Development and Validation of the CR-DECIDE Models to Predict Major Adverse Cardiovascular Events and Health Status in Stable Coronary Artery Disease
Bibliographic record
Abstract
Background: Guidelines emphasize individualized care in the management of stable coronary artery disease (CAD). We aimed to develop and validate clinical prediction models for major adverse cardiovascular events (MACEs) and health status among patients with stable CAD to support individualized, shared decision-making. Methods: For model development and internal validation, we used registries of outpatients with obstructive CAD on coronary angiography in British Columbia (2004-2015) and Alberta (2004-2020). Models were externally validated in ISCHEMIA trial participants with obstructive CAD on coronary computed tomography angiography. Outcomes included MACE (death, myocardial infarction, or stroke) within 3 years, angina-free status, and good-to-excellent physical functioning at 1 year, based on the Seattle Angina Questionnaire. Results: Median age was of study patients was 66-67 years, and 77% were male in both the MACE (n = 34,990) and health status (n = 13,312) model development cohorts. MACEs occurred in 9% (2026 patients) at 3 years. A 14-variable model had a C statistic of 0.68, calibration slope of 0.98, and positive net benefit in decision-curve analysis. At baseline, 41% were angina-free and 21% had good-to-excellent physical functioning, which increased to 64.5% and 72% at 1 year, respectively. C statistics for the angina-free and physical functioning models were 0.67 and 0.78, respectively, and calibration slopes were 0.98-0.99. In external validation, discrimination was modestly reduced and all models slightly underpredicted their respective outcomes, yet the MACE model retained positive net benefit. Conclusions: The CR-DECIDE models had moderate ability to predict MACEs and health status in patients with stable CAD and warrant further assessment of their impact at the point of care.
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 | 0.028 | 0.049 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| 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".