Abstract

Pain is a highly unpleasant sensory and emotional experience, and no objective diagnosis test exists to assess it. In clinical practice there are two main methods for the estimation of pain, a patient’s self-report and clinical judgement. However, these methods are highly subjective and the need of biomarkers to measure pain is important to improve pain management, reduce risk factors, and contribute to a more objective, valid, and reliable diagnosis. Therefore, in this study we propose the use of functional near-infrared spectroscopy (fNIRS) and machine learning for the identification of a possible biomarker of pain. We collected pain information from 18 volunteers using the thermal test of the quantitative sensory testing (QST) protocol, according to temperature level (cold and hot) and pain intensity (low and high). Feature extraction was completed in three different domains (time, frequency, and wavelet), and a total of 69 features were obtained. Feature selection was carried out according to three criteria, information gain (IG), joint mutual information (JMI), and Chi-squared (χ2). The significance of each feature ranking was evaluated using three learning models separately, linear discriminant analysis (LDA), the K-nearest neighbour (K-NN) and support vector machines (SVM) using the linear and Gaussian and polynomial kernels. The results showed that the Gaussian SVM presented the highest accuracy (94.17%) using only 25 features to identify the four types of pain in our database. In addition, we propose the use of the top 13 features according to the JMI criteria, which exhibited an accuracy of 89.44%, as promising biomarker of pain. This study contributes to the idea of developing an objective assessment of pain and proposes a potential biomarker of human pain using fNIRS.

Highlights

  • Pain itself is a biomarker of many diseases, injuries, or emotional stress and serves as warning mechanism for the brain to act against something wrong in the body[1]

  • Thermal threshold and tolerance of pain perception were obtained following the thermal test in the quantitative sensory testing (QST)

  • By obtaining the QST thermal tests, we aimed to minimize the subjective nature of self-reported pain scores and to apply a set of standard stimuli to all the participants

Read more

Summary

Introduction

Pain itself is a biomarker of many diseases, injuries, or emotional stress and serves as warning mechanism for the brain to act against something wrong in the body[1]. Bornhovd et al.[3] described the tasks that the pain processing system serves to prevent potentially life-threatening conditions: collect and analyse nociceptive sensory input, shift the focus of attention towards pain processing, maintain pain-related information in working memory, have prompt communication with the motor system to avoid further damage, and memory-encode the problem to avoid future damage All of these actions induced by the human pain mechanism have obvious importance for survival. Activation of brain areas related to the processing of pain can be identified in response to noxious stimuli[8] One of these neuroimaging methods is functional near-infrared spectroscopy (fNIRS), which facilitates (in a non-invasive manner) the measurement of brain activity by reading cerebral haemodynamics and oxygenation[9]. This technique has been widely used in diverse clinical and experimental settings, offering advantages over other technologies (fMRI, EEG, PET) such as, better temporal and spatial resolution, less exposure to ionising radiation, safe to use over long periods and repeatedly, less expensive, easy to use, and portable[10]

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call