Unified Neural Network Based Pathologic Event Reconstruction Using Spatial Heart Model
This paper presents a new way to solve the inverse problem of electrocardiography in terms of heart model parameters. The developed event estimation and recognition method uses a unified neural network (UNN)-based optimization system to determine the most relevant heart model parameters. A UNN-based preliminary ECG analyzer system has been created to reduce the searching space of the optimization algorithm. The optimal model parameters were determined by a relation between objective function minimization and robustness of the solution. The final evaluation results, validated by physicians, were about 96% correct. Starting from the fact that input ECGs contained various malfunction cases, such as Wolff-Parkinson-White (WPW) syndrome, atrial and ventricular fibrillation, these results suggest this approach provides a robust inverse solution, circumventing most of the difficulties of the ECG inverse problem.
KeywordsHeart model unified neural network inverse ECG problem
- 8.Mirvis, D.M.: Validation of body surface electrocardiographic mapping. In: Mirvis, D.M. (ed.) Body surface electrocardiographic mapping, pp. 63–74. Kluwer, Boston-Dordrecht-London (1988)Google Scholar
- 16.Smola, A., Scholkopf, B.: A tutorial on support vector regression. Royal Holloway College, Univ. London, NeuroColt Tech. Rep. NV2-TR-1998-030Google Scholar
- 17.Szilágyi, S.M., Benyó, Z., Dávid, L.: Heart model based ECG signal processing. In: Proc. 5th IFAC Symp. Modell. Contr. Biomed. Syst. pp. 213–217 (2003)Google Scholar
- 18.Szilágyi, S.M., Benyó, Z., Dávid, L.: WPW syndrome identification and classification using ECG analysis. Proc. World Congr. Med. Phys. Biomed. Eng. 4423.pdf (2003)Google Scholar
- 19.Szilágyi, S.M.: Event recognition, separation and classification from ECG recordings. In: Proc. 20th Ann. Int. Conf. IEEE EMBS, pp. 236–239 (1998)Google Scholar