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

Donor-Recipient Matching for Kidney Transplantation Using Uncertainty Estimation in Generalized Propensity Score.

Syed Asil Ali Naqvi1, Karthik Tennankore2, Samina Abidi3

  • 1NICHE Research Group, Faculty of Computer Science, Dalhousie University, Halifax, Canada.

Studies in Health Technology and Informatics
|May 17, 2025
PubMed
Summary

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

Outcomes for Frail Dialysis Patients Not Referred for Transplantation: A Cohort Study.

Journal of the American Geriatrics Society·2026
Same author

Finding Associative and Causal Effects of Temporal Changes in Health Features for Prevalent and Incident Cancer in Males: A Machine Learning Approach.

Studies in health technology and informatics·2026
Same author

A Knowledge Graph to Represent and Predict Cancer Mechanistic Associations.

Studies in health technology and informatics·2026
Same author

Unlexi: Developing a Prototype of a Digital Emotion-Focused Therapy Tool for Alexithymia.

Studies in health technology and informatics·2026
Same author

External Validation and Recalibration of a Risk Calculator for Major Bleeding After Diagnostic Kidney Biopsy.

Kidney medicine·2026
Same author

Caregiver Perspectives on Supporting Kidney Transplant Recipients Through Graft Loss.

Kidney international reports·2026
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 summary is machine-generated.

This study enhances kidney donor-recipient matching using Generalized Propensity Score (GPS) modeling and Sufficient Dimensionality Reduction (SDR). SDR methods preserve causal links, improving allocation strategies and counterfactual analysis.

Area of Science:

  • Medical Informatics
  • Biostatistics
  • Health Services Research

Background:

  • Kidney donor-recipient matching is complex, involving numerous clinical and demographic factors.
  • Effective allocation requires advanced analytical techniques beyond traditional methods.

Purpose of the Study:

  • To explore Generalized Propensity Score (GPS) modeling integrated with Sufficient Dimensionality Reduction (SDR) for improved kidney transplant matching.
  • To evaluate dimensionality reduction techniques and uncertainty estimation methods for causal inference in matching.

Main Methods:

  • Applied various dimensionality reduction techniques, assessing performance via Root Mean Squared Error (RMSE) and Pearson Correlation (PC).
  • Utilized Quantile Regression, Ensemble methods, and Bayesian MC Dropout for uncertainty estimation.
Keywords:
Counterfactual AnalysisGeneralized Propensity ScoreOrgan TransplantationSufficient Dimensionality ReductionUncertainty Estimation

Related Experiment Videos

  • Employed propensity score matching and adversarial learning for counterfactual analysis.

    • Main Results:

    • The regression method (MLP) demonstrated superior performance in dimensionality reduction, achieving the lowest RMSE (1163) and highest PC (0.23) with a single dimension.
    • Quantile Regression proved more reliable for uncertainty assessment compared to Ensemble and Bayesian MC Dropout methods.
    • Uncertainty-based subset analysis significantly enhanced counterfactual analysis.

    Conclusions:

    • Sufficient Dimensionality Reduction (SDR) methods are beneficial for preserving causal relationships in complex matching scenarios.
    • Uncertainty estimation, particularly with Quantile Regression, improves the reliability of counterfactual analyses in kidney allocation.
    • Integrating advanced modeling techniques like GPS and SDR offers a pathway to optimize kidney donor-recipient matching.