Application of Support Vector Machine to the Detection of Delayed Gastric Emptying from Electrogastrograms

Abstract

The radioscintigraphy is currently the gold standard for gastric emptying test, but it involves radiation exposure and considerable expenses. Recent studies reported neural network approaches for the non-invasive diagnosis of delayed gastric emptying from the cutaneous electrogastrograms (EGGs). Using support vector machines, we show that this relatively new technique can be used for detection of delayed gastric emptying and is in fact able to improve the performance of the conventional neural networks.