Grant: Project Grant

While everyone ages chronologically at the same rate, some individuals experience accelerated age-related biological changes. The application of machine learning algorithms to brain imaging data enables the calculation of the biological age of the brain (brain-age); individuals with accelerated aging have a higher brain-age than their chronological age. This application pioneers the study of Network-Based Brain Age Gap Estimation (brainAGE) that examines the rate of age-related changes within defined brain networks. The current application has three aims; (1) to enhance the precision of measuring brain-age by developing normative models of brain-age for each of the main brain networks; this model will be freely and publicly available to support research into the aging process across multiple conditions. (2) to demonstrate the usefulness of network-based brainAGE compared to global brainAGE measures for cognition and psychopathology across most of the human lifespan. (3) to provide a clinical example of how Network-brainAGE can advance our understanding of psychiatric disorders using psychosis as an exemplar.