Related Experiment Video
Updated: Feb 24, 2026
A Modified Method for Heterotopic Mouse Heart Transplantion
Published on: June 23, 2014
Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New
Yingtao Luo1, Reza Skandari2, Carlos Martinez3
1Carnegie Mellon University, Pittsburgh, PA, USA.
Insights
Machine learning models accurately predict heart transplant waitlist mortality using patient data. These advanced tools can improve patient urgency assessment and refine organ allocation policies for better outcomes.
Area of Science:
- Cardiology
- Medical Informatics
- Biostatistics
Background:
- Heart transplant waitlist management relies on ad-hoc committee decisions.
- Increasingly available longitudinal data from the United Network for Organ Sharing (UNOS) offers opportunities for data-driven decision support.
- Analytical approaches are needed to support clinical decisions at the time of organ availability.
Purpose of the Study:
- To benchmark machine learning models for time-dependent, time-to-event modeling of waitlist mortality.
- To leverage longitudinal waitlist history data for improved prediction accuracy.
- To support clinical decision-making in heart transplant management.
Main Methods:
- Trained machine learning models on 23,807 patient records with 77 variables.
- Utilized longitudinal waitlist history data.
- Evaluated models for survival prediction and discrimination at a 1-year horizon.
Main Results:
- The best model achieved a C-Index of 0.94 and an AUROC of 0.89.
- Performance significantly outperformed previous models.
- Identified key predictors aligning with known risk factors and revealed novel associations.
Conclusions:
- Machine learning models can effectively predict heart transplant waitlist mortality.
- Findings support improved urgency assessment for patients on the waitlist.
- Results can inform policy refinement for more equitable organ allocation.
Abstract:
Decisions about managing patients on the heart transplant waitlist are currently made by committees of doctors who consider multiple factors, but the process remains largely ad-hoc. With the growing volume of longitudinal patient, donor, and organ data collected by the United Network for Organ Sharing (UNOS) since 2018, there is increasing interest in analytical approaches to support clinical decision-making at the time of organ availability. In this study, we benchmark machine learning models that leverage longitudinal waitlist history data for time-dependent, time-to-event modeling of waitlist mortality. We train on 23,807 patient records with 77 variables and evaluate both survival prediction and discrimination at a 1-year horizon. Our best model achieves a C-Index of 0.94 and AUROC of 0.89, significantly outperforming previous models. Key predictors align with known risk factors while also revealing novel associations. Our findings can support urgency assessment and policy refinement in heart transplant decision making.
Related Concept Videos
01:18Introduction To Survival Analysis
The primary goal of survival analysis is to estimate survival time—the time...
01:24Kaplan-Meier Approach
01:20Comparing the Survival Analysis of Two or More Groups
01:20Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
01:09Truncation in Survival Analysis
Left truncation occurs when individuals who experienced the event of interest before a certain time are not included in the study. This is often due to a "delayed entry" into the study where only those who survive until a certain entry point are...
01:15Assumptions of Survival Analysis