM), pp 1–6.  https://doi.org/10.1109/SPCOM.2014.6983931
  59. 59.
    Sharma M, Vanmali AV, Gadre VM (2013) Construction of wavelets: principles and practices in wavelets and fractals in earth system sciences. CRC Press, Taylor and Francis Group, Boca RatonGoogle Scholar
  60. 60.
    Sharma M, Tan RS, Acharya UR (2018) A novel automated diagnostic system for classification of myocardial infarction ECG signals using an optimal biorthogonal filter bank. Comput Biol Med.  https://doi.org/10.1016/j.compbiomed.2018.07.005 Google Scholar
  61. 61.
    Thakor NV, Zhu YS, Pan KY (1990) Ventricular tachycardia and fibrillation detection by a sequential hypothesis testing algorithm. IEEE Trans Biomed Eng 37(9):837–843Google Scholar
  62. 62.
    Tripathy R, Sharma L, Dandapat S (2016) Detection of shockable ventricular arrhythmia using variational mode decomposition. J Med Syst 40(4):79Google Scholar
  63. 63.
    Unser M, Aldroubi A (1996) A review of wavelets in biomedical applications. Proc IEEE 84(4):626–638Google Scholar
  64. 64.
    Yang H, Bukkapatnam ST, Komanduri R (2007) Nonlinear adaptive wavelet analysis of electrocardiogram signals. Phys Rev E 76:026214Google Scholar
  65. 65.
    Yildirim O (2018) A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput Biol Med 96:189–202Google Scholar
  66. 66.
    Yildirim O, Baloglu U (2018) Heartbeat type classification with optimized feature vectors. Int J Optim Control Theories Appl 8(2):170–175MathSciNetGoogle Scholar
  67. 67.
    Yildirim O, Plawiak P, Tan RS, Acharya R (2018) Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med 102:411–420Google Scholar
  68. 68.
    Yildirim O, Tan RS, Acharya UR (2018) An efficient compression of ecg signals using deep convolutional autoencoders. Cogn Syst Res 52:198–211.  https://doi.org/10.1016/j.cogsys.2018.07.004 Google Scholar
  69. 69.
    Zadeh LA (1996) Fuzzy sets. In: Klir GJ (ed) Fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by Lotfi A Zadeh. World Scientific, Singapore, pp 394–432Google Scholar
  70. 70.
    Zala J, Sharma M, Bhalerao R (2018) Tunable q-wavelet transform based features for automated screening of knee-joint vibroarthrographic signals. In: 2018 5th international conference on signal processing and integrated networks (SPIN), pp 348–352.  https://doi.org/10.1109/SPIN.2018.8474117
  71. 71.
    Zhang XS, Zhu YS, Thakor NV, Wang ZZ (1999) Detecting ventricular tachycardia and fibrillation by complexity measure. IEEE Trans Biomed Eng 46(5):548–555Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electrical EngineeringInstitute of Infrastructure, Technology, Research and Management (IITRAM)AhmedabadIndia
  2. 2.National Heart Centre SingaporeSingaporeSingapore
  3. 3.Nagee Department of Electronics and Computer EngineeringNgee Ann PolytechnicSingaporeSingapore
  4. 4.Department of Biomedical Engineering, School of Science and TechnologySUSS UniversitySingaporeSingapore
  5. 5.Department of Biomedical Engineering, Faculty of EngineeringUniversity of MalayaKuala LumpurMalaysia

Personalised recommendations