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 Video

Updated: Jul 30, 2025

Author Spotlight: Advancing Labor Management Through Electromyometrial Imaging for Understanding Uterine Contractions
08:07

Author Spotlight: Advancing Labor Management Through Electromyometrial Imaging for Understanding Uterine Contractions

Published on: May 26, 2023

1.2K

Predicting preterm births from electrohysterogram recordings via deep learning.

Uri Goldsztejn1, Arye Nehorai2

  • 1Department of Biomedical Engineering, McKelvey School of Engineering, Washington University in St. Louis, St. Louis, MO, United States of America.

Plos One
|May 11, 2023
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

Cardiac radiotherapy induces electrical conduction reprogramming in the absence of transmural fibrosis.

Nature communications·2021
Same author

Public policy and economic dynamics of COVID-19 spread: A mathematical modeling study.

PloS one·2020
Same author

Designing machine learning workflows with an application to topological data analysis.

PloS one·2019
Same author

Electro-Mechanical Ionic Channel Modeling for Uterine Contractions and Oxytocin Effect during Pregnancy.

Sensors (Basel, Switzerland)·2019
Same author

Estimating uterine source current during contractions using magnetomyography measurements.

PloS one·2018

Predicting preterm birth is challenging. A new deep learning model uses electrohysterogram (EHG) data to forecast preterm births over a week in advance, improving early intervention for better infant outcomes.

Area of Science:

  • Biomedical Engineering
  • Maternal-Fetal Medicine
  • Artificial Intelligence in Healthcare

Background:

  • Preterm birth affects 1 in 10 infants, causing mortality and long-term neurological issues.
  • Current methods struggle to predict preterm birth more than a week before it occurs.
  • Early prediction is crucial for timely interventions to improve neonatal outcomes.

Purpose of the Study:

  • To develop and validate a deep learning model for predicting preterm birth.
  • To utilize electrohysterogram (EHG) recordings for early preterm birth prediction.
  • To assess the efficacy of EHG spectral patterns in forecasting preterm labor.

Main Methods:

  • A recurrent neural network model was developed using short-time Fourier transforms of EHG signals.

More Related Videos

Preterm EEG: A Multimodal Neurophysiological Protocol
19:32

Preterm EEG: A Multimodal Neurophysiological Protocol

Published on: February 18, 2012

28.5K
Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates
05:58

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Published on: September 6, 2017

39.0K

Related Experiment Videos

Last Updated: Jul 30, 2025

Author Spotlight: Advancing Labor Management Through Electromyometrial Imaging for Understanding Uterine Contractions
08:07

Author Spotlight: Advancing Labor Management Through Electromyometrial Imaging for Understanding Uterine Contractions

Published on: May 26, 2023

1.2K
Preterm EEG: A Multimodal Neurophysiological Protocol
19:32

Preterm EEG: A Multimodal Neurophysiological Protocol

Published on: February 18, 2012

28.5K
Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates
05:58

Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates

Published on: September 6, 2017

39.0K
  • Clinical data from two public datasets were integrated with EHG recordings.
  • The model was trained to predict preterm births around 31 weeks of gestation.

    • Main Results:

    • The deep learning model achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.78 (95% CI: 0.76-0.80).
    • Spectral patterns in EHG recordings were found to be more predictive than temporal patterns.
    • Automated prediction of preterm birth from short EHG recordings is feasible.

    Conclusions:

    • Deep learning analysis of EHG signals can predict preterm births weeks in advance.
    • This predictive capability enables earlier therapeutic interventions.
    • Improved prediction of preterm birth can reduce infant mortality and morbidity.