A Novel Approach to Objectively Quantify the Subjective Perception of Pain Through Electroencephalogram Signal Analysis

Abstract

Pain is a complex subjective unpleasant experience that can potentially cause tissue damage. In the clinical practice, the main method used in assessing pain is self-report; however, it is not possibly adopted in a huge number of vulnerable populations or by non-communicative patients such as those with disorders of speech and consciousness. Thus, the availability of an objective measure of the subjective pain's perception that complements the self-report pain assessments is a great significant demand in several clinical applications. The aim of this paper is to propose a novel approach to objectively quantify the subjective perception of pain. We integrated signal processing techniques and machine learning principles to learn brain signals associated with pain and classify them into one of four pain intensities (no pain, low, moderate, and high). We found that the signal processing revealed a direct correlation between Alpha frequency band power and the pain intensity, and the classifier could achieve an accuracy of 94.83%. This study provides a clue for the betterment of the collective scientific understanding of the brain's activities inflicted by the physical pain and helps in building a reliable automated prediction of pain.

A systematic review of neurophysiological sensing for the assessment of acute pain

“…Power in Theta band (4–8 Hz) has also shown an increase (↑) after mechanical 59 and thermal pain 62 . Power in Alpha band (8–12 Hz) was the most common indicator in the literature, the power in this band showed a decreased (↓) after cold pressor test 60 , 61 , 63 and noxious laser stimulation 64 . Power in Beta band (12–30 Hz) showed an increase (↑) after heat stimulation 65 .…”

“…Power in Beta band (12–30 Hz) showed an increase (↑) after heat stimulation 65 . Finally, power in Gamma band (30–45 Hz) exhibited an increased (↑) after heat stimuli 62 , 65 and cold pressor test 63 .…”

“… 62 , a high-pass filter with a cutoff frequency of 0.25 Hz, while in refs. 63 , 64 , 72 , 83 , 84 a band-pass filter with a low- and high-cutoff frequency of 0.01–1 Hz and 30–100 Hz, were used respectively. Another common source of noise is the power line interference at 50 or 60 Hz, in ref.…”

“…Another distinct source of noise is eye movements and blinks, in ref. 63 a visual inspection and a subsequent manual rejection was implemented; while, in refs. 62 , 72 , 83 , 84 independent component analysis (ICA) was used, and in ref.…”

“…A popular machine learning model used in the literature is support vector machines (SVM) 43 , 94 , which often solves learning problems by using kernel functions to map the input data into higher-dimensional space in which the data can be separable (e.g., no pain or pain); kernel methods identified in the reviewed literature are Linear (L-SVM) 45 , 53 , 59 , 61 , 72 and Gaussian (G-SVM) 31 , 39 , 40 , 46 , 62 , 69 , 71 , 92 , with G-SVM showing better results than L-SVM. Other popular classification methods in the literature are random forest (RF) 29 , 34 , 37 , 38 , 42 , 49 , 84 , logistic regression (LR) 32 , 36 , 70 , 83 , k-nearest neighbour (KNN) 66 , 86 , 93 , discriminant function analysis (DFA) 33 , sparse Bayesian extreme learning machine (SBELM) 64 , and artificial neural networks (ANN) 41 , 56 , 63 . In addition, deep learning models such as deep belief network (DBN) 52 , convolutional neural networks(CNN) 35 , 96 , and bi-directional long-short term memory networks (Bi-LSTM) 85 were implemented to decode pain from sensor data.…”