A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome

Mingjing Yang, Huiru Zheng, Haiying Wang, Sally McClean, Jane Hall, Nigel Harris

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Complex Regional Pain Syndrome (CRPS) is a condition that causes a long-term burning pain in a limb or part of a limb and it can cause various degrees of the physical functional performance deterioration. Objective assessment of physical functional performance of patients is one critical component to evaluate the therapy outcome for CRPS. This paper aims to investigate the feasibility of assessing the physical performance of patients with Complex Regional Pain Syndrome based on the analysis of gait data recorded by an accelerometer in short walking distances. Ten subjects with CRPS and ten control subjects were recruited. Thirty three features were extracted from each recording. A machine learning method, Multilayer perceptron neural-networks (MLP), was applied to classify the normal and abnormal gait patterns from data obtained on a 2.4 m performance evaluation test. The best classification accuracy (99.38%) was achieved using 3 features selected by a step-wise-forward method. To further validate its performance, an independent test set including 14 cases extracted from data obtained on a 20 m performance evaluation test was adopted. A prediction accuracy of 85.7% was obtained.
LanguageEnglish
Pages740-746
JournalMedical Engineering and Physics
Volume34
Issue number6
DOIs
Publication statusPublished - Jul 2012

Fingerprint

Complex Regional Pain Syndromes
Multilayer neural networks
Gait
Accelerometers
Deterioration
Learning systems
Neural networks
Extremities
Neural Networks (Computer)
Walking
Pain
Machine Learning

Keywords

  • Accelerometer
  • Gait analysis
  • Complex Regional Pain Syndrome
  • Feature extraction
  • Classification

Cite this

@article{86bcd87a332d48109fd13e03d6778391,
title = "A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome",
abstract = "Complex Regional Pain Syndrome (CRPS) is a condition that causes a long-term burning pain in a limb or part of a limb and it can cause various degrees of the physical functional performance deterioration. Objective assessment of physical functional performance of patients is one critical component to evaluate the therapy outcome for CRPS. This paper aims to investigate the feasibility of assessing the physical performance of patients with Complex Regional Pain Syndrome based on the analysis of gait data recorded by an accelerometer in short walking distances. Ten subjects with CRPS and ten control subjects were recruited. Thirty three features were extracted from each recording. A machine learning method, Multilayer perceptron neural-networks (MLP), was applied to classify the normal and abnormal gait patterns from data obtained on a 2.4 m performance evaluation test. The best classification accuracy (99.38{\%}) was achieved using 3 features selected by a step-wise-forward method. To further validate its performance, an independent test set including 14 cases extracted from data obtained on a 20 m performance evaluation test was adopted. A prediction accuracy of 85.7{\%} was obtained.",
keywords = "Accelerometer, Gait analysis, Complex Regional Pain Syndrome, Feature extraction, Classification",
author = "Mingjing Yang and Huiru Zheng and Haiying Wang and Sally McClean and Jane Hall and Nigel Harris",
year = "2012",
month = "7",
doi = "10.1016/j.medengphy.2011.09.018",
language = "English",
volume = "34",
pages = "740--746",
number = "6",

}

A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome. / Yang, Mingjing; Zheng, Huiru; Wang, Haiying; McClean, Sally; Hall, Jane; Harris, Nigel.

Vol. 34, No. 6, 07.2012, p. 740-746.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome

AU - Yang, Mingjing

AU - Zheng, Huiru

AU - Wang, Haiying

AU - McClean, Sally

AU - Hall, Jane

AU - Harris, Nigel

PY - 2012/7

Y1 - 2012/7

N2 - Complex Regional Pain Syndrome (CRPS) is a condition that causes a long-term burning pain in a limb or part of a limb and it can cause various degrees of the physical functional performance deterioration. Objective assessment of physical functional performance of patients is one critical component to evaluate the therapy outcome for CRPS. This paper aims to investigate the feasibility of assessing the physical performance of patients with Complex Regional Pain Syndrome based on the analysis of gait data recorded by an accelerometer in short walking distances. Ten subjects with CRPS and ten control subjects were recruited. Thirty three features were extracted from each recording. A machine learning method, Multilayer perceptron neural-networks (MLP), was applied to classify the normal and abnormal gait patterns from data obtained on a 2.4 m performance evaluation test. The best classification accuracy (99.38%) was achieved using 3 features selected by a step-wise-forward method. To further validate its performance, an independent test set including 14 cases extracted from data obtained on a 20 m performance evaluation test was adopted. A prediction accuracy of 85.7% was obtained.

AB - Complex Regional Pain Syndrome (CRPS) is a condition that causes a long-term burning pain in a limb or part of a limb and it can cause various degrees of the physical functional performance deterioration. Objective assessment of physical functional performance of patients is one critical component to evaluate the therapy outcome for CRPS. This paper aims to investigate the feasibility of assessing the physical performance of patients with Complex Regional Pain Syndrome based on the analysis of gait data recorded by an accelerometer in short walking distances. Ten subjects with CRPS and ten control subjects were recruited. Thirty three features were extracted from each recording. A machine learning method, Multilayer perceptron neural-networks (MLP), was applied to classify the normal and abnormal gait patterns from data obtained on a 2.4 m performance evaluation test. The best classification accuracy (99.38%) was achieved using 3 features selected by a step-wise-forward method. To further validate its performance, an independent test set including 14 cases extracted from data obtained on a 20 m performance evaluation test was adopted. A prediction accuracy of 85.7% was obtained.

KW - Accelerometer

KW - Gait analysis

KW - Complex Regional Pain Syndrome

KW - Feature extraction

KW - Classification

U2 - 10.1016/j.medengphy.2011.09.018

DO - 10.1016/j.medengphy.2011.09.018

M3 - Article

VL - 34

SP - 740

EP - 746

IS - 6

ER -