Artificial intelligence-analyzed computed tomography in patients undergoing transcatheter tricuspid valve repair
Bibliographic record
Abstract
BACKGROUND: Baseline right ventricular (RV) function derived from 3-dimensional analyses has been demonstrated to be predictive in patients undergoing transcatheter tricuspid valve repair (TTVR). The complex nature of these cumbersome analyses makes patient selection based on established imaging methods challenging. Artificial intelligence (AI)-driven computed tomography (CT) segmentation of the RV might serve as a fast and predictive tool for evaluating patients prior to TTVR. METHODS: Patients suffering from severe tricuspid regurgitation underwent full cycle cardiac CT. AI-driven analyses were compared to conventional CT analyses. Outcome measures were correlated with survival free of rehospitalization for heart-failure or death after TTVR as the primary endpoint. RESULTS: Automated AI-based image CT-analysis from 100 patients (mean age 77 ± 8 years, 63% female) showed excellent correlation for chamber quantification compared to conventional, core-lab evaluated CT analysis (R 0.963-0.966; p < 0.001). At 1 year (mean follow-up 229 ± 134 days) the primary endpoint occurred significantly more frequently in patients with reduced RV ejection fraction (EF) <50% (36.6% vs. 13.7%; HR 2.864, CI 1.212-6.763; p = 0.016). Furthermore, patients with dysfunctional RVs defined as end-diastolic RV volume > 210 ml and RV EF <50% demonstrated worse outcome than patients with functional RVs (43.7% vs. 12.2%; HR 3.753, CI 1.621-8.693; p = 0.002). CONCLUSIONS: Derived RVEF and dysfunctional RV were predictors for death and hospitalization after TTVR. AI-facilitated CT analysis serves as an inter- and intra-observer independent and time-effective tool which may thus aid in optimizing patient selection prior to TTVR in clinical routine and in trials.
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 | 0.000 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".