Abstract 10797: Applying Cardiotoxicity Risk Prediction Scores in Women with Early-Stage Breast
Bibliographic record
Abstract
Background: Cardiotoxicity is a common complication of anthracyclines and HER2-targeted therapies in breast cancer patients. Despite recognized risk factors, accurate prediction of cardiotoxicity risk remains a challenge. We applied 3 published risk prediction scores (Table) to a cohort of women with HER2+ breast cancer treated with anthracycline and trastuzumab and described their predictive accuracy. Methods: Women with stage I-III HER2+ breast cancer treated at the Princess Margaret Cancer Centre (Toronto) between 2006-2019 were identified retrospectively. Those with a pre-therapy MUGA scan or 2D echocardiography and ≥ 3 follow up scans using the same modality were included. CREC criteria were applied to define cardiotoxicity. Three risk prediction scores (Ezaz et al., Romond et al., and HFA-ICOS proformas) were used to classify patients into low/medium/high cardiotoxicity risk according to pretreatment characteristics. The proportion of patients who developed cardiotoxicity across risk categories were compared within each score using chi-square test. Results: Of 629 women (mean age 52.4 ± 10.9 years), 151 (24%) met CREC cardiotoxicity criteria. With the Ezaz et al. score , proportion of patients that developed cardiotoxicity was 24.4% (n = 141/577), 20% (n = 9/45) and 14.3% (n =1/7), in the low, medium, and high predicted risk groups, respectively (p = 0.665). With Romond et al. score , this was 17.9% (n = 40/223), 24.5% (n = 50/204) and 30.5% (n = 61/200), respectively (p = 0.01). HFA-ICOS was 15.5% (n = 30/193), 26.9% (n = 109/404), and 37.5% (n = 12/32), respectively (p = 0.002). Conclusion: In women with early stage HER2+ breast cancer receiving trastuzumab therapy, risk scores by Romond et al., and the HFA-ICOS proformas predict cardiotoxicity risk. However, for both these scores the incidence of cardiotoxicity in the “low” predicted risk group remains high (15.5%-17.9%). Therefore, there remains a need to develop more accurate risk prediction scores.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".