Dynamic Causal Modeling of Preclinical Autosomal-Dominant Alzheimer's Disease

Abstract

Dynamic causal modeling (DCM) is a framework for making inferences about changes in brain connectivity using neuroimaging data. We fitted DCMs to high-density EEG data from subjects performing a semantic picture matching task. The subjects are carriers of the PSEN1 mutation, which leads to early onset Alzheimer's disease, but at the time of EEG acquisition in 1999, these subjects were cognitively unimpaired. We asked 1) what is the optimal model architecture for explaining the event-related potentials in this population, 2) which connections are different between this Presymptomatic Carrier (PreC) group and a Non-Carrier (NonC) group performing the same task, and 3) which network connections are predictive of subsequent Mini-Mental State Exam (MMSE) trajectories. We found 1) a model with hierarchical rather than lateral connections between hemispheres to be optimal, 2) that a pathway from right inferotemporal cortex (IT) to left medial temporal lobe (MTL) was preferentially activated by incongruent items for subjects in the PreC group but not the NonC group, and 3) that increased effective connectivity among left MTL, right IT, and right MTL was predictive of subsequent MMSE scores.

Keywords: Autosomal dominant; EEG; dynamic causal modeling; effective connectivity; multivariate.

Fig.1

Model Space. All models have 6 nodes comprising the regions left and right medial temporal lobe (LMTL, RMTL), left and right inferotemporal cortex (LIT, RIT), and left and right middle occipital gyrus (LMOG, RMOG). The models differ as to whether they have within-region congruency effects (top versus bottom row - within-region effects are depicted as self-connections in the top row), hierarchical and lateral connections between hemispheres (column 1), lateral connections between hemispheres (column 2), hierarchical connections between hemispheres (column 3) or no connections between hemispheres (column 4). All models receive input, u, to bilateral MOG.

Fig.2

Trajectories of Mini-Mental State Exam (MMSE) scores. MMSE trajectories during follow-up period for 4 subjects from the PreC group. The x-axis labels Year with 0 corresponding to 2000. The EEG data were acquired in 1999. Blue dots denote empirical MMSE scores and the red line indicates the trajectory estimated using a logistic decay model. The MY values above each plot correspond to MMSE-Years, computed as the integral under the curve. References to color relate to the online version of this article.

Fig.3

Congruency and correlation effects in the PreC group. The left panel illustrates that the RIT to LMTL pathway is strengthened for incongruent items (red arrow) whereas the RIT to RMTL pathway is weakened for incongruent items (dark blue arrow). The right panel illustrates the two connections that are significantly larger in the PreC than NonC groups and show a significant correlation with MMSE-Years (red arrows). References to color relate to the online version of this article.

Fig.4

Regressing MMSE-Years onto brain connectivity. Stronger activation of the Left MTL to Right IT pathway, ā, is associated with smaller MY values. A value of ā = 1 corresponds to the prior mean value. Here, the x-axis corresponds to pathway strength for congruent items. Adjusted MY is the MY score computed as the area under the MMSE trajectory curves (over the period 1999 to 2015) shown in Fig. 2 but adjusted for the effects of age and performance using multiple regression as described in Supplementary Material 5. The Left MTL to Right IT value is a parameter of a DCM fitted to EEG data acquired in 1999.