A Physiological-Inspired Classification Strategy to Classify Five Levels of Pain

Current research on quantitative pain measurement using the electroencephalogram (EEG) signals showed a promising result just on classifying pain from no-pain states. In this paper, we go one step further introducing pain-level dependent EEG features as well as proposing a physiologically-inspired hierarchical classifier to provide promising results for differentiating five classes of pain. In this research, forty four subjects were voluntarily enrolled, each of whom executed the Cold-Pressor Test (CPT), while their EEGs were simultaneously recorded. We filtered the EEGs through the alpha band and elicited meaningful features to reveal the behavior of signals in terms of distribution, spectrum and complexity at each pain state. To assess the susceptibility of the features in classifying one/group of classes against others, Kruscall-Walis test was applied to give a clue in order to construct the structure of our decision tree, where a Bayesian optimized support vector machine (BSVM) was trained at each node. After arranging the tree, sequential forward selection (SFS) was applied to select a customized subset of features for each node. Our results provide 93.33% accuracy for the five classes and also generate 99.8% for pain and non-pain classes, which is statistically superior (P<0.05) to state-of-the-art methods over the same dataset.

[1]  S. Lautenbacher,et al.  EEG responses to tonic heat pain , 2006, Experimental Brain Research.

[2]  Maryam Vatankhah,et al.  Perceptual pain classification using ANFIS adapted RBF kernel support vector machine for therapeutic usage , 2013, Appl. Soft Comput..

[3]  Yeong-Ray Wen,et al.  A Novel Fuzzy Pain Demand Index Derived From Patient-Controlled Analgesia for Postoperative Pain , 2007, IEEE Transactions on Biomedical Engineering.

[4]  R. Boostani,et al.  Presenting an effective EEG-based index to monitor the depth of anesthesia , 2012, The 16th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP 2012).

[5]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[6]  Janaina Mourão Miranda,et al.  Quantitative prediction of subjective pain intensity from whole-brain fMRI data using Gaussian processes , 2010, NeuroImage.

[7]  H. O. Hartley,et al.  Universal Bounds for Mean Range and Extreme Observation , 1954 .

[8]  Benjamin Blankertz,et al.  Presenting a Spatial-Geometric EEG Feature to Classify BMD and Schizophrenic Patients , 2016 .

[9]  Anna Domingo,et al.  The Wong-Baker Pain FACES Scale Measures Pain, Not Fear , 2013, Pediatric emergency care.

[10]  U Salvolini,et al.  Mechanical noxious stimuli cause bilateral activation of parietal operculum in callosotomized subjects. , 2002, Cerebral cortex.

[11]  R. Boostani,et al.  A Novel Classification Strategy to Distinguish Five Levels of Pain Using the EEG Signal Features , 2018, IEEE Transactions on Affective Computing.

[12]  Joachim Gross,et al.  Prefrontal Gamma Oscillations Encode Tonic Pain in Humans , 2015, Cerebral cortex.

[13]  Maryam Vatankhah,et al.  Pain Level Measurement Using Discrete Wavelet Transform , .

[14]  Reza Boostani,et al.  INTRODUCING A NOVEL INDEX FOR MEASURING DEPTH OF ANESTHESIA BASED ON VISUAL EVOKED POTENTIAL (VEP) FEATURES , 2012 .

[15]  Alon Sinai,et al.  Tonic pain and continuous EEG: Prediction of subjective pain perception by alpha-1 power during stimulation and at rest , 2012, Clinical Neurophysiology.

[16]  Leontios J. Hadjileontiadis,et al.  EEG-Based Tonic Cold Pain Characterization Using Wavelet Higher Order Spectral Features , 2015, IEEE Transactions on Biomedical Engineering.

[17]  R. Treede,et al.  Human brain mechanisms of pain perception and regulation in health and disease , 2005, European journal of pain.

[18]  Reza Boostani,et al.  Comparative Application of Non-negative Decomposition Methods in Classifying Fatigue and Non-fatigue States , 2014 .

[19]  Arnab Roy,et al.  Automated classification of pain perception using high-density electroencephalography data. , 2017, Journal of neurophysiology.

[20]  Gian Domenico Iannetti,et al.  A novel approach to predict subjective pain perception from single-trial laser-evoked potentials , 2013, NeuroImage.

[21]  Reza Boostani,et al.  Classification of ADHD and BMD patients using visual evoked potential , 2013, Clinical Neurology and Neurosurgery.

[22]  D. Boas,et al.  Specificity of Hemodynamic Brain Responses to Painful Stimuli: A functional near-infrared spectroscopy study , 2015, Scientific Reports.

[23]  M. Mccaffery,et al.  Pain ratings: the fifth vital sign. , 1997, The American journal of nursing.

[24]  Joachim M. Buhmann,et al.  Decoding the perception of pain from fMRI using multivariate pattern analysis , 2012, NeuroImage.