Analysis of longitudinal diffusion-weighted images in healthy and pathological aging: An ADNI study

•Voxel-based morphometry is extended to analyze longitudinal images via a mixed-effects model.•This method is applied to distinguish healthy and pathological aging in the brain‘s white matter.•A parameter at the single subject level describes individual differences associated with aging.•A classifier discriminates patients with Alzheimer’s disease with a predictive power of 0.99.•This model provides a promising biomarker predicting the risk of conversion to Alzheimer’s disease.