Early-onset Alzheimer disease clinical variants: multivariate analyses of cortical thickness

Abstract

Objective: To assess patterns of reduced cortical thickness in different clinically defined variants of early-onset Alzheimer disease (AD) and to explore the hypothesis that these variants span a phenotypic continuum rather than represent distinct subtypes.

Methods: The case-control study included 25 patients with posterior cortical atrophy (PCA), 15 patients with logopenic progressive aphasia (LPA), and 14 patients with early-onset typical amnestic AD (tAD), as well as 30 healthy control subjects. Cortical thickness was measured using FreeSurfer, and differences and commonalities in patterns of reduced cortical thickness were assessed between patient groups and controls. Given the difficulty of using mass-univariate statistics to test ideas of continuous variation, we use multivariate machine learning algorithms to visualize the spectrum of subjects and to assess separation of patient groups from control subjects and from each other.

Results: Although each patient group showed disease-specific reductions in cortical thickness compared with control subjects, common areas of cortical thinning were identified, mainly involving temporoparietal regions. Multivariate analyses permitted clear separation between control subjects and patients and moderate separation between patients with PCA and LPA, while patients with tAD were distributed along a continuum between these extremes. Significant classification performance could nevertheless be obtained when every pair of patient groups was compared directly.

Conclusions: Analyses of cortical thickness patterns support the hypothesis that different clinical presentations of AD represent points in a phenotypic spectrum of neuroanatomical variation. Machine learning shows promise for syndrome separation and for identifying common anatomic patterns across syndromes that may signify a common pathology, both aspects of interest for treatment trials.

Figure 1. Regional differences in cortical thickness between control subjects and subjects with (A) posterior cortical atrophy (PCA), (B) logopenic progressive aphasia (LPA), and (C) typical amnestic Alzheimer disease (tAD)

The color scale represents familywise error−corrected p values thresholded at 0.05. Red and yellow represent lower cortical thickness in the patient groups compared with control subjects (no regions had significantly greater cortical thickness; blue colors). (D) Intersection map showing conjunctions of reduced cortical thickness between subjects with PCA and control subjects, subjects with LPA and control subjects, and subjects with tAD and control subjects: (a) no reductions in cortical thickness; (b) reduced in PCA only; (c) reduced in LPA only; (d) reduced in tAD only; (e), reduced in any 2 patient groups; (f) reduced in all 3 patient groups, each compared with control subjects. A = anterior; P = posterior.

Figure 2. Two-dimensional visualizations of the distribution of subjects in terms of their high-dimensional cortical thickness profiles

(A) Multidimensional scaling (MDS), which tries to represent the distances between subjects' multivariate cortical thickness profiles from the high-dimensional space as accurately as possible in the low-dimensional visualization, in terms of minimum squared distance error. (B) t-distributed stochastic neighbor embedding (t-SNE), which optimizes a nonlinear function of the distances to better balance the representation of the overall structure of the data with the local neighborhood structure of clusters. Axes are arbitrary and have been rotated for visual agreement between MDS and t-SNE. LPA = logopenic progressive aphasia; PCA = posterior cortical atrophy; tAD = typical amnestic Alzheimer disease.

Figure 3. Supervised support vector machine (SVM) classification of control subjects and patients and of AD variant groups

(A) SVM trained to separate all 54 patients from control subjects, with patients subsequently relabeled into their separate groups. (B) Results from 3 separate SVM analyses, each trained to separate 1 patient group from another patient group. All SVMs used a kernel matrix derived from the distance matrix used in figure 2. Performance of each SVM is summarized by the area under the curve (AUC) of the receiver operating characteristic, with 95% confidence intervals in parentheses. LPA = logopenic progressive aphasia; PCA = posterior cortical atrophy; tAD = typical amnestic Alzheimer disease.