Characterizing the SEMG patterns with myofascial pain using a multi-scale wavelet model through machine learning approaches

Yu-Ching Lin, Nan Ying Yu, Ching Fen Jiang, Shao Hsia Chang

Research output: Contribution to journalArticle

Abstract

In this paper, we introduce a newly developed multi-scale wavelet model for the interpretation of surface electromyography (SEMG) signals and validate the model's capability to characterize changes in neuromuscular activation in cases with myofascial pain syndrome (MPS) via machine learning methods. The SEMG data collected from normal (N = 30; 27 women, 3 men) and MPS subjects (N = 26; 22 women, 4 men) were adopted for this retrospective analysis. SMEGs were measured from the taut-band loci on both sides of the trapezius muscle on the upper back while he/she conducted a cyclic bilateral backward shoulder extension movement within 1 min. Classification accuracy of the SEMG model to differentiate MPS patients from normal subjects was 77% using template matching and 60% using K-means clustering. Classification consistency between the two machine learning methods was 87% in the normal group and 93% in the MPS group. The 2D feature graphs derived from the proposed multi-scale model revealed distinct patterns between normal subjects and MPS patients. The classification consistency using template matching and K-means clustering suggests the potential of using the proposed model to characterize interference pattern changes induced by MPS.

Original languageEnglish
Pages (from-to)147-153
Number of pages7
JournalJournal of Electromyography and Kinesiology
Volume41
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Myofascial Pain Syndromes
Electromyography
Pain
Cluster Analysis
Superficial Back Muscles
Machine Learning

All Science Journal Classification (ASJC) codes

  • Neuroscience (miscellaneous)
  • Biophysics
  • Clinical Neurology

Cite this

@article{be1d2866c92b4dc5993e68828408a372,
title = "Characterizing the SEMG patterns with myofascial pain using a multi-scale wavelet model through machine learning approaches",
abstract = "In this paper, we introduce a newly developed multi-scale wavelet model for the interpretation of surface electromyography (SEMG) signals and validate the model's capability to characterize changes in neuromuscular activation in cases with myofascial pain syndrome (MPS) via machine learning methods. The SEMG data collected from normal (N = 30; 27 women, 3 men) and MPS subjects (N = 26; 22 women, 4 men) were adopted for this retrospective analysis. SMEGs were measured from the taut-band loci on both sides of the trapezius muscle on the upper back while he/she conducted a cyclic bilateral backward shoulder extension movement within 1 min. Classification accuracy of the SEMG model to differentiate MPS patients from normal subjects was 77{\%} using template matching and 60{\%} using K-means clustering. Classification consistency between the two machine learning methods was 87{\%} in the normal group and 93{\%} in the MPS group. The 2D feature graphs derived from the proposed multi-scale model revealed distinct patterns between normal subjects and MPS patients. The classification consistency using template matching and K-means clustering suggests the potential of using the proposed model to characterize interference pattern changes induced by MPS.",
author = "Yu-Ching Lin and Yu, {Nan Ying} and Jiang, {Ching Fen} and Chang, {Shao Hsia}",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.jelekin.2018.05.004",
language = "English",
volume = "41",
pages = "147--153",
journal = "Journal of Electromyography and Kinesiology",
issn = "1050-6411",
publisher = "Elsevier Limited",

}

Characterizing the SEMG patterns with myofascial pain using a multi-scale wavelet model through machine learning approaches. / Lin, Yu-Ching; Yu, Nan Ying; Jiang, Ching Fen; Chang, Shao Hsia.

In: Journal of Electromyography and Kinesiology, Vol. 41, 01.08.2018, p. 147-153.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characterizing the SEMG patterns with myofascial pain using a multi-scale wavelet model through machine learning approaches

AU - Lin, Yu-Ching

AU - Yu, Nan Ying

AU - Jiang, Ching Fen

AU - Chang, Shao Hsia

PY - 2018/8/1

Y1 - 2018/8/1

N2 - In this paper, we introduce a newly developed multi-scale wavelet model for the interpretation of surface electromyography (SEMG) signals and validate the model's capability to characterize changes in neuromuscular activation in cases with myofascial pain syndrome (MPS) via machine learning methods. The SEMG data collected from normal (N = 30; 27 women, 3 men) and MPS subjects (N = 26; 22 women, 4 men) were adopted for this retrospective analysis. SMEGs were measured from the taut-band loci on both sides of the trapezius muscle on the upper back while he/she conducted a cyclic bilateral backward shoulder extension movement within 1 min. Classification accuracy of the SEMG model to differentiate MPS patients from normal subjects was 77% using template matching and 60% using K-means clustering. Classification consistency between the two machine learning methods was 87% in the normal group and 93% in the MPS group. The 2D feature graphs derived from the proposed multi-scale model revealed distinct patterns between normal subjects and MPS patients. The classification consistency using template matching and K-means clustering suggests the potential of using the proposed model to characterize interference pattern changes induced by MPS.

AB - In this paper, we introduce a newly developed multi-scale wavelet model for the interpretation of surface electromyography (SEMG) signals and validate the model's capability to characterize changes in neuromuscular activation in cases with myofascial pain syndrome (MPS) via machine learning methods. The SEMG data collected from normal (N = 30; 27 women, 3 men) and MPS subjects (N = 26; 22 women, 4 men) were adopted for this retrospective analysis. SMEGs were measured from the taut-band loci on both sides of the trapezius muscle on the upper back while he/she conducted a cyclic bilateral backward shoulder extension movement within 1 min. Classification accuracy of the SEMG model to differentiate MPS patients from normal subjects was 77% using template matching and 60% using K-means clustering. Classification consistency between the two machine learning methods was 87% in the normal group and 93% in the MPS group. The 2D feature graphs derived from the proposed multi-scale model revealed distinct patterns between normal subjects and MPS patients. The classification consistency using template matching and K-means clustering suggests the potential of using the proposed model to characterize interference pattern changes induced by MPS.

UR - http://www.scopus.com/inward/record.url?scp=85048180283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048180283&partnerID=8YFLogxK

U2 - 10.1016/j.jelekin.2018.05.004

DO - 10.1016/j.jelekin.2018.05.004

M3 - Article

C2 - 29890503

AN - SCOPUS:85048180283

VL - 41

SP - 147

EP - 153

JO - Journal of Electromyography and Kinesiology

JF - Journal of Electromyography and Kinesiology

SN - 1050-6411

ER -