A data-driven model of brain volume changes in progressive supranuclear palsy

Abstract

The most common clinical phenotype of progressive supranuclear palsy is Richardson syndrome, characterized by levodopa unresponsive symmetric parkinsonism, with a vertical supranuclear gaze palsy, early falls and cognitive impairment. There is currently no detailed understanding of the full sequence of disease pathophysiology in progressive supranuclear palsy. Determining the sequence of brain atrophy in progressive supranuclear palsy could provide important insights into the mechanisms of disease progression, as well as guide patient stratification and monitoring for clinical trials. We used a probabilistic event-based model applied to cross-sectional structural MRI scans in a large international cohort, to determine the sequence of brain atrophy in clinically diagnosed progressive supranuclear palsy Richardson syndrome. A total of 341 people with Richardson syndrome (of whom 255 had 12-month follow-up imaging) and 260 controls were included in the study. We used a combination of 12-month follow-up MRI scans, and a validated clinical rating score (progressive supranuclear palsy rating scale) to demonstrate the longitudinal consistency and utility of the event-based model's staging system. The event-based model estimated that the earliest atrophy occurs in the brainstem and subcortical regions followed by progression caudally into the superior cerebellar peduncle and deep cerebellar nuclei, and rostrally to the cortex. The sequence of cortical atrophy progresses in an anterior to posterior direction, beginning in the insula and then the frontal lobe before spreading to the temporal, parietal and finally the occipital lobe. This in vivo ordering accords with the post-mortem neuropathological staging of progressive supranuclear palsy and was robust under cross-validation. Using longitudinal information from 12-month follow-up scans, we demonstrate that subjects consistently move to later stages over this time interval, supporting the validity of the model. In addition, both clinical severity (progressive supranuclear palsy rating scale) and disease duration were significantly correlated with the predicted subject event-based model stage (P < 0.01). Our results provide new insights into the sequence of atrophy progression in progressive supranuclear palsy and offer potential utility to stratify people with this disease on entry into clinical trials based on disease stage, as well as track disease progression.

Keywords: biomarkers; disease progression; event-based model; machine learning; progressive supranuclear palsy.

Graphical Abstract

Figure 1

Sequence of atrophy progression in PSP-RS. (A) Regional volume biomarker positional variance diagram showing the sequence of atrophy progression in PSP-RS. (B) Re-estimation of positional variance after cross-validation of the maximum likelihood event sequence by bootstrap resampling (100 bootstraps). For (A) and (B), the vertical ordering on the y-axis (from top to bottom) shows the maximum likelihood sequence estimated by the EBM (earliest to latest event). The bottom x-axis shows EBM stage while the top x-axis represents the percentage of regions atrophic (abnormal) at each stage. Colour intensity of the squares represents the posterior confidence in each biomarker’s position in the sequence, from either (A) MCMC samples of the posterior or (B) bootstrapping. SCP, superior cerebellar peduncle; ventral DC, ventral diencephalon. Note that because these volumes are covariate-adjusted the control distribution will be centred at zero. (C) Graphic representation of the event sequence with relevant region transitioning from healthy (grey) to unhealthy (coloured). Dark red denotes first regions to atrophy, light yellow denotes last regions to atrophy. Created with BioRender.com.

Figure 2

Histogram of event-based model staging results for PSP-RS. Healthy controls in blue and PSP-RS cases in orange. Each bar represents the proportion of patients in each category at each EBM stage. Each EBM stage on x-axis represents the occurrence of a new biomarker transition event. Stage 0 corresponds to no events having occurred and Stage 19 corresponds to all events having occurred. Events are ordered by the maximum likelihood sequence for the whole PSP-RS population as shown in Fig. 1A.

Figure 3

Longitudinal consistency of baseline EBM. Scatter plot showing predicted stage at baseline (x-axis) versus predicted stage at 12 months (y-axis) for those PSP-RS subjects with a follow-up scan (n = 255). The area of a circle is weighted by the number of subjects at each point.

Figure 4

Association between predicted EBM stage, PSP rating scale score and disease duration. (A) PSP rating scale score versus EBM stage* (β = 1.46, 95% CI: 1.2–1.8, P < 0.001, conditional R² of 0.56 (marginal 0.22) (B) Disease duration (years) versus EBM stage** (β = 0.29, 95% CI: 0.24–0.34, P < 0.001 and a conditional R² of 0.68 (marginal 0.41). For both (A) and (B), the line represents the linear fixed effect model fit to all subjects, and 95% CIs. Subject Id was modelled as a random effect (random intercept) due to some subjects having two MRI scans at different time points. Significance was calculated using Satterthwaite’s method to estimate degrees of freedom and generate P-values. * 473 scans (241 baseline and 232 12-month follow-up) with PSP-RS score. ** 130 scans (87 baseline and 43 12-month follow-up) with disease duration.