The use of the SPSA method in ECG analysis

The classification, monitoring, and compression of electrocardiogram (ECG) signals recorded of a single patient over a relatively long period of time is considered. The particular application we have in mind is high-resolution ECG analysis, such as late potential analysis, morphology changes in QRS during arrythmias, T-wave alternants, or the study of drug effects on ventricular activation. We propose to apply a modification of a classical method of cluster analysis or vector quantization. The novelty of our approach is that we use a new distortion measure to quantify the distance of two ECG cycles, and the class-distortion measure is defined using a min-max criterion. The new class-distortion-measure is much more sensitive to outliers than the usual distortion measures using average-distance. The price of this practical advantage is that computational complexity is significantly increased. The resulting nonsmooth optimization problem is solved by an adapted version of the simultaneous perturbation stochastic approximation (SPSA) method of J. Spall (IEEE Trans. Automat. Contr., vol. 37, p. 332-41, Mar. 1992). The main idea is to generate a smooth approximation by a randomization procedure. The viability of the method is demonstrated on both simulated and real data. An experimental comparison with the widely used correlation method is given on real data.

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

[2]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[3]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[4]  C A Calvert,et al.  High-resolution electrocardiography. , 1998, The Veterinary clinics of North America. Small animal practice.

[5]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[6]  S M Jalaleddine,et al.  Compression of Holter ECG data. , 1988, Biomedical sciences instrumentation.

[7]  Biing-Hwang Juang,et al.  Hidden Markov Models for Speech Recognition , 1991 .

[8]  M. Simson.  Use of Signals in the Terminal QRS Complex to Identify Patients with Ventricular Tachycardia After Myocardial Infarction , 1981, Circulation.

[9]  L. Gerencser,et al.  SPSA for non-smooth optimization with application in ECG analysis , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[10]  Han-Fu Chen,et al.  A Stochastic Approximation Algorithm with Random Differences , 1996 .

[11]  Qiang Du,et al.  Centroidal Voronoi Tessellations: Applications and Algorithms , 1999, SIAM Rev..

[12]  László Gerencsér,et al.  Non-smooth optimization via SPSA , 1999 .

[13]  M. Tinova,et al.  Feasibility of a predictive algorithm for identifying characteristic events of cardiac activation: results of a model study , 1994, Computers in Cardiology 1994.

[14]  László Gerencsér,et al.  Convergence rate of moments in stochastic approximation with simultaneous perturbation gradient approximation and resetting , 1999, IEEE Trans. Autom. Control..

[15]  G. Breithardt,et al.  Standards for analysis of ventricular late potentials using high resolution or signal-averaged electrocardiography. A statement by a Task Force Committee between the European Society of Cardiology, the American Heart Association and the American College of Cardiology. , 1991, European heart journal.

[16]  Michael R. Anderberg,et al.  Cluster Analysis for Applications , 1973 .

[17]  C. Lemaréchal.  Nondifferentiable optimization , 1989 .

[18]  C. Lemaréchal.  Chapter VII Nondifferentiable optimization , 1989 .

[19]  A J Moss,et al.  ECG features of microvolt T-wave alternans in coronary artery disease and long QT syndrome patients. , 1998, Journal of electrocardiology.