Posterior AD-type pathology: cognitive subtypes emerging from a cluster analysis

Abstract

Background: "Posterior shift" of the neuropathological changes of Alzheimer's disease (AD) produces a syndrome (posterior cortical atrophy) (PCA) dominated by high-level visual deficits.

Objective: To explore in patients with AD-type pathology whether a data-driven analysis (cluster analysis) based on neuropsychological findings resulted in the emergence of different subgroups of patients; in particular to find out whether it was possible to identify patients with visuospatial deficits consistent with the hypothesis that PCA is a "dorsal stream" syndrome or, rather, whether there were subgroups of patients with different types of impairment within the high-level visual domain.

Methods: 23 PCA and 16 DAT patients were studied. By a principal component analysis performed on a wide range of neuropsychological tasks, 15 variables were obtained that loaded onto five main factors (memory, language, perceptual, visuospatial, and calculation) which entered a hierarchical cluster analysis.

Results: Four clusters of cognitive impairment emerged: visuospatial/perceptual, memory, perceptual/calculation, and language. Only in the first cluster a visuospatial deficit clearly emerged. conclusions: AD pathology produces not only variants dominated by memory (DAT) and, to a lesser extent, visuospatial deficit (PCA), but also other distinct syndromic subtypes with disorders in visual perception and language which reflect a different vulnerability of specific functional networks.

Figure 1

The dendrogram generated by the cluster analysis. Each patient (N = 39) begins as single clusters and step-by-step the most similar clusters are progressively joined together resulting at the end of the process (in the right-most part of the figure) in a single cluster grouping all the patients. The distance along the x-axis represents a measure of similarity between the patients; the vertical red line represents the linkage chosen to select the clusters.

Figure 2

Plots (a)–(d) illustrate cluster 1–4. Mean factor scores and standard errors obtained by clusters, as a function of the factors extracted by the principal component analysis, are reported (M: memory, L: language, P: perceptual, VS: visuospatial/perceptual, C: calculation). High scores indicate lower performance. Each cluster number of patients and percentage of PCA are also reported.