RESUMEN
INTRODUCTION: Traditional methods for assessing movement quality rely on subjective standardized scales and clinical expertise. This limitation creates challenges for assessing patients with spinocerebellar ataxia (SCA), in whom changes in mobility can be subtle and varied. We hypothesized that a machine learning analytic system might complement traditional clinician-rated measures of gait. Our objective was to use a video-based assessment of gait dispersion to compare the effects of troriluzole with placebo on gait quality in adults with SCA. METHODS: Participants with SCA underwent gait assessment in a phase 3, double-blind, placebo-controlled trial of troriluzole (NCT03701399). Videos were processed through a deep learning pose extraction algorithm, followed by the estimation of a novel gait stability measure, the Pose Dispersion Index, quantifying the frame-by-frame symmetry, balance, and stability during natural and tandem walk tasks. The effects of troriluzole treatment were assessed in mixed linear models, participant-level grouping, and treatment group-by-visit week interaction adjusted for age, sex, baseline modified Functional Scale for the Assessment and Rating of Ataxia (f-SARA), and time since diagnosis. RESULTS: From 218 randomized participants, 67 and 56 participants had interpretable videos of a tandem and natural walk attempt, respectively. At Week 48, individuals assigned to troriluzole exhibited significant (p = 0.010) improvement in tandem walk Pose Dispersion Index versus placebo {adjusted interaction coefficient: 0.584 [95% confidence interval (CI) 0.137 to 1.031]}. A similar, nonsignificant trend was observed in the natural walk assessment [coefficient: 1.198 (95% CI - 1.067 to 3.462)]. Further, lower baseline Pose Dispersion Index during the natural walk was significantly (p = 0.041) associated with a higher risk of subsequent falls [adjusted Poisson coefficient: - 0.356 [95% CI - 0.697 to - 0.014)]. CONCLUSION: Using this novel approach, troriluzole-treated subjects demonstrated improvement in gait as compared to placebo for the tandem walk. Machine learning applied to video-captured gait parameters can complement clinician-reported motor assessment in adults with SCA. The Pose Dispersion Index may enhance assessment in future research. TRIAL REGISTRATION-CLINICALTRIALS. GOV IDENTIFIER: NCT03701399.
RESUMEN
Recommendations in the UK suggest restricting treatment of Alzheimer's disease with cholinesterase inhibitors, on cost-effectiveness grounds, to patients with moderate cognitive decline. As the economic analyses that informed these recommendations have been the subject of debate, we sought to address the potential limitations of existing models and produce estimates of donepezil treatment cost effectiveness in the UK using the most recent available data and simulation techniques. A discrete-event simulation was developed that predicts progression of Alzheimer's disease through correlated changes in cognition, behavioural disturbance and function. Patient-level data from seven randomized, placebo-controlled donepezil trials and a 7-year follow-up registry provided the basis for modeling longitudinal outcomes. Individuals in the simulation were assigned unique demographic and clinical characteristics and then followed for 10 years, with severity of disease tracked on continuous scales. Patient mix and costs were developed from UK-specific literature. Analyses were run for severity subgroups to evaluate outcomes for sub-populations with disease of mild versus moderate severity from both a healthcare payer and societal perspective. All costs are reported in pound, year 2007 values, and all outcomes are discounted at 3.5% per annum. Over 10 years, treatment of all patients with mild to moderate disease reduces overall direct medical costs by an average of over pound2300 per patient. When unpaid caregiver time is also taken into consideration, savings increase to over pound4700 per patient. Compared with untreated patients, patients receiving donepezil experience a discounted gain in QALYs averaging 0.11, with their caregivers gaining, on average, 0.01 QALYs. For the subset of patients starting treatment with more severe disease, savings are more modest, averaging about pound1600 and pound3750 from healthcare and societal perspectives, respectively. In probabilistic sensitivity analyses, donepezil dominated no treatment between 57% and 62% of replications when only medical costs were considered, and between 74% and 79% of replications when indirect costs were included, with results more favourable for treatment initiation in the mild versus moderate severity stages of the disease. Although the simulation results are not definitive, they suggest that donepezil leads to health benefits and cost savings when used to treat mild to moderately severe Alzheimer's disease in the UK. They also indicate that both benefits and savings may be greatest when treatment is started while patients are still in the mild stages of Alzheimer's disease.
