Longitudinal assessment of neuroimaging and clinical markers in autosomal dominant Alzheimer's disease: a prospective cohort study

Abstract

Background: The biomarker model of Alzheimer's disease postulates a dynamic sequence of amyloidosis, neurodegeneration, and cognitive decline as an individual progresses from preclinical Alzheimer's disease to dementia. Despite supportive evidence from cross-sectional studies, verification with long-term within-individual data is needed.

Methods: For this prospective cohort study, carriers of autosomal dominant Alzheimer's disease mutations (aged ≥21 years) were recruited from across the USA through referrals by physicians or from affected families. People with mutations in PSEN1, PSEN2, or APP were assessed at the University of Pittsburgh Alzheimer's Disease Research Center every 1-2 years, between March 23, 2003, and Aug 1, 2014. We measured global cerebral amyloid β (Aβ) load using (11)C-Pittsburgh Compound-B PET, posterior cortical metabolism with (18)F-fluorodeoxyglucose PET, hippocampal volume (age and sex corrected) with T1-weighted MRI, verbal memory with the ten-item Consortium to Establish a Registry for Alzheimer's Disease Word List Learning Delayed Recall Test, and general cognition with the Mini Mental State Examination. We estimated overall biomarker trajectories across estimated years from symptom onset using linear mixed models, and compared these estimates with cross-sectional data from cognitively normal control individuals (age 65-89 years) who were negative for amyloidosis, hypometabolism, and hippocampal atrophy. In the mutation carriers who had the longest follow-up, we examined the within-individual progression of amyloidosis, metabolism, hippocampal volume, and cognition to identify progressive within-individual changes (a significant change was defined as an increase or decrease of more than two Z scores standardised to controls).

Findings: 16 people with mutations in PSEN1, PSEN2, or APP, aged 28-56 years, completed between two and eight assessments (a total of 83 assessments) over 2-11 years. Significant differences in mutation carriers compared with controls (p<0·01) were detected in the following order: increased amyloidosis (7·5 years before expected onset), decreased metabolism (at time of expected onset), decreased hippocampal volume and verbal memory (7·5 years after expected onset), and decreased general cognition (10 years after expected onset). Among the seven participants with longest follow-up (seven or eight assessments spanning 6-11 years), three individuals had active amyloidosis without progressive neurodegeneration or cognitive decline, two amyloid-positive individuals showed progressive neurodegeneration and cognitive decline without further progressive amyloidosis, and two amyloid-positive individuals showed neither active amyloidosis nor progressive neurodegeneration or cognitive decline.

Interpretation: Our results support amyloidosis as the earliest component of the biomarker model in autosomal dominant Alzheimer's disease. Our within-individual examination suggests three sequential phases in the development of autosomal dominant Alzheimer's disease-active amyloidosis, a stable amyloid-positive period, and progressive neurodegeneration and cognitive decline-indicating that Aβ accumulation is largely complete before progressive neurodegeneration and cognitive decline occur. These findings offer supportive evidence for efforts to target early Aβ deposition for secondary prevention in individuals with autosomal dominant Alzheimer's disease.

Funding: National Institutes of Health and Howard Hughes Medical Institute.

Figure 1. Raw data and estimated group trajectories of neuroimaging and clinical markers

Raw data for each neuroimaging and clinical marker is plotted against EYO (top row). Each contiguous colored line represents longitudinal data from a single participant. Raw data is being presented without smoothing or jitter as all participants are aware of their mutation status. The estimated trajectory and 99% CI from the mixed models (blue line + blue shaded area) are plotted against EYO for each marker (bottom row). For the hippocampal W-score trajectories, open diamond markers were used to indicate measurements acquired on the 1·5T scanner. A regression correction function had been applied to these measurements to correct for scanner differences.

Figure 2. Longitudinal PiB SUVR images from a single participant across eight assessments

Transaxial PiB SUVR images from a single participant across eight longitudinal assessments, demonstrating increasing then plateauing PiB retention.

Figure 3. Comparison between ADAD and Stage-0 older controls

We compared the mixed model estimates for the neuroimaging and clinical markers in ADAD to cross-section data from “Stage-0” older controls who were selected to have normal PiB, FDG, age-corrected hippocampal W-score and cognition. Significant (p<0·01) increases in ADAD are indicated in red while significant decreases are indicated in blue.

Figure 4. Temporal evolution of relative abnormality in AD markers

The ADAD trajectories of Aβ deposition (Global-PiB), neurodegeneration (PC-FDG and hippocampal W-score) and cognition (MMSE scores) were transformed onto a zero to one abnormality scale based on the minimally and maximally abnormal values of each marker within the −15 EYO to +15 EYO period examined in our study. The trajectory for delayed word recall was not included due to the limited dynamic range of this measure leading to an early floor effect.

Figure 5. Within-individual trajectories of neuroimaging and clinical markers

Raw data for each marker was first converted to Z-scores by standardizing to cross-sectional data from the Stage-0 older controls. Each subplot (labeled with the participant’s unique Family ID) presents longitudinal values of Global-PiB, PC-FDG, hippocampal W-score, and MMSE score from a single individual over his/her entire study period. Each horizontal grid line denotes a span of 5 Z-score units. Colored asterisks denote the presence of progressive amyloidosis (increase of greater than two in Z-scores in Global-PiB over the longitudinal study period), and the presence of progressive neurodegeneration and cognitive decline (decrease of greater than two in Z-scores in PC-FDG, hippocampal W-score, or MMSE score, over the longitudinal study period). For the hippocampal W-score trajectories, open diamond markers were used to indicate measurements acquired on the 1·5T scanner. A regression correction function had been applied to these measurements to correct for scanner differences. The trajectory for delayed word recall was not included due to the limited dynamic range of this measure leading to an early floor effect.