Documentation
Description:
Data from three population cohorts were used to create a synthetic dataset (synth1.0) for system development, methods development and training purposes. The synthetic dataset does not contain any personally identifiable information.
Variables were selected to represent those typically used in dementia research and to cover survey, biomarker and imaging data modalities. Sixty-one variables were modelled, to these was added a unique participant identifier resulting in a dataset of 62 variables.
Variable distributions and covariance from the source cohorts were used to parameterise the model. Generated data were checked for range, distributions, and associations.
The generated dataset comprised 150,618 individuals.
Coverage
Spatial:
US
Follow Up:
Unknown
Provenance
Temporal
Accrual Periodicity:
Static
Start Date:
01 January 2026
Time Lag:
Not applicable
Accessibility
Access
Access Rights:
See dataset for details. Access data at:
Usage
Resource Creators:
Josh Bauermeister
Observations
Statistical Population
Population Description
Population Size
Measured Property
Observation Date
Persons
150618
Count
01 January 2026