A methodology for the automated creation of fuzzy expert systems for ischaemic and arrhythmic beat classification based on a set of rules obtained by a decision tree

OBJECTIVE In the current work we propose a methodology for the automated creation of fuzzy expert systems, applied in ischaemic and arrhythmic beat classification. METHODS The proposed methodology automatically creates a fuzzy expert system from an initial training dataset. The approach consists of three stages: (a) extraction of a crisp set of rules from a decision tree induced from the training dataset, (b) transformation of the crisp set of rules into a fuzzy model and (c) optimization of the fuzzy model's parameters using global optimization. MATERIAL The above methodology is employed in order to create fuzzy expert systems for ischaemic and arrhythmic beat classification in ECG recordings. The fuzzy expert system for ischaemic beat detection is evaluated in a cardiac beat dataset that was constructed using recordings from the European Society of Cardiology ST-T database. The arrhythmic beat classification fuzzy expert system is evaluated using the MIT-BIH arrhythmia database. RESULTS The fuzzy expert system for ischaemic beat classification reported 91% sensitivity and 92% specificity. The arrhythmic beat classification fuzzy expert system reported 96% average sensitivity and 99% average specificity for all categories. CONCLUSION The proposed methodology provides high accuracy and the ability to interpret the decisions made. The fuzzy expert systems for ischaemic and arrhythmic beat classification compare well with previously reported results, indicating that they could be part of an overall clinical system for ECG analysis and diagnosis.

[1]  Zuhair Bandar,et al.  Genetic tuning of fuzzy inference within fuzzy classifier systems , 2006, Expert Syst. J. Knowl. Eng..

[2]  Erik Sandøe,et al.  Arrhythmia : a guide to clinical electrocardiology , 1991 .

[3]  G. Moody,et al.  Analysis of transient ST segment changes during ambulatory monitoring using the Karhunen-Loeave transform , 1992, Proceedings Computers in Cardiology.

[4]  V. Somers,et al.  Heart Rate Variability: , 2003, Journal of cardiovascular electrophysiology.

[5]  Dimitrios I. Fotiadis,et al.  An association rule mining-based methodology for automated detection of ischemic ECG beats , 2006, IEEE Transactions on Biomedical Engineering.

[6]  N Maglaveras,et al.  ECG processing techniques based on neural networks and bidirectional associative memories. , 1998, Journal of medical engineering & technology.

[7]  D. Ge,et al.  Cardiac arrhythmia classification using autoregressive modeling , 2002, Biomedical engineering online.

[8]  Peter W Macfarlane,et al.  A comparison of commonly used QT correction formulae: the effect of heart rate on the QTc of normal ECGs. , 2004, Journal of electrocardiology.

[9]  Dimitrios I. Fotiadis,et al.  An ischemia detection method based on artificial neural networks , 2002, Artif. Intell. Medicine.

[10]  I.K. Duskalov,et al.  Developments in ECG acquisition, preprocessing, parameter measurement, and recording , 1998, IEEE Engineering in Medicine and Biology Magazine.

[11]  Metin Akay,et al.  Nonlinear Biomedical Signal Processing: Fuzzy Logic, Neural Networks, and New Algorithms , 2000 .

[12]  P. Laguna,et al.  ST-T segment change recognition using artificial neural networks and principal component analysis , 1995, Computers in Cardiology 1995.

[13]  Roger G. Mark,et al.  Analysis of transient ST segment changes during ambulatory monitoring , 1991, [1991] Proceedings Computers in Cardiology.

[14]  Yorgos Goletsis,et al.  Automated ischemic beat classification using genetic algorithms and multicriteria decision analysis , 2004, IEEE Transactions on Biomedical Engineering.

[15]  Philip Langley,et al.  An algorithm to distinguish ischaemic and non-ischaemic ST changes in the Holter ECG , 2003, Computers in Cardiology, 2003.

[16]  Witold Pedrycz,et al.  Genetically optimized fuzzy decision trees , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[18]  C. Pappas,et al.  An adaptive backpropagation neural network for real-time ischemia episodes detection: development and performance analysis using the European ST-T database , 1998, IEEE Transactions on Biomedical Engineering.

[19]  Robert Babuska,et al.  Neuro-fuzzy methods for nonlinear system identification , 2003, Annu. Rev. Control..

[20]  Cezary Z. Janikow,et al.  Fuzzy decision trees: issues and methods , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[21]  E. Clark,et al.  Effect of age and gender on diagnostic accuracy of ECG diagnosis of acute myocardial infarction , 2004, Computers in Cardiology, 2004.

[22]  Yorgos Goletsis,et al.  A multicriteria decision based approach for ischaemia detection in long duration ECGs , 2003, 4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine, 2003..

[23]  Stanislaw Osowski,et al.  Support vector machine-based expert system for reliable heartbeat recognition , 2004, IEEE Transactions on Biomedical Engineering.

[24]  Li-Xin Wang,et al.  A Course In Fuzzy Systems and Control , 1996 .

[25]  Ashok N. Srivastava,et al.  Data Mining: Concepts, Models, Methods, and Algorithms , 2005, J. Comput. Inf. Sci. Eng..

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

[27]  Roger G. Mark,et al.  Performance measures for algorithms to detect transient ischemic ST segment changes , 1991, [1991] Proceedings Computers in Cardiology.

[28]  J H van Bemmel,et al.  A reference data base for multilead electrocardiographic computer measurement programs. , 1987, Journal of the American College of Cardiology.

[29]  Stanislaw Osowski,et al.  ECG beat recognition using fuzzy hybrid neural network , 2001, IEEE Trans. Biomed. Eng..

[30]  C. Papaloukas,et al.  A knowledge-based technique for automated detection of ischaemic episodes in long duration electrocardiograms , 2006, Medical and Biological Engineering and Computing.

[31]  Michael G. Strintzis,et al.  ECG analysis using nonlinear PCA neural networks for ischemia detection , 1998, IEEE Trans. Signal Process..

[32]  Dimitrios I. Fotiadis,et al.  An arrhythmia classification system based on the RR-interval signal , 2005, Artif. Intell. Medicine.

[33]  Sorina Zahan,et al.  A fuzzy approach to computer-assisted myocardial ischemia diagnosis , 2001, Artif. Intell. Medicine.

[34]  C.Z. Janikow,et al.  FID4.1: an overview , 2004, IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04..

[35]  Jonathan M. Garibaldi,et al.  Application of simulated annealing fuzzy model tuning to umbilical cord acid-base interpretation , 1999, IEEE Trans. Fuzzy Syst..

[36]  F. Jager,et al.  Characterization of transient ischemic and non-ischemic ST segment changes , 1995, Computers in Cardiology 1995.

[37]  Zuhair Bandar,et al.  On constructing a fuzzy inference framework using crisp decision trees , 2006, Fuzzy Sets Syst..

[38]  G. Carrault,et al.  Comparing wavelet transforms for recognizing cardiac patterns , 1995 .

[39]  Boriana L. Milenova,et al.  Fuzzy and neural approaches in engineering , 1997 .

[40]  Vipin Kumar,et al.  Introduction to Data Mining, (First Edition) , 2005 .

[41]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[42]  Willis J. Tompkins,et al.  Biomedical Digital Signal Processing , 1993 .

[43]  Louis Wehenkel,et al.  A complete fuzzy decision tree technique , 2003, Fuzzy Sets Syst..

[44]  Tamer Ölmez,et al.  ECG beat classification by a novel hybrid neural network , 2001, Comput. Methods Programs Biomed..

[45]  D. Edwards Data Mining: Concepts, Models, Methods, and Algorithms , 2003 .

[46]  Dimitris G. Papageorgiou,et al.  PANMIN: sequential and parallel global optimization procedures with a variety of options for the local search strategy ✩ , 2004 .

[47]  Witold Pedrycz,et al.  An algorithmic framework for development and optimization of fuzzy models , 1996, Fuzzy Sets Syst..

[48]  Anastasios Bezerianos,et al.  Ischemia detection with a self-organizing map supplemented by supervised learning , 2001, IEEE Trans. Neural Networks.

[49]  I. K. Daskalov,et al.  Automatic detection of the electrocardiogram T-wave end , 1999, Medical & Biological Engineering & Computing.

[50]  Mehmed Kantardzic,et al.  Data Mining: Concepts, Models, Methods, and Algorithms , 2002 .

[51]  Gary Riley,et al.  Expert Systems: Principles and Programming , 2004 .

[52]  Dimitrios I. Fotiadis,et al.  Arrhythmia classification using the RR-interval duration signal , 2002, Computers in Cardiology.

[53]  S. Sitharama Iyengar,et al.  Classification of heart rate data using artificial neural network and fuzzy equivalence relation , 2003, Pattern Recognit..

[54]  Willis J. Tompkins,et al.  Quantitative Investigation of QRS Detection Rules Using the MIT/BIH Arrhythmia Database , 1986, IEEE Transactions on Biomedical Engineering.

[55]  Dimitrios I Fotiadis,et al.  Use of a novel rule-based expert system in the detection of changes in the ST segment and the T wave in long duration ECGs. , 2002, Journal of electrocardiology.

[56]  M. J. Goldman Principles of Clinical Electrocardiography , 1973 .

[57]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[58]  Carsten Peterson,et al.  Clustering ECG complexes using Hermite functions and self-organizing maps , 2000, IEEE Trans. Biomed. Eng..

[59]  Naip Tuna,et al.  Arrhythmia—A Guide to Clinical Electrocardiology , 1994 .