Blind separation of multichannel electrogastrograms using independent component analysis based on a neural network

The electrogastrogram (EGG) is an abdominal surface measurement of gastric myo-electrical activity which regulates gastric contractions. It is of grea t clinical importance to record and analyse multichannel EGGs, which provid e more information on the propagation and co-ordination of gastric contract ions. EGGs are, however, contaminated by myo-electric interference from oth er organs and artefacts such as motion and respiration. The aim of the stud y is to separate the gastric signal from noisy multichannel EGGs without an y information on the interference, using independent component analysis. A neural-network model is proposed, and corresponding unsupervised learning a lgorithms are developed to achieve the separation. The performance of the p roposed method is investigated using artificial data simulating real EGG si gnals. Experimental EGG data are obtained from humans and dogs. The process ed results of both simulated and real EGG data show the following: first, t he proposed method is able to separate normal gastric slow waves from respi ratory artefacts and random noises. It is also able to extract gastric slow waves, even when the EGG is contaminated by severe respiratory and ECG art efacts. Secondly, when the stomach contains various gastric electric signal s with different frequencies, the proposed method is able to separate these different signals, as illustrated by simulations. These data suggest that the proposed method can be used to separate gastric slow waves, respiratory and motion artefacts, and intestinal myo-electric interference that are mi xed in the EGG. It can also be used to detect gastric slow-wave uncoupling, during which the stomach has multiple gastric signals with different frequ encies. It is believed that the proposed method may also be applicable to o ther biomedical signals.