Toward a functional near-infrared spectroscopy-based monitoring of pain assessment for nonverbal patients

Raul Fernandez Rojas, Xu Huang, Keng Liang Ou

研究成果: 雜誌貢獻文章

6 引文 (Scopus)

摘要

Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53%) and SVM (90.83%). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.

原文英語
文章編號106013
期刊Journal of Biomedical Optics
22
發行號10
DOIs
出版狀態已發佈 - 十月 1 2017

指紋

Near infrared spectroscopy
pain
infrared spectroscopy
Neuroimaging
Support vector machines
Monitoring
Learning systems
machine learning
Oxyhemoglobins
Learning algorithms
Time series
oxyhemoglobin
bags
histograms
Testing
learning
magnetic resonance
deviation
heat
thresholds

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Biomedical Engineering

引用此文

Toward a functional near-infrared spectroscopy-based monitoring of pain assessment for nonverbal patients. / Fernandez Rojas, Raul; Huang, Xu; Ou, Keng Liang.

於: Journal of Biomedical Optics, 卷 22, 編號 10, 106013, 01.10.2017.

研究成果: 雜誌貢獻文章

@article{98170f2f1e104ba8ae57c1412d69c05c,
title = "Toward a functional near-infrared spectroscopy-based monitoring of pain assessment for nonverbal patients",
abstract = "Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08{\%}) than SVM (91.25{\%}) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53{\%}) and SVM (90.83{\%}). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.",
keywords = "bag-of-words, biomarker, discrete wavelet transform, K-nearest neighbor, machine learning, means, near-infrared spectroscopy, pain, principal component analysis, support vector machine, wavelet",
author = "{Fernandez Rojas}, Raul and Xu Huang and Ou, {Keng Liang}",
year = "2017",
month = "10",
day = "1",
doi = "10.1117/1.JBO.22.10.106013",
language = "English",
volume = "22",
journal = "Journal of Biomedical Optics",
issn = "1083-3668",
publisher = "SPIE",
number = "10",

}

TY - JOUR

T1 - Toward a functional near-infrared spectroscopy-based monitoring of pain assessment for nonverbal patients

AU - Fernandez Rojas, Raul

AU - Huang, Xu

AU - Ou, Keng Liang

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53%) and SVM (90.83%). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.

AB - Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53%) and SVM (90.83%). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.

KW - bag-of-words

KW - biomarker

KW - discrete wavelet transform

KW - K-nearest neighbor

KW - machine learning

KW - means

KW - near-infrared spectroscopy

KW - pain

KW - principal component analysis

KW - support vector machine

KW - wavelet

UR - http://www.scopus.com/inward/record.url?scp=85032945593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032945593&partnerID=8YFLogxK

U2 - 10.1117/1.JBO.22.10.106013

DO - 10.1117/1.JBO.22.10.106013

M3 - Article

AN - SCOPUS:85032945593

VL - 22

JO - Journal of Biomedical Optics

JF - Journal of Biomedical Optics

SN - 1083-3668

IS - 10

M1 - 106013

ER -