Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

2024-2025 COVID-19 Vaccine and Major Adverse Cardiovascular Events Among US Veterans.

JAMA internal medicine·2026

Same author

Trimeric hemagglutinin vaccine provides chickens complete protection against lethal H5 subtype avian influenza virus from clade 2.3.4.4b.

Emerging microbes & infections·2026

Same author

Discovery of Glycosylated β-Amino Acid-Containing Macrolactams from <i>Nonomuraea</i> sp. 0L2P via Genome Mining.

ACS chemical biology·2026

Same author

Noble metal nanozymes: synthesis, mechanism, activity regulation and detection applications.

Mikrochimica acta·2026

Same author

The Polymer Brush of Sub-Nanometer Molecular Clusters: Surface Click-Chemistry for Precise Modulation of Visco-Elasticity.

Macromolecular rapid communications·2026

Same author

A mouse model of human-derived H10N3 influenza enables preclinical evaluation of antiviral efficacy.

Antiviral research·2026

Same journal

Sex disparities in body composition trends among elementary school students based on grade.

Frontiers in pediatrics·2026

Same journal

Case Report: Reversible myelodysplastic syndrome secondary to sodium valproate in an epileptic child.

Frontiers in pediatrics·2026

Same journal

Multiplex PCR-based epidemiology of viral acute respiratory infections in hospitalized children: implications for antibiotic stewardship in Saudi Arabia.

Frontiers in pediatrics·2026

Same journal

Omalizumab for severe IgE-mediated food allergy and severe asthma after pediatric liver transplantation: a case report.

Frontiers in pediatrics·2026

Same journal

Accidental alcohol ingestion triggering severe disulfiram-like reaction in a child receiving cefoperazone-sulbactam: a rare case report.

Frontiers in pediatrics·2026

Same journal

Research on the severity of symptoms in children with ASD based on integrated machine learning and structural equation modeling: age-specific predictive features and mediation effect path analysis.

Frontiers in pediatrics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 3, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Predicting preterm birth using auto-ML frameworks: a large observational study using electronic inpatient discharge

Deming Kong¹, Ye Tao¹, Haiyan Xiao¹

¹Wuhan Children's Hospital (Wuhan Maternal and Child Healthcare Hospital), Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.

Frontiers in Pediatrics

|February 16, 2024

Summary

This summary is machine-generated.

This study compared AutoML frameworks for predicting preterm birth. H2O AutoML achieved the highest accuracy (AUC 0.846), offering a promising tool for improving prenatal care using electronic medical records.

Keywords:

China administrative data autoML machine learning preterm birth

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Related Experiment Videos

Last Updated: Jul 3, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Area of Science:

Medical Informatics
Machine Learning
Computational Biology

Background:

Premature birth poses significant risks to maternal and infant health.
Accurate prediction of preterm birth is crucial for timely intervention and improved outcomes.
Electronic medical records (EMR) offer a rich data source for developing predictive models.

Purpose of the Study:

To develop and compare the performance of various automated machine learning (AutoML) frameworks and models for predicting preterm birth.
To identify the most effective AutoML framework and machine learning models for preterm birth prediction.
To determine key predictive features from EMR data.

Main Methods:

Utilized a large EMR database encompassing 715,962 participants with a principal diagnosis code for childbirth.
Employed three AutoML frameworks (H2O AutoML, AutoGluon, Auto-sklearn) to build prediction models, including tree-based, ensembled, and deep neural networks.
Assessed model performance using Area Under the Curve (AUC) and training times, with feature importance calculated via permutation-shuffling.

Main Results:

H2O AutoML demonstrated the highest median AUC (0.846) and lowest training time (0.14 min).
Gradient Boosting Machines (GBM), Extreme Gradient Boosting (XGBoost), stacked ensembles, and random forest models showed superior predictive performance (median AUCs ≥ 0.842).
Key predictors for preterm birth included premature rupture of membranes (PROM), incompetent cervix, occupation, and preeclampsia.

Conclusions:

Machine learning models, particularly those utilizing AutoML frameworks like H2O AutoML, can effectively predict preterm birth risk.
Leveraging readily available EMR data for preterm birth prediction holds significant potential for enhancing prenatal care and improving patient outcomes.
Further integration of predictive analytics in obstetrics can lead to more proactive and personalized maternal-fetal medicine.