Artificial Intelligence-Based Echocardiographic Assessment for Monitoring Disease Progression in Transthyretin Cardiac Amyloidosis
Bibliographic record
Abstract
AIMS: In transthyretin amyloid cardiomyopathy (ATTR-CM), reduced stroke volume (SV) portends a poor prognosis. Artificial intelligence (AI) enables rapid, standardized assessment of left ventricular outflow tract velocity-time integral (LVOT-VTI), which is a reliable surrogate for SV. We investigated longitudinal changes in AI-derived LVOT-VTI as outcome predictors in ATTR-CM. METHODS AND RESULTS: Consecutive patients with ATTR-CM underwent baseline and 12 ± 1 month transthoracic echocardiography between 2007 and 2021. Scans were processed by an AI platform for fully automated measurements including LVOT-VTI. Changes in echocardiographic variables were related to all-cause mortality in a landmark analysis using multivariable Cox models adjusting for clinical covariates (age, sex, TTR genotype, atrial fibrillation status, New York Heart Association class and National Amyloidosis Centre stage). Time-dependent receiver-operating characteristic analysis identified the optimal threshold of LVOT-VTI change. A total of 752 patients (74 ± 9 years; 88% men; 66% wild-type) were followed for a median of 3.3 years (interquartile range 2.1-5.0 years), during which 334 (44.4%) died. Among changes in echocardiographic parameters over 12 months, only LVOT-VTI change remained independently prognostic (adjusted hazard ratio [HR] per 1% decrease 0.994, p = 0.025). A ≥5% decrease (n = 377 patients, 50%) independently predicted all-cause mortality (adjusted HR 1.41, 95% confidence interval 1.13-1.76; p = 0.003), and improved risk reclassification (integrated discrimination improvement = 0.012; continuous net reclassification improvement = 0.21, both p < 0.001). CONCLUSIONS: A ≥5% decrease of AI-derived LVOT-VTI over 12 months, a simple indicator of SV loss, is independently associated with worse outcome in ATTR-CM. Routine monitoring of this automated AI metric may guide earlier therapeutic escalation and is a possible endpoint for future 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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".