Prediction model for cardiac allograft vasculopathy: Comparison of three multivariable methods
Related Experiment Video
Updated: Mar 7, 2026
Orthotopic Aortic Transplantation: A Rat Model to Study the Development of Chronic Vasculopathy
Published on: December 4, 2010
Evan P Kransdorf1, Natasha A Loghmanpour2, Manreet K Kanwar3
1Cedars-Sinai Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Insights
A new clinical prediction model helps identify heart transplant recipients at risk for cardiac allograft vasculopathy (CAV). This tool aids clinicians in personalizing interventions to prevent graft failure and improve long-term outcomes.
Area of Science:
- Cardiology
- Transplantation Medicine
- Biostatistics
Background:
- Cardiac allograft vasculopathy (CAV) is a primary cause of graft failure post-heart transplantation (HT).
- Existing research has identified CAV risk factors, but lacks predictive clinical models for individual patient risk assessment.
- There is a critical need for tools to quantify CAV risk in heart transplant recipients.
Purpose of the Study:
- To develop and validate a clinical prediction model for cardiac allograft vasculopathy (CAV) risk.
- To identify key variables at the time of heart transplantation (HT) predictive of CAV development.
- To create a user-friendly tool for clinicians to assess individual CAV risk.
Main Methods:
- Analysis of a large cohort (14,328) of heart transplant recipients from the ISHLT Registry (2000-2010).
- Utilized multivariable modeling techniques including stepwise Cox, regularized Cox proportional hazard, and Bayesian networks.
- Model performance was optimized using a training (75%) and testing (25%) dataset split.
Main Results:
- Cardiac allograft vasculopathy (CAV) occurred in 29.7% of recipients within a median of 3 years post-HT.
- The regularized Cox proportional hazard model demonstrated optimal performance and parsimony.
- An internet-based risk calculator application was developed based on the optimal model.
Conclusions:
- A validated clinical prediction model for CAV risk is now available.
- The model utilizes variables available at the time of heart transplantation (HT).
- This tool can guide clinicians in selecting recipients who may benefit from targeted interventions to mitigate CAV risk and progression.
Background:
Cardiac allograft vasculopathy (CAV) remains an important cause of graft failure after heart transplantation (HT). Although many risk factors for CAV have been identified, there are no clinical prediction models that enable clinicians to determine each recipient's risk of CAV.
Methods:
We studied a cohort of 14 328 heart transplant recipients whose data were reported to the International Society for Heart and Lung Transplantation Registry between 2000 and 2010. The cohort was divided into training (75%) and test (25%) sets. Multivariable modeling was performed in the test set using variables available at the time of heart transplant using three methods: (i) stepwise Cox proportional hazard, (ii) regularized Cox proportional hazard, and (iii) Bayesian network.
Results:
Cardiac allograft vasculopathy developed in 4259 recipients (29.7%) at a median time of 3.0 years after HT. The regularized Cox proportional hazard model yielded the optimal performance and was also the most parsimonious. We deployed this model as an Internet-based risk calculator application.
Conclusions:
We have developed a clinical prediction model for assessing a recipient's risk of CAV using variables available at the time of HT. Application of this model may allow clinicians to determine which recipients will benefit from interventions to reduce the risk of development and progression of CAV.
