A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 Objective Was To Develop And Validate An Artificial Neural Network For Estimating Contributions To H From 12 Body Segments Using Only Five Inertial Measurement Units. The Network Was Trained, Tested And Validated On Data From Five Able-Bodied Individuals Performing Forty Trials Each Of A Circuit Involving Complex Walking Tasks, Including Stairs, Ramp, And Direction Changes. The Network Was Also Separately Tested On Four Trials Of An Individual With Parkinson'S Disease Walking On The Circuit. The Output Of The Network Was Strongly Correlated With The Segment Contributions To H In Both Able-Bodied (R= 0.997) And Parkinson'S Disease (R= (0.998) Subjects. The Estimated Values Also Had Low Error Relative To The Signal Magnitude, With The Largest Mean ± SD Rootmean-Squared Errors Of 8.04 ± 1.76% Peak Signal Magnitude In Able-Bodied Individuals And 7.96 ± 0.91% In The Individual With Parkinson'S Disease. These Promising Results Establish The Feasibility Of Using A Sparse Set Of Inertial Measurement Units To Provide Quantitative Data To Clinicians For Targeted Balance Rehabilitation Across Different Patients.

Original languageEnglish (US)
Title of host publication40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1202-1205
Number of pages4
Volume2018-July
ISBN (Electronic)9781538636466
DOIs
StatePublished - Oct 26 2018
Event40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 - Honolulu, United States
Duration: Jul 18 2018Jul 21 2018

Other

Other40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
CountryUnited States
CityHonolulu
Period7/18/187/21/18

Fingerprint

Patient rehabilitation
Parkinson Disease
Learning systems
Units of measurement
Rehabilitation
Walking
Sensors
Stairs
Architectural Accessibility
Networks (circuits)
Angular momentum
Proxy
Set theory
Learning algorithms
Neural networks
Research
Machine Learning
Direction compound

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Pickle, N. T., Shearin, S. M., & Fey, N. (2018). A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (Vol. 2018-July, pp. 1202-1205). [8512530] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2018.8512530

A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set. / Pickle, Nathaniel T.; Shearin, Staci M.; Fey, Nicholas.

40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. p. 1202-1205 8512530.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pickle, NT, Shearin, SM & Fey, N 2018, A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. vol. 2018-July, 8512530, Institute of Electrical and Electronics Engineers Inc., pp. 1202-1205, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018, Honolulu, United States, 7/18/18. https://doi.org/10.1109/EMBC.2018.8512530
Pickle NT, Shearin SM, Fey N. A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1202-1205. 8512530 https://doi.org/10.1109/EMBC.2018.8512530
Pickle, Nathaniel T. ; Shearin, Staci M. ; Fey, Nicholas. / A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1202-1205
@inproceedings{2916e53263c54ed9966e3875a9b67ed2,
title = "A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set",
abstract = "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 Objective Was To Develop And Validate An Artificial Neural Network For Estimating Contributions To H From 12 Body Segments Using Only Five Inertial Measurement Units. The Network Was Trained, Tested And Validated On Data From Five Able-Bodied Individuals Performing Forty Trials Each Of A Circuit Involving Complex Walking Tasks, Including Stairs, Ramp, And Direction Changes. The Network Was Also Separately Tested On Four Trials Of An Individual With Parkinson'S Disease Walking On The Circuit. The Output Of The Network Was Strongly Correlated With The Segment Contributions To H In Both Able-Bodied (R= 0.997) And Parkinson'S Disease (R= (0.998) Subjects. The Estimated Values Also Had Low Error Relative To The Signal Magnitude, With The Largest Mean ± SD Rootmean-Squared Errors Of 8.04 ± 1.76{\%} Peak Signal Magnitude In Able-Bodied Individuals And 7.96 ± 0.91{\%} In The Individual With Parkinson'S Disease. These Promising Results Establish The Feasibility Of Using A Sparse Set Of Inertial Measurement Units To Provide Quantitative Data To Clinicians For Targeted Balance Rehabilitation Across Different Patients.",
author = "Pickle, {Nathaniel T.} and Shearin, {Staci M.} and Nicholas Fey",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/EMBC.2018.8512530",
language = "English (US)",
volume = "2018-July",
pages = "1202--1205",
booktitle = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set

AU - Pickle, Nathaniel T.

AU - Shearin, Staci M.

AU - Fey, Nicholas

PY - 2018/10/26

Y1 - 2018/10/26

N2 - 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 Objective Was To Develop And Validate An Artificial Neural Network For Estimating Contributions To H From 12 Body Segments Using Only Five Inertial Measurement Units. The Network Was Trained, Tested And Validated On Data From Five Able-Bodied Individuals Performing Forty Trials Each Of A Circuit Involving Complex Walking Tasks, Including Stairs, Ramp, And Direction Changes. The Network Was Also Separately Tested On Four Trials Of An Individual With Parkinson'S Disease Walking On The Circuit. The Output Of The Network Was Strongly Correlated With The Segment Contributions To H In Both Able-Bodied (R= 0.997) And Parkinson'S Disease (R= (0.998) Subjects. The Estimated Values Also Had Low Error Relative To The Signal Magnitude, With The Largest Mean ± SD Rootmean-Squared Errors Of 8.04 ± 1.76% Peak Signal Magnitude In Able-Bodied Individuals And 7.96 ± 0.91% In The Individual With Parkinson'S Disease. These Promising Results Establish The Feasibility Of Using A Sparse Set Of Inertial Measurement Units To Provide Quantitative Data To Clinicians For Targeted Balance Rehabilitation Across Different Patients.

AB - 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 Objective Was To Develop And Validate An Artificial Neural Network For Estimating Contributions To H From 12 Body Segments Using Only Five Inertial Measurement Units. The Network Was Trained, Tested And Validated On Data From Five Able-Bodied Individuals Performing Forty Trials Each Of A Circuit Involving Complex Walking Tasks, Including Stairs, Ramp, And Direction Changes. The Network Was Also Separately Tested On Four Trials Of An Individual With Parkinson'S Disease Walking On The Circuit. The Output Of The Network Was Strongly Correlated With The Segment Contributions To H In Both Able-Bodied (R= 0.997) And Parkinson'S Disease (R= (0.998) Subjects. The Estimated Values Also Had Low Error Relative To The Signal Magnitude, With The Largest Mean ± SD Rootmean-Squared Errors Of 8.04 ± 1.76% Peak Signal Magnitude In Able-Bodied Individuals And 7.96 ± 0.91% In The Individual With Parkinson'S Disease. These Promising Results Establish The Feasibility Of Using A Sparse Set Of Inertial Measurement Units To Provide Quantitative Data To Clinicians For Targeted Balance Rehabilitation Across Different Patients.

UR - http://www.scopus.com/inward/record.url?scp=85056564147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056564147&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8512530

DO - 10.1109/EMBC.2018.8512530

M3 - Conference contribution

C2 - 30440605

AN - SCOPUS:85056564147

VL - 2018-July

SP - 1202

EP - 1205

BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -