logo
ResearchBunny Logo
Abstract
This paper proposes a machine learning-based approach using wearable sensor data to estimate clinical scores for upper-limb motor impairment and movement quality in stroke and traumatic brain injury (TBI) survivors. Strong agreement was found between sensor-based estimates and clinician-generated scores (R² = 0.86 for impairment severity, R² = 0.79 for movement quality). This approach enables continuous monitoring of patient response to rehabilitation, paving the way for patient-specific interventions to maximize motor recovery.
Publisher
npj Digital Medicine
Published On
Sep 21, 2020
Authors
Catherine Adans-Dester, Nicolas Hankov, Anne O’Brien, Gloria Vergara-Diaz, Randie Black-Schaffer, Ross Zafonte, Jennifer Dyer, Sunghoon L. Lee, Paolo Bonato
Tags
machine learning
wearable sensors
upper-limb motor impairment
movement quality
stroke
traumatic brain injury
rehabilitation

Related Publications

Explore these studies to deepen your understanding of the subject.

Using machine learning to understand social isolation and loneliness in schizophrenia, bipolar disorder, and the community
Psychology

Using machine learning to understand social isolation and loneliness in schizophrenia, bipolar disorder, and the community

S. J. Abplanalp, M. F. Green, et al.

Machine-learning algorithms for asthma, COPD, and lung cancer risk assessment using circulating microbial extracellular vesicle data and their application to assess dietary effects
Medicine and Health

Machine-learning algorithms for asthma, COPD, and lung cancer risk assessment using circulating microbial extracellular vesicle data and their application to assess dietary effects

A. Mcdowell, J. Kang, et al.

Exploring multiyear-to-decadal North Atlantic sea level predictability and prediction using machine learning
Earth Sciences

Exploring multiyear-to-decadal North Atlantic sea level predictability and prediction using machine learning

Q. Gu, L. Zhang, et al.

Using the interest theory of rights and Hohfeldian taxonomy to address a gap in machine learning methods for legal document analysis
Computer Science

Using the interest theory of rights and Hohfeldian taxonomy to address a gap in machine learning methods for legal document analysis

A. Izzidien

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny