Contributions of lifestyle, education, and cardiovascular risk factors to the brain age gap

Abstract

The brain age gap is the difference between chronological age and the age predicted from Magnetic Resonance Imaging (MRI) brain scans. We investigated the influence of life habits and cardio-metabolic factors on this gap. A convolutional neural network (CNN) was trained on structural MRI scans from dementia-free participants in the Rotterdam Study.

Scans were collected every 3–4 years from 2005 to 2016. 10,989 images from 5,167 participants (mean age: 64 years [range: 45–98], 54 % female) were used to train and evaluate the model. We run analysis of variance and linear mixed models to assess associations between brain age gap and smoking, sleep, alcohol consumption, education, and cardio-metabolic factors.

The brain age gap in participants who developed dementia was elevated relative to cognitively healthy individuals and showed a progressive increase throughout the study period.

We found that together, the examined factors explained no more than 21% of the variance in brain age gap. Smoking, alcohol consumption, and elevated glucose levels are significantly associated with an increased brain age gap, consistent with earlier studies linking these factors to brain atrophy and cognitive decline.