Clinical subgroup-stratified plasma proteomic signatures improve risk prediction for myocardial infarction: SCORE2-Pro
Authors' conclusion
By adopting a clinical subgroup stratification approach using factors derived from SCORE2, we identified subgroup-specific proteomic signatures for MI that considerably improve predictive accuracy and reclassification beyond traditional clinical models.
Study context
- Population
- UK Biobank participants aged 40–69 years without myocardial infarction (MI) at baseline; 54.9% female70% development, 30% validation
- Participants
- 51,010 participants
- Comparison
- SCORE2-Pro vs clinical model
- Outcome
- Prediction of MI
Methodological detailsclinical subgroup-stratified, internal hold-out validation, light gradient boosting machine classifiers, Cox proportional hazards models
- Clinical subgroup-stratified
- Internal hold-out validation
- Light gradient boosting machine classifiers
- Cox proportional hazards models
Performance
As reported in the abstract
MI prediction vs clinical model, by subgroup
AUC improvement (females, 9-protein model)
+ 0.061
P = 1.51 × 10-3
Between SCORE2-Pro and Clinical model
Net reclassification index (NRI) (females, 9-protein model)
+ 0.125
P = 2.69 × 10-6
Between SCORE2-Pro and Clinical model
NRI (high-risk populations)
+ 0.121
P = 0.020
SCORE2-Pro vs Clinical model
- 7-protein model, middle-aged subpopulation: AUC improvement (P = 0.033)
- + 0.036
- 7-protein model, middle-aged subpopulation: NRI (P = 8.09 × 10-11)
- + 0.127
Original publication
Clinical subgroup-stratified plasma proteomic signatures improve risk prediction for myocardial infarction: SCORE2-Pro. Cardiovasc Diabetol. Published 2 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →