Automated ECG segmentation with dynamic time warping

To detect an abnormal conduction of the heart, cardiologists annotate certain points in the electrocardiogram (ECG) manually. As this is a very strenuous task, several algorithms have been developed to segment the ECG automatically. In this paper, we describe several such methods, and we further present a new single-lead method based on dynamic time warping (DTW). The results are tested on the QT database and compared to Laguna et al.'s (1997) two-lead method. DTW produces a smaller mean error, but has a higher standard deviation than Laguna's method.

[1]  P. Laguna,et al.  ECG data compression with the Karhunen-Loeve transform , 1996, Computers in Cardiology 1996.

[2]  Recommendations for measurement standards in quantitative electrocardiography. The CSE Working Party. , 1985, European heart journal.

[3]  S.N. Tandon,et al.  Using wavelet transforms for ECG characterization. An on-line digital signal processing system , 1997, IEEE Engineering in Medicine and Biology Magazine.

[4]  P Caminal,et al.  Automatic detection of wave boundaries in multilead ECG signals: validation with the CSE database. , 1994, Computers and biomedical research, an international journal.

[5]  J. S. Sahambi,et al.  Using Wavelet Transforms for ECG Characterization , 1997 .

[6]  L. Clavier,et al.  Segmentation of electrocardiograms using a hidden Markov model , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  R. Jane,et al.  Evaluation of an automatic threshold based detector of waveform limits in Holter ECG with the QT database , 1997, Computers in Cardiology 1997.

[8]  Pablo Laguna,et al.  A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG , 1997, Computers in Cardiology 1997.

[9]  Bas A. de Mol,et al.  A decision-driven design of a decision support system in anesthesia , 1997, Artif. Intell. Medicine.

[10]  A. Koski,et al.  Segmentation of digital signals based on estimated compression ratio , 1996, IEEE Transactions on Biomedical Engineering.

[11]  G.G. Cano,et al.  An approach to cardiac arrhythmia analysis using hidden Markov models , 1990, IEEE Transactions on Biomedical Engineering.