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 networks for recognizing patterns in cardiotocograms

C Ulbricht1, G Dorffner, A Lee

  • 1Austrian Research Institute for Artificial Intelligence, Vienna. claudia@ai.univie.ac.at

Artificial Intelligence in Medicine
|June 17, 1998
PubMed
Summary

Artificial intelligence, specifically neural networks, can significantly improve the interpretation of cardiotocogram (CTG) traces for fetal monitoring. This AI-powered approach offers better results than traditional methods, aiding timely interventions during labor.

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

Hello and goodbye: a study of social engagement in autism.

Journal of autism and developmental disorders·1998
Same author

Respiratory ultrasonography of human parasternal intercostal muscle in vivo.

Ultrasound in medicine & biology·1998
Same author

Negative reexploration for cardiac postoperative bleeding: can it be therapeutic?

The Annals of thoracic surgery·1998
Same author

The effect of N-acetylcysteine on oxygen transport and uptake in patients with fulminant hepatic failure.

Hepatology (Baltimore, Md.)·1998
Same author

Localization of alpha2C-adrenergic receptor immunoreactivity in catecholaminergic neurons in the rat central nervous system.

Neuroscience·1998
Same author

Intestinal tuberculosis: clinicopathologic analysis and diagnosis by endoscopic biopsy.

The American journal of gastroenterology·1998

Area of Science:

  • Obstetrics and Gynecology
  • Medical Technology
  • Artificial Intelligence in Medicine

Background:

  • Cardiotocogram (CTG) is essential for fetal monitoring during labor.
  • Interpretation of CTG traces requires specialized expertise, leading to potential delays in intervention.
  • Automated monitoring systems can reduce detection-to-intervention time.

Purpose of the Study:

  • To evaluate the efficacy of artificial intelligence (AI) techniques, particularly neural networks, in recognizing patterns within CTG traces.
  • To compare the performance of AI methods against conventional techniques for CTG analysis.
  • To assess the potential of AI in developing an automated alarm system for suspicious fetal events.

Main Methods:

  • Development of an automated alarm system utilizing AI, specifically neural networks.

Related Experiment Videos

  • Comparative study design to evaluate AI performance against conventional methods.
  • Analysis of CTG traces to identify suspicious patterns indicative of fetal distress.

    • Main Results:

    • Neural networks demonstrated significantly superior performance in recognizing patterns in CTG traces compared to conventional methods.
    • The AI-based approach showed promise for immediate reporting of suspicious events.
    • AI techniques offer a more accurate and efficient alternative for CTG interpretation.

    Conclusions:

    • AI, particularly neural networks, is highly suitable for automated CTG pattern recognition.
    • AI-powered systems can enhance the accuracy and speed of fetal monitoring.
    • Implementing AI in obstetric monitoring can lead to improved patient outcomes by reducing diagnostic delays.