Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls

►MRI combined with multivariate analysis accurately classifies AD patients from controls. ►A sensitivity of 90% and a specificity of 94% was achieved. ►Global and regional MRI measures in combination gave the best predictive accuracy. ►The model shows potential in predicting conversion from MCI to AD. ►Our approach may allow disease related atrophy patterns to be obtained.