Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion

Nathaniel T. Pickle, Staci M. Shearin, Nicholas Fey

Research output: Contribution to journalArticle

Abstract

Background: Clinical balance assessments often rely on functional tasks as a proxy for balance (e.g., Timed Up and Go). In contrast, analyses of balance in research settings incorporate quantitative biomechanical measurements (e.g., whole-body angular momentum, H) using motion capture techniques. Fully instrumenting patients in the clinic is not feasible, and thus it is desirable to estimate biomechanical quantities related to balance from measurements taken from a subset of the body segments. Machine learning algorithms are well-suited for this type of low- to high-dimensional mapping. Thus, our goal was to develop and test an artificial neural network that to predict segment contributions to whole-body angular momentum from linear acceleration and angular velocity signals (i.e., those typically available to wearable inertial measurement units, IMUs) taken from a sparse set of body segments. Methods: Optical motion capture data were collected from five able-bodied individuals and five individuals with Parkinson's disease (PD) walking on a non-steady-state locomotor circuit comprising stairs, ramps and changes of direction. Motion data were used to calculate angular momentum (i.e., "gold standard" output data) and body-segment linear acceleration and angular velocity data from local reference frames at the wrists, ankles and neck (i.e., network input). A dynamic nonlinear autoregressive neural network was trained using the able-bodied data (pooled across subjects). The neural network was tested on data from individuals with PD with noise added to simulate real-world IMU data. Results: Correlation coefficients of the predicted segment contributions to whole-body angular momentum with the gold standard data were 0.989 for able-bodied individuals and 0.987 for individuals with PD. Mean RMS errors were between 2 and 7% peak signal magnitude for all body segments during completion of the locomotor circuits. Conclusion: Our results suggest that estimating segment contributions to angular momentum from mechanical signals (linear acceleration, angular velocity) from a sparse set of body segments is a feasible method for assessing coordination of balance - even using a network trained on able-bodied data to assess individuals with neurological disease. These targeted estimates of segmental momenta could potentially be delivered to clinicians using a sparse sensor set (and likely in real-time) in order to enhance balance rehabilitation of people with PD.

Original languageEnglish (US)
Article number88
JournalJournal of NeuroEngineering and Rehabilitation
Volume16
Issue number1
DOIs
StatePublished - Jul 12 2019

Fingerprint

Locomotion
Parkinson Disease
Architectural Accessibility
Nonlinear Dynamics
Proxy
Wrist
Ankle
Walking
Noise
Neck
Rehabilitation
Research

Keywords

  • Balance
  • Biomechanics
  • Gait
  • Machine learning
  • Parkinson's disease
  • Rehabilitation
  • Sparse sensing
  • Wearable sensing

ASJC Scopus subject areas

  • Rehabilitation
  • Health Informatics

Cite this

@article{9ca32f9129f14830b1618cf766e920b7,
title = "Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion",
abstract = "Background: Clinical balance assessments often rely on functional tasks as a proxy for balance (e.g., Timed Up and Go). In contrast, analyses of balance in research settings incorporate quantitative biomechanical measurements (e.g., whole-body angular momentum, H) using motion capture techniques. Fully instrumenting patients in the clinic is not feasible, and thus it is desirable to estimate biomechanical quantities related to balance from measurements taken from a subset of the body segments. Machine learning algorithms are well-suited for this type of low- to high-dimensional mapping. Thus, our goal was to develop and test an artificial neural network that to predict segment contributions to whole-body angular momentum from linear acceleration and angular velocity signals (i.e., those typically available to wearable inertial measurement units, IMUs) taken from a sparse set of body segments. Methods: Optical motion capture data were collected from five able-bodied individuals and five individuals with Parkinson's disease (PD) walking on a non-steady-state locomotor circuit comprising stairs, ramps and changes of direction. Motion data were used to calculate angular momentum (i.e., {"}gold standard{"} output data) and body-segment linear acceleration and angular velocity data from local reference frames at the wrists, ankles and neck (i.e., network input). A dynamic nonlinear autoregressive neural network was trained using the able-bodied data (pooled across subjects). The neural network was tested on data from individuals with PD with noise added to simulate real-world IMU data. Results: Correlation coefficients of the predicted segment contributions to whole-body angular momentum with the gold standard data were 0.989 for able-bodied individuals and 0.987 for individuals with PD. Mean RMS errors were between 2 and 7{\%} peak signal magnitude for all body segments during completion of the locomotor circuits. Conclusion: Our results suggest that estimating segment contributions to angular momentum from mechanical signals (linear acceleration, angular velocity) from a sparse set of body segments is a feasible method for assessing coordination of balance - even using a network trained on able-bodied data to assess individuals with neurological disease. These targeted estimates of segmental momenta could potentially be delivered to clinicians using a sparse sensor set (and likely in real-time) in order to enhance balance rehabilitation of people with PD.",
keywords = "Balance, Biomechanics, Gait, Machine learning, Parkinson's disease, Rehabilitation, Sparse sensing, Wearable sensing",
author = "Pickle, {Nathaniel T.} and Shearin, {Staci M.} and Nicholas Fey",
year = "2019",
month = "7",
day = "12",
doi = "10.1186/s12984-019-0550-8",
language = "English (US)",
volume = "16",
journal = "Journal of NeuroEngineering and Rehabilitation",
issn = "1743-0003",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion

AU - Pickle, Nathaniel T.

AU - Shearin, Staci M.

AU - Fey, Nicholas

PY - 2019/7/12

Y1 - 2019/7/12

N2 - Background: Clinical balance assessments often rely on functional tasks as a proxy for balance (e.g., Timed Up and Go). In contrast, analyses of balance in research settings incorporate quantitative biomechanical measurements (e.g., whole-body angular momentum, H) using motion capture techniques. Fully instrumenting patients in the clinic is not feasible, and thus it is desirable to estimate biomechanical quantities related to balance from measurements taken from a subset of the body segments. Machine learning algorithms are well-suited for this type of low- to high-dimensional mapping. Thus, our goal was to develop and test an artificial neural network that to predict segment contributions to whole-body angular momentum from linear acceleration and angular velocity signals (i.e., those typically available to wearable inertial measurement units, IMUs) taken from a sparse set of body segments. Methods: Optical motion capture data were collected from five able-bodied individuals and five individuals with Parkinson's disease (PD) walking on a non-steady-state locomotor circuit comprising stairs, ramps and changes of direction. Motion data were used to calculate angular momentum (i.e., "gold standard" output data) and body-segment linear acceleration and angular velocity data from local reference frames at the wrists, ankles and neck (i.e., network input). A dynamic nonlinear autoregressive neural network was trained using the able-bodied data (pooled across subjects). The neural network was tested on data from individuals with PD with noise added to simulate real-world IMU data. Results: Correlation coefficients of the predicted segment contributions to whole-body angular momentum with the gold standard data were 0.989 for able-bodied individuals and 0.987 for individuals with PD. Mean RMS errors were between 2 and 7% peak signal magnitude for all body segments during completion of the locomotor circuits. Conclusion: Our results suggest that estimating segment contributions to angular momentum from mechanical signals (linear acceleration, angular velocity) from a sparse set of body segments is a feasible method for assessing coordination of balance - even using a network trained on able-bodied data to assess individuals with neurological disease. These targeted estimates of segmental momenta could potentially be delivered to clinicians using a sparse sensor set (and likely in real-time) in order to enhance balance rehabilitation of people with PD.

AB - Background: Clinical balance assessments often rely on functional tasks as a proxy for balance (e.g., Timed Up and Go). In contrast, analyses of balance in research settings incorporate quantitative biomechanical measurements (e.g., whole-body angular momentum, H) using motion capture techniques. Fully instrumenting patients in the clinic is not feasible, and thus it is desirable to estimate biomechanical quantities related to balance from measurements taken from a subset of the body segments. Machine learning algorithms are well-suited for this type of low- to high-dimensional mapping. Thus, our goal was to develop and test an artificial neural network that to predict segment contributions to whole-body angular momentum from linear acceleration and angular velocity signals (i.e., those typically available to wearable inertial measurement units, IMUs) taken from a sparse set of body segments. Methods: Optical motion capture data were collected from five able-bodied individuals and five individuals with Parkinson's disease (PD) walking on a non-steady-state locomotor circuit comprising stairs, ramps and changes of direction. Motion data were used to calculate angular momentum (i.e., "gold standard" output data) and body-segment linear acceleration and angular velocity data from local reference frames at the wrists, ankles and neck (i.e., network input). A dynamic nonlinear autoregressive neural network was trained using the able-bodied data (pooled across subjects). The neural network was tested on data from individuals with PD with noise added to simulate real-world IMU data. Results: Correlation coefficients of the predicted segment contributions to whole-body angular momentum with the gold standard data were 0.989 for able-bodied individuals and 0.987 for individuals with PD. Mean RMS errors were between 2 and 7% peak signal magnitude for all body segments during completion of the locomotor circuits. Conclusion: Our results suggest that estimating segment contributions to angular momentum from mechanical signals (linear acceleration, angular velocity) from a sparse set of body segments is a feasible method for assessing coordination of balance - even using a network trained on able-bodied data to assess individuals with neurological disease. These targeted estimates of segmental momenta could potentially be delivered to clinicians using a sparse sensor set (and likely in real-time) in order to enhance balance rehabilitation of people with PD.

KW - Balance

KW - Biomechanics

KW - Gait

KW - Machine learning

KW - Parkinson's disease

KW - Rehabilitation

KW - Sparse sensing

KW - Wearable sensing

UR - http://www.scopus.com/inward/record.url?scp=85068892603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068892603&partnerID=8YFLogxK

U2 - 10.1186/s12984-019-0550-8

DO - 10.1186/s12984-019-0550-8

M3 - Article

C2 - 31300001

AN - SCOPUS:85068892603

VL - 16

JO - Journal of NeuroEngineering and Rehabilitation

JF - Journal of NeuroEngineering and Rehabilitation

SN - 1743-0003

IS - 1

M1 - 88

ER -