论文信息 - Novel Method for Deriving Vectorcardiographic Leads Based on Artificial Neural Networks

Novel Method for Deriving Vectorcardiographic Leads Based on Artificial Neural Networks

Many methods for deriving vectorcardiographic (VCG) leads from 12-lead electrocardiogram (ECG) were published. All of them are based on a linear transformation. Differences are only in coefficients of transformation matrixes which are designed based on a model or on linear regression methods. This paper presents and assesses a new nonlinear transformation method based on artificial neural networks (ANNs) which offer better accuracy of the transformation. Derived VCG leads were compared with directly measured Frank leads for a group of 283 records from the PTB database. Methods based on ANNs achieve significantly lower MSE in all leads and significantly higher correlation coefficient in Z lead compared with both Kors and inverse Dower method.

[1] Ralf Bousseljot,et al. Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet , 2009 .

[2] P Rubel,et al. Quantitative assessment of eight different methods for synthesizing Frank VCGs from simultaneously recorded standard ECG leads. , 1992, Journal of electrocardiology.

[3] A. Sittig,et al. Reconstruction of the Frank vectorcardiogram from standard electrocardiographic leads: diagnostic comparison of different methods. , 1990, European heart journal.

[4] Paul Rubel,et al. A Novel Neural-Network Model for Deriving Standard 12-Lead ECGs From Serial Three-Lead ECGs: Application to Self-Care , 2010, IEEE Transactions on Information Technology in Biomedicine.

[5] O. Pahlm,et al. Vectorcardiogram synthesized from a 12-lead ECG: superiority of the inverse Dower matrix. , 1988, Journal of electrocardiology.