AbstractObjectiveIn vivo functional changes in white matter during the progression of Alzheimer’s disease (AD) have not been previously reported. Our objectives are to measure changes in white matter functional connectivity (FC) in an aging population undergoing cognitive decline as AD develops, to establish their relationship to neuropsychological scores of cognitive abilities, and to assess their performance as predictors of AD.MethodsAnalyses were conducted using resting state functional MRI (rsfMRI) and neuropsychological data from 383 ADNI participants, including 136 cognitive normal (CN) controls, 46 with significant memory concern, 83 with early mild cognitive impairment (MCI), 37 with MCI, 46 with late MCI, and 35 with AD dementia. We used novel analyses of whole brain rsfMRI data to derive FC metrics between white matter tracts and discrete cortical volumes, as well as FC metrics between different white matter tracts, and their relationship to 6 cognitive measures. We then implemented supervised machine learning on white matter FCs to classify the participants and evaluated the performance.ResultsSignificant decreases were found in white matter FCs with prominent, specific, regional deficits appearing in late MCI and AD dementia patients relative to CN. These changes significantly correlated with behavioral measurements of impairments in cognition and memory. The sensitivity and specificity for distinguishing AD dementia and CN using white matter FCs were 0.83 and 0.81 respectively.Conclusions and RelevanceThe white matter FC decreased in late MCI and AD dementia patients compared to CN participants, and the white matter FC correlates with cognitive measures. White matter FC based classification shows promise for differentiating AD patients from CN. It is suggested that white matter FC may be a novel imaging biomarker of AD progression.