A computationally light-weight real-time classification method to identify different ECG signals

Ventricular arrhythmia is the main cause of cardiac arrest in patients with chronic heart disease. An undetected episode of ventricular tachycardia (VT) can be fatal if emergency medical assistance is not provided. Therefore, it is important to devise a real-time mobile ECG signal analysis algorithm for detection of ventricular tachycardia (VT). This paper presents an algorithm for automatic identification of normal sinus rhythm (NSR) and ventricular tachycardia (VT) which is applicable in a mobile environment. The algorithm employs peak-valley detector and cross-correlation technique to compute a feature vector. The selected features are beats-per-minute (BPM), NSR template accuracy and VT template accuracy. Based on the selected features, a fuzzy k-NN classifier is trained for classification. The algorithm specificity and sensitivity for classifying between NSR and VT ECG signal is 92.5% and 93.5% respectively.

[1]  Stephanie Schuckers,et al.  Ventricular arrhythmia detection using time-domain template algorithms , 1998, Proceedings of the IEEE 24th Annual Northeast Bioengineering Conference (Cat. No.98CH36210).

[2]  Sugata Munshi,et al.  Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification. , 2010, Medical engineering & physics.

[3]  R. Bousselijot,et al.  ECG signal analysis by pattern comparison , 1998, Computers in Cardiology 1998. Vol. 25 (Cat. No.98CH36292).

[4]  Shamsun Nahar,et al.  Automatic detection of premature ventricular contraction beat using morphological transformation and cross-correlation , 2009, 2009 3rd International Conference on Signal Processing and Communication Systems.

[5]  James M. Keller,et al.  A fuzzy K-nearest neighbor algorithm , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Tao Zhang,et al.  A fast Critical Arrhythmic ECG waveform identification method using cross-correlation and multiple template matching , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[7]  A. Lazkano,et al.  Distinction of ventricular fibrillation and ventricular tachycardia using cross correlation , 2003, Computers in Cardiology, 2003.

[8]  A. B. Ramli,et al.  Correlation analysis for abnormal ECG signal features extraction , 2003, 4th National Conference of Telecommunication Technology, 2003. NCTT 2003 Proceedings..

[9]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[10]  J.M. Jenkins,et al.  Template matching analysis of unipolar and bipolar electrograms in the differentiation of ventricular tachycardia and fibrillation from sinus rhythm , 1992, Proceedings Computers in Cardiology.

[11]  Kap Luk Chan,et al.  Real-time classification of electrocardiogram based on fractal and correlation analyses , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[12]  J.M. Jenkins,et al.  Pattern recognition of cardiac arrhythmias using two intracardiac channels , 1993, Proceedings of Computers in Cardiology Conference.