Brain age is a predicted age based on brain imaging via machine learning. Brain age gap (BAG), the difference between the predicted biological age and the chronological age in a given individual, can be interpreted as delayed or accelerated development/aging. We will build machine learning models based on UK biobank dataset (combine with some other datasets, including IXI, ADHD-200, NCANDA, etc.) to predict biological age, calculate multi-modal BAGs, and then measure the interactive effect of genetic AD risk factors and family connectedness on BAG in both children and familiar elders. The central premise of the proposed project is that lifespan development effects of genetic risk factors for Alzheimer’s disease (AD) can be assessed with increased speed, rigor, and validity by enriching development (child) samples with a matched sample of biologically related familial elders. Our approach will provide key findings regarding the effects of genetic risk factors for AD in development and aging that would otherwise require decades of longitudinal monitoring of child participants.
