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 Video

Updated: Apr 12, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

870

Pediatric readmission classification using stacked regularized logistic regression models.

Gregor Stiglic1, Fei Wang2, Adam Davey3

  • 1University of Maribor, Maribor, Slovenia.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|May 9, 2015
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Receiver Operating Characteristic Plot01:15

Receiver Operating Characteristic Plot

583
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
583

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Frailty Markers and Falls Among US Clergy.

Journal of religion and health·2025
Same author

A comparison of visual and molecular methods for inferring biological communities in aquaculture enriched sediments - Impact assessment and cost-benefit analysis.

Marine pollution bulletin·2024
Same author

Associations between Brain Alpha-Tocopherol Stereoisomer Profile and Hallmarks of Brain Aging in Centenarians.

Antioxidants (Basel, Switzerland)·2024
Same author

Person-Centred Care: A Support Strategy for Managing Non-Communicable Diseases.

Healthcare (Basel, Switzerland)·2024
Same author

Cancer and the family: Variations by sex and race/ethnicity.

Cancer medicine·2024
Same author

Communal coping and glycemic control: Daily patterns among young adult couples with type 1 diabetes.

Families, systems & health : the journal of collaborative family healthcare·2023
Same journal

Sensitivity Analyses of a Scoring System for a Contraception Decision Aid.

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

Improving electronic health record processing of large language models via retrieval-augmented generation: A case study on dietary supplements.

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

Developing a User-Centered Mobile Application Prototype: Bridging Lower-Limb Fracture Care from Skilled Nursing Facility and Back to the Community.

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

KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs.

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

Automating Adjudication of Cardiovascular Events Using Large Language Models.

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

Predictive Factors and State-Level Barriers to Postpartum Birth Control Usage in the United States: Insights from PRAMS Phase 8.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
See all related articles

Sharing predictive models offers an alternative to healthcare data exchange. This study introduces a novel, interpretable two-level classification approach for improved outcome prediction without centralizing patient data.

Area of Science:

  • Health Informatics
  • Machine Learning
  • Clinical Prediction Models

Background:

  • Healthcare data sharing is restricted by regulations and privacy concerns.
  • Sharing predictive models built on distributed data is a viable alternative for outcome prediction.
  • Interpreting results from ensemble-learning methods remains a challenge.

Purpose of the Study:

  • To propose a novel classification approach for distributed healthcare data.
  • To achieve high predictive performance while maintaining result comprehensibility.
  • To enable outcome prediction in environments where data centralization is not feasible.

Main Methods:

  • Developed a two-level regularized sparse regression model for classification.
  • Utilized interpretable regression coefficients to rank hospital contributions.

Related Experiment Videos

Last Updated: Apr 12, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

870
  • Applied the approach to predict 30-day all-cause readmissions in pediatric patients.

    • Main Results:

    • The two-level classification model achieved an Area Under the ROC Curve (AUC) of 0.787.
    • Performance was comparable to a single model built on centralized data (AUC=0.789).
    • The method successfully uncovered the importance and contribution of individual hospitals.

    Conclusions:

    • Presents a novel approach for improved classification using shared predictive models.
    • Demonstrates effectiveness in environments with restricted data centralization.
    • Achieved significant improvements in classification performance and result interpretability.