Comparison of four estimators of the 3D cardiac electrical activity for surface ECG synthesis from intracardiac recordings

The aim of this study is to facilitate the home follow-up of patients treated with cardiac implantable devices. A new procedure to synthesize 12-lead ECG from intracardiac EGM is proposed. It is based on the estimation of: (i) a 3D representation of the cardiac electrical activity both for ECG (VCG) and EGM (VGM), and (ii) the transfer function between the VGM and the VCG. The extraction of VCG and VGMis performed by comparing four different algorithms based on PCA and ICA, whereas the non-linear transfer function between VCG and VGM is estimated using a specific neural network. Results demonstrate the effectiveness of the proposed method in comparison with our previous work. Indeed, the correlation coefficients, between the real ECG and the synthesized ECG, lie between 0.78 and 0.99, whereas correlation coefficients of the previous method (combining PCA and linear Wiener filter) lie between 0.6 and 0.94.

[1]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[2]  B. Drew,et al.  Comparison of a vectorcardiographically derived 12-lead electrocardiogram with the conventional electrocardiogram during wide QRS complex tachycardia, and its potential application for continuous bedside monitoring. , 1992, The American journal of cardiology.

[3]  L. Sornmo Vectorcardiographic loop alignment and morphologic beat-to-beat variability , 1998, IEEE Transactions on Biomedical Engineering.

[4]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[5]  Ch. L. Levkov,et al.  Orthogonal electrocardiogram derived from the limb and chest electrodes of the conventional 12-lead system , 1987, Medical and Biological Engineering and Computing.

[6]  Stefan P Nelwan,et al.  Reconstruction of the 12-lead electrocardiogram from reduced lead sets. , 2004, Journal of electrocardiology.

[7]  Guy Carrault,et al.  Atrial activity enhancement by Wiener filtering using an artificial neural network , 2001, IEEE Transactions on Biomedical Engineering.

[8]  G. Dower,et al.  On Deriving the Electrocardiogram from Vectorcardiographic Leads , 1980, Clinical cardiology.

[9]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[10]  Amar Kachenoura,et al.  Using Intracardiac Vectorcardiographic Loop for Surface ECG Synthesis , 2008, EURASIP J. Adv. Signal Process..

[11]  Juha Karhunen,et al.  Principal component neural networks — Theory and applications , 1998, Pattern Analysis and Applications.

[12]  E. Sowton Primer of Vectorcardiography , 1973 .

[14]  P. Rubel,et al.  A neural network approach for patient-specific 12-lead ECG synthesis in patient monitoring environments , 2004, Computers in Cardiology, 2004.

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  Pablo Laguna,et al.  Bioelectrical Signal Processing in Cardiac and Neurological Applications , 2005 .

[17]  A. Cichocki,et al.  Robust whitening procedure in blind source separation context , 2000 .