This study was carried out to determine the usefulness of standard electrocardiography for the diagnosis of early canine heartworm disease. Baseline electrocardiograms were recorded in 12 dogs. Thirty artificial Dirofilaria immitis worms were inserted in the pulmonary artery of each dog. New electrocardiograms were recorded on days 1-4, 7, 14, 21, 28 and 35 after insertion of worms. A significant attenuation of amplitude of Q wave in lead I was recorded on days 1-4, 7, 14, 21, 28 and 35; of R wave in lead II on days 21, 28 and 35; and of S wave in lead aVR on days 7, 14, 21, 28 and 35. Duration of the QRS complex in lead AVF was significantly prolonged on day 14. In 41.6% of the dogs, right axis deviation was recorded. These results suggest that for a dog whose normal baseline standard electrocardiogram is known, a comparison of the QRS complex of the baseline with those of subsequent standard electrocardiograms may suggest early canine heartworm disease when there is an attenuation of amplitude of Q wave in lead I, R wave in lead II and S wave in lead aVR. An additional indication can be right axis deviation.

This thesis discusses the utilization of the artificial neural networks (ANN) for detection of coronary artery disease (CAD) in frequency area. The first part of this thesis is orientated towards the theoretical knowledge. Describes the issue of ECG pathological changes. ECQ are converted to frequency area. Described statistical methods and methods for automatic detection of CAD and MI. Explained the issue of the perceptron and ANN. The second deals with use of Neural Network Toolbox MATLAB®. This part focuses on counting and finding suitable parameters and making connection of band. At the end of the thesis UNS is used to detect ischemic parameters and the results are discussed. Average values for the best settings are 100% accuracy.