Differentiating amyloid beta spread in autosomal dominant and sporadic Alzheimer's disease

Abstract

Amyloid-beta deposition is one of the hallmark pathologies in both sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease, the latter of which is caused by mutations in genes involved in amyloid-beta processing. Despite amyloid-beta deposition being a centrepiece to both sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease, some differences between these Alzheimer's disease subtypes have been observed with respect to the spatial pattern of amyloid-beta. Previous work has shown that the spatial pattern of amyloid-beta in individuals spanning the sporadic Alzheimer's disease spectrum can be reproduced with high accuracy using an epidemic spreading model which simulates the diffusion of amyloid-beta across neuronal connections and is constrained by individual rates of amyloid-beta production and clearance. However, it has not been investigated whether amyloid-beta deposition in the rarer autosomal-dominant Alzheimer's disease can be modelled in the same way, and if so, how congruent the spreading patterns of amyloid-beta across sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease are. We leverage the epidemic spreading model as a data-driven approach to probe individual-level variation in the spreading patterns of amyloid-beta across three different large-scale imaging datasets (2 sporadic Alzheimer's disease, 1 autosomal-dominant Alzheimer's disease). We applied the epidemic spreading model separately to the Alzheimer's Disease Neuroimaging initiative (n = 737), the Open Access Series of Imaging Studies (n = 510) and the Dominantly Inherited Alzheimer's Network (n = 249), the latter two of which were processed using an identical pipeline. We assessed inter- and intra-individual model performance in each dataset separately and further identified the most likely subject-specific epicentre of amyloid-beta spread. Using epicentres defined in previous work in sporadic Alzheimer's disease, the epidemic spreading model provided moderate prediction of the regional pattern of amyloid-beta deposition across all three datasets. We further find that, whilst the most likely epicentre for most amyloid-beta-positive subjects overlaps with the default mode network, 13% of autosomal-dominant Alzheimer's disease individuals were best characterized by a striatal origin of amyloid-beta spread. These subjects were also distinguished by being younger than autosomal-dominant Alzheimer's disease subjects with a default mode network amyloid-beta origin, despite having a similar estimated age of symptom onset. Together, our results suggest that most autosomal-dominant Alzheimer's disease patients express amyloid-beta spreading patterns similar to those of sporadic Alzheimer's disease, but that there may be a subset of autosomal-dominant Alzheimer's disease patients with a separate, striatal phenotype.

Keywords: Alzheimer’s disease; amyloid beta; brain networks; diffusion models.

Graphical Abstract

Figure 1

Comparison of global model fit across datasets and epicentres. ESM performance (global fit) across the ADNI, OASIS and DIAN datasets using either the (A) PC and caudal anterior cingulate or (B) caudate and putamen as epicentres. Each dot represents the observed and predicted mean signal for an ROI across all subjects within a dataset. Only amyloid-beta positive subjects were included.

Figure 2

Epicentre frequency and within-subject performance across all datasets. (A) Epicentre frequency across all subjects in each dataset. (B) The same information when only amyloid-beta positive subjects are included from each dataset and epicentre group, using only amyloid-beta positive subjects. (C) The ESM within-subject performance is shown using the CAC and posterior cingulate as epicentres. (D) The ESM within-subject performance is shown using the caudate and putamen as epicentres.

Figure 3

Demographic differences across epicentre subgroups in DIAN (only amyloid-beta positive individuals). (A) Within-subject amyloid-beta composite signal across the epicentre subgroups. (B) Comparison of whole-brain amyloid-beta signal across the epicentre sub-groups. Regions are colour-coded based on their t-value for the particular group, with red indicating that there is more amyloid-beta signal in the respective group compared with the other two groups. (C) Within-subject EYO and age differences across the epicentre subgroups were compared using a Mann–Whitney–Wilcoxon test. There were no significant differences for age whereas the DMN group was significantly older than the striatum and other group (DMN versus striatum: U = 1091, P = 0.003; DMN versus other: U = 2089, P = 0.005 two-tailed with Bonferoni correction).

Figure 4

Evaluating epicentre reliability across timepoints in DIAN. (A) Confusion matrix for epicentre subgroups at timepoint 1 (T1) versus timepoint 2 (T2). Values along the diagonal represent individuals who remain the same epicentre subgroup at visits 1 and 2. (B) Swarm plot representing composite amyloid-beta change in each T1/T2 epicentre subgroup combination.