Automatic classification of esophageal motility records

Summary form only given. Signal processing techniques as well as feature extraction and pattern classification criteria were utilized to develop a system that automatically classifies esophageal motility records into normal and different abnormal cases. The system consists of four parts: processing the recorded signal to remove noise interference, automatic isolation of the different parts of the esophagus, extracting a set of features that quantifies the esophageal records, and a classifier to discriminate the different cases. Classification was accomplished by two-multi-layer feedforward neural network classifiers trained using the back-propagation algorithm: one for the tubular part and the second for the lower esophageal sphincter (LES). The results have shown that 97.4% and 100% correct classification were obtained for the tubular esophagus and LES, respectively. It is concluded that the adopted techniques are highly relevant to esophageal data and that the approach followed is feasible and can become a powerful tool for automatic esophageal diagnosis.