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

External validation of a machine learning model for delivery mode prediction after induction.

Iolanda Ferreira1,2, Joana Simões3, João Correia3

  • 1Obstetrics Department, Unidade Local de Saúde Coimbra, Coimbra, Portugal. 10862@ulscoimbra.min-saude.pt.

NPJ Digital Medicine
|April 28, 2026
PubMed
Summary

Related Concept Videos

Prediction Intervals01:03

Prediction Intervals

2.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
2.5K

You might also read

Related Articles

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

Sort by
Same author

Computer-guided enzyme engineering of PET hydrolase mutants towards improved PET affinity.

BMC biotechnology·2026
Same author

Perinatal management of congenital long QT syndrome: A case of maternal and fetal manifestations.

HeartRhythm case reports·2026
Same author

Unobtrusive Sensing at Home Towards Healthcare 5.0: Technologies, Applications, and Future Directions.

Biosensors·2026
Same author

Cardiac morphologic changes induced by a 10-week water treadmill training for show jumping horses: A preliminary evaluation.

Veterinary journal (London, England : 1997)·2026
Same author

Successful pregnancy under benralizumab: a case of severe eosinophilic asthma.

Monaldi archives for chest disease = Archivio Monaldi per le malattie del torace·2026
Same author

NeoProspect HER2-low: Response and Prognosis After Neoadjuvant Treatment in Patients with HER2-low Breast Cancer.

Cureus·2026

This study developed and validated a machine learning model to predict delivery mode after labor induction. The model shows clinical utility, accurately predicting vaginal delivery while minimizing cesarean section predictions.

Area of Science:

  • Obstetrics and Gynecology
  • Medical Informatics
  • Machine Learning in Healthcare

Background:

  • Predicting delivery mode after labor induction (IOL) is crucial for maternal and infant outcomes.
  • Existing machine learning (ML) models for predicting delivery mode lack external validation.
  • Accurate prediction can optimize clinical decision-making and resource allocation.

Purpose of the Study:

  • To develop and externally validate a machine learning model for predicting delivery mode (vaginal delivery or cesarean section) following labor induction.
  • To assess the model's performance and clinical utility using independent datasets.

Main Methods:

  • Development and internal validation using Portuguese tertiary center data (n=2434).
  • External validation using the Consortium on Safe Labor dataset (n=10,591).

Related Experiment Videos

  • Logistic regression model selected for simplification and external validation based on performance metrics (AUROC, F1-score, PPV) and decision curve analysis (DCA).

    • Main Results:

    • The simplified 13-feature model achieved strong performance in external validation: AUROC 0.808, F1-score 0.781, PPV 0.822.
    • The model demonstrated a strong tendency towards predicting vaginal delivery (99.6%) with a low false-positive rate for cesarean section (0.5%).
    • Calibration curves underestimated cesarean section risk, potentially due to outcome imbalance, but DCA indicated good clinical utility.

    Conclusions:

    • The developed and validated machine learning model shows significant clinical utility for predicting delivery mode after labor induction.
    • The model's performance suggests it can aid clinicians in decision-making, potentially improving patient care.
    • Further investigation into calibration discrepancies due to outcome imbalance is warranted.