Cluster Computing

, Volume 21, Issue 1, pp 1033–1044 | Cite as

Arrhythmia and ischemia classification and clustering using QRS-ST-T (QT) analysis of electrocardiogram

  • Akash Kumar BhoiEmail author
  • Karma Sonam Sherpa
  • Bidita Khandelwal


The objective is to propose a collective analytical model for QRS complex, ST segment and T wave (i.e., QT complex) of electrocardiogram to evaluate the onset or occurrence of cardiovascular abnormalities. The proposed methodologies also classify healthy subjects, arrhythmic and ischemic patients. The idea is to extract the QRS-ST-T features; where, QT interval and 99% occupied bandwidth (Hz) features are extracted from QT complex and QRS versus ST-T interval ratio (%) is also formulated after segmenting the QT complex into QRS complex and ST-T segment by localizing the inflection points. The evaluation of this proposed approach has been carried out using the selected 36 recordings (true positive (TP) beats) from each standard databases i.e., MIT-BIH arrhythmia database, FANTASIA and European ST-T database. The method is initiated with the preprocessing stage and then the inflection points (i.e., \(Q,S,T_{\mathrm{offset}})\) are detected using Pan-Tompkins method and curve analysis techniques. Then the time-frequency domain features (e.g. QT interval (s) and 99% occupied bandwidth (Hz)) are extracted from the segmented mean QT complex and the QRS versus ST-T interval (%) ratio is extracted from the segmented mean QRS versus ST-T segments simultaneously. These features are introduced to the classifier like decision tree, support vector machine and K-means for clustering operation. The classification success rate is 97.03% and resubstitution error rate is 2.97% among the arrhythmia, ischemia and healthy classes using QT interval and QRS versus ST-T interval ratio (%) features. The evaluations of other features are also analyzed along with graphical classification results. Allied evaluation of segments belonging to ventricular depolarization (QRS complex) and repolarization (ST segment and T wave) i.e., QT complex, will certainly improve the detection probability of ischemia and arrhythmia with further correlative parametric features. This also leads to automatic detection and classification of arrhythmia and ischemia by avoiding visual inspection and error free decison making.


Electrocardiogram (ECG) Arrhythmia Ischemia Decision tree Support vector machine (SVM) K-means clustering 


  1. 1.
    Jiménez-Candil, J., Martín, C.: Luengo.: QT interval and Acute Myocardial Ischemia: Past Promises, New Evidences. Rev Esp Cardiol 61(6), 561–3 (2008)CrossRefGoogle Scholar
  2. 2.
    Pueyo, E., Sörnmo, L., Laguna, P.: QRS slopes for detection and characterization of myocardial ischemia. IEEE Trans. Biomed. Eng. 55(2), 468–477 (2008)CrossRefGoogle Scholar
  3. 3.
    Pettersson, J., Pahlm, O., Cairo, E., Edenbrandt, L., Ringborn, M., Sörnmo, L., Warren, S.G., Wagner, G.S.: Changes in high-frequency QRS components are more sensitive than ST-segment deviation for detecting acute coronary artery occlusion. J. Am. Coll. Cardiol. 36, 1827–1834 (2000)CrossRefGoogle Scholar
  4. 4.
    Abboud, S., Cohen, R.J., Selwyn, A., Ganz, P., Sadeh, D., Friedman, P.L.: Detection of transient myocardial ischemia by computer analysis of standard and signal-averaged high frequency electrocardiograms in patients undergoing percutaneous transluminal coronary angioplasty. Circulation 76(3), 585–596 (1987)CrossRefGoogle Scholar
  5. 5.
    Beker, A., Pinchas, A., Erel, J., Abboud, S.: Analysis of high frequency QRS potential during exercise testing in patients with coronary artery disease and in healthy subjects. Pacing Clin. Electrophysiol. 19(12), 2040–2050 (1996)CrossRefGoogle Scholar
  6. 6.
    Hanna, E.B., Glancy, D.L.: ST-segment depression and T-wave inversion: classification, differential diagnosis, and caveats. Clevel. Clin. J. Med. 78(6), 404–414 (2011)CrossRefGoogle Scholar
  7. 7.
    Berger, R.D.: QT interval variability. J. Am. Coll. Cardiol. 54(9), 851–852 (2009)CrossRefGoogle Scholar
  8. 8.
    Priori, S.G., et al.: ESC guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death. Eur. Heart J. 36(41), 2793–2867 (2015). 10.1093/eurheartj/ehv316MathSciNetCrossRefGoogle Scholar
  9. 9.
    Jain, K.K., Garg, Y.: ECG changes in patients of acute cerebrovascular diseases. MedPulse 2(4), 256–259 (2015)Google Scholar
  10. 10.
    SasanYazdani, J.-M.V.: Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology. Digital Signal Process. 56, 100–109 (2016)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Korürek, M., Nizam, A.: Clustering MIT-BIH arrhythmias with ant colony optimization using time domain and PCA compressed wavelet coefficients. Digital Signal Process. 20, 1050–1060 (2010)CrossRefGoogle Scholar
  12. 12.
    Chen, X., Tereshchenko, L.G., Berger, R.D., Trayanova, N.A.: Arrhythmia risk stratification based on QT interval instability: an intracardiac electrocardiogram study. Heart Rhythm 10(6), 875–880 (2013)CrossRefGoogle Scholar
  13. 13.
    Baumert, M., Schmidt, M., Zaunseder, S., Porta, A.: Effects of ECG sampling rate on QT interval variability measurement. Biomed. Signal Process. Control 25, 159–164 (2016)CrossRefGoogle Scholar
  14. 14.
    Thakor, N.V., Webster, J.G., Tompkins, W.J.: Estimation of QRS complex power spectra for design of a QRS filter. IEEE Trans. Biomed. Eng. 31(11), 702–706 (1984)CrossRefGoogle Scholar
  15. 15.
    Elgendi, M., Jonkman, M., De Boer, F.: Improved QRS detection algorithm using dynamic thresholds. Int. J. Hybrid Inform. Technol. 2(1), 65–80 (2009)Google Scholar
  16. 16.
    Lin, C.-H.: Frequency-domain features for ECG beat discrimination using grey relational analysis-based classifier. Comput. Math. Appl. 55, 680–690 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Jain, K.K., Garg, Y.: ECG changes in patients of acute cerebrovascular diseases. MedPulse 2(4), 256–259 (2015)Google Scholar
  18. 18.
    Thomas, M., Das, M.K., Ari, S.: Automatic ECG arrhythmia classification using dual tree complexwavelet based features. Int. J. Electron. Commun. 69, 715–721 (2015)CrossRefGoogle Scholar
  19. 19.
    Gad, M.M.A.: Feature extraction of electrocardiogram signals using discrete sinc transform. In: The 2016 Biomedical Engineering International Conference (BMEiCON-2016)Google Scholar
  20. 20.
    Kumar, A., Singh, M.: Ischemia detection using isoelectric energy function. Comput. Biol. Med. 68, 76–83 (2016)CrossRefGoogle Scholar
  21. 21.
    Liu, R., Pan, T., Li, Z.: Multi-model recursive identification for nonlinear systems with non-uniformly sampling. Clust. Comput. 20, 25–32 (2017). doi: 10.1007/s10586-016-0688-0 CrossRefGoogle Scholar
  22. 22.
    Alhussein, M.: Automatic facial emotion recognition using weber local descriptor for e-Healthcare system. Cluster Comput. 19, 99–108 (2016). doi: 10.1007/s10586-016-0535-3 CrossRefGoogle Scholar
  23. 23.
    Han, C.: Improved SLIC imagine segmentation algorithm based on K-means. Cluster Comput. (2017). doi: 10.1007/s10586-017-0792-9
  24. 24.
    Orhan, U., Hekim, M., Ozer, M.: EEG signals classification using the K-means clustering and a multilayer perceptron neural network model. Expert Syst. Appl. 38, 13475–13481 (2011)CrossRefGoogle Scholar
  25. 25.
    Choi, J.-K., Jeon, K.-H., Won, Y.: Application of big data analysis with decision tree for the foot disorder. Cluster Comput 18, 1399–1404 (2015). doi: 10.1007/s10586-015-0480-6 CrossRefGoogle Scholar
  26. 26.
    Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.K., Stanley, H.E.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)CrossRefGoogle Scholar
  27. 27.
    Iyengar, N., Peng, C.K., Morin, R., Goldberger, A.L., Lipsitz, L.A.: Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics. Am. J. Physiol. 271, 1078–1084 (1996)Google Scholar
  28. 28.
    Kannathal, N., Acharya, U.R., Joseph, K.P., Lim, C.M., Suri, J.S.: Analysis of electrocardiograms. Adv. Card. Signal Process. XXII(2), 55–82 (2007)CrossRefGoogle Scholar
  29. 29.
    Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 32(3), 230–236 (1985)CrossRefGoogle Scholar
  30. 30.
    Bhoia, A.K., Sherpa, K.S.: Bidita khandelwal, multimodal classification of arrhythmia and ischemia using QRS-ST analysis. In: Advances in Systems, Control and Automation. Lecture Notes in Electrical Engineering, vol. 442 (2017)Google Scholar
  31. 31.
    Singh, Y.N., Gupta, P.: ECG to individual identification. In: 2nd IEEE International Conference on Biometrics: Theory, Applications and Systems. IEEE (2008)Google Scholar
  32. 32.
    Kiranyaz, S., Ince, T., Pulkkinen, J., Gabbouj, M.: Personalized long-term ECG classification: a systematic approach. Expert Syst. Appl. 38, 3220–3226 (2011)CrossRefGoogle Scholar
  33. 33.
    Chatterjee, H.K., Gupta, R., Mitra, M.: A statistical approach for determination of time plane features from digitized ECG. Comput. Biol. Med. 41, 278–284 (2011)CrossRefGoogle Scholar
  34. 34.
    Melgani, F., Bazi, Y.: Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans. Inform. Technol. Biomed. 12(5), 667–677 (2008)CrossRefGoogle Scholar
  35. 35.
    Mehta, S.S., Shete, D.A., Lingayat, N.S., Chouhan, V.S.: K-means algorithm for the detection and delineation of QRS-complexes in electrocardiogram. IRBM 31, 48–54 (2010)CrossRefGoogle Scholar
  36. 36.
    Tseng, Y.-L., Lin, K.-S., Jaw, F.-S.: Comparison of support-vector machine and sparse representation using a modified rule-based method for automated myocardial ischemia detection. Comput. Math. Method Med. 2016, 9460375 (2016)Google Scholar
  37. 37.
    Escalona-Moran, M.A., Soriano, M.C., Fischer, I., Mirasso, C.R.: Electrocardiogram classification using reservoir computing with logistic regression. IEEE J. Biomed. Health Inform. 19(3), 892–898 (2015)CrossRefGoogle Scholar
  38. 38.
    Oster, J., Behar, J., Sayadi, O., Nemati, S., Johnson, A.E., Clifford, G.D.: Semisupervised ECG ventricular beat classification with novelty detection based on switching Kalman filters. IEEE Trans. Biomed. Eng. 62(9), 2125–2134 (2015)CrossRefGoogle Scholar
  39. 39.
    Afkhami, R.G., Azarnia, G., Tinati, M.A.: Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals. Pattern Recognit. Lett. 70, 45–51 (2016)CrossRefGoogle Scholar
  40. 40.
    Elhaj, F.A., Salim, N., Harrisb, A.R., Swee, T.T., Ahmed, T.: Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals. Comput. Method Programs Biomed. 127, 52–63 (2016)CrossRefGoogle Scholar
  41. 41.
    Raj, S., Ray, K.C.: ECG signal analysis using DCT-based DOST and PSO optimized SVM. IEEE Trans. Instrum. Meas. 66(3) (2017)Google Scholar
  42. 42.
    Han, J., Kamber, M.: Data Mining Concepts and Techniques. Morgan Kaufmann Publisher, Burlington (2001)zbMATHGoogle Scholar
  43. 43.
    Stanevski, N., Tsvetkov, D.: Using support vector machine as a binary classifier. In: International Conference on Computer Systems and Technologies—CompSysTech (2005)Google Scholar
  44. 44.
    Cristianini, N., Taylor, J.S.: An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge (2000)CrossRefzbMATHGoogle Scholar
  45. 45.
    Yeh, Y.C., Chiou, C.W., Lin, H.-J.: Analyzing ECG for cardiac arrhythmia using cluster analysis. Expert Syst. Appl. 39, 1000–1010 (2012)CrossRefGoogle Scholar
  46. 46.
    Haldar, N.A.H., Khan, F.A., Ali, A., Abbas, H.: Arrhythmia classification using Mahalanobis distance based improved Fuzzy C-means clustering for mobile health monitoring systems. Neurocomputing 220, 221–235 (2017)CrossRefGoogle Scholar
  47. 47.
    Merino, M., Gómez, I.M., Molina, A.J.: Envelopment filter and K-means for the detection of QRS waveforms in electrocardiogram. Med. Eng. Phys. 37, 605–609 (2015)CrossRefGoogle Scholar
  48. 48.
    Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. In: SODA ‘07: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035 (2007)Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Akash Kumar Bhoi
    • 1
    Email author
  • Karma Sonam Sherpa
    • 1
  • Bidita Khandelwal
    • 2
  1. 1.Department of Electrical and Electronics Engineering, Sikkim Manipal Institute of Technology (SMIT)Sikkim Manipal UniversityRangpoIndia
  2. 2.Department General Medicine, Central Referral Hospital and SMIMSSikkim Manipal UniversityGangtokIndia

Personalised recommendations