Data-driven models of dominantly-inherited Alzheimer's disease progression

Abstract

See Li and Donohue (doi:10.1093/brain/awy089) for a scientific commentary on this article.Dominantly-inherited Alzheimer's disease is widely hoped to hold the key to developing interventions for sporadic late onset Alzheimer's disease. We use emerging techniques in generative data-driven disease progression modelling to characterize dominantly-inherited Alzheimer's disease progression with unprecedented resolution, and without relying upon familial estimates of years until symptom onset. We retrospectively analysed biomarker data from the sixth data freeze of the Dominantly Inherited Alzheimer Network observational study, including measures of amyloid proteins and neurofibrillary tangles in the brain, regional brain volumes and cortical thicknesses, brain glucose hypometabolism, and cognitive performance from the Mini-Mental State Examination (all adjusted for age, years of education, sex, and head size, as appropriate). Data included 338 participants with known mutation status (211 mutation carriers in three subtypes: 163 PSEN1, 17 PSEN2, and 31 APP) and a baseline visit (age 19-66; up to four visits each, 1.1 ± 1.9 years in duration; spanning 30 years before, to 21 years after, parental age of symptom onset). We used an event-based model to estimate sequences of biomarker changes from baseline data across disease subtypes (mutation groups), and a differential equation model to estimate biomarker trajectories from longitudinal data (up to 66 mutation carriers, all subtypes combined). The two models concur that biomarker abnormality proceeds as follows: amyloid deposition in cortical then subcortical regions (∼24 ± 11 years before onset); phosphorylated tau (17 ± 8 years), tau and amyloid-β changes in cerebrospinal fluid; neurodegeneration first in the putamen and nucleus accumbens (up to 6 ± 2 years); then cognitive decline (7 ± 6 years), cerebral hypometabolism (4 ± 4 years), and further regional neurodegeneration. Our models predicted symptom onset more accurately than predictions that used familial estimates: root mean squared error of 1.35 years versus 5.54 years. The models reveal hidden detail on dominantly-inherited Alzheimer's disease progression, as well as providing data-driven systems for fine-grained patient staging and prediction of symptom onset with great potential utility in clinical trials.

Figure 1

Event-based model of dominantly-inherited Alzheimer’s disease progression. Positional variance diagrams. Left: Event-based model estimated on all mutation carriers in the DIAN dataset. Right: Cross-validation through bootstrapping. The vertical ordering (top to bottom) is given by the maximum likelihood sequence estimated by the model. Greyscale intensity represents posterior confidence in each event’s position (each row), from Markov chain Monte Carlo samples of the posterior (left) or from bootstrapping (right). AB = amyloid-β; Postcng = posterior cingulate; ptau = phosphorylated tau.

Figure 2

Event-based models of dominantly-inherited Alzheimer’s disease: APOE ɛ4 groups. Data-driven sequences of biomarker abnormality shown as positional variance diagrams for mutation carriers in the DIAN dataset who are: (A) APOE ɛ4-positive (n = 61); (B) APOE ɛ4-negative (n = 150). C.f.Fig. 1 (all groups combined): similar ordering, with a notable difference: APOE ɛ4-positive participants showed earlier CSF amyloid-β₄₂ abnormality. AB = amyloid-β; Postcng = posterior cingulate; ptau = phosphorylated tau.

Figure 3

Event-based model staging results for dominantly-inherited Alzheimer’s disease. (A) Staging by diagnostic group: all non-carriers are at stage zero (black), and advancing disease stage is correlated strongly with cognitive impairment (green to blue to red). (B) Staging consistency across visits within 3 years of baseline for the n = 30 participants having complete longitudinal data (18 mutation carriers; 16 PSEN1, two APP). Most participants advance to a later stage (disease progresses towards the right). The green circle shows the single participant (a PSEN1 mutation carrier) who regressed from event-based model stage 9 to stage 1, which arose due to discordant amyloid measurements between CSF and PiB-PET at baseline. The blue triangle indicates clinical progression from cognitively normal to MCI. AD = probable dementia due to dominantly-inherited Alzheimer's disease (global CDR > 0.5); BL = baseline; CN = cognitively normal (global CDR = 0); M = month; MCI = very mild dementia consistent with mild cognitive impairment (global CDR = 0.5).

Figure 4

Differential equation models: dominantly-inherited Alzheimer’s disease biomarker trajectories. Shown are fits for selected biomarkers (see ‘Models’ section). Fits for other biomarkers are provided in the Supplementary material. Heavy black dashed lines show the average trajectory, with grey lines showing trajectories sampled from the posterior distribution. Time is expressed relative to the median biomarker value (red line) for symptomatic mutation carriers in the DIAN dataset (first visit with a non-zero CDR score), so that negative time suggests the average presymptomatic phase of dominantly-inherited Alzheimer’s disease. Box plots show biomarker distributions for asymptomatic (green, left, canonical normal) and symptomatic (red, right, canonical abnormal) mutation carriers (denoted aMC and sMC, respectively), with the distribution for estimated time between canonical normal and canonical abnormal (abnormality transition time) shown in blue. Details of included participants are given in Table 1. For comparison, the magenta fits in B–E are those from the linear mixed models of baseline DIAN data against estimated year of onset (EYO) from Bateman et al. (2012). SUVR = standardized uptake value ratio (relative to the cerebellum); p-tau = phosphorylated tau.

Figure 5

Differential equation models: selected data-driven sigmoids for dominantly-inherited Alzheimer’s disease biomarker progression. Cumulative probability of abnormality (vertical axis) is the empirical distribution of the abnormality transition time in years prior to canonical abnormality (horizontal axis) as per Fig. 4, calculated from each biomarker trajectory in Fig. 4. The horizontal axis shows years prior to canonical abnormality. The order of biomarkers in the legend follows the order in which they reach a cumulative probability of abnormality of 0.5 (horizontal dotted grey line). Green–blue–yellow colour scale (viridis) with alternating solid/dashed lines in order of cumulative abnormality probability reaching 0.5 (legend). p-tau = phosphorylated tau.

Figure 6

Predicting onset of clinical symptoms. For the six DIAN participants for whom global CDR became non-zero during the study (as of Data Freeze 6): (A) Estimated versus actual years to onset at baseline using our model-based approach and using familial age of onset (EYO) and mutation type age of onset (Mutation EYO). Mutation EYO is calculated from the average age of onset within the three mutation types, using data from Table e-1 in Ryman et al. (2014), with the average weighted by the number of affected individuals per mutation. The light grey line shows perfect correlation as a reference and participants’ data points are connected by dotted grey vertical lines. Our model-derived ETO (red asterisks and dashed line fit) correlates with actual years to onset better than familial EYO (blue triangles and solid line fits), as shown by the adjusted coefficient of determination (R²). The green circle highlights an individual for whom our approach (ETO) is superior to the traditional approach (EYO) for predicting years to onset. (B) Quartile boxplots of the error in predicting onset using each estimate: ETO (left) has a superior root-mean-squared error (RMSE) to both EYO (middle) and Mutation EYO (right), and predicts symptom onset to occur sooner rather than later, which is likely to be more accurate due to interval censoring (symptom onset occurring between visits to the clinic). ETO = estimated time from onset; EYO = estimated years from onset; RMSE = root mean squared error.

Figure 7

Summary: data-driven models of dominantly-inherited Alzheimer’s disease progression. (A) Event-based model for all mutation carriers in the DIAN, from Fig. 1. Biomarkers (imaging, molecular, cognitive) along the vertical axis are ordered by the maximum likelihood disease progression sequence (from top to bottom). The horizontal axis shows variance in the posterior sequence sampled using Markov chain Monte Carlo, with positional likelihood given by greyscale intensity. (B) Differential equation models. Each model-estimated biomarker trajectory (Fig. 4 and Supplementary Figs 5–7) estimates a probabilistic Abnormality Transition Time (years from canonical normal to canonical abnormal) and corresponding cumulative/empirical probability of abnormality (Fig. 5). Biomarkers along the vertical axis are ordered by the estimated sequence in which they reach 50% cumulative probability of abnormality (black asterisks). The viridis colour scale shows cumulative probability of abnormality increasing from the left (normal, yellow) to the right (abnormal, blue) as a function of years prior to canonical abnormality. White horizontal bars show the interquartile range of the abnormality transition time density, which visualizes the rate and duration of biomarker progression. p-tau = phosphorylated tau.