Download PDF
Methods Inf Med 1994; 33(01): 157-160
DOI: 10.1055/s-0038-1634978
Original Article
Schattauer GmbH

Neural Network for Automatic Analysis of Motility Data

E. Jakobsen
1   The Esophagus Laboratory, Department of Thoracic and Cardiovascular Surgery, Odense University Hospital, Odense, Denmark
,
S. Kruse-Andersen
1   The Esophagus Laboratory, Department of Thoracic and Cardiovascular Surgery, Odense University Hospital, Odense, Denmark
,
J. Kolberg
1   The Esophagus Laboratory, Department of Thoracic and Cardiovascular Surgery, Odense University Hospital, Odense, Denmark
› Author Affiliations
Further Information

Publication History

Publication Date:
08 February 2018 (online)

   Permissions and Reprints

Abstract:

Continuous recording of intraluminal pressures for extended periods of time is currently regarded as a valuable method for detection of esophageal motor abnormalities. A subsequent automatic analysis of the resulting motility data relies on strict mathematical criteria for recognition of pressure events. Due to great variation in events, this method often fails to detect biologically relevant pressure variations. We have tried to develop a new concept for recognition of pressure events based on a neural network. Pressures were recorded for over 23 hours in 29 normal volunteers by means of a portable data recording system. A number of pressure events and non-events were selected from 9 recordings and used for training the network. The performance of the trained network was then verified on recordings from the remaining 20 volunteers. The accuracy and sensitivity of the two systems were comparable. However, the neural network recognized pressure peaks clearly generated by muscular activity that had escaped detection by the conventional program. In conclusion, we believe that neu-rocomputing has potential advantages for automatic analysis of gastrointestinal motility data.

Keywords

Neural Network - Esophagus - Motility - Esophageal Physio-pathology
 

  • REFERENCES

  • 1 Kruse-Andersen S, Wallin L, Madsen T. Ambulatory 23-hour recording of intraeso-phageal pressures in normal volunteers; a propagation analysis from one proximal and two distal recording sites. GUT. 1991-32-1270-4..
    PubMed
  • 2 Kolberg J. Feature detection in a medical time series. . The Technical University of Denmark IMSOR. 1992: 1-39.
    PubMedSearch in Google Scholar
  • 3 Schlang MF. Neural networks for segmentation and clustering of biomagnetical signals. In: Proceedings of the 1992 IEEE-SP Workshop. The Technical University of Denmark, IMSOR 1992; 343-9.
    PubMedSearch in Google Scholar
  • 4 Hu YH, Tompkins WJ, Xue Q. Artificial neural networks for ECG Arrhythmia Monitoring. In: Proceedings of the 1992 IEEE-SP Workshop. The Technical University of Denmark, IMSOR 1992; 350-9.
    PubMedSearch in Google Scholar
  • 5 Kosko B. Neural networks for signal processing. . New Jersey: Prentice-Hall; 1992: 1-399.
    Search in Google Scholar
  • 6 Kruse-Andersen S. Extended recording of intraesophageal pressures and pH. . (Medical Dissertation). Odense, Denmark 1992; 9-113.
    PubMedSearch in Google Scholar