A hybrid neuro-fuzzy system for ECG classification of myocardial infarction

We present an approach to the automated ECG classification based on a hybrid neuro-fuzzy model. The classification power of the connectionist paradigm has been coupled with the ability of the fuzzy set formalism to treat in a quantitative way natural language. This allows us to build up a system capable of both a good classification accuracy and to give meaningful explanations of the proposed diagnoses, in the form of symbolic IF-THEN rules.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  J A Kors,et al.  Classification Methods for Computerized Interpretation of the Electrocardiogram , 1990, Methods of Information in Medicine.

[3]  J. L. Willems,et al.  Comparison of the classification ability of the electrocardiogram and vectorcardiogram. , 1987, The American journal of cardiology.

[4]  Giovanni Bortolan,et al.  Neural networks for ECG classification , 1990, [1990] Proceedings Computers in Cardiology.

[5]  C. Derwael,et al.  Computer interpretation of the 12-lead electrocardiogram, the Frank-lead vectorcardiogram and the reconstructed vectorcardiogram , 1994, Computers in Cardiology 1994.

[6]  J L Willems,et al.  Reference Standards for Software Evaluation , 1990, Methods of Information in Medicine.

[7]  Lotfi A. Zadeh,et al.  A Theory of Approximate Reasoning , 1979 .

[8]  J. L. Willems,et al.  Diagnostic ECG classification based on neural networks. , 1993, Journal of electrocardiology.

[9]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[10]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[11]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..