Detection of Extra Components of T Wave by Independent Component Analysis in Congenital Long-QT Syndrome

Background— The main ECG criteria for the diagnosis of long-QT syndrome (LQTS) include abnormal T-wave morphology as well as prolonged QT interval. The T wave in LQTS probably includes additional components of the myocardial repolarization process, which are derived from aberrant ion currents. We investigated whether independent component analysis (ICA) can extract such abnormal repolarization components. Methods and Results— Digital ECG data were obtained as a time series from 10 channels using 20 surface electrodes in 22 patients with genetically confirmed LQTS type 1 (LQT1) and 30 normal subjects. In each case, T-wave area was analyzed by radical ICA after noise reduction by the wavelet thresholding method. Furthermore, inverse ICA was applied to determine the origin of each independent component (IC). Radical ICA revealed that a T-wave consisted of 4 basic ICs in all control subjects, whereas ≥5 (mostly 6) ICs were identified in all 22 patients with LQT1. The extra ICs, which were not evident in normal subjects, were assumed to contribute to the formation of abnormal T-wave morphology. The extra ICs were identified even in patients with normal QTc values and in those taking &bgr;-blockers. Inverse ICA indicated that the additional ICs originate predominantly from the late phase of the T wave of the left ventricle. Conclusions— Extra ICs appear during repolarization in all patients with LQT1 but not in normal subjects. ICA is a potentially useful multivariate statistical method to differentiate patients with LQT1 from normal subjects.

[1]  M. Leppert,et al.  The spectrum of symptoms and QT intervals in carriers of the gene for the long-QT syndrome. , 1992, The New England journal of medicine.

[2]  A. Moss,et al.  ECG T-wave patterns in genetically distinct forms of the hereditary long QT syndrome. , 1995, Circulation.

[3]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[4]  B. Surawicz,et al.  Will QT Dispersion Play a Role in Clinical Decision‐Making? , 1996, Journal of cardiovascular electrophysiology.

[5]  S. Priori,et al.  Evaluation of the spatial aspects of T-wave complexity in the long-QT syndrome. , 1997, Circulation.

[6]  Jean-Franois Cardoso.  High-Order Contrasts for Independent Component Analysis , 1999, Neural Computation.

[7]  Wojciech Zareba,et al.  Spectrum of ST-T–Wave Patterns and Repolarization Parameters in Congenital Long-QT Syndrome: ECG Findings Identify Genotypes , 2000, Circulation.

[8]  R. Gencay,et al.  An Introduction to Wavelets and Other Filtering Methods in Finance and Economics , 2001 .

[9]  B. Howard,et al.  Principal Component Analysis of the T Wave and Prediction of Cardiovascular Mortality in American Indians , 2002 .

[10]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[11]  Richard B. Devereux,et al.  Principal Component Analysis of the T Wave and Prediction of Cardiovascular Mortality in American Indians: The Strong Heart Study , 2002, Circulation.

[12]  C. Antzelevitch.  Molecular Genetics of Arrhythmias and Cardiovascular Conditions Associated with Arrhythmias , 2003, Journal of cardiovascular electrophysiology.

[13]  John W. Fisher,et al.  ICA Using Spacings Estimates of Entropy , 2003, J. Mach. Learn. Res..

[14]  Michael Christiansen,et al.  T wave morphology analysis distinguishes between KvLQT1 and HERG mutations in long QT syndrome. , 2004, Heart rhythm.

[15]  Rémi Dubois,et al.  T‐Wave Morphology Parameters Based on Principal Component Analysis Reproducibility and Dependence on T−Offset Position , 2007, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[16]  Paul G A Volders,et al.  In vivo mechanisms precipitating torsades de pointes in a canine model of drug-induced long-QT1 syndrome. , 2007, Cardiovascular research.

[17]  B. Everitt.  An R and S-Plus® Companion to Multivariate Analysis , 2007 .

[18]  H. Tsutsumi,et al.  Inverse Independent Component Analysis Facilitates Clarification of the Accessory Conductive Pathway of Wolf–Parkinson–White Syndrome Electrocardiogram , 2008, Pediatric Cardiology.

[19]  Wojciech Zareba,et al.  A quantitative assessment of T-wave morphology in LQT1, LQT2, and healthy individuals based on Holter recording technology. , 2008, Heart rhythm.

[20]  Pierre Comon,et al.  Handbook of Blind Source Separation: Independent Component Analysis and Applications , 2010 .

[21]  Seungjin Choi,et al.  Independent Component Analysis , 2009, Handbook of Natural Computing.