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

A new machine learning classifier for high dimensional healthcare data.

Rema Padman1, Xue Bai, Edoardo M Airoldi

  • 1The H. John Heinz III School of Public Policy and Management, Carnegie Mellon University, Pittsburgh, PA 15213, USA. rpadman@cmu.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

Reply to: Reassessing the evidence linking clinical leadership to AI deployment outcomes.

NPJ digital medicine·2026
Same author

An Artificial Intelligence-Enabled Cardiopulmonary Resuscitation Instructor.

JAMA internal medicine·2026
Same author

No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

The impact of leadership on AI deployment study outcomes in healthcare: an integrative analysis.

NPJ digital medicine·2025
Same author

Enhancing end-stage renal disease outcome prediction: a multisourced data-driven approach.

Journal of the American Medical Informatics Association : JAMIA·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

This study introduces a new method combining metaheuristic search and Bayesian Networks for efficient prediction modeling in healthcare. The Tabu Search enhanced Markov Blanket (TS/MB) procedure quickly identifies parsimonious models with improved predictive accuracy.

Area of Science:

  • Computational statistics
  • Machine learning
  • Health informatics

Background:

  • High-dimensional discrete data with few cases presents challenges for predictive modeling.
  • Existing machine learning methods may struggle with efficiency and interpretability in such domains.

Purpose of the Study:

  • To develop an efficient and effective prediction model for datasets with many discrete variables and few cases.
  • To combine metaheuristic search with Bayesian Networks for learning graphical models.

Main Methods:

  • Proposed a novel Tabu Search enhanced Markov Blanket (TS/MB) procedure.
  • Utilized restricted neighborhoods within a Bayesian Network framework, constrained by the Markov condition (Markov Blanket Neighborhoods).
  • Applied the method to two real-world healthcare datasets.

Related Experiment Videos

Main Results:

  • The TS/MB procedure demonstrated fast convergence.
  • Identified parsimonious models with significantly fewer predictor variables compared to the full dataset.
  • Achieved comparable or superior prediction performance against established machine learning methods.

Conclusions:

  • The TS/MB procedure offers an efficient approach for learning predictive models from high-dimensional, sparse data.
  • The method provides valuable insights into potential causal relationships among variables.
  • This technique is applicable to various domains including healthcare, commerce, and information security.