Abstract 13213: Performance of a Modified RAISE Score to Screen for Cardiac Amyloidosis in Patients Undergoing Transcatheter Aortic Valve Implantation
Bibliographic record
Abstract
Background: A high prevalence of cardiac amyloidosis (CA) can be found in specific populations such as TAVI [transcatheter aortic valve implantation] referrals. However, CA diagnosis is complex and often missed. Several institutions have engaged active chart review by a multidisciplinary clinical committee (MCC) - a highly labor intensive process - to identify patients at risk for CA. Objective: To assess whether the recently published RAISE score (Remodeling, Age, cardiac Injury, Systemic and Electrical abnormalities) could be a substitute to optimize the MCC based pre-screening process in a TAVI population. Methods: Our institutional MCC reviewed the medical chart of all patients who underwent TAVI in the past 3 years and appreciated the utility of scintigraphic screening. The decision to screen or not was based on the presence of red flags and the anticipated clinical benefice. The original RAISE score was slightly modified (mRAISE, Figure ) to facilitate its use in our TAVI patients, for whom CA suspicion had never been raised. A patient with a score ≥3 was considered at high risk for CA (best cutoff previously published). The mRAISE score was compared to the MCC’s decision using a Cohen’s k. Results: Among 239 included patients (79±7y, 55% male), an mRAISE score ≥3 was found in 47 (20%), of whom the MCC suggested screening to only 25 (53% agreement), most of the remaining 22 being asymptomatic following TAVI. Of 192 patients (79%) with an mRAISE score <3, the MDC decided on “no screening” for 180 (94% agreement) and “screening” for the other 12; 3 patients refused and 9 had a negative screening. When compared with the MCC’s decision, global agreement of the mRAISE score was 86% with k=0.52 ( Figure ). Conclusions: The mRAISE score is not a perfect substitute for a MCC but rather an ideal pre-screening tool to optimize efficiency. If calculated prior to MCC meetings, an mRAISE score <3 can dramatically reduce the number of medical charts that need extensive review (>3/4 in our cohort).
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".