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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

YOLO-MIRNet: detection of distracted driving with enhanced generalization using a lightweight multi-scale interaction optimized model.

Traffic injury prevention·2026
Same author

Inhibition of ferroptosis improves developmental competence of vitrified-warmed oocytes.

Frontiers in endocrinology·2026
Same author

[Polygenic risk score-based comprehensive assessment model for breast cancer risk and its application for preimplantation embryo selection in a <i>BRCA1</i> mutation carrier].

Zhejiang da xue xue bao. Yi xue ban = Journal of Zhejiang University. Medical sciences·2026
Same author

Gender-related perceptions among healthcare providers and mothers in a pregnancy and early childhood obesity prevention intervention in Shanghai, China.

International journal for equity in health·2026
Same author

Charting human organogenesis across the Carnegie stages from a whole-embryo perspective.

GigaScience·2026
Same author

Spatiotemporal transcriptome atlas of human embryos after gastrulation.

Nature·2026

Related Experiment Video

Updated: Jul 20, 2025

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse
07:04

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

8.3K

Fetal weight estimation based on deep neural network: a retrospective observational study.

Yifei Wang1,2, Yi Shi3, Chenjie Zhang1,2

  • 1International Peace Maternity and Child Health Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China.

BMC Pregnancy and Childbirth
|August 2, 2023
PubMed
Summary

A new deep neural network (DNN) model improves estimated fetal weight (EFW) calculation accuracy using electronic health records. This AI approach offers better clinical decision-making for obstetricians, reducing potential complications.

Keywords:
Computer neural networksDecision makingFetal monitoringFetal weightObstetrics and gynecology

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings
14:40

Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings

Published on: October 25, 2015

9.5K

Related Experiment Videos

Last Updated: Jul 20, 2025

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse
07:04

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

8.3K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings
14:40

Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings

Published on: October 25, 2015

9.5K

Area of Science:

  • Medical Artificial Intelligence
  • Obstetrics and Gynecology
  • Perinatal Medicine

Background:

  • Accurate estimated fetal weight (EFW) is crucial for obstetric decision-making and reducing perinatal complications.
  • Current methods for EFW calculation may have limitations in precision.
  • Electronic health records (EHRs) offer a rich data source for developing improved EFW models.

Purpose of the Study:

  • To develop and evaluate a deep neural network (DNN) model for enhanced EFW calculation.
  • To compare the accuracy of the DNN model against established methods like Hadlock's formula.
  • To explore the utility of EHR data, including previously unreported factors, for EFW prediction.

Main Methods:

  • Retrospective analysis of EHR data from pregnant women delivering live births between January 2016 and December 2018.
  • Development of a DNN model utilizing obstetric EHR data.
  • Evaluation of the DNN model's performance using root-mean-square error (RMSE) and mean absolute percentage error (MAPE), compared to Hadlock's formula and multiple linear regression.

Main Results:

  • The developed DNN model achieved a significantly lower RMSE (189.64 g) and MAPE (5.79%) compared to Hadlock's formula (240.36 g and 6.46%).
  • Incorporating additional factors, such as prior birth weights, into a concise 10-parameter DNN model improved accuracy.
  • The enhanced DNN model demonstrated an accuracy rate of 83.87% with an RMSE of 243.80 g.

Conclusions:

  • The proposed DNN model represents a more accurate approach to EFW calculation than existing methods.
  • The DNN model's superior accuracy supports its adoption for improved fetal monitoring and clinical decision-making in obstetrics.
  • Leveraging EHR data with advanced modeling techniques can significantly enhance perinatal care.