Ontology highlight
ABSTRACT: Background
Cardiometabolic risk factors - including diabetes, hypertension, and obesity - have long been linked with adverse health outcomes such as strokes, but more subtle brain changes in regional brain volumes and cortical thickness associated with these risk factors are less understood. Computer models can now be used to estimate brain age based on structural magnetic resonance imaging data, and subtle brain changes related to cardiometabolic risk factors may manifest as an older-appearing brain in prediction models; thus, we sought to investigate the relationship between cardiometabolic risk factors and machine learning-predicted brain age.Methods
We performed a systematic search of PubMed and Scopus. We used the brain age gap, which represents the difference between
SUBMITTER: Selitser M
PROVIDER: S-EPMC11908789 | biostudies-literature | 2025 Mar-Apr
REPOSITORIES: biostudies-literature