Brain age gap, the difference between an individual's brain predicted age and their chronological age, is used as a biomarker of brain disease and aging. To date, although previous studies used structural magnetic resonance imaging (MRI) data to predict brain age, less work has used functional network connectivity (FNC) estimated from functional MRI to predict brain age and its association with Alzheimer's disease progression. This study used FNC estimated from 951 normal cognitive functions (NCF) individuals aged 42-95 years to train a support vector regression (SVR) to predict brain age. In the next step, we tested the trained model on two unseen datasets, including NCF and mild dementia (MD) subjects with similar age distribution (between 50-80 years old, N=70). The mean brain age gap for the NCF and MD groups was -2.25 and 2.08, respectively. We also found a significant difference between the brain age gap of NCF and MD groups. This piece of evidence introduces the brain age gap estimated from FNC as a biomarker of Alzheimer's disease progression.
Read full abstract