Integration of biomarker polygenic risk score improves prediction of coronary heart disease in UK Biobank and FinnGen
Bibliographic record
Abstract
Abstract Background In addition to age and sex, also smoking history and levels of blood pressure, cholesterol, lipoproteins and inflammation are established biomarkers for coronary heart disease (CHD). As standard polygenic risk scores (PRS) have recently proven successful for CHD prediction, it remains of high interest to determine how a combined PRS of biomarkers (BioPRS) constructed from statistically relevant biomarkers can further improve genetic prediction of CHD. Methods We developed CHDBioPRS, which combines BioPRS with PRS of CHD, via regularized regression in UK Biobank (UKB) training data ( n = 208,010). The resulting CHDBioPRS was tested on an independent UK Biobank subset ( n = 25,765) and on the FinnGen study ( n = 306,287). Results We observed a consistent pattern across all data sets where BioPRS was clearly predictive of CHD and improved standard PRS for CHD when the two were combined. In UKB test data, CHDPRS had a hazard ratio (HR) of 1.78 (95% confidence interval 1.67-1.91, area under the curve (AUC) 0.808) and CHDBioPRS had a HR of 1.88 (1.75-2.01, AUC 0.811) per one standard deviation of PRS. In FinnGen data, HR of CHDPRS was 1.57 (1.55-1.60, AUC 0.752) and HR of CHDBioPRS was 1.60 (1.58-1.62, AUC 0.755). We observed larger effects of CHDBioPRS in subsets of early onset cases with HR of 2.07 (1.85-2.32, AUC 0.790) in UKB test data and of 2.10 (2.04-2.16, AUC 0.791) in FinnGen. Results were similar when stratified by sex. Conclusions Integration of biomarker based BioPRS improved on the standard PRS for CHD and the gain was largest with early onset CHD cases. These findings highlight the benefit of enriching polygenic risk prediction of CHD with the genetics of associated biomarkers.
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 | 0.007 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".