Enhancing the Prediction of Cardiac Allograft Vasculopathy Using Intravascular Ultrasound and Machine Learning: A
Yasbanoo Moayedi1,2, Eduard Rodenas-Alesina1, Emily Somerset3
1Ted Rogers Centre of Excellence in Heart Research (Y.M., E.R.-A., N.A., F.B., H.J.R.), Peter Munk Cardiac Centre, University Health Network, Toronto, ON, Canada.
Insights
Researchers identified four distinct risk clusters for cardiac allograft vasculopathy (CAV) in heart transplant recipients. This stratification aids in personalized surveillance and early treatment of CAV, improving graft survival.
Area of Science:
- Cardiology
- Transplantation Medicine
- Data Science in Healthcare
Background:
- Cardiac allograft vasculopathy (CAV) is a primary cause of late graft dysfunction after heart transplantation.
- Predicting early CAV development is crucial for patient outcomes.
Purpose of the Study:
- To identify distinct patient clusters for cardiac allograft vasculopathy (CAV) using serial maximal intimal thickness and clinical risk factors.
- To predict the development of early CAV in heart transplant recipients.
Main Methods:
- Retrospective single-center study of adult heart transplant recipients.
- Latent class mixed-effects modeling to identify patient clusters based on maximal intimal thickness trajectories.
- Analysis of pretransplant covariates associated with each cluster.
Main Results:
- Four patient phenotypes (very low, low, moderate, high risk) were identified among 186 recipients.
- Five-year CAV risk varied significantly: 49.1% (high risk) to 0% (very low risk).
- Moderate to high-risk clusters showed significantly higher rates of severe CAV (ISHLT CAV 2-3) at 5 years.
Conclusions:
- Four clusters with distinct maximal intimal thickness trajectories were identified.
- These clusters effectively predict the development of angiographic CAV.
- This approach enables personalized surveillance and targeted treatment for CAV, potentially preventing advanced disease.
Background:
Cardiac allograft vasculopathy (CAV) is the leading cause of late graft dysfunction in heart transplantation. Building on previous unsupervised learning models, we sought to identify CAV clusters using serial maximal intimal thickness and baseline clinical risk factors to predict the development of early CAV.
Methods:
This is a single-center retrospective study including adult heart transplantation recipients. A latent class mixed-effects model was used to identify patient clusters with similar trajectories of maximal intimal thickness posttransplant and pretransplant covariates associated with each cluster.
Results:
Among 186 heart transplantation recipients, we identified 4 patient phenotypes: very low, low, moderate, and high risk. The 5-year risk (95% CI) of the International Society for Heart and Lung Transplantation-defined CAV in the high, moderate, low, and very low risk groups was 49.1% (35.2%-68.5%), 23.4% (13.3%-41.2%), 5.0% (1.3%-19.6%), and 0%, respectively. Only patients in the moderate to high risk cluster developed the International Society for Heart and Lung Transplantation CAV 2-3 at 5 years (P=0.02). Of the 4 groups, the low risk group had significantly younger female recipients, shorter ischemic time, and younger female donors compared with the high risk group.
Conclusions:
We identified 4 clusters characterized by distinct maximal intimal thickness trajectories. These clusters were shown to discriminate against the development of angiographic CAV. This approach allows for the personalization of surveillance and CAV-directed treatment before the development of angiographically apparent disease.
