Machine learning models for blood pressure phenotypes combining multiple polygenic risk scores
Hrytsenko, Y.; Shea, B.; Elgart, M.; Kurniansyah, N.; Lyons, G.; Morrison, A.; Carson, A. P.; Haring, B.; Mitchell, B. D.; Psaty, B. M.; Jaeger, B.; Gu, C. C.; Kooperberg, C.; Levy, D.; Lloyd-Jones, D. M.; Choi, E.; Brody, J. A.; Smith, J. A.; Rotter, J.; Moll, M.; Fornage, M.; Simon, N.; Castaldi, P.; Casanova, R.; Chung, R.-H.; Kaplan, R.; Loos, R. J. F.; Loos, R. J. F.; Kardia, S.; Rich, S.; Redline, S.; Kelly, T.; O'Connor, T.; Zhao, W.; Guo, X.; Chen, Y.-D. I.; Sofer, T.
Show abstract
We construct non-linear machine learning (ML) prediction models for systolic and diastolic blood pressure (SBP, DBP) using demographic and clinical variables and polygenic risk scores (PRSs). We developed a two-model ensemble, consisting of a baseline model, where prediction is based on demographic and clinical variables only, and a genetic model, where we also include PRSs. We evaluate the use of a linear versus a non-linear model at both the baseline and the genetic model levels and assess the improvement in performance when incorporating multiple PRSs. We report the ensemble models performance as percentage variance explained (PVE) on a held-out test dataset. A non-linear baseline model improved the PVEs from 28.1% to 30.1% (SBP) and 14.3% to 17.4% (DBP) compared with a linear baseline model. Including seven PRSs in the genetic model computed based on the largest available GWAS of SBP/DBP improved the genetic model PVE from 4.8% to 5.1% (SBP) and 4.7% to 5% (DBP) compared to using a single PRS. Adding additional 14 PRSs computed based on two independent GWASs further increased the genetic model PVE to 6.3% (SBP) and 5.7% (DBP). PVE differed across self-reported race/ethnicity groups, with primarily all non-White groups benefitting from the inclusion of additional PRSs.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A multi-ethnic polygenic risk score is associated with hypertension prevalence and progression throughout adulthood 96%
- JointPRS: A Data-Adaptive Framework for Multi-Population Genetic Risk Prediction Incorporating Genetic Correlation 94%
- The expected polygenic risk score (ePRS) framework: an equitable metric for quantifying polygenetic risk via modeling of ancestral makeup 94%
Similar papers in this journal
Similar papers in this journal
- Optimization of Multi-Ancestry Polygenic Risk Score Disease Prediction Models 95%
- Can machine learning improve risk prediction of incident hypertension? An internal method comparison and external validation of the Framingham risk model using HUNT Study data 94%
- Biobank-scale methods and projections for sparse polygenic prediction from machine learning 94%
Similar papers in this journal
- Joint Modeling of Effect Sizes for Two Correlated Traits: Characterizing Trait Properties to Enhance Polygenic Risk Prediction 95%
- Noise-augmented directional clustering of genetic association data identifies distinct mechanisms underlying obesity 94%
- Refining fine-mapping: effect sizes and regional heritability 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.