Fig. 2

Estimated rating scores of irregularity (A) and impairment (B) at T0 (first video) and T1 (last video) across all therapies, with points at the respective mean of the posterior distributions, and error bars showing the 95% credibility interval. Insets present the differences between the posteriors at both time points, with the red shaded areas designating the region between the upper 5% of the density mass and zero, with zero corresponding to no difference between the two time points