Real-life ankle submovements and computer mouse use reflect patient-reported function in adult ataxias

Abstract

Novel disease modifying therapies are being evaluated in spinocerebellar ataxias and multiple system atrophy. Clinician-performed disease rating scales are relatively insensitive for measuring disease change over time, resulting in large and long clinical trials. We tested the hypothesis that sensors worn continuously at home during natural behavior and a web-based computer mouse task performed at home could produce interpretable, meaningful, and reliable motor measures for potential use in clinical trials. Thirty-four individuals with degenerative ataxias (spinocerebellar ataxia types 1, 2, 3, and 6 and multiple system atrophy of the cerebellar type) and eight age-matched controls completed the cross-sectional study. Participants wore an ankle and wrist sensor continuously at-home for one week and completed the Hevelius computer mouse task eight times over four weeks. We examined properties of motor primitives called “submovements” derived from the continuous wearable sensors and properties of computer mouse clicks and trajectories in relationship to patient-reported measures of function (PROM-Ataxia) and ataxia rating scales (Scale for the Assessment and Rating of Ataxia and the Brief Ataxia Rating Scale). The test-retest reliability of digital measures and differences between ataxia and control participants were evaluated. Individuals with ataxia had smaller, slower, and less powerful ankle submovements during natural behavior at home. A composite measure based on ankle submovements strongly correlated with ataxia rating scale scores (Pearson’s r = 0.82-0.88), strongly correlated with self-reported function (r = 0.81), had high test-retest reliability (intraclass correlation coefficient = 0.95), and distinguished ataxia and control participants, including preataxic individuals (N=4) from controls. A composite measure based on computer mouse movements and clicks strongly correlated with ataxia rating scale total (r = 0.86-0.88) and arm scores (r = 0.65-0.75), correlated well with self-reported function (r = 0.72-0.73), and had high test-retest reliability (intraclass correlation coefficient = 0.99). These data indicate that interpretable, meaningful, and highly reliable motor measures can be obtained from continuous measurement of natural movement, particularly at the ankle location, and from computer mouse movements during a simple point-and-click task performed at home. This study supports the use of these two inexpensive and easy-to-use technologies in longitudinal natural history studies in spinocerebellar ataxias and multiple system atrophy of the cerebellar type and shows promise as potential motor outcome measures in interventional trials.

Consumer-grade wearables and machine learning sensitively capture disease progression in amyotrophic lateral sclerosis

“…In individuals with ataxia, wrist submovements during a point-to-point reaching task 31 and ankle submovements during a gait task 32 become smaller and slower with increasing ataxia severity. Similarly, during natural at-home behavior, ankle submovement distance, peak velocity, and peak acceleration are smaller in adults with spinocerebellar ataxias and multiple system atrophy compared to controls and become progressively smaller and less variable as selfreported function decreased and ataxia severity increase 21 . The submovement analysis approach contrasts with a prior analysis of task-free, at-home measurement in 42 individuals with ALS using waist-worn accelerometers, which quantified overall activity levels (e.g., activity count, percent of day active) 19 .…”

“…The analysis approach for quantifying motor function in ALS centered on extraction and characterization of motor primitives called submovements during natural behavior, which was previously developed for quantifying motor function in ataxia-telangiectasia 20 and adult cerebellar ataxias 21 . There is evidence that motor control is achieved by combining submovements to compose complex voluntary motor behaviors [24][25][26][27] and that submovements change in a consistent manner with the state of the motor system.…”

“…Gravity and high frequency noise were removed from the acceleration time-series using a sixth order Butterworth filter with cutoff frequencies of 0.1 and 20 Hz. 20,21,41,43 Several classes of features were extracted from daytime ankle and wrist sensor data as in prior work 20,21 . These included total power in the 0.1-5 Hz frequency range and features based on the distribution of activity intensity computed in 1-second time bins.…”

“…Here we demonstrate that a submovement-focused analysis of triaxial accelerometer data 20,21 , recorded from wrist and ankle sensors worn by hundreds of individuals with ALS at home during natural behavior, produces interpretable and robust measures of motor function and disease progression. We develop a machine learning approach to train a model that is sensitive to disease change by utilizing the information for how individuals' sensor-based movement patterns change over time, rather than being constrained by existing clinical assessments such as ALSFRS-R. We show that the model's severity estimates and longitudinal trajectories are reliable and consistent with ALSFRS-R, but are more sensitive than the clinical scale for measuring change over time.…”

“…Longitudinal analysis was conducted using data from participants with at least three data collection sessions spanning a minimum of 0.75 years (188 ALS and 6 control participants). Submovement, activity bout, activity index, and spectral movement features (85 total) were extracted from each session as previously described 20,21 (Figure 1C, Supplementary Table 1). Single feature analysis was performed on a subset of 24 key submovement (SM) features of interest.…”