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

Learning patient-specific predictive models from clinical data.

Shyam Visweswaran1, Derek C Angus, Margaret Hsieh

  • 1Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA. shv3@pitt.edu

Journal of Biomedical Informatics
|May 11, 2010
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

Mortality As a Measure of Treatment Effect in Clinical Trials Recruiting Critically Ill Patients.

Critical care medicine·2023
Same author

Impact of adherence to procalcitonin antibiotic prescribing guideline recommendations for low procalcitonin levels on antibiotic use.

BMC infectious diseases·2023
Same author

Long-term (180-Day) Outcomes in Critically Ill Patients With COVID-19 in the REMAP-CAP Randomized Clinical Trial.

JAMA·2022
Same author

Invited commentary on Sepsis.

Surgery·2022
Same author

Evaluation of Bebtelovimab for Treatment of Covid-19 During the SARS-CoV-2 Omicron Variant Era.

Open forum infectious diseases·2022
Same author

Proteomic changes associated with racial background and sepsis survival outcomes.

Molecular omics·2022
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

This study presents a patient-specific algorithm using Markov blanket (MB) models for improved clinical outcome prediction. Utilizing local structure representations and Bayesian model averaging enhances predictive performance over population-wide models.

Area of Science:

  • Computational biology
  • Medical informatics
  • Machine learning in healthcare

Background:

  • Population-wide models predict average outcomes but may miss individual patient nuances.
  • Patient-specific models offer personalized predictions based on individual clinical data.
  • Markov blanket (MB) models are a framework for understanding conditional independence in probabilistic models.

Purpose of the Study:

  • To develop and evaluate a patient-specific algorithm for predicting clinical outcomes.
  • To assess the impact of local structure representation within MB models.
  • To compare Bayesian model averaging with traditional model selection for personalized prediction.

Main Methods:

  • Developed a patient-specific algorithm utilizing Markov blanket (MB) models.

Related Experiment Videos

  • Employed Bayesian model averaging over a selected set of MB models for outcome prediction.
  • Evaluated local structure representation versus global structure representation in MB models.

    • Main Results:

    • The patient-specific algorithm demonstrated improved performance on clinical datasets.
    • Using local structure representation in MB models enhanced predictive accuracy.
    • Bayesian model averaging outperformed model selection in this patient-specific context.

    Conclusions:

    • Patient-specific modeling using MB models can improve clinical outcome prediction.
    • Local structure representations within MB models are beneficial for personalized prediction.
    • Bayesian model averaging is a robust method for learning patient-specific predictive models.