ClinicalAge, a framework for modelling ageing trajectories from longitudinal electronic health records in the UK: a model development and validation study
Routine medical records can be used to measure biological aging and predict functional decline and disease risk, helping identify people who need closer monitoring.
A transformer model converted routine longitudinal health records into an interpretable measure of biological ageing. Across more than five million people, the measure was associated with functional decline, ageing-related diseases, and all-cause mortality.
What the study was
- Study design
- Model development and external validation study using longitudinal electronic health records
- Population
- UK Biobank and UK primary-care populations
- Sample size
- 5,049,267 across development and validation cohorts
- Category
- Public Health
- Maturity
- Validated
- Journal
- The Lancet. Digital health
Why it surfaced
Exceptional external-validation scale and broad clinical relevance justify high priority despite the observational design.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.