Detection and delineation of the enigmatic U-wave in an electrocardiogram

  • Lakhan Dev SharmaEmail author
  • Ramesh Kumar Sunkaria
Original Research


Electrocardiogram (ECG) comprises of P-QRS-T wave components and sometimes U-wave. As per literature, the U-wave is said to be associated with certain cardiac disorders, but no more efforts have been made in developing techniques for detection of presence of U-wave and its delineation. The proposed technique presents a novel approach which can detect the presence of U-wave in the TP-segment and can delineate its peak. Features extracted from the TP-segment have been fed to random forest algorithm (RFA) and K-nearest neighbors (KNN) for classification. Sensitivity (Se%) = 96.66, specificity (Sp%) = 97.29, positive predictivity (+P%) = 97.31, Accuracy (Ac%) = 96.97, area under the receiver operating characteristic curve (Roc) = 0.994 using RFA and Se% = 96.23, Sp% = 94.70, +P% = 94.61, Ac% = 95.45, Roc = 0.973 using KNN have been achieved. The proposed technique also delineates the U-wave peak with an overall mean difference of 30.02 ms.


Electrocardiogram (ECG) U-wave Random forest algorithm (RFA) K-nearest neighbors (KNN) 


Compliance with ethical standards

Conflict of interest

Authors have no conflict of interest.


  1. 1.
    Postema PG, van Eck HJ, Opthof T, van Herpen G, van Dessel PF, Priori SG et al (2009) I K1 modulates the U-wave: insights in a 100-year-old enigma. Heart Rhythm 6(3):393–400CrossRefGoogle Scholar
  2. 2.
    Riera AP, Ferreira C, Ferreira Filho C, Ferreira M, Meneghini A, Uchida AH et al (2008) The enigmatic sixth wave of the electrocardiogram: the U wave. Cardiol J 15(5):408–421Google Scholar
  3. 3.
    Levis JT (2012) ECG diagnosis: hypokalemia. Perm J 16(2):57CrossRefGoogle Scholar
  4. 4.
    Kirchhof P, Franz MR, Bardai A, Wilde AM (2009) Giant TU waves precede torsades de pointes in long QT syndrome: a systematic electro-cardiographic analysis in patients with acquired and congenital QT prolongation. JACC 54(2):143–149CrossRefGoogle Scholar
  5. 5.
    Hefer D, Bukharovich I, Nasrallah EJ, Plotnikov A (2005) Prominent positive U waves appearing with high-dose intravenous phenylephrine. Electrocardiol 38(4):378–382CrossRefGoogle Scholar
  6. 6.
    Conrath CE, Opthof T (2005) The patient U wave. Cardiovasc Res 67(2):184–186CrossRefGoogle Scholar
  7. 7.
    Verma N, Figueredo VM, Greenspan AM, Pressman GS (2011) Giant U waves: an important clinical clue. Res Rep Clin Cardiol 2:51Google Scholar
  8. 8.
    Gorshkov-Cantacuzne V (2016) To the question of the etiology and clinical significance of the U wave of the ECG. BNP 10:130–133Google Scholar
  9. 9.
    Vila JA, Gang Y, Presedo JM, Fernndez-Delgado M, Barro S, Malik M (2000) A new approach for TU complex characterization. IEEE Trans Biomed Eng 47(6):764–772CrossRefGoogle Scholar
  10. 10.
    Johannesenl L, Grovel USL, Sorensen1 JS, Schmidt1 ML, Couderc JP, Graff C (2010) A wavelet based algorithm for delineation and classification of wave patterns in continuous Holter ECG recordings. Comput Cardiol 2010; Belfast, UK, 26–29 September 2010Google Scholar
  11. 11.
    Laguna P, Mark RG, Goldberg A, Moody GB (1997) A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG. In: Comput Cardiol; IEEE: pp 673–676Google Scholar
  12. 12.
    Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG et al (2000) Physiobank, physiotoolkit, and physionet components of a new research resource for complex physiologic signals. Circulation 101(23):e215–e220CrossRefGoogle Scholar
  13. 13.
    Sharma LD, Sunkaria RK (2016) A robust QRS detection using novel pre-processing techniques and kurtosis based enhanced efficiency. Measurement 87:194–204CrossRefGoogle Scholar
  14. 14.
    Sharma LD, Sunkaria RK (2017) Inferior myocardial infarction detection using stationary wavelet transform and machine learning approach. Signal Image Video Process 12(2):199–206CrossRefGoogle Scholar
  15. 15.
    Sharma LD, Sunkaria RK (2018) Stationary wavelet transform based technique for automated external defibrillator using optimally selected classifiers. Measurement 125:29–36CrossRefGoogle Scholar
  16. 16.
    Strumillo P (2002) Nested median filtering for detecting T-wave offset in ECGs. Electron Lett 38(14):1CrossRefGoogle Scholar
  17. 17.
    Goutas A, Ferdi Y, Herbeuval JP, Boudraa M, Boucheham B (2005) Digital fractional order differentiation-based algorithm for P and T-waves detection and delineation. ITBM-RBM 26(2):127–132CrossRefGoogle Scholar
  18. 18.
    Lin C, Kail G, Giremus A, Mailhes C, Tourneret JY, Hlawatsch F (2014) Sequential beat-to-beat P and T wave delineation and waveform estimation in ECG signals: block Gibbs sampler and marginalized particle filter. Signal Process 104:174–187CrossRefGoogle Scholar
  19. 19.
    Madeiro JP, Nicolson WB, Cortez PC, Marques JA, Vzquez-Seisdedos CR, Elangovan N et al (2013) New approach for T-wave peak detection and T-wave end location in 12-lead paced ECG signals based on a mathematical model. Med Eng Phys 35(8):1105–1115CrossRefGoogle Scholar
  20. 20.
    Lin C, Mailhes C, Tourneret JY (2010) P-and T-wave delineation in ECG signals using a Bayesian approach and a partially collapsed Gibbs sampler. IEEE Trans Biomed Eng 57(12):2840–2849CrossRefGoogle Scholar
  21. 21.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefzbMATHGoogle Scholar
  22. 22.
    Mitchell TM (1997) Machine Learning. McGraw-Hill Science, BostonzbMATHGoogle Scholar
  23. 23.
    Webb AR (2003) Statistical pattern recognition. Wiley, ChichesterzbMATHGoogle Scholar

Copyright information

© Bharati Vidyapeeth's Institute of Computer Applications and Management 2019

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringDr. B. R. Ambedkar National Institute of TechnologyJalandharIndia

Personalised recommendations