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

Comparing decision support methodologies for identifying asthma exacerbations.

Judith W Dexheimer1, Laura E Brown, Jeffrey Leegon

  • 1Department of Biomedical Informatics, Vanderbilt University, Nashville, TN 37232-8340, USA. judith.dexheimer@vanderbilt.edu

Studies in Health Technology and Informatics
|October 4, 2007
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

Precision risk assessment for pediatric hospitalization using address-level data in Cincinnati, Ohio.

Journal of clinical and translational science·2026
Same author

Heterogenous effect of automated alerts on mortality.

Journal of the American Medical Informatics Association : JAMIA·2025
Same author

Integrating secondary prevention of rheumatic heart disease into the primary healthcare system in Northern Uganda.

BMJ global health·2025
Same author

Heterogeneous Effect of Automated Alerts on Mortality.

medRxiv : the preprint server for health sciences·2025
Same author

Precision risk assessment for pediatric hospitalization using address-level data in Cincinnati, Ohio.

medRxiv : the preprint server for health sciences·2025
Same author

Forecasting school violence risk with incomplete interview data: an automated assessment approach.

JAMIA open·2025
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

Machine learning models accurately identified pediatric asthma patients eligible for guidelines in emergency departments. An automatically constructed Bayesian network performed comparably to expert systems, suggesting potential for real-time detection.

Area of Science:

  • Pediatric Emergency Medicine
  • Artificial Intelligence in Healthcare
  • Clinical Decision Support Systems

Background:

  • Asthma guideline eligibility in pediatric emergency departments is crucial for timely and appropriate care.
  • Accurate identification of eligible patients can be challenging in a fast-paced emergency setting.
  • Machine learning (ML) offers potential for automated and accurate patient assessment.

Purpose of the Study:

  • To compare the performance of common machine learning techniques against an expert-built Bayesian Network.
  • To evaluate the ability of these methods to determine eligibility for asthma guidelines in pediatric emergency department patients.
  • To assess the feasibility of using ML for real-time asthma patient identification.

Main Methods:

Related Experiment Videos

  • A retrospective study included pediatric patients (2-18 years) presenting to an emergency department.
  • Four ML models were developed: artificial neural network, support vector machine, Gaussian process, and a learned Bayesian network.
  • Performance was evaluated using area under the receiver operating characteristic curves (AUC), sensitivity, specificity, and predictive values.

    • Main Results:

    • The study analyzed a training set (n=3017) and a test set (n=1006).
    • All ML methods demonstrated high accuracy, with AUC values ranging from 0.937 to 0.962.
    • The automatically constructed Bayesian network achieved an AUC of 0.962, closely matching the expert-built network's AUC of 0.959.

    Conclusions:

    • All four machine learning approaches achieved high accuracy in identifying patients eligible for asthma guidelines.
    • An automatically constructed Bayesian network performed comparably to an expert-designed network.
    • These ML methods show promise for developing real-time systems to detect pediatric asthma patients efficiently.