Abstract
Decline of cognitive abilities with age is one of the main factors that impair quality of life. However, striking individual variability is observed in ageing: while some older adults may experience rapid cognitive decline, others retain cognitive capacities well into old age. Predicting individual cognitive health and understanding the underlying biological mechanisms are key challenges in neuroscience with high priority for health economies, given the translational potential for early diagnosis and intervention.
To understand the key factors that mediate cognitive health across the lifespan, we will use machine-learning algorithms and implement predictive models to estimate the critical factors that underlie cognitive health. We will incorporate demographic, physiological, cognitive and brain imaging data from healthy individuals across age groups (18-80) as well as early dementia patients (Mild Cognitive Impairment) as input features to machine learning algorithms that learn to solve a metric learning problem. We will extend our predictive models to compare metrics of interactive predictors across repeated measurements and track individual profiles over time. We will further train these models with data collected at a given age and test how well they predict cognitive capacity or decline as measured at a later age.
