A novel computational method to predict hypoattenuated leaflet thickening post-transcatheter aortic valve replacement using preprocedural computed tomography scans
Bibliographic record
Abstract
Objective Hypoattenuated leaflet thickening (HALT) is a computed tomography (CT) finding after transcatheter aortic valve replacement (TAVR) that is indicative of bioprosthetic valvular thrombosis. There are currently no standardized or validated methods for predicting HALT, which can cause bioprosthetic valve dysfunction and has been associated with adverse patient outcomes. The objective was to develop a novel fast-response, artificial intelligence, and machine learning (ML)-driven computational pipeline to predict HALT using preprocedural CT scans. Methods The pipeline consisted of (1) pre-TAVR CT reconstruction and reduced order modeling simulations to automatically predict postprocedural geometric parameters , (2) a landmark-guided automated left ventricle segmentation method to predict hemodynamic parameters , and (3) statistical and ML analyses to develop HALT predictive metrics. Results Pre- and postprocedural scans from 45 patients (21 with HALT, 24 without) were used as inputs for the pipeline. We identified statistically significant relationships between HALT and peak systolic blood velocity ( P < .01) and peak systolic blood flow through the bioprosthetic valve ( P < .01), left ventricular ejection time ( P < .01), ejection volume ( P < .05), and right coronary height ( P < .05). ML-yielded metrics related to circulation in the neosinuses correlated strongly with HALT occurrence ( P < .001) along with the greatest accuracy of 84.40% and area under receiver operating characteristic curve of 0.87. Conclusions A computational pipeline using pre-procedural CT scans as inputs that outputs post-TAVR geometric and hemodynamic measurements was developed to assess metrics with the potential to predict the risk of HALT. Such a tool may help guide decision-making and understanding of prevention of postprocedural thrombosis.
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 | 0.001 | 0.002 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".