Neural networks in cardiac electrophysiological signal classification.

The aim of this work was to develop a method by which intra-cardiac electrograms could be classified. A new algorithm for training this particular network has been established and applied to the task of finding the onset times of intra-cardiac electrograms. The algorithm is based on adding a choice function to the combination function of each neuron. The choice function enables the network to consider delays in each of its synapses. The gradient of error is then calculated with respect to the weights and delays. A synaptic delay-based artificial neural network was implemented using MATLAB and used to detect the onset times of the atrial, His and ventricular electrograms from the His catheter recordings. Results from a subset of a clinical, 12-channel electrophysiology study demonstrated the ability of the network to successfully identify peak potentials and onset times. Errors in detection of onset times were in the range of 1-2 ms. This method, which does not utilise traditional windowing and/or thresholding operations, can be effectively used to detect temporal patterns in a range of electrophysiological and biological signals.