Computerised electrocardiology employing bi-group neural networks

A configuration of bi-group neural networks (BGNN) is proposed combined with an evidential reasoning framework to interpret 12-lead electrocardiograms for three mutually exclusive classes. A number of pre-processing feature selection techniques were investigated prior to application of the input feature vector to each individual BGNN. The network outputs were discounted within a belief interval of 1 based on their performance on test data prior to combination. It was found that the application of the feature selection techniques enhanced the individual performance of the BGNN, and subsequently enhanced the overall performance. The proposed framework was compared with conventional classification techniques of multi-output neural networks and linear multiple regression. The framework attained a higher level of classification in comparison with the other methods; 70.4% compared with 66.7% for both multi-output neural and statistical techniques.

[1]  Giovanni Bortolan,et al.  Fuzzy decision-making in electrocardiography , 1989, Artif. Intell. Medicine.

[2]  Jerzy Stefanowski,et al.  Feature subset selection for classification of histological images , 1997, Artif. Intell. Medicine.

[3]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[4]  Chee Peng Lim,et al.  Application of autonomous neural network systems to medical pattern classification tasks , 1997, Artif. Intell. Medicine.

[5]  Lawrence E. Widman A model-based approach to the diagnosis of the cardiac arrhythmias , 1992, Artif. Intell. Medicine.

[6]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[7]  O. H. Schmitt,et al.  Report of committee on electrocardiography, American Heart Association. Recommendations for standardization of leads and of specifications for instruments in electrocardiography and vectorcardiography. , 1967, Circulation.

[8]  Etienne E. Kerre,et al.  Outline of an expert system for ECG diagnosis using fuzzy sets , 1989, Artif. Intell. Medicine.

[9]  J L Willems Computer analysis of the electrocardiogram. , 1981, Endeavour.

[10]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[11]  C Brohet,et al.  Effect of combining electrocardiographic interpretation results on diagnostic accuracy. , 1988, European heart journal.

[12]  R L Lux,et al.  Electrocardiographic body surface potential mapping. , 1982, Critical reviews in biomedical engineering.

[13]  J M Anderson,et al.  Portable cardiac mapping assessment of acute ischaemic injury. , 1994, Methods of information in medicine.

[14]  Ian Horrocks,et al.  The GRAIL concept modelling language for medical terminology , 1997, Artif. Intell. Medicine.

[15]  J. R. Cox,et al.  Digital analysis of the electroencephalogram, the blood pressure wave, and the electrocardiogram , 1972 .

[16]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[17]  B. Tabachnick,et al.  Using Multivariate Statistics , 1983 .

[18]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[19]  A. Graybiel,et al.  Recommendations for Standardization of Electrocardiographic and Vectorcardiographic Leads , 1954, Circulation.

[20]  J. Michaelis,et al.  Evaluation of ECG Interpretation Results Obtained by Computer and Cardiologists , 1990, Methods of Information in Medicine.

[21]  Clifford Lau,et al.  Neural Networks: Theoretical Foundations and Analysis , 1991 .

[22]  P W Macfarlane,et al.  Methodology of ECG Interpretation in the Glasgow Program , 1990, Methods of Information in Medicine.

[23]  J M Jenkins,et al.  Computer diagnosis of abnormal cardiac rhythms employing a new P-wave detector for interval measurement. , 1978, Computers and biomedical research, an international journal.

[24]  David M. Mirvis,et al.  Body Surface Electrocardiographic Mapping , 2012, Developments in Cardiovascular Medicine.

[25]  J. Cornfield,et al.  Clinical application of a second generation electrocardiographic computer program. , 1975, The American journal of cardiology.

[26]  C Zywietz,et al.  Common Standards for Quantitative Electrocardiography: Goals and Main Results , 1990, Methods of Information in Medicine.