Automated Video-Based Characterization of Movement Quality in a Phase III Clinical Trial of Troriluzole in Subjects with Spinocerebellar Ataxia



Poster Number: M275


Michele Potashman, M.S., PhD, Biohaven, Evangelos Oikonomou, MD, DPhil, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Ha, Rohan Khera, MD, MS, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Ha, Melissa Beiner, MD, Biohaven Pharmaceuticals, Inc., Vlad Coric, MD, Biohaven Pharmaceuticals, Inc., New Haven, CT, USA, Jeremy D Schmahmann, MD, Ataxia Center, Laboratory for Neuroanatomy and Cerebellar Neurobiology, Department of Neurology, MGH, Susan Perlman, MD, University of California, Los Angeles, Gil L'italien, PhD, Biohaven

Background: Traditional methods for assessing disease progression use structured scales with fixed rating options that can limit assessment of patients with spinocerebellar ataxia (SCA), as changes in mobility can be subtle and varied. We hypothesized that a machine learning analytic system may provide a novel perspective, complementing traditional clinician-rated measures.

Objective: To examine the effects of troriluzole versus placebo on gait quality through video-based assessment of gait dispersion among subjects with SCA.

Methods: This study analyzed videos from participants with SCA who underwent gait assessment in a phase III double-blind placebo-controlled trial of troriluzole (NCT03701399). Videos were analyzed using a deep neural network architecture that tracked coordinates of key body parts and was used to define interpretable kinematic features of dynamic pose dispersion, through the integrated Pose Dispersion Index (PDI) that tracks symmetry, balance, and stability during normal and tandem walk tasks. The effects of troriluzole on PDI were assessed in mixed linear models using fixed effects, subject-level grouping, and ‘treatment group’-by-‘visit week’ interaction, adjusted for age, sex, baseline f-SARA, and time since diagnosis.

Results: From 218 randomized subjects, 67 and 56 subjects had interpretable videos of a tandem and normal walk attempt, respectively. Over 48-weeks, individuals assigned to troriluzole exhibited significant improvement in tandem walk versus placebo (adj. interaction coefficient: 0.58 (95% CI: 0.14 to 1.03)). A similar but not statistically significant trend was observed in the normal walk assessment (coef. 1.20 (95%CI: -1.07 to 3.46)). Lower baseline PDI during normal walk was associated with a higher risk of subsequent falls (adj. Poisson coef. -0.36 [95% CI -0.70 to -0.01]).

Conclusions: Machine learning applied to video-captured gait parameters introduces an alternative quantitative approach to motor assessment in cerebellar ataxia. The pose dispersion metrics show that troriluzole-treated individuals with SCA improved in cerebellar motor function compared to controls.