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

Exploiting missing clinical data in Bayesian network modeling for predicting medical problems.

Jau-Huei Lin1, Peter J Haug

  • 1Department of Biomedical Informatics, University of Utah, 26 South 2000 East Room 5775 HSEB, Salt Lake City, UT 84112-5750, USA. jauhuei.lin@utah.edu

Journal of Biomedical Informatics
|July 13, 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

Computer clinical decision support that automates personalized clinical care: a challenging but needed healthcare delivery strategy.

Journal of the American Medical Informatics Association : JAMIA·2022
Same author

CheXED: Comparison of a Deep Learning Model to a Clinical Decision Support System for Pneumonia in the Emergency Department.

Journal of thoracic imaging·2021
Same author

Contemporary clinical decision support standards using Health Level Seven International Fast Healthcare Interoperability Resources.

Journal of the American Medical Informatics Association : JAMIA·2021
Same author

Enabling a learning healthcare system with automated computer protocols that produce replicable and personalized clinician actions.

Journal of the American Medical Informatics Association : JAMIA·2021
Same author

Implementation of Real-Time Electronic Clinical Decision Support for Emergency Department Patients with Pneumonia Across a Healthcare System.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2020
Same author

The design and evaluation of a Bayesian system for detecting and characterizing outbreaks of influenza.

Online journal of public health informatics·2019
Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026
Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026
Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026
Same journal

Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients.

Journal of biomedical informatics·2026
Same journal

DeepEN: A deep reinforcement learning framework for personalized enteral nutrition in critical care.

Journal of biomedical informatics·2026
See all related articles

Missing clinical data may hold valuable information. Explicitly modeling data absence in machine learning prediction models often improves performance, suggesting its utility in clinical decision support systems.

Area of Science:

  • Clinical Informatics
  • Machine Learning
  • Data Science

Background:

  • Clinical data collection is often inconsistent.
  • Missing data in clinical records is common and can be clinically relevant.
  • The absence of data may contain inherent information.

Purpose of the Study:

  • To investigate if the "missingness" of clinical data can provide useful information for building prediction models.
  • To evaluate the impact of explicitly modeling data absence on model performance.
  • To inform the design of clinical decision support systems.

Main Methods:

  • Experimented with four methods for treating missing values in a clinical dataset.
  • Two methods explicitly modeled data absence.
  • Trained four types of Bayesian classifiers on datasets with different missing value treatments.

Related Experiment Videos

  • Compared classifier performance using the area under the ROC curve.

    • Main Results:

    • Classifiers trained with explicit missing value treatments generally performed better.
    • Explicitly modeling data "missingness" improved prediction model performance in most cases.
    • The absence of data appears to hold predictive information.

    Conclusions:

    • Information can be derived from the "missingness" of clinical data itself.
    • Explicitly representing data presence/absence in the underlying logic is recommended for decision support systems.
    • Leveraging missing data patterns can enhance clinical prediction models.