A computational framework for quantitative evaluation of movement during rehabilitation

Yinpeng Chen, Margaret Duff, Nicole Lehrer, Hari Sundaram, Jiping He, Steven L. Wolf, Thanassis Rikakis

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

Abstract

This paper presents a novel generalized computational framework for quantitative kinematic evaluation of movement in a rehabilitation clinic setting. The framework integrates clinical knowledge and computational data-driven analysis together in a systematic manner. The framework provides three key benefits to rehabilitation: (a) the resulting continuous normalized measure allows the clinician to monitor movement quality on a fine scale and easily compare impairments across participants, (b) the framework reveals the effect of individual movement components on the composite movement performance helping the clinician decide the training foci, and (c) the evaluation runs in real-time, which allows the clinician to constantly track a patient's progress and make appropriate adaptations to the therapy protocol. The creation of such an evaluation is difficult because of the sparse amount of recorded clinical observations, the high dimensionality of movement and high variations in subject's performance. We address these issues by modeling the evaluation function as linear combination of multiple normalized kinematic attributes y=Σwiφi(xi) and estimating the attribute normalization function φi(·) by integrating distributions of idealized movement and deviated movement. The weights wi are derived from a therapist's pair-wise comparison using a modified RankSVM algorithm. We have applied this framework to evaluate upper limb movement for stroke survivors with excellent results - the evaluation results are highly correlated to the therapist's observations.

Original languageEnglish (US)
Title of host publication2011 International Symposium on Computational Models for Life Sciences, CMLS-11
Pages317-326
Number of pages10
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 International Symposium on Computational Models for Life Sciences, CMLS-11 - Toyama City, Japan
Duration: Oct 11 2011Oct 13 2011

Publication series

NameAIP Conference Proceedings
Volume1371
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Other

Other2011 International Symposium on Computational Models for Life Sciences, CMLS-11
CountryJapan
CityToyama City
Period10/11/1110/13/11

Keywords

  • Kinematic impairment measure (KIM)
  • Quantitative evaluation
  • Rehabilitation

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'A computational framework for quantitative evaluation of movement during rehabilitation'. Together they form a unique fingerprint.

Cite this