Skip to main content

Table 3 Feature weights resulting from multivariate logistic regression

From: Highly elevated polygenic risk scores are better predictors of myocardial infarction risk early in life than later

Feature Weight (IHD Score) Weight (MI Score) Weight (early MI Score)
FDR202 0.09 ± 0.01 0.14 ± 0.00 0.24 ± 0.01
GRS46K 0.16 ± 0.00 0.23 ± 0.00 0.24 ± 0.02
1.7M 0.12 ± 0.00 0.17 ± 0.00 0.44 ± 0.01
6M 1.83 ± 0.02 1.85 ± 0.02 0.23 ± 0.01
Diabetes type 2 1.00 ± 0.01 0.80 ± 0.01 1.10 ± 0.05
Family History of Heart Disease 1.01 ± 0.00 0.98 ± 0.01 1.54 ± 0.04
Sex 0.65 ± 0.00 1.02 ± 0.01 1.46 ± 0.04
Birth year − 0.78 ± 0.00 − 0.79 ± 0.00 1.22 ± 0.02
Systolic blood pressure − 0.03 ± 0.00 − 0.07 ± 0.00 − 0.37 ± 0.01
BMI 0.23 ± 0.00 0.19 ± 0.00 0.36 ± 0.02
Cholesterol − 0.34 ± 0.01 − 0.39 ± 0.00 − 0.84 ± 0.02
Triglycerides 0.18 ± 0.00 0.19 ± 0.00 0.32 ± 0.01
LDL 0.17 ± 0.01 0.27 ± 0.02 − 0.77 ± 0.07
Smoking status 0.34 ± 0.00 0.45 ± 0.00 0.57 ± 0.02
PC1 0.17 ± 0.00 0.05 ± 0.04 − 0.09 ± 0.48
PC2 0.16 ± 0.02 0.16 ± 0.04 − 0.39 ± 0.30
PC3 0.01 ± 0.00 0.02 ± 0.00 0.05 ± 0.01
PC4 0.00 ± 0.00 0.01 ± 0.00 0.02 ± 0.01
  1. Feature weights from training the 14-feature logistic regression algorithm, with 95% confidence intervals from 10-fold cross-validation