Abstract 11451: Development and Validation of the CANHEART Population-Based Laboratory Prediction Models for Atherosclerotic Cardiovascular Disease
Bibliographic record
Abstract
Background: The use of atherosclerotic cardiovascular disease (ASCVD) prediction models is suboptimal in clinical practice partly because of the need to gather history, physical and laboratory measures. Automation of risk assessment using only demographic and laboratory results may overcome this limitation. Our objective was to develop and validate sex-specific prediction models for ASCVD using age and routine laboratory tests and compare their performance to the Pooled Cohort Equations (PCEs). Methods: Models were derived and internally validated in Ontario residents aged 40 to 75 years without cardiovascular disease who had outpatient laboratory testing from April 1, 2009 to December 31, 2015. Estimates of the 5-year risk of ASCVD (myocardial infarction, stroke, death from ischemic heart or cerebrovascular disease) were obtained from Fine-Gray models that included age, total cholesterol, high-density lipoprotein cholesterol, triglycerides, hemoglobin, mean corpuscular volume, platelets, leukocytes, estimated glomerular filtration rate, and glucose as predictors. Models were externally validated in a primary care cohort assembled from electronic medical record data and compared with the PCEs. Results: Sex-specific models were developed and internally validated in 2,160,497 women and 1,833,147 men. They were well calibrated with less than 2% relative difference between mean predicted and observed risk. The C-statistic was 0.77 in women and 0.72 in men. External validation in 31,697 primary care patients demonstrated less than 15% relative and less than 0.3% absolute difference in mean predicted and observed risks ( Figure ). The C-statistics for the lab models were 0.72 for both sexes and were not significantly different from the C-statistics for the PCEs in women (p=0.18 for difference) or men (p=0.35). Conclusions: We developed and validated the CANHEART Lab Models that predict ASCVD with similar accuracy to more complex models such as the PCEs.
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 | 0.015 | 0.032 |
| 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 | 0.000 |
| Open science | 0.002 | 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".