Abstract
Ambulatory long-term motility recording is used increasingly for evaluation of esophageal function. The enormous amount of motility data recorded by this method demands subsequent computer analysis. One of the most crucial steps of this analysis becomes the process of automatic selection of relevant pressure peaks at the various recording levels. Until now, this selection has been performed entirely by rule-based systems, requiring each pressure deflection to fit within predefined rigid numerical limits in order to be detected. However, due to great variations in the shapes of the pressure curves generated by muscular contractions, rule-based criteria do not always select the pressure events most relevant for further analysis. We have therefore been searching for a new concept for automatic event recognition. The present study describes a new system, based on the method of neurocomputing. A large sample of normal esophageal pressure deflections was used as a “learning set,” and the performance of the trained neural networks was subsequently verified on different sets of data from normal subjects. Our trained networks detected pressure deflections with sensitivities of 0.79–0.99 and accuracies of 0.89–0.98, depending on the recording level within the esophageal lumen. The neural networks often recognized peaks that clearly represented true contractions but that had been rejected by a rule-based system. We conclude that neural networks have potentials for automatic detections of esophageal, and possibly also other kinds of gastrointestinal, pressure variations.
Similar content being viewed by others
References
Smout AJPM, Breedijk M, van der Zouw C, Akkermans LMA: Physiological gastroesophageal reflux and esophageal motor activity studied with a new system for 24-hour recording and automated analysis. Dig Dis Sci 34:372–378, 1989
Emde C, Armstrong D, Bumm R, Kaufhold H-J, Riecken E-O, Blum AL: Twenty-four hour continuous ambulatory measurement of esophageal pH and pressure: a digital recording system and computer-aided analysis. J Ambulat Monit 3:47–62, 1990
Eypasch EP, Stein HJ, DeMeester TR, Johansson K-E, Barlow AP, Schneider GT: A new technique to define and clarify esophageal motor disorders. Am J Surg 159:144–152, 1990
Kruse-Andersen S, Wallin L, Madsen T: Ambulatory 23 hour recording of intraoesophageal pressures in normal volunteers: A propagation analysis from one proximal and two distal recording sites. Gut 32:1270–1274, 1991
Stein HJ, DeMeester TR: Indications, technique, and clinical use of ambulatory 24-hour esophageal motility monitoring in a surgical practice. Ann Surg 217:128–137, 1993
Janssens J, Annese V, Vantrappen G: Bursts of non-deglutitive simultaneous contractions may be a normal oesophageal motility pattern. Gut 34:1021–1024, 1993
Kruse-Andersen S: Extended recording of intraoesophageal pressures and pH. With special attention to the incidence of abnormal oesophageal contractions and the relationship between abnormal pressure waves and acid reflux. Thesis. Private edition. October 1992
Hertz J, Krogh A, Palmer RG: Introduction to the Theory of Neural Computation. Reading, Massachusetts, Addison Wesley, 1991
Stein HJ, DeMeester TR, Eypasch EP, Klingman RR: Ambulatory 24-hour esophageal manometry in the evaluation of esophageal motor disorders and noncardiac chest pain. Surgery 110:753–763, 1991
Langevin S, DeNuna SF, Castell DO: Does dict affect values obtained during prolonged ambulatory pressure monitoring. Dig Dis Sci 38:225–232, 1993
Tijskens G, Janssens J, Vantrappen G, De Bondt F: Validation of a fully automated analysis of esophageal body contractility and lower esophageal sphincter function: A study on the effect of the PGE1 analogue rioprostil on human esophageal motility. J Gastrointest Motil 1:21–28, 1989
Breumelhof R, Nadorp JHSM, Akkermans LMA, Smout AJPM: Analysis of 24-hour esophageal pressure and pH data in unselected patients with noncardiac chest pain. Gastroenterology 99:1257–1264, 1990
Baxt WG: Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med 115:843–848, 1991
Devine B, Macfarlane PW: Detection of electrocardiographic “left ventricular strain” using neural nets. Med Biol Eng Comput 31:343–348, 1993
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kruse-Andersen, S., Rütz, K., Kolberg, J. et al. Automatic detection of esophageal pressure events. Digest Dis Sci 40, 1659–1668 (1995). https://doi.org/10.1007/BF02212686
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02212686