Polygenic Hazard Score for Predicting Age-associated Risk of Alzheimer’s Disease in European Populations: Development and Validation
Bibliographic record
Abstract
Abstract Objectives Polygenic hazard score (PHS) models can be used to predict the age-associated risk for complex diseases, including Alzheimer’s disease (AD). In this study, we present an improved PHS model for AD that incorporates a large number of genetic variants and demonstrates enhanced predictive accuracy for age of onset in European populations compared to alternative models. Methods We used the genotyped European Alzheimer & Dementia Biobank (EADB) sample (n=42,120) to develop and evaluate the performance of the PHS model. We developed a PHS model building on 720 genetic variants, including Apolipoprotein E ( APOE ) ε2 and ε4 alleles. We used Elastic Net-regularized Cox regression approach to develop the PHS model. Results The new PHS model (EADB720) improved prediction accuracy compared to alternative models in European populations, with the Odds Ratio OR80/20 from the highest quintile of risk (80th risk percentile and above) to the lowest quintile of risk (20th risk percentile and below) varying between 5.10 and 13.15 within the range of age of onset from 65 – 85 years. Our model also improved risk stratification across ε3/3 individuals of European ancestry (OR80/20 ranges from 1.95 to 3.52). It was also successfully validated in independent datasets (HUSK, DemGene and ADNI) by achieving OR80/20 up to 10.00 in each independent dataset. Conclusion Our EADB720 model significantly improves the accuracy of age-associated risk of AD across European populations (pval<0.03). Accurately predicting the age of onset of AD is of large clinical importance to implementing new AD medication and early intervention in clinical settings.
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 | 0.017 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".