Brain-predicted age in Down syndrome is associated with beta amyloid deposition and cognitive decline

Abstract

Individuals with Down syndrome (DS) are more likely to experience earlier onset of multiple facets of physiological aging. This includes brain atrophy, beta amyloid deposition, cognitive decline, and Alzheimer's disease-factors indicative of brain aging. Here, we employed a machine learning approach, using structural neuroimaging data to predict age (i.e., brain-predicted age) in people with DS (N = 46) and typically developing controls (N = 30). Chronological age was then subtracted from brain-predicted age to generate a brain-predicted age difference (brain-PAD) score. DS participants also underwent [¹¹C]-PiB positron emission tomography (PET) scans to index the levels of cerebral beta amyloid deposition, and cognitive assessment. Mean brain-PAD in DS participants' was +2.49 years, significantly greater than controls (p < 0.001). The variability in brain-PAD was associated with the presence and the magnitude of PiB-binding and levels of cognitive performance. Our study indicates that DS is associated with premature structural brain aging, and that age-related alterations in brain structure are associated with individual differences in the rate of beta amyloid deposition and cognitive impairment.

Keywords: Amyloid PET; Brain aging; Cognitive decline; Down syndrome; MRI; Machine learning.

Fig. 1

Overview of the brain-predicted age analysis pipeline. Illustration of the methods used to generate brain-predicted ages. 3D T1-weighted MRI scans were segmented into gray matter (GM) and white matter (WM) before being normalized to common space using nonlinear image registration. Normalized GM and WM images were concatenated and converted into vectors for each participant. These vectors were then projected into an N × N similarity matrix based on vector dot-products. (A) Once in similarity matrix form, the training participants' data were used as predictors in a Gaussian Processes regression model with age as the outcome variable. (B) Model accuracy was assessed in a 10-fold cross-validation procedure, comparing brain-predicted age with original chronological age labels. (C) Model coefficients learned during training were then applied to the data from DS participants and controls to generate brain-predicted ages. (D) A metric to summarize the variation in brain-predicted age was defined; the brain-predicted age difference. Abbreviation: brain-PAD, brain-predicted age difference.

Fig. 2

Brain-predicted age in individuals with Down syndrome (DS) and controls. (A) Box plot of brain-PAD (years) according to group, showing DS participants (red box) and controls (blue box). Whiskers (i.e., bars) on the box plots represent the absolute range of data points for each group. (B) Scatterplot of age (x-axis) and brain-predicted age (y-axis) indicates DS participants (red circles) and controls (blue controls). Plotted are linear regression lines representing a linear fit of age regressed onto brain-predicted each, colored according to group (DS = red line, control = blue line). Abbreviation: brain-PAD, brain-predicted age difference. (For interpretation of the references to color in this figure legend, the reader is referred to the Web version of this article.)

Fig. 3

Brain-predicted age in individuals with Down syndrome (DS), according to [¹¹C]-PiB status. (A) Box plot of brain-PAD (years) according to [¹¹C]-PiB status in DS participants. PiB-positive (red box) and PiB-negative (white box). Whiskers (i.e., bars) on the box plots represent the absolute range of data points for each group. (B) Scatterplot of age (x-axis) and brain-predicted age (y-axis) indicate PiB-positive DS participants (filled red circles) and PiB-negative DS participants (open red circles). Plotted are linear regression lines representing a linear fit of age regressed onto brain-predicted each, colored according to group (PiB-positive = solid red line, PiB-negative = dashed red line). Abbreviations: [¹¹C]-PiB, [¹¹C]-Pittsburgh compound B; brain-PAD, brain-predicted age difference. (For interpretation of the references to color in this figure legend, the reader is referred to the Web version of this article.)

Fig. 4

Cambridge Cognitive Battery (CAMCOG) performance relates to brain-PAD, according to [11C]-PiB status. Scatterplot of CAMCOG score (x-axis) against brain-PAD (y-axis) in DS participants indicate PiB-positive individuals (filled red circles) and PiB-negative individuals (open red circles). Plotted are linear fit lines of CAMCOG score regressed onto brain-PAD for each group (PiB-positive: solid line; PiB-negative: dashed line), to illustrate the interaction between brain-PAD and PiB-status in predicting CAMCOG score. Abbreviations: [¹¹C]-PiB, [¹¹C]-Pittsburgh compound B; brain-PAD, brain-predicted age difference. (For interpretation of the references to color in this figure legend, the reader is referred to the Web version of this article.)