Detection and delineation of the enigmatic U-wave in an electrocardiogram
- 4 Downloads
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.
KeywordsElectrocardiogram (ECG) U-wave Random forest algorithm (RFA) K-nearest neighbors (KNN)
Compliance with ethical standards
Conflict of interest
Authors have no conflict of interest.
- 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
- 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.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
- 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.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