Enhancing the Prediction of Cardiac Allograft Vasculopathy Using Intravascular Ultrasound and Machine Learning: A Proof of Concept
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".