Clustering ECG complexes using Hermite functions and self-organizing maps

An integrated method for clustering of QRS complexes is presented which includes basis function representation and self-organizing neural networks (NN's). Each QRS complex is decomposed into Hermite basis functions and the resulting coefficients and width parameter are used to represent the complex. By means of this representation, unsupervised self-organizing NN's are employed to cluster the data into 25 groups. Using the MIT-BIH arrhythmia database, the resulting clusters are found to exhibit a very low degree of misclassification (1.5%). The integrated method outperforms, on the MIT-BIH database, both a published supervised learning method as well as a conventional template cross-correlation clustering method.

[1]  W.J. Tompkins,et al.  A patient-adaptable ECG beat classifier using a mixture of experts approach , 1997, IEEE Transactions on Biomedical Engineering.

[2]  T Y YOUNG,et al.  ON THE REPRESENTATION OF ELECTROCARDIOGRAMS. , 1963, IEEE transactions on bio-medical engineering.

[3]  J. L. Willems,et al.  The Diagnostic Performance of Computer Programs for the Interpretation of Electrocardiograms , 1991 .

[4]  Olle Pahlm,et al.  A Method for Evaluation of QRS Shape Features Using a Mathematical Model for the ECG , 1981, IEEE Transactions on Biomedical Engineering.

[5]  Roger G. Mark,et al.  Detection of ventricular ectopic beats using neural networks , 1992, Proceedings Computers in Cardiology.

[6]  P. Macfarlane,et al.  Recommendations for standardization and specifications in automated electrocardiography: bandwidth and digital signal processing. A report for health professionals by an ad hoc writing group of the Committee on Electrocardiography and Cardiac Electrophysiology of the Council on Clinical Cardiology, , 1990, Circulation.

[7]  G. Moody,et al.  The European ST-T database: standard for evaluating systems for the analysis of ST-T changes in ambulatory electrocardiography. , 1992, European heart journal.

[8]  F. Jager,et al.  Assessing the robustness of algorithms for detecting transient ischemic ST segment changes , 1994, Computers in Cardiology 1994.

[9]  N. Ahmed,et al.  Electrocardiographic Data Compression Via Orthogonal Transforms , 1975, IEEE Transactions on Biomedical Engineering.

[10]  P W Macfarlane,et al.  Use of artificial neural networks within deterministic logic for the computer ECG diagnosis of inferior myocardial infarction. , 1994, Journal of electrocardiology.

[11]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[12]  J. L. Willems,et al.  The diagnostic performance of computer programs for the interpretation of electrocardiograms. , 1992, The New England journal of medicine.

[13]  P. Caminal,et al.  Adaptive Hermite models for ECG data compression: performance and evaluation with automatic wave detection , 1993, Proceedings of Computers in Cardiology Conference.

[14]  L. Edenbrandt,et al.  Acute myocardial infarction detected in the 12-lead ECG by artificial neural networks. , 1997, Circulation.

[15]  T. Kohonen.  Self-organized formation of topology correct feature maps , 1982 .

[16]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[17]  C. Combi,et al.  A hybrid neuro-fuzzy system for ECG classification of myocardial infarction , 1996, Computers in Cardiology 1996.

[18]  Raymond L. Watrous,et al.  A patient-adaptive neural network ECG patient monitoring algorithm , 1995, Computers in Cardiology 1995.

[19]  Alberto Macerata,et al.  QRS morphological classification using artificial neural networks , 1991, [1991] Proceedings Computers in Cardiology.