Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Neural network for automatic analysis of motility data

E Jakobsen1, S Kruse-Andersen, J Kolberg

  • 1Department of Thoracic and Cardiovascular Surgery, Odense University Hospital, Denmark.

Methods of Information in Medicine
|March 1, 1994
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Lung cancer registries in Denmark, Finland, Norway and Sweden: a comparison and proposal for harmonization.

Acta oncologica (Stockholm, Sweden)·2023
Same author

Impact of health care organization on surgical lung cancer care.

Lung cancer (Amsterdam, Netherlands)·2019
Same author

History of Depression in Lung Cancer Patients: Impact of Delay.

Clinical oncology (Royal College of Radiologists (Great Britain))·2017
Same author

Consequences of persistent pain after lung cancer surgery: a nationwide questionnaire study.

Acta anaesthesiologica Scandinavica·2010
Same author

The prognostic importance of cyclooxygenase 2 and HER2 expression in epithelial ovarian cancer.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2007
Same author

Prognostic significance of p53, Her-2, and EGFR overexpression in borderline and epithelial ovarian cancer.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2004

A new neural network approach improves the detection of esophageal motor abnormalities from long-term pressure recordings. This advanced method identifies subtle muscular activity missed by traditional analysis, enhancing diagnostic accuracy.

Area of Science:

  • Gastroenterology
  • Biomedical Engineering
  • Computational Neuroscience

Background:

  • Continuous intraluminal pressure recording is vital for diagnosing esophageal motility disorders.
  • Conventional automatic analysis uses strict mathematical criteria but often misses subtle, biologically relevant pressure variations due to event variability.

Purpose of the Study:

  • To develop and evaluate a novel concept for recognizing esophageal pressure events using a neural network.
  • To compare the performance of a neural network-based system against conventional mathematical criteria for motility data analysis.

Main Methods:

  • Esophageal pressures were recorded for over 23 hours in 29 healthy volunteers using a portable system.
  • A neural network was trained on selected pressure events and non-events from 9 recordings.

Related Experiment Videos

  • The trained network's performance was validated on recordings from the remaining 20 volunteers.

    • Main Results:

    • The neural network and conventional methods showed comparable accuracy and sensitivity.
    • The neural network successfully identified pressure peaks from muscular activity that were missed by the conventional program.
    • This highlights the potential of neurocomputing in analyzing complex motility data.

    Conclusions:

    • Neurocomputing offers significant advantages for the automatic analysis of gastrointestinal motility data.
    • Neural networks can improve the detection of esophageal motor abnormalities by recognizing subtle pressure variations.
    • This technology holds promise for more accurate and comprehensive diagnosis of motility disorders.