Bouts MJRJ, et al. - In this investigation, researchers determined the generalizability of probability scores for MRI-based classification to detect mild cognitive impairment (MCI) in a general population on an individual basis. In order to determine the probability of classification, the Alzheimer's disease (AD), and mild- and moderate-AD detection model were developed via anatomical and diffusion measurements of MRI calculated from the clinical AD cohort and subsequently applied to a population-based cohort with 48 MCI and 617 normal aging individuals. Investigators did not find that the probability scores for multiparametric MRI-based classification were appropriate as an auxiliary tool for the accurate detection of MCI in the general population. They concluded that MRI-based algorithms that are effective in clinical cohorts might not straightforwardly translate to MCI detection.