Filter banks and neural network-based feature extraction and automatic classification of electrogastrogram

Dysrhythmia in gastric myoelectrical activity has been frequently observed in patients with gastric motor disorders and gastrointestinal symptoms. The assessment of the regularity of gastric myoelectrical activity is of great clinical significance. The aim of this study was to develop an automated assessment method for the regularity of gastric myoelectrical activity from the surface electrogastrogram (EGG). The method proposed in this paper was based on the filter bank and neural network. First, the EGG signal was divided into frequency subbands using filter bank analysis. Second, a parameter called the subband energy ratio (SER) was computed for each subband signal. A multilayer perceptron neural network was then used to automatically classify the EGG signal into four categories: bradygastria, normal, tachygastria, and arrhythmia, using the SER as the input. The EGG recording was made using the standard method of electrogastrography by placing electrodes on the abdominal surface. The study was performed in 40 patients with various gastric motor disorders, ten healthy adults, and ten healthy children. The neural network was trained and tested using the EGG data obtained from the patients. The regularity of gastric myoelectrical activity was assessed based on the classification of the minute-by-minute EGG segments. Using the running spectral analysis method as a gold standard, the proposed automated method had an accuracy of 100% for the training set and 97% for the test set. It was concluded that the proposed method provides an accurate and automatic assessment of the regularity of gastric myoelectrical activity from the EGG.