Abstract 12072: Predictors of Cardiovascular and Non-Cardiovascular Death: From the Clinic to the Lab
Bibliographic record
Abstract
Introduction: Mortality risk estimates are often limited by the availability of individual patient risk factor data. We developed a series of prediction models for cardiovascular (CV) and non-cardiovascular (non-CV) death using increasing levels of information starting with the 1) standard history and physical examination, with incremental addition of 2) ECG and common lab values, 3) catheterization variables, and 4) research lab values. Methods: BARI 2D enrolled 2368 patients with type 2 diabetes and documented stable coronary artery disease from 6 countries. Patients were treated according to national diabetes, hypertension and cholesterol guidelines. Average follow-up was 5.4 years, and an independent adjudication committee classified 149 deaths as cardiovascular and 167 as non-cardiovascular. A series of four multivariable Cox regression models corresponding to the above levels of information were generated for CV and non-CV death, and Harrell c-statistics were used to evaluate model discrimination. Results: A history of heart failure, COPD and eGFR were significant independent predictors of both types of death. Classic cardiac risk factors including history of hypertension, ST depression, number of vessels with ≥50% stenosis, and reduced LV function were predictors of death due to cardiovascular causes whereas elevated CRP and total number of lesions were associated with death due to non-cardiovascular causes. Model discrimination for CV death improved with the addition of lab, ECG and angiographic information (c-statistic=0.720 with demographic and clinical predictors only, c-statistics=0.770 with all candidate variables). Improvement in model discrimination across the four models for non-CV death was less marked (c-statistics 0.740 to 0.766). Conclusion: Incremental prediction models provide clinically useful information as a patient is sequentially evaluated from the clinical to the lab.
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 | 0.004 | 0.010 |
| 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 | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".