Hematologic biomarkers of aging (HemeAge) and cardiovascular risk: a machine learning analysis in two cohorts
Standard blood count data combined with machine learning can now flag cardiovascular risk without extra testing, making risk assessment faster and more accessible.
This study develops and validates a machine learning model (HemeAge) that extracts aging signals from standard complete blood count data to predict cardiovascular risk, validated across two independent cohorts. The findings directly support the clinical utility of ML on routine CBC parameters for cardiovascular risk stratification, requiring no additional testing.
What the study was
- Study design
- Machine learning analysis; two-cohort validation
- Population
- General adult population in two independent cohorts
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- American Journal of Preventive Cardiology
Why it surfaced
Two-cohort ML validation of CBC-derived aging biomarkers for CVD risk is immediately translatable to clinical practice; novel application of routine CBC data with dual watchlist relevance.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.