Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Oct 3;148(10):3623-3634.
doi: 10.1093/brain/awaf154.

At-home wearables and machine learning capture motor impairment and progression in adult ataxias

Rohin Manohar  1 , Faye X Yang  1 , Christopher D Stephen  1   2 , Jeremy D Schmahmann  1   2 , Nicole M Eklund  1   3 , Anoopum S Gupta  1   2
Affiliations

At-home wearables and machine learning capture motor impairment and progression in adult ataxias

Rohin Manohar et al. Brain. .

Abstract

A significant barrier to developing disease-modifying therapies for spinocerebellar ataxias (SCAs) and multiple system atrophy of the cerebellar type (MSA-C) is the scarcity of tools to measure disease progression sensitively in clinical trials. Wearable sensors worn continuously during natural behaviour at home have the potential to produce ecologically valid and precise measures of motor function by leveraging frequent and numerous high-resolution samples of behaviour. Here we test whether movement building block characteristics (i.e. submovements), obtained from the wrist and ankle during natural behaviour at home, can capture disease progression sensitively in SCAs and MSA-C, as recently shown in amyotrophic lateral sclerosis and ataxia telangiectasia. Remotely collected cross-sectional (n = 76) and longitudinal (n = 27) data were analysed from individuals with ataxia (SCAs 1, 2, 3 and 6, MSA-C) and controls. Machine learning models were trained to produce composite outcome measures based on submovement properties. Two models were trained on data from individuals with ataxia to estimate ataxia rating scale scores. Two additional models, previously trained entirely on longitudinal amyotrophic lateral sclerosis data to optimize sensitivity to change, were also evaluated. All composite outcomes from both wrist and ankle sensor data had moderate to strong correlations with ataxia rating scales and self-reported function, showed differences between ataxia and control groups with high effect size, and had high within-week reliability. The composite outcomes trained on longitudinal amyotrophic lateral sclerosis data most strongly captured disease progression over time. These data demonstrate that outcome measures based on accelerometers worn at home can capture the ataxia phenotype accurately and measure disease progression sensitively. This assessment approach is scalable and can be used in clinical or research settings with relatively low individual burden.

Keywords: digital biomarkers; machine learning; motor phenotyping; multiple system atrophy; spinocerebellar ataxia; wearable sensors.

PubMed Disclaimer

Conflict of interest statement

For the methods for extracting and characterizing sub-movements from wearable sensor data, a US national phase patent application (no. 18/719,106) titled 'System and method for clinical disorder assessment' was filed on 12 June 2024. The patent applicant is the General Hospital Corporation d/b/a Massachusetts General Hospital, and the inventor is Anoopum Gupta. A.S.G. has received research support from Biogen and Insmed. He has served as a paid consultant for Biogen, Insmed, Servier, Verge Genomics, OM1, Everyone Medicines, Quince Therapeutics, and Trace Neuroscience. C.D.S. has provided scientific advisory for SwanBio Therapeutics and Xenon Pharmaceuticals. His institution has received research funding from Sanofi-Genzyme for a study of video oculography in late-onset GM2 gangliosidosis. He has received financial support from Encora Therapeutics, SwanBio Therapeutics, Sanofi-Genzyme, Biogen, and Biohaven for the conduct of clinical trials. J.D.S. is the inventor of the PROM-Ataxia and Brief Ataxia Rating Scale, both of which are copyright protected by The General Hospital Corporation, and is the site PI for Biohaven Pharma NCT02960893 and NCT03701399. The remaining authors report no competing interests.

Update of

References

    1. Paulson HL, Shakkottai VG, Clark HB, Orr HT. Polyglutamine spinocerebellar ataxias—From genes to potential treatments. Nat Rev Neurosci. 2017;18:613–626. - PMC - PubMed
    1. Scoles DR, Meera P, Schneider MD, et al. Antisense oligonucleotide therapy for spinocerebellar ataxia type 2. Nature. 2017;544:362–366. - PMC - PubMed
    1. Scoles DR, Pulst SM. Oligonucleotide therapeutics in neurodegenerative diseases. RNA Biol. 2018;15:707–714. - PMC - PubMed
    1. Hauser S, Helm J, Kraft M, Korneck M, Hübener-Schmid J, Schöls L. Allele-specific targeting of mutant ataxin-3 by antisense oligonucleotides in SCA3-iPSC-derived neurons. Mol Ther Nucleic Acids. 2022;27:99–108. - PMC - PubMed
    1. Buur L, Wiedemann J, Larsen F, et al. Randomized phase I trial of the α-synuclein antibody Lu AF82422. Mov Disord. 2024;39:936–944. - PubMed

LinkOut - more resources