Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain

Xu Huang, Raul Fernandez Rojas, Allan C. Madoc, Sheikh Md Rabiul Islam

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

One of major biomedical signals, pain, and its diagnosis has been critical but hard in clinical practice, in particularly for nonverbal patients. However, as we know that neuroimaging methods, such as functional near-infrared spectroscopy (fNIRS), have shown some great encouraging assessing neuronal function corresponding to nociception and pain. Specially some research results strongly suggest that neuroimaging, together with supports from machine learning, may be practically used to not only facilitate but also can predict different cognitive tasks over this challenge. The aim of this current research is to expand our previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (we define cold and hot) and corresponding pain intensity (say low and high) by means of machine learning models. In order to find out the relations between temperatures and pain intensity, we defined and used the quantitative sensory testing to determine pain threshold and pain tolerance for the cold and heat in all eighteen-healthy people. The classification algorithm is based on a bag-of-words approach, a histogram representation was used in document classification based on the frequencies of extracted words and adapted for time series. Two machine learning algorithms were used separately, namely, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was made in our classification task. The results showed that K-NN obtained slightly better results (92.1%) than SVM (91.3%) with all the 24 channels; however, the performances slightly dropped if using only channels from the region of interest with K-NN (91.5%) and SVM (90.8%). These research results encourage potential applications of fNIRS in the development of a physiologically based diagnosis of human pain, including in clinical parties.

Original languageEnglish
Title of host publication2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages396-400
Number of pages5
ISBN (Electronic)9781538672235
ISBN (Print)9781538672242
DOIs
Publication statusPublished - 6 Jul 2018
Event10th International Conference on Communication Software and Networks, ICCSN 2018 - Chengdu, China
Duration: 6 Jul 20189 Jul 2018

Conference

Conference10th International Conference on Communication Software and Networks, ICCSN 2018
CountryChina
CityChengdu
Period6/07/189/07/18

Fingerprint

Neuroimaging
Near infrared spectroscopy
Signal analysis
Signal processing
Support vector machines
Learning systems
Learning algorithms
Time series
Temperature
Testing

Cite this

Huang, X., Rojas, R. F., Madoc, A. C., & Islam, S. M. R. (2018). Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain. In 2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018 (pp. 396-400). [8488323] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCSN.2018.8488323
Huang, Xu ; Rojas, Raul Fernandez ; Madoc, Allan C. ; Islam, Sheikh Md Rabiul. / Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain. 2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018. IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 396-400
@inproceedings{7035f531203f4baea5011273636b7786,
title = "Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain",
abstract = "One of major biomedical signals, pain, and its diagnosis has been critical but hard in clinical practice, in particularly for nonverbal patients. However, as we know that neuroimaging methods, such as functional near-infrared spectroscopy (fNIRS), have shown some great encouraging assessing neuronal function corresponding to nociception and pain. Specially some research results strongly suggest that neuroimaging, together with supports from machine learning, may be practically used to not only facilitate but also can predict different cognitive tasks over this challenge. The aim of this current research is to expand our previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (we define cold and hot) and corresponding pain intensity (say low and high) by means of machine learning models. In order to find out the relations between temperatures and pain intensity, we defined and used the quantitative sensory testing to determine pain threshold and pain tolerance for the cold and heat in all eighteen-healthy people. The classification algorithm is based on a bag-of-words approach, a histogram representation was used in document classification based on the frequencies of extracted words and adapted for time series. Two machine learning algorithms were used separately, namely, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was made in our classification task. The results showed that K-NN obtained slightly better results (92.1{\%}) than SVM (91.3{\%}) with all the 24 channels; however, the performances slightly dropped if using only channels from the region of interest with K-NN (91.5{\%}) and SVM (90.8{\%}). These research results encourage potential applications of fNIRS in the development of a physiologically based diagnosis of human pain, including in clinical parties.",
keywords = "clinical parties, fNIRS, k-means, pain, SVM",
author = "Xu Huang and Rojas, {Raul Fernandez} and Madoc, {Allan C.} and Islam, {Sheikh Md Rabiul}",
year = "2018",
month = "7",
day = "6",
doi = "10.1109/ICCSN.2018.8488323",
language = "English",
isbn = "9781538672242",
pages = "396--400",
booktitle = "2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Huang, X, Rojas, RF, Madoc, AC & Islam, SMR 2018, Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain. in 2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018., 8488323, IEEE, Institute of Electrical and Electronics Engineers, pp. 396-400, 10th International Conference on Communication Software and Networks, ICCSN 2018, Chengdu, China, 6/07/18. https://doi.org/10.1109/ICCSN.2018.8488323

Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain. / Huang, Xu; Rojas, Raul Fernandez; Madoc, Allan C.; Islam, Sheikh Md Rabiul.

2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018. IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 396-400 8488323.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain

AU - Huang, Xu

AU - Rojas, Raul Fernandez

AU - Madoc, Allan C.

AU - Islam, Sheikh Md Rabiul

PY - 2018/7/6

Y1 - 2018/7/6

N2 - One of major biomedical signals, pain, and its diagnosis has been critical but hard in clinical practice, in particularly for nonverbal patients. However, as we know that neuroimaging methods, such as functional near-infrared spectroscopy (fNIRS), have shown some great encouraging assessing neuronal function corresponding to nociception and pain. Specially some research results strongly suggest that neuroimaging, together with supports from machine learning, may be practically used to not only facilitate but also can predict different cognitive tasks over this challenge. The aim of this current research is to expand our previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (we define cold and hot) and corresponding pain intensity (say low and high) by means of machine learning models. In order to find out the relations between temperatures and pain intensity, we defined and used the quantitative sensory testing to determine pain threshold and pain tolerance for the cold and heat in all eighteen-healthy people. The classification algorithm is based on a bag-of-words approach, a histogram representation was used in document classification based on the frequencies of extracted words and adapted for time series. Two machine learning algorithms were used separately, namely, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was made in our classification task. The results showed that K-NN obtained slightly better results (92.1%) than SVM (91.3%) with all the 24 channels; however, the performances slightly dropped if using only channels from the region of interest with K-NN (91.5%) and SVM (90.8%). These research results encourage potential applications of fNIRS in the development of a physiologically based diagnosis of human pain, including in clinical parties.

AB - One of major biomedical signals, pain, and its diagnosis has been critical but hard in clinical practice, in particularly for nonverbal patients. However, as we know that neuroimaging methods, such as functional near-infrared spectroscopy (fNIRS), have shown some great encouraging assessing neuronal function corresponding to nociception and pain. Specially some research results strongly suggest that neuroimaging, together with supports from machine learning, may be practically used to not only facilitate but also can predict different cognitive tasks over this challenge. The aim of this current research is to expand our previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (we define cold and hot) and corresponding pain intensity (say low and high) by means of machine learning models. In order to find out the relations between temperatures and pain intensity, we defined and used the quantitative sensory testing to determine pain threshold and pain tolerance for the cold and heat in all eighteen-healthy people. The classification algorithm is based on a bag-of-words approach, a histogram representation was used in document classification based on the frequencies of extracted words and adapted for time series. Two machine learning algorithms were used separately, namely, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was made in our classification task. The results showed that K-NN obtained slightly better results (92.1%) than SVM (91.3%) with all the 24 channels; however, the performances slightly dropped if using only channels from the region of interest with K-NN (91.5%) and SVM (90.8%). These research results encourage potential applications of fNIRS in the development of a physiologically based diagnosis of human pain, including in clinical parties.

KW - clinical parties

KW - fNIRS

KW - k-means

KW - pain

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85056381461&partnerID=8YFLogxK

U2 - 10.1109/ICCSN.2018.8488323

DO - 10.1109/ICCSN.2018.8488323

M3 - Conference contribution

SN - 9781538672242

SP - 396

EP - 400

BT - 2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Huang X, Rojas RF, Madoc AC, Islam SMR. Biomedic Signal Processing and Analysis of Neuroimaging from fNIRS for Human Pain. In 2018 10th IEEE International Conference on Communication Software and Networks, ICCSN 2018. IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 396-400. 8488323 https://doi.org/10.1109/ICCSN.2018.8488323