Abstract
The most important health problem affecting large groups of people is related to the malfunction of the heart, usually caused by heart attack, rhythm disturbances, and pathological degenerations. One of the main goals of health study is to predict these kinds of tragic events, and by identifying the patients situated in the most dangerous states, to make it possible to apply a preventing therapy. Creating a heart model is important (Thaker & Ferrero, 1998) as the computer, while applying traditional signal processing algorithms recognizes lots of waves, but it does not really “understand” what is happening. To overcome this, the computer needs to know the origin and the evolvement process of the ECG signal (MacLeod & Brooks, 1998). During signal processing, if the traditional algorithm finds an unrecognizable waveform, the model-based approach is activated, which tries to estimate the causes of the encountered phenomenon (e.g., quick recognition of ventricular fibrillation) (Szilágyi, 1998).
Key Terms in this Chapter
Inverse Electrocardiography: A methodology that reconstructs the inner structure of the heart using multichannel ECG.
Unified Neural Network: An advanced neural network whose criterion function includes the topology of the classified samples.
ECG Analysis: A collection of ECG signal processing methods aiming at the determination of medical parameters.
Wolff-Parkinson-White (WPW) Syndrome: A syndrome of pre-excitation of the ventricles of the heart due to an accessory pathway that causes an abnormal electrical communication from the atria to the ventricles.
Support Vector Machine (SVM): A set of related supervised learning methods used for classification and regression.
Search Space Reduction: A method for decreasing the problem complexity.
Heart Simulation: A simulation that focuses on the functional modeling of the heart.
Body Surface Potential Map: A massively multi-channel measurement of the ECG signal using several dozens or hundreds of electrodes that cover the whole torso