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: Feb 22, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Deep Learning in Predicting Preterm Birth: A Comparative Study of Machine Learning Algorithms.

Fangchao Zhang1, Lingling Tong2, Chen Shi3

  • 1Department of Gynecology and Obstetrics, Peking University Third Hospital, Beijing 100191, China.

Maternal-Fetal Medicine (Wolters Kluwer Health, Inc.)
|May 23, 2025
PubMed
Summary

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

Toxic epidermal necrolysis and acute kidney injury following co-trimoxazole rechallenge and voriconazole accumulation as an exacerbating cofactor: a case report.

Frontiers in toxicology·2026
Same author

Discovery of N-(6-Acetylpyridin-3-yl)-2-(4-(ethylsulfonyl)phenyl)acetamide derivatives as a novel series of selective RORγt antagonists.

European journal of medicinal chemistry·2026
Same author

Gut commensal Bacteroides-derived pantothenic acid alleviates metabolic syndrome.

Cell host & microbe·2026
Same author

Face-To-Face Vs. Online Behavioral Parent Training for Young Children with ADHD: Child and Parent Outcomes.

Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53·2026
Same author

AI-Physics-Experiment Trinity for Integrated Protein Dynamics Modeling.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Structure-Guided Discovery of Potent, Selective, and Orally Bioavailable Werner Syndrome RecQ Helicase Inhibitors for the Treatment of Microsatellite Instability-High Tumors.

Journal of medicinal chemistry·2026
Same journal

From Retrospective to Prospective: The Contribution of Artificial Intelligence Dystocia Algorithm in Understanding and Preventing Dystocia in Intrapartum Cesarean Delivery.

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
Same journal

Expert Consensus on the Diagnosis and Management of Cervical Insufficiency in China (2026 Revision).

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
Same journal

Prenatal Exposure to Organochlorine Compounds and Other Pesticides: A Systematic Review of Neonatal Health Outcomes.

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
Same journal

Correlations Between Pregnancy-Associated Plasma Protein A Levels and Pregnancy Characteristics, Placental Volume, Vascularization, and Histopathology.

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
Same journal

Umbilical Artery Thrombosis in the Third Trimester of Pregnancy: A Retrospective Analysis of 13 Cases.

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
Same journal

A National Survey on Critically Ill Obstetric Patients Care Centers.

Maternal-fetal medicine (Wolters Kluwer Health, Inc.)·2026
See all related articles
This summary is machine-generated.

Deep learning, particularly transformer models, shows promise for predicting preterm birth. This advanced algorithm outperformed traditional methods in a recent study.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Maternal-Fetal Medicine

Background:

  • Preterm birth remains a significant global health challenge.
  • Accurate prediction of preterm birth is crucial for timely intervention and improved neonatal outcomes.

Purpose of the Study:

  • To evaluate the efficacy of deep learning algorithms for predicting preterm birth.
  • To compare the performance of transformer models against other machine learning algorithms in preterm birth prediction.

Main Methods:

  • A retrospective study analyzed 30,965 birth records from January 2018 to June 2023.
  • Four algorithms (logistic regression, random forest, support vector machine, transformer) were trained and validated.
  • Performance was assessed using metrics including Area Under the Curve (AUC), sensitivity, and specificity.
Keywords:
Artificial intelligenceMachine learningPreterm birthTransformer

Related Experiment Videos

Last Updated: Feb 22, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Main Results:

  • The transformer model achieved superior performance, with an AUC of 79.20% in the test dataset.
  • The transformer model demonstrated higher sensitivity (73.67%) and specificity (72.48%) compared to other models.
  • Significant differences in various factors were observed between preterm and full-term birth groups.

Conclusions:

  • Deep learning algorithms, specifically the transformer model, are suitable for predicting preterm birth.
  • The transformer algorithm offers a promising tool for enhancing the prediction of preterm birth.