Advertisement

Optimal Lead Selection for Evaluation Ventricular Premature Beats Using Machine Learning Approach

  • Pedro David Arini
  • Drago TorkarEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 690)

Abstract

Repolarization heterogeneity (RH) has been shown to increase with ventricular premature beats (VPBs). Moreover, several differences between left ventricle (Lv) and right ventricle (Rv), such as fibrillation threshold and anatomic properties have been presented. Nevertheless, few results exist regarding the influence of the origin site of VPBs on modulation of ventricular RH, as well as the optimal electrode location to assess the origin of VPBs. We studied electrocardiographic indices as a function of the coupling interval and the site of VPBs, in an isolated rabbit heart preparation (n = 18) using ECG multi-lead (5 rows \(\times \) 8 columns) system. In both ventricles, results have shown significant increases in ventricular depolarization duration. Also, we have observed that when the VPBs were applied to the Lv, a significant decrease of the total repolarization duration was detected, while in the Rv premature stimulation we have not found significant changes of total repolarization duration. Also, we compared twenty machine learning classification techniques with the aim to find the optimal electrode placement (row4–column4 to Lv stimulation and row5–column3 to Rv stimulation) and interpret the site of origin of VPBs. It was observed that the Random Forest classifier has shown the best performance among all the techniques studied. Finally, we found differences in the overall duration of repolarization associated to transmural RH.

Keywords

ECG Ventricular transmural dispersion ECG multi-lead Learning machine Ventricular premature beats 

References

  1. 1.
    Yan, G., Jack, M.: Electrocardiographic T wave: a symbol of transmural dispersion of repolarization in the ventricles. J. Cardiovasc. Electrophysiol. 14, 639–640 (2003)CrossRefGoogle Scholar
  2. 2.
    Noble, D., Cohen, I.: The interpretation of the T wave of the electrocardiogram. Cardiovasc. Res. 12, 13–27 (1978)Google Scholar
  3. 3.
    Di Diego, J.M., Sun, Z.Q., Antzelevitch, C.: Ito and action potential notch are smaller in left vs. right canine ventricular epicardium. A. J. Physiol. 271, H548 (1996)Google Scholar
  4. 4.
    Surawicz, B.: Ventricular fibrillation and dispersion of repolarization. J. Cardiovasc. Electrophysiol. 8, 1009–1012 (1997)CrossRefGoogle Scholar
  5. 5.
    Kuo, C.S., Munakata, K., Reddy, P., Surawicz, B.: Characteristics and possible mechanism of ventricular arrhythmia dependent on the dispersion of action potential. Circulation 67, 1356–1367 (1983)CrossRefGoogle Scholar
  6. 6.
    Shimizu, W., Antzelevitch, C.: Cellular basis for the ECG features of the LQT1 form of the long QT syndrome: effects of \(\beta \) adrenergic agonist and antagonist and sodium channel blockers on transmural dispersion of repolarization and torsades de pointes. Circulation 98, 2314–2322 (1998)Google Scholar
  7. 7.
    Fuller, M.S., Sándor, G., Punske, B., Taccardi, B., MacLeod, R.S., Ershler, P.R., Green, L.S., Lux, R.L: Estimates of repolarization and its dispersion from electrocardiographic measurements: direct epicardial assesment in the canine heart. J. Electrocardiol. 33, 171–180 (2000)Google Scholar
  8. 8.
    Arini, P.D., Bertrán, G.C., Valverde, E.R., Laguna, P.: T-wave width as an index for quantification of ventricular repolarization dispersion: evaluation in an isolated rabbit heart model. Biomed. Signal Proc. Control 3, 67–77 (2008)Google Scholar
  9. 9.
    Antzelevitch, Ch., Viskin, S., Shimizu, W., Yan, G., Kowey, P., Zhang, L., Sicouri, S., Diego, J., Burashnikov, A.: Does Tpeak-Tend provide an index of transmural dispersion of repolarization? J. Mol. Biol. 4(8), 1114–1119 (2007)Google Scholar
  10. 10.
    Smetana, P., Schmidt, A., Zabel, M., Hnatkova, K., Franz, M., Huber, K., Malik, M.: Assessment of repolarization heterogeneity for prediction of mortality in cardiovascular disease: peak to the end of the T wave interval and nondipolar repolarization components. J. Electrocardiol. 44, 301–308 (2011)Google Scholar
  11. 11.
    Yuan, S., Blomström-Lundqvist, C., Pherson, C., Wohlfart, B., Olsson, S.B.: Dispersion of ventricular repolarization following double and triple programmed stimulation: a clinical study using the monophasic action potential recording technique. Eur. Heart J. 17, 1080–1091 (1996)Google Scholar
  12. 12.
    Horowitz, L.N., Spear, J.F., Moore, E.N.: Relation of endocardial and epicardial ventricular fibrillation thresholds of the right and left ventricles. Am. J. Cardiol. 48, 698–701 (1981)CrossRefGoogle Scholar
  13. 13.
    Zabel, M., Portnoy, S., Franz, M.R.: Electrocardiographic indexes of dispersion of ventricular repolarization: an isolated heart validation study. J. Am. Coll. Cardiol. 25, 746–752 (1995)CrossRefGoogle Scholar
  14. 14.
    Laurita, K.R., Girouard, S.D., Fadi, G.A., Rosenbaum, D.S.: Modulated dispersion explains changes in arrhythmia vulnerability during premature stimulation of the heart. Circulation 98, 2774–2780 (1998)CrossRefGoogle Scholar
  15. 15.
    Spear, J., Moore, E.: Modulation of arrhytmias by isoproterenol in a rabbit heart model of d-Sotalol induced long QT intervals. American J. Physiol. 279, H15–H25 (2000)Google Scholar
  16. 16.
    Mendieta, J.G.: Algoritmo para el delineado de señales ECG en un modelo animal empleando técnicas avanzadas de procesamiento de señales. Facultad de Ingeniería de la Universidad de Buenos Aires (2012)Google Scholar
  17. 17.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. 11(1), 10–18 (2009)Google Scholar
  18. 18.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)Google Scholar
  19. 19.
    Liaw, A., Wiener, M.: Classification and regression by random forest. R News 2/3, 18–22 (2002)Google Scholar
  20. 20.
    Emanet, N.: ECG beat classification by using discrete wavelet transform and random forest algorithm. In: Fifth International Conference on Soft Computing, ICSCCW 2009 (2009)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Facultad de Ingeniería, Instituto de Ingeniería BiomédicaUniversidad de Buenos AiresBuenos AiresArgentina
  2. 2.Instituto Argentino de Matemática, ‘Alberto P. Calderón’CONICETBuenos AiresArgentina
  3. 3.Jožef Stefan InstituteLjubljanaSlovenia

Personalised recommendations