Background and objectives: Cognitive deficits in MS are common, also early in the disease course. We aimed to identify if estimated brain age from MRI could serve as an imaging marker for early cognitive symptoms in a longitudinal MS study.Methods: A group of 76 MS patients (mean age 34 years, 71% females, 96% relapsingremitting) was examined 1, 2 and 5 years after diagnosis. A machine-learning model using Freesurfer-processed T1-weighted brain MRI data from 3208 healthy controls, was applied to develop a prediction model for brain age. The difference between estimated and chronological brain age was calculated (brain age gap). Tests of memory, attention and executive functions were performed. Associations between brain age gap and cognitive performance were assessed using linear mixed effects (LME) models and corrected for multiple testing.Results: LME models revealed a significant association between the Color Naming condition of Color-Word Interference Test and brain age gap (t=2.84, p=0.005). Conclusions:In this study, decreased information processing speed correlated with increased brain age gap. Our findings suggest that brain age estimation using MRI provides a useful semi-automated approach applying machine learning for individual level brain phenotyping and correlates with information processing speed in the early course of MS. and Oslo University hospital, especially Marte Wendel-Haga for her contribution at time point 2. We also thank the research assistants Kristin Liltved Grønsberg, May-Britt Gjengstø Utheim, Julia Timofeeva, Hedda Maurud and Siren Tønnessen who all contributed in the cognitive testing of the patients.