Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models

Vishal Vijayakumar; Michelle Case; Sina Shirinpour; Bin He

doi:10.1109/TBME.2017.2756870

Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models

Vishal Vijayakumar, Michelle Case, Sina Shirinpour, Bin He

Biomedical Engineering

Research output: Contribution to journal › Article › peer-review

51 Scopus citations

Abstract

Objective: Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. Methods: A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. Results: The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. Conclusion: The robustness and generalizability of the classifier are demonstrated. Significance: Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.

Original language	English (US)
Article number	8049487
Pages (from-to)	2988-2996
Number of pages	9
Journal	IEEE Transactions on Biomedical Engineering
Volume	64
Issue number	12
DOIs	https://doi.org/10.1109/TBME.2017.2756870
State	Published - Dec 2017

Bibliographical note

Funding Information:
Manuscript received May 22, 2017; revised August 8, 2017 and September 8, 2017; accepted September 9, 2017. Date of publication September 26, 2017; date of current version November 20, 2017. This work was supported in part by the U.S. National Institutes of Health under Grant HL117664, Grant AT009263, Grant NS096761, Grant EB021027, and Grant OD021721 and in part by the U.S. National Science Foundation under Grant DGE-1069104. (Corresponding author: Bin He.) V. Vijayakumar is with the Department of Electrical and Computer Engineering, University of Minnesota.

Publisher Copyright:
© 2017 IEEE.

Keywords

Cingulate cortex
electroencephalography (EEG)
gamma oscillations
machine learning
pain quantification

Access

10.1109/TBME.2017.2756870

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5718188

OpenUrl availability

Full text

Cite this

@article{384e0c94ab674aabb55ed98c86c1398d,

title = "Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models",

abstract = "Objective: Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. Methods: A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. Results: The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. Conclusion: The robustness and generalizability of the classifier are demonstrated. Significance: Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.",

keywords = "Cingulate cortex, electroencephalography (EEG), gamma oscillations, machine learning, pain quantification",

author = "Vishal Vijayakumar and Michelle Case and Sina Shirinpour and Bin He",

note = "Funding Information: Manuscript received May 22, 2017; revised August 8, 2017 and September 8, 2017; accepted September 9, 2017. Date of publication September 26, 2017; date of current version November 20, 2017. This work was supported in part by the U.S. National Institutes of Health under Grant HL117664, Grant AT009263, Grant NS096761, Grant EB021027, and Grant OD021721 and in part by the U.S. National Science Foundation under Grant DGE-1069104. (Corresponding author: Bin He.) V. Vijayakumar is with the Department of Electrical and Computer Engineering, University of Minnesota. Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2017",

month = dec,

doi = "10.1109/TBME.2017.2756870",

language = "English (US)",

volume = "64",

pages = "2988--2996",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "12",

}

TY - JOUR

T1 - Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models

AU - Vijayakumar, Vishal

AU - Case, Michelle

AU - Shirinpour, Sina

AU - He, Bin

N1 - Funding Information: Manuscript received May 22, 2017; revised August 8, 2017 and September 8, 2017; accepted September 9, 2017. Date of publication September 26, 2017; date of current version November 20, 2017. This work was supported in part by the U.S. National Institutes of Health under Grant HL117664, Grant AT009263, Grant NS096761, Grant EB021027, and Grant OD021721 and in part by the U.S. National Science Foundation under Grant DGE-1069104. (Corresponding author: Bin He.) V. Vijayakumar is with the Department of Electrical and Computer Engineering, University of Minnesota. Publisher Copyright: © 2017 IEEE.

PY - 2017/12

Y1 - 2017/12

N2 - Objective: Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. Methods: A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. Results: The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. Conclusion: The robustness and generalizability of the classifier are demonstrated. Significance: Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.

AB - Objective: Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. Methods: A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. Results: The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. Conclusion: The robustness and generalizability of the classifier are demonstrated. Significance: Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.

KW - Cingulate cortex

KW - electroencephalography (EEG)

KW - gamma oscillations

KW - machine learning

KW - pain quantification

UR - http://www.scopus.com/inward/record.url?scp=85030667350&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030667350&partnerID=8YFLogxK

U2 - 10.1109/TBME.2017.2756870

DO - 10.1109/TBME.2017.2756870

M3 - Article

C2 - 28952933

AN - SCOPUS:85030667350

SN - 0018-9294

VL - 64

SP - 2988

EP - 2996

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 12

M1 - 8049487

ER -

Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this