In this study, we tested the capability of individualized prediction for mild cognitive impairment (MCI) by using the information of whole brain tract integrity produced by tract-based automatic analysis method. The information was trained to search the tract segments that could most accurately separate the MCI patients and healthy participants. The optimal tract segments were searched with the area under receiver operating characteristic curve of 0.76. These specific segments of white matter tracts could potentially serve as imaging biomarker for predicting patients with MCI.
This abstract and the presentation materials are available to members only; a login is required.