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

Computer-based models to identify high-risk children with asthma

T A Lieu1, C P Quesenberry, M E Sorel

  • 1Division of Research, Kaiser Permanente, Oakland, California 94611, USA. tal@dor.Kaiser.org

American Journal of Respiratory and Critical Care Medicine
|May 1, 1998
PubMed
Summary

Computer models can identify children with asthma at high risk for hospitalization and emergency department (ED) visits. These models use health utilization data to flag patients needing closer asthma management.

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

Recurrence after hospitalization for acute coronary syndrome among HIV-infected and HIV-uninfected individuals.

HIV medicine·2018
Same author

Breastfeeding and growth during infancy among offspring of mothers with gestational diabetes mellitus: a prospective cohort study.

Pediatric obesity·2018
Same author

Moderate intensity sports and exercise is associated with glycaemic control in women with gestational diabetes.

Diabetes & metabolism·2017
Same author

Post-partum weight loss and glucose metabolism in women with gestational diabetes: the DEBI Study.

Diabetic medicine : a journal of the British Diabetic Association·2014
Same author

A survey of training in pediatric flexible bronchoscopy.

Pediatric pulmonology·2013
Same author

Trends in annual incidence of methicillin-resistant Staphylococcus aureus (MRSA) infection in HIV-infected and HIV-uninfected patients.

Epidemiology and infection·2013

Area of Science:

  • Pediatric Pulmonology
  • Health Informatics
  • Epidemiology

Background:

  • Effective asthma management necessitates identifying high-risk pediatric patients.
  • Computerized health utilization data offers a potential resource for risk stratification.

Purpose of the Study:

  • To develop and validate prediction models for asthma-related hospitalizations and emergency department (ED) visits.
  • Utilize data from a large health maintenance organization (HMO) for predictive modeling.

Main Methods:

  • Retrospective cohort design with split-sample validation.
  • Analysis of 16,520 children with asthma-related utilization.
  • Proportional-hazards models and classification trees used to identify risk factors.

Related Experiment Videos

Main Results:

  • Predictors of hospitalization included prior oral steroid prescriptions (RR: 1.9), previous hospitalizations (RR: 1.7), and lack of a personal physician (RR: 1.6).
  • Classification trees identified prior hospitalization/ED visits, frequent beta-agonist use, and multiple prescribers as key predictors.
  • Models identified children with a threefold increased risk of hospitalization and twofold increased risk of ED visits.

Conclusions:

  • Computer-based prediction models effectively identify children at high risk for adverse asthma outcomes.
  • These models can support population-based asthma management strategies.
  • Early identification facilitates targeted interventions to improve patient outcomes.