Intelligent Modeling of the Electrical Activity of the Human Heart

The aim of this contribution is to present a new approach in modeling the electrical activity of the human heart. A recurrent artificial neural network is being used in order to exhibit a subset of the dynamics of the electrical behavior of the human heart. The proposed model can also be used, when integrated, as a diagnostic tool of the human heart system. What makes this approach unique is the fact that every model is being developed from physiological measurements of an individual. This kind of approach is very difficult to apply successfully in many modeling problems, because of the complexity and entropy of the free variables describing the complex system. Differences between the modeled variables and the variables of an individual, measured at specific moments, can be used for diagnostic purposes. The sensor fusion used in order to optimize the utilization of biomedical sensors is another point that this paper focuses on. Sensor fusion has been known for its advantages in applications such as control and diagnostics of mechanical and chemical processes.

Authors:

• Lambros V. Skarlas
• Grigorios N. Beligiannis
• Efstratios F. Georgopoulos
• Adam V. Adamopoulos

Keywords:

• Artificial Neural Networks
• Diagnostic System
• Health Condition Modeling Tool
• Heart Diagnostics Model
• Heart Electricity Model.

References:

[1] J. Sundnes, G. Lines, P. Gr├©ttum and A. Tveito, "Numerical methods
and software for modeling the electrical activity of the heart", in
Computational Partial Differential Equations Using Diffpack -
advanced topics, H. P. Langtangen and A. Tveito, Eds. Springer LNCSE
series, to be published.
[2] D. D. Di Bernardo, M. G. Signorini and S. Cerutti, "A model of two
nonlinear coupled oscillators for the study of heartbeat dynamics", Int.
Journal of Bifurcation and Chaos, Vol. 8, No. 10, 1998.
[3] D. Jones, "Neural Networks for Medical Diagnosis", in Handbook of
Neural Computing Applications, Academic Press, 1990, pp. 309-318,
[4] S. Haykin, Neural Networks: A Comprehensive Foundation, Upper
Saddle River, NJ. Prentice Hall PTR, 1994.
[5] H. White, "Learning in artificial neural networks: A statistical
perspective", Neural Computation, Vol. 1, pp. 425-464, 1989.
[6] A. G. Parlos, K. T. Chong and A. F. Atiya, "Application of the recurrent
multilayer perceptron in modeling complex process dynamics", IEEE
Trans. Neural Networks, vol. 5, pp. 255-266, March 1994.
[7] M. H. Hassoun, "Neural Networks in Bioprocessing and Chemical
Engineering", IEEE Trans. Neural Networks, vol. 7, pp. 1053, July
1996.
[8] P. J. Edwards, A. F. Murray, G. Papadopoulos, A. R. Wallace, J.
Barnard and G. Smith, "The application of neural networks to the
papermaking industry", IEEE Trans. Neural Networks, vol. 10, pp.
1456-1464, Nov. 1999.
[9] S. L. Ho, M. Xie, L. C. Tang, K. Xu, T. N. Goh, "Neural network
modeling with confidence bounds: a case study on the solder paste
deposition process", IEEE Trans. Neural Networks, vol. 24, pp. 323-
332, Oct 2001.
[10] R. Gutierrez-Osuna and A. Gutierrez-Galvez, "Habituation in the KIII
olfactory model with chemical sensor arrays", IEEE Trans. Neural
Networks, vol. 14, pp. 1565-1568, Nov 2003.
[11] W. G. Baxt, "Use of an artificial neural network for data analysis in
clinical decision-making: The diagnosis of acute coronary occlusion",
Neural Computation, Vol. 2, pp. 480-489, 1991.
[12] B. Blumenfeld, "A Connectionist Approach to the Processing of Time
Dependent Medical Parameters", in Proc. of the 1990 Int. Joint Conf. on
Neural Networks, Washington, DC, Vol. 2, 1990, pp. 575-578.
[13] G. Dorffner, E. Leitgeb and H. Koller, "Toward Improving Exercise
ECG for Detecting Ischemic Heart Disease with Recurrent and
FeedForward Neural Nets", in Neural Networks for Signal Processing,
vol. IV, J. Vlontzos, et al. Eds. Institute of Electrical and Electronics
Engineers, Inc., New York, NY, 1994, pp. 499-508.
[14] R. L. Kennedy, R. F. Harrison, S. J. Marshall and C.A. Hardisty,
"Analysis of clinical and electrocardiographic data from patients with
acute chest pain using a neurocomputer", Q J Med., Vol. 80, pp. 788-
789, 1991.
[15] R. Silipo and C. Marchesi, Artificial Neural Networks for Automatic
ECG Analysis, IEEE Trans. Signal Processing, vol. 46, pp. 1417-1425,
1998.
[16] A. V. Adamopoulos, E. F. Georgopoulos, S. D. Likothanassis and P. A.
Anninos, "Forecasting the MagnetoEncephaloGram (MEG) of Epileptic
Patients Using Genetically Optimized Neural Networks", in Proc.
GECCO-99, Orlando, USA, July 14-17, 1999, pp. 1457-1462.
[17] K. I. Minami, H. Nakajima, and T. Toyoshima, "Real-time
discrimination of ventricular tachycardia with Fourier-transform neural
network", IEEE Trans. Biomedical Engineering, vol. 46, pp. 179-185,
1999.
[18] S. D. Likothanassis and E. F. Georgopoulos, "Self-organised
evolutionary neural networks: algorithms and applications", in Highly
parallel computations: algorithms and applications, WIT Press, 2001,
pp. 397-433.
[19] Y. Hou, J. M. Zurada, and W. Karwowski, "Prediction of EMG Signals
of Trunk Muscles in Manual Lifting Using a Neural Network Model", in
Proc. of the International Joint Conference on Neural Networks,
Budapest, Hungary, July 2004, pp. 1935-1940.