NONINVASIVE IDENTIFICATION OF GASTRIC CONTRACTIONS FROM SURFACE ELECTROGASTROGRAM USING BACKPROPAGATION NEURAL NETWORKS

Gastric contractions play an important role in the digestive process o f the stomach. The established method for the measurement of gastric c ontractions is invasive and involves the insertion through the nose of a manometric probe into the stomach. A non-invasive method is introdu ced in this paper for the identification fo gastric contractions using the surface electrogastrogram. The electrogastrogram (ECG) was measur ed by placing surface electrodes on the abdominal skin over the stomac h in ten subjects. Gastric contractions were simultaneously monitored using an intraluminal manometric probe. The back-propagation neural ne twork was applied to identify gastric contractions from the ECG. The i nput of the neural network was composed of spectral data points of the ECG which was computed using the exponential distribution method. Exp eriments were conducted to optimize network structures and parameters. Using the ECG data in five subjects as the training set and the ECG d ata in another five subjects as the testing set, an overall accuracy o f 92% was achieved in the identification of gastric contractions with an optimized three-layer back-propagation neural network (number of no des for input: hidden: output layers being 64:20:2).