Grey matter volume and CSF biomarkers predict neuropsychological subtypes of MCI

We demonstrated that mild cognitive impairment (MCI) participants of the ADNI database (N=640)can be discriminated into 3 coherent and neuropsychologically-defined subgroups. Our clusteringapproach revealed an amnestic MCI, a mixed MCI and a false positive subgroup. Furthermore, weinvestigated the neurobiological foundation of these automatically extracted MCI subgroups.Classification modelling exposed that specific predictive features can be used to differentiateamnestic and mixed MCI from healthy controls: CSF Aβ1-42 concentration for the former and CSF Aβ1-42concentration, tau concentration as well as cortical atrophies (especially in the temporal and occipitallobes) for the latter. In contrast, false positive participants exhibited an identical profile to healthyparticipants in terms of cognitive performance, brain structure and CSF biomarker levels. Ourcomprehensive data-analytics strategy provide further evidence that multimodal neuropsychologicalsubtyping is both clinically and neurobiologically meaningful