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

Information retrieval performance of probabilistically generated, problem-specific computerized provider order entry

Adam S Rothschild1, Harold P Lehmann

  • 1Department of Biomedical Informatics, Columbia University, Vanderbilt Clinic 5th Floor, 622 West 168th Street, New York, NY 10032, USA. adam.rothschild@dbmi.columbia.edu

Journal of the American Medical Informatics Association : JAMIA
|February 3, 2005
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

An examination of the availability and characteristics of social needs data in the electronic health records: a path to social data harmonization and standardization at Johns Hopkins medicine.

JAMIA open·2026
Same author

Neuroretinal Layer Thinning on OCT Imaging and Hemoglobin A1c in Youth With Type 1 Diabetes.

JAMA ophthalmology·2026
Same author

Beyond Missingness: Systematizing Methods for Comprehensive Data Fitness Assessment in Clinical Research.

Journal of medical Internet research·2026
Same author

The Potential Implications of Informatics for Value-Based Bare.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Assessing Usefulness of the Dashboard Instrument to Review Equity (DIRE) Checklist to Evaluate Equity in Public Health Dashboards: Reliability Study.

JMIR public health and surveillance·2025
Same author

Assessing Usefulness of the DIRE Checklist to Evaluate Equity in Public Health Dashboards: A Reliability Study.

JMIR public health and surveillance·2025

This study shows it is feasible to create problem-specific computerized provider order entry (CPOE) pick-lists using linked clinical data. Further research is needed to confirm its real-world usefulness.

Area of Science:

  • Clinical Informatics
  • Health Information Technology
  • Medical Decision Support

Background:

  • Computerized provider order entry (CPOE) systems aim to improve patient care and safety.
  • Generating relevant order suggestions within CPOE is challenging.
  • Problem-specific pick-lists could enhance CPOE efficiency and accuracy.

Purpose of the Study:

  • To determine the feasibility of probabilistically generating problem-specific CPOE pick-lists.
  • To evaluate the potential of using linked orders and problems from clinical cases.
  • To assess the performance of a novel pick-list generation method.

Main Methods:

  • A pilot retrospective study using internal medicine cases.
  • Physicians linked orders to specific problems identified in patient records.

Related Experiment Videos

  • Probability of Linkage of Order and Problem (PLOP) was calculated based on order-problem pair prevalence.
  • System-generated pick-lists were evaluated against physician-created standards.

    • Main Results:

    • Recall and precision varied inversely with the PLOP threshold, demonstrating classic information retrieval behavior.
    • Maximum recall of 0.67 was achieved at a PLOP threshold of 0, with a precision of 0.17.
    • Maximum precision of 0.73 was achieved at a PLOP threshold of 0.9, with a recall of 0.09.

    Conclusions:

    • Probabilistically generating problem-specific CPOE pick-lists from linked clinical data is feasible.
    • The developed method shows potential for improving CPOE systems.
    • Further research is required to validate the clinical utility in real-world settings.