Abstract
Developing an objective pain identification system can provide caregivers with a second opinion to improve the treatment of patients who are unable to verbally communicate their pain. In this study, we present a new EEG-based approach for pain recognition. The proposed approach is employed to identify four different states that a human can feel during tonic cold pain stimulation. These states are the relax state, relax-to-pain state (RPS), pain state (PS), and pain-to-relax state (PRS). A sliding window has been used to decompose the EEG signals into overlapping segments. Each EEG segment is analyzed using the discrete wavelet transform to construct a time–frequency representation of the EEG signals and extract a set of nonlinear features. These features are used to construct a two-layer hierarchical classification framework that can identify the aforementioned four pain states. The first layer identifies whether an EEG segment is relax or pain segment. In the second layer, the pain segments are classified into one of the three pain states (i.e., RPS, PS, and PRS). To evaluate the performance of the proposed approach, we recorded EEG data for 24 healthy subjects who were exposed to tonic cold pain stimulation. Three procedures were employed to evaluate the capability of the approach to detect the four states associated with tonic cold pain stimulation. The experimental results demonstrate the efficacy of our approach for accurate tonic cold pain identification. Moreover, these promising results suggest the feasibility of expanding the proposed approach to characterize clinical pain, such as cancer-related pain.
Similar content being viewed by others
References
Abibullaev B, Kim MS, Seo HD (2010) Seizure detection in temporal lobe epileptic EEGs using the best basis wavelet functions. J Med Syst 34(4):755–765
Aftanas L, Reva N, Varlamov A, Pavlov S, Makhnev V (2004) Analysis of evoked EEG synchronization and desynchronization in conditions of emotional activation in humans: temporal and topographic characteristics. Neurosci Behav Physiol 34(8):859–867
Akansu AN, Haddad RA (2001) Multiresolution signal decomposition: transforms, subbands, and wavelets. Academic Press, Cambridge
Akin M (2002) Comparison of wavelet transform and FFT methods in the analysis of EEG signals. J Med Syst 26(3):241–247
Alazrai R, Alwanni H, Baslan Y, Alnuman N, Daoud M (2017) EEG-based brain–computer interface for decoding motor imagery tasks within the same hand using Choi–Williams time–frequency distribution. Sensors 17(9):1937
Alazrai R, Momani M, Daoud M (2017) Fall detection for elderly from partially observed depth-map video sequences based on view-invariant human activity representation. Appl Sci 7(4):316
Alazrai R, Mowafi Y, Lee CG (2015) Anatomical-plane-based representation for human–human interactions analysis. Pattern Recognit 48(8):2346–2363
Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27
Chen AC (1993) Human brain measures of clinical pain: a review i. Topographic mappings. Pain 54(2):115–132
Christine M, Matthew B, Roger C, Yvonne D, Craig H, Laurie H, Jahangir Malekiand Renee M (2008) Principles of analgesic use in the treatment of acute pain and cancer pain. American Pain Society, Glenview
Chua K, Chandran V, Rajendra Acharya U, Lim C (2009) Analysis of epileptic EEG signals using higher order spectra. J Med Eng Technol 33(1):42–50
Chua KC, Chandran V, Acharya UR, Lim CM (2011) Application of higher order spectra to identify epileptic EEG. J Med Syst 35(6):1563–1571
Delorme A, Makeig S (2004) Eeglab: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134(1):9–21
Dowman R, Rissacher D, Schuckers S (2008) Eeg indices of tonic pain-related activity in the somatosensory cortices. Clin Neurophysiol 119(5):1201–1212
Emotiv Systems Inc. San Francisco, C.: URL https://www.emotiv.com/
Gómez-Herrero G, De Clercq W, Anwar H, Kara O, Egiazarian K, Van Huffel S, Van Paesschen W (2006) Automatic removal of ocular artifacts in the eeg without an eog reference channel. In: Proceedings of the 7th IEEE nordic signal processing symposium, pp 130–133
Hadjileontiadis LJ (2015) Eeg-based tonic cold pain characterization using wavelet higher order spectral features. IEEE Trans Biomed Eng 62(8):1981–1991
Herr K, Coyne PJ, McCaffery M, Manworren R, Merkel S (2011) Pain assessment in the patient unable to self-report: position statement with clinical practice recommendations. Pain Manag Nurs 12(4):230–250
Ingvar M (1999) Pain and functional imaging. Philos Transe R Soc Lond B Biol Sci 354(1387):1347–1358
Kamdar MM (2010) Principles of analgesic use in the treatment of acute pain and cancer pain. J Palliat Med 13(2):217–218
Khokhar ZO, Xiao ZG, Menon C (2010) Surface emg pattern recognition for real-time control of a wrist exoskeleton. BioMed Eng OnLine 9(1):41
Lamothe M, Roy JS, Bouffard J, Gagné M, Bouyer LJ, Mercier C (2014) ffect of tonic pain on motor acquisition and retention while learning to reach in a force field. PLoS ONE 9(6):e99,159
Lawhern V, Hairston WD, McDowell K, Westerfield M, Robbins K (2012) Detection and classification of subject-generated artifacts in EEG signals using autoregressive models. J Neurosci Methods 208(2):181–189
Mohammadi Z, Frounchi J, Amiri M (2016) Wavelet-based emotion recognition system using EEG signal. Neural Comput Appl pp 1–6
Nicolas-Alonso LF, Gomez-Gil J (2012) Brain computer interfaces, a review. Sensors 12(2):1211–1279
Nikias CL, Mendel JM (1993) Signal processing with higher-order spectra. IEEE Sig Process Mag 10(3):10–37
Nir RR, Sinai A, Raz E, Sprecher E, Yarnitsky D (2010) Pain assessment by continuous eeg: association between subjective perception of tonic pain and peak frequency of alpha oscillations during stimulation and at rest. Brain Res 1344:77–86
Panavaranan P, Wongsawat Y (2013) Eeg-based pain estimation via fuzzy logic and polynomial kernel support vector machine. In: 6th Biomedical engineering international conference (BMEiCON), pp 1–4
Penfield W, Rasmussen T, Erickson T (1954) The cerebral cortex of man, a clinical study of localization of function. Am J Phys Med Rehabil 33(2):126
Press WH, Teukolsky SA, Vetterling WT, Flannery BP (2007) Numerical recipes 3rd edition: the art of scientific computing. Cambridge University Press, New York
Price DD (2000) Psychological and neural mechanisms of the affective dimension of pain. Science 288(5472):1769–1772
Rissacher D, Dowman R, Schuckers S (2007) Identifying frequency-domain features for an eeg-based pain measurement system. In: IEEE 33rd annual northeast bioengineering conference,, pp 114–115
Shao S, Shen K, Yu K, Wilder-Smith EP, Li X (2012) Frequency-domain eeg source analysis for acute tonic cold pain perception. Clin Neurophysiol 123(10):2042–2049
Sinke C, Schmidt K, Forkmann K, Bingel U (2015) Phasic and tonic pain differentially impact the interruptive function of pain. PLoS ONE 10(2):e0118,363
Stam CJ (2005) Nonlinear dynamical analysis of eeg and meg: review of an emerging field. Clin Neurophysiol 116(10):2266–2301
Subha DP, Joseph PK, Acharya UR, Lim CM (2010) Eeg signal analysis: a survey. J Med Syst 34(2):195–212
Treede RD, Kenshalo DR, Gracely RH, Jones AK (1999) The cortical representation of pain. Pain 79(2):105–111
Vatankhah M, Toliyat A (2016) Pain level measurement using discrete wavelet transform. Int J Eng Technol 8(5):380
Williamson A, Hoggart B (2005) Pain: a review of three commonly used pain rating scales. J Clin Nurs 14(7):798–804
Acknowledgements
This research is supported by the Seed Grant program at the German Jordanian University (Grant no. SAMS 8/2014), and partially supported by the Scientific Research Support Fund - Jordan (Grant no. ENG/1/9/2015).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Alazrai, R., Momani, M., Khudair, H.A. et al. EEG-based tonic cold pain recognition system using wavelet transform. Neural Comput & Applic 31, 3187–3200 (2019). https://doi.org/10.1007/s00521-017-3263-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3263-6