Skip to main content
SpringerLink
Log in

Automatic arrhythmia recognition from electrocardiogram signals using different feature methods with long short-term memory network model

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

The high mortality rate that has been prevailing among cardiac patients can be reduced to some extent through early detection of the heart-related diseases which can be done with the help of automated computer-aided diagnosing machines. There is a need for an expert system that automatically detects the abnormalities in the heart rhythms. Various new feature extraction methods employing long short-term memory network (LSTM) model have been presented in this paper, which help in the detection of heart rhythms from electrocardiogram signals. Based on higher-order statistics, wavelets, morphological descriptors, and R–R intervals, the electrocardiogram signals are decomposed into 45 features. All these features are used as a sequence, for input, to a single LSTM model. The publically available MIT-BIH arrhythmia database has been used for training and testing. The proposed model has helped to classify five distinct arrhythmic rhythms (including normal beats). Performance evaluation of the proposed system model has obtained values like precision of 96.73%, accuracy of 99.37%, specificity of 99.14%, F-score of 95.77%, and sensitivity of 94.89%, respectively.

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
Fig. 2

Similar content being viewed by others

Abbreviations

ECG:

Electrocardiogram

LSTM:

Long short-term memory

LBBB:

Left bundle branch block

RBBB:

Right bundle branch block

PVC:

Premature ventricular contraction

AP:

Atrial premature

ML-II:

Modified limb lead-2

HOS:

Higher-order statistics

SVM:

Support vector machine

PSO:

Particle swarm optimization

MLP:

Multilayer perceptron

ANN:

Artificial neural network

BPNN:

Backpropagation neural network

MPNN:

Multilayered probabilistic neural network

FFNN:

Feedforward neural network

QDA:

Quadratic discriminant analysis

DWT:

Discrete wavelet transform

FSC:

Feature statistic calculation

SFE:

Samples features extraction

References

  1. Mozaffarian, D., et al.: Executive summary: heart disease and stroke statistics—2016 update: a report from the American Heart Association. Circulation 133(4), 447–454 (2016)

    Google Scholar 

  2. World Health Organization: Cardiovascular Diseases (CVDs): Fact Sheet No. 317. 2015 (2016)

  3. Altan, G., Kutlu, Y.: ECG based human identification using logspace grid analysis of second order difference plot. In: 2015 23rd Signal Processing and Communications Applications Conference (SIU). IEEE (2015)

  4. Sannino, G., De Pietro, G.: A deep learning approach for ECG-based heartbeat classification for arrhythmia detection. Future Gener. Comput. Syst. 86, 446–455 (2018)

    Google Scholar 

  5. Elhaj, F.A., et al.: Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals. Comput. Methods Programs Biomed. 127, 52–63 (2016)

    Google Scholar 

  6. Rai, H.M., Chatterjee, K.: A unique feature extraction using MRDWT for automatic classification of abnormal heartbeat from ECG big data with multilayered probabilistic neural network classifier. Appl. Soft Comput. 72, 596–608 (2018)

    Google Scholar 

  7. Thomas, M., Das, M.K., Ari, S.: Automatic ECG arrhythmia classification using dual tree complex wavelet based features. AEU-Int. J. Electron. Commun. 69(4), 715–721 (2015)

    Google Scholar 

  8. Ebrahimzadeh, A., Khazaee, A.: Detection of premature ventricular contractions using MLP neural networks: a comparative study. Measurement 43(1), 103–112 (2010)

    Google Scholar 

  9. Übeyli, E.D.: Statistics over features of ECG signals. Expert Syst. Appl. 36(5), 8758–8767 (2009)

    Google Scholar 

  10. Rajpurkar, P., et al.: Cardiologist-level arrhythmia detection with convolutional neural networks. ArXiv preprint arXiv:1707.01836 (2017)

  11. Warrick, P., Homsi, M.N.: Cardiac arrhythmia detection from ECG combining convolutional and long short-term memory networks. In: 2017 Computing in Cardiology (CinC). IEEE (2017)

  12. Zink, M.D., et al.: Heartbeat cycle length detection by a ballistocardiographic sensor in atrial fibrillation and sinus rhythm. BioMed Res. Int. 2015, 1–10 (2015)

    Google Scholar 

  13. Sadek, I., Biswas, J.: Nonintrusive heart rate measurement using ballistocardiogram signals: a comparative study. Signal Image Video Process. 13(3), 475–482 (2019)

    Google Scholar 

  14. Hong, S., et al.: Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings. Physiol. Meas. 40, 054009 (2019)

    Google Scholar 

  15. Hannun, A.Y., et al.: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 25(1), 65 (2019)

    Google Scholar 

  16. Yıldırım, Ö., et al.: Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput. Biol. Med. 102, 411–420 (2018)

    Google Scholar 

  17. Yang, J., et al.: A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression. Int. J. Mach. Learn. Cybern. 9(10), 1733–1740 (2018)

    Google Scholar 

  18. Güler, N.F., Übeyli, E.D., Güler, I.: Recurrent neural networks employing Lyapunov exponents for EEG signals classification. Expert Syst. Appl. 29(3), 506–514 (2005)

    Google Scholar 

  19. Salloum, R., Kuo, C.-C.J.: ECG-based biometrics using recurrent neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2017)

  20. Goldberger, A.L., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)

    Google Scholar 

  21. Moody, G.B., Mark, R.G.: The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20(3), 45–50 (2001)

    Google Scholar 

  22. De Chazal, P., O’Dwyer, M., Reilly, R.B.: Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51(7), 1196–1206 (2004)

    Google Scholar 

  23. Mar, T., et al.: Optimization of ECG classification by means of feature selection. IEEE Trans. Biomed. Eng. 58(8), 2168–2177 (2011)

    Google Scholar 

  24. Zhang, Z., et al.: Heartbeat classification using disease-specific feature selection. Comput. Biol. Med. 46, 79–89 (2014)

    Google Scholar 

  25. Mondéjar-Guerra, V., et al.: Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomed. Signal Process. Control 47, 41–48 (2019)

    Google Scholar 

  26. Rai, H.M., et al.: R-peak detection using daubechies wavelet and ECG signal classification using radial basis function neural network. J. Inst. Eng. (India) Ser B 95(1), 63–71 (2014)

    Google Scholar 

  27. Mendel, J.M.: Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applications. Proc. IEEE 79(3), 278–305 (1991)

    Google Scholar 

  28. Ye, C., Kumar, B.V.K.V., Coimbra, M.T.: Heartbeat classification using morphological and dynamic features of ECG signals. IEEE Trans. Biomed. Eng. 59(10), 2930–2941 (2012)

    Google Scholar 

  29. Luz, E.J.D.S., et al.: ECG-based heartbeat classification for arrhythmia detection: a survey. Comput. Methods Programs Biomed. 127, 144–164 (2016)

    Google Scholar 

  30. Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE (2013)

  31. Hüsken, M., Stagge, P.: Recurrent neural networks for time series classification. Neurocomputing 50, 223–235 (2003)

    MATH  Google Scholar 

  32. Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)

  33. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Google Scholar 

  34. Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)

  35. Olah, C.: Understanding LSTM networks (2015)

  36. Yan, S.: Understanding LSTM and its diagrams. MLReview.com. https://towardsdatascience.com/data-science-performance-metrics-for-everyone-4d68f4859eef (2016)

  37. Srivastava, N., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  38. Duch, W., Jankowski, N.: Survey of neural transfer functions. Neural Comput. Surv. 2(1), 163–212 (1999)

    Google Scholar 

  39. Singh, S., et al.: Classification of ECG arrhythmia using recurrent neural networks. Proc. Comput. Sci. 132, 1290–1297 (2018)

    Google Scholar 

  40. Khazaee, A., Zadeh, A.E.: ECG beat classification using particle swarm optimization and support vector machine. Front. Comput. Sci. 8(2), 217–231 (2014)

    MathSciNet  Google Scholar 

  41. Dalvi, R.D.F., Zago, G.T., Andreão, R.V.: Heartbeat classification system based on neural networks and dimensionality reduction. Res. Biomed. Eng. 32(4), 318–326 (2016)

    Google Scholar 

  42. Maji, U., Mitra, M., Pal, S.: Imposed target based modification of Taguchi method for feature optimisation with application in arrhythmia beat detection. Expert Syst. Appl. 56, 268–281 (2016)

    Google Scholar 

  43. Li, H., et al.: Genetic algorithm for the optimization of features and neural networks in ECG signals classification. Sci. Rep. 7, 41011 (2017)

    Google Scholar 

  44. Casas, M.M., et al.: Bayesian classification models for premature ventricular contraction detection on ECG traces. J. Healthc. Eng. 2018 (2018)

  45. Rai, H.M., Chatterjee, K.: A novel adaptive feature extraction for detection of cardiac arrhythmias using hybrid technique MRDWT and MPNN classifier from ECG big data. Big Data Res. 12, 13–22 (2018)

    Google Scholar 

  46. Oh, S.L., et al.: Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Comput. Biol. Med. 102, 278–287 (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, National Institute of Technology, Raipur, Raipur, India

    Saroj Kumar Pandey & Rekh Ram Janghel

Authors
  1. Saroj Kumar Pandey
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rekh Ram Janghel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Saroj Kumar Pandey.

Additional information

Publisher's Note

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

Appendix

Appendix

For multiclass classification, the value of TP, FN, TN, and FP is calculated from confusion matrix as follows.

Original

Beat type

Predicted

N

L

R

V

A

N

Nn

Nl

Nr

Nv

Na

L

Ln

Ll

Lr

Lv

La

R

Rn

Rl

Rr

Rv

Ra

V

Vn

Vl

Vr

Vv

Va

A

An

Al

Ar

Av

Aa

For class N classification results

$$ \begin{aligned} {\text{TP}}_{\text{N}} & = {\text{Nn}} \\ {\text{FN}}_{\text{N}} & = {\text{Nl}} + {\text{Nr}} + {\text{Nv}} + {\text{Na}} \\ TN_{N} & = {\text{Ll}} + {\text{Lr}} + {\text{Lv}} + {\text{La}} + {\text{Rl}} + {\text{Rr}} + {\text{Rv}} + {\text{Ra}}\\ &\quad + {\text{Vl}} + {\text{Vr}} + {\text{Vv}} + {\text{Va}} + {\text{Al}} + {\text{Ar}} + {\text{Av}} + {\text{Aa}} \\ {\text{FP}}_{\text{N}} & = {\text{Ln}} + {\text{Rn}} + {\text{Vn}} + {\text{An}} \\ \end{aligned} $$

In the same way, the value of TP, FP, TN, and FN for other classes is calculated then fit to the following formulas and calculate the classification results.

$$ {\text{Precision}}\,\left( {\text{P}} \right) = \frac{\text{TP}}{{{\text{TP}} + {\text{FP}}}} $$
$$ {\text{Specificity}}\,\left( {\text{Sp}} \right) = \frac{\text{TN}}{{{\text{TN}} + {\text{FP}}}} $$
$$ {\text{Recall}}\,\left( {\text{Se}} \right) = \frac{\text{TP}}{{{\text{TP}} + {\text{FN}}}} $$
$$ {\text{F-score}} = 2\frac{{{\text{P}}*{\text{Se}}}}{{{\text{P}} + {\text{Se}}}} $$

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pandey, S.K., Janghel, R.R. Automatic arrhythmia recognition from electrocardiogram signals using different feature methods with long short-term memory network model. SIViP 14, 1255–1263 (2020). https://doi.org/10.1007/s11760-020-01666-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-020-01666-8

Keywords

Search

Navigation