Enhancing the Prediction of Cardiac Allograft Vasculopathy Using Intravascular Ultrasound and Machine Learning: A Proof of Concept
Authors' conclusion
We identified 4 clusters characterized by distinct maximal intimal thickness trajectories. These clusters were shown to discriminate against the development of angiographic CAV.
Study context
- Population
- Adult heart transplantation recipients
- Participants
- 186 recipients
- Exposure
- Cardiac allograft vasculopathy (CAV) risk clusters by maximal intimal thickness trajectories
- Outcome
- ISHLT-defined CAV
- Follow-up
- 5 years
Methodological detailssingle-centre, latent class mixed-effects model
- Single-centre
- Latent class mixed-effects model
Main finding
As reported in the abstract
5-year risk of ISHLT-defined CAV
Observational data: associations, not effects.
Further findings
ISHLT CAV 2-3 · 5 years
- Only patients in moderate to high risk cluster developed ISHLT CAV 2-3
- P = 0.02
Pretransplant covariates, low vs high risk
- Low risk group had significantly younger female recipients, shorter ischemic time and younger female donors vs high risk group
Original publication
Enhancing the Prediction of Cardiac Allograft Vasculopathy Using Intravascular Ultrasound and Machine Learning: A Proof of Concept. Circ Heart Fail. Published 5 February 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →