Black-white hole pattern: an investigation on the automated chronic neuropathic pain detection using EEG signals

Irem Tasci1, Mehmet Baygin2, Prabal Datta Barua3, Abdul Hafeez-Baig4, Sengul Dogan5, Turker Tuncer5, Ru-San Tan6,7, U. Rajendra Acharya8
1Department of Neurology, School of Medicine, Firat University, Elazig, Turkey
2Department of Computer Engineering, Faculty of Engineering and Architecture, Erzurum Technical University, Erzurum, Turkey
3School of Business (Information System), University of Southern Queensland, Toowoomba, Australia
4School of Management and Enterprise, University of Southern Queensland, Toowoomba, Australia
5Department of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, Turkey
6Duke-NUS Medical School, Singapore, Singapore
7Department of Cardiology, National Heart Centre Singapore, Singapore, Singapore
8School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia

Tóm tắt

Electroencephalography (EEG) signals provide information about the brain activities, this study bridges neuroscience and machine learning by introducing an astronomy-inspired feature extraction model. In this work, we developed a novel feature extraction function, black-white hole pattern (BWHPat) which dynamically selects the most suitable pattern from 14 options. We developed BWHPat in a four-phase feature engineering model, involving multileveled feature extraction, feature selection, classification, and cortex map generation. Textural and statistical features are extracted in the first phase, while tunable q-factor wavelet transform (TQWT) aids in multileveled feature extraction. The second phase employs iterative neighborhood component analysis (INCA) for feature selection, and the k-nearest neighbors (kNN) classifier is applied for classification, yielding channel-specific results. A new cortex map generation model highlights the most active channels using median and intersection functions. Our BWHPat-driven model consistently achieved over 99% classification accuracy across three scenarios using the publicly available EEG pain dataset. Furthermore, a semantic cortex map precisely identifies pain-affected brain regions. This study signifies the contribution to EEG signal classification and neuroscience. The BWHPat pattern establishes a unique link between astronomy and feature extraction, enhancing the understanding of brain activities.

Từ khóa


Tài liệu tham khảo

Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 123:69–87 Anderson K, Chirion C, Fraser M, Purcell M, Stein S, Vuckovic A (2021) Markers of central neuropathic pain in Higuchi fractal analysis of EEG signals from people with spinal cord injury. Front Neurosci 15:705652 Aydın S (2022) Cross-validated adaboost classification of emotion regulation strategies identified by spectral coherence in resting-state. Neuroinformatics 20:627–639 Aydın S, Onbaşı L (2023) Graph theoretical brain connectivity measures to investigate neural correlates of music rhythms associated with fear and anger Cognitive Neurodynamics:1–18 Bonanni R, Cariati I, Tancredi V, Iundusi R, Gasbarra E, Tarantino U (2022) Chronic pain in musculoskeletal diseases: do you know your enemy? J Clin Med 11:2609 Campbell JN, Meyer RA (2006) Mechanisms of neuropathic pain. Neuron 52:77–92 Cascella M et al (2023) Artificial intelligence for automatic pain assessment: research methods and perspectives. Pain Res Manag 2023:6018736 Chen D et al (2022) Scalp EEG-based pain detection using convolutional neural network. IEEE Trans Neural Syst Rehabil Eng 30:274–285 Cohen SP, Mao J (2014) Neuropathic pain: mechanisms and their clinical implications. Bmj 348:f7656. https://doi.org/10.1136/bmj.f7656 Dansie EJ, Turk DC (2013) Assessment of patients with chronic pain. Br J Anaesth 111:19–25 Elsayed M, Sim KS, Tan SC (2020) A novel approach to objectively quantify the subjective perception of pain through electroencephalogram signal analysis. IEEE Access 8:199920–199930 Erdemoglu AK, Koc R (2013) Brief Pain Inventory score identifying and discriminating neuropathic and nociceptive pain. Acta Neurol Scand 128:351–358 Finnerup NB et al (2018) Neuropathic pain clinical trials: factors associated with decreases in estimated drug efficacy. Pain 159:2339 Fisher R, Clarkson E (2023) Medication management of neuropathic pain disorders. Dent Clin 68(1):121–131 Freynhagen R, Baron R, Gockel U, Tölle TR (2006) Pain DETECT: a new screening questionnaire to identify neuropathic components in patients with back pain. Curr Med Res Opin 22:1911–1920 Goldberger J, Hinton GE, Roweis S, Salakhutdinov RR (2004) Neighbourhood components analysis. Adv Neural Inf Process Syst 17:513–520 Hinton G (2022) The forward-forward algorithm: some preliminary investigations. arXiv preprint arXiv:2212.13345 Kim HJ, Ban MG, Yoon KB, Yang YS, Kim SH (2023) Neuropathic pain component and its association with time elapsed since pain onset in patients with low back pain. Pain Pract 23(6):580–588 Lubec D, Müllbacher W, Finsterer J, Mamoli B (1999) Diagnostic work-up in peripheral neuropathy: an analysis of 171 cases. Postgrad Med J 75:723–727 Mussigmann T, Bardel B, Lefaucheur J-P (2022) Resting-state electroencephalography (EEG) biomarkers of chronic neuropathic pain. A systematic review. Neuroimage 258:119351 Nezam T, Boostani R, Abootalebi V, Rastegar K (2018) A novel classification strategy to distinguish five levels of pain using the EEG signal features. IEEE Trans Affect Comput 12:131–140 Nishikawa N, Nomoto M (2017) Management of neuropathic pain. J General Family Med 18:56–60 Nudell Y, Dym H, Sun F, Benichou M, Malakan J, Halpern LR (2022) Pharmacologic management of neuropathic pain. Oral Maxillofac Surg Clin 34:61–81 Özçelik YB, Altan A (2023) Overcoming nonlinear dynamics in diabetic retinopathy classification: a robust AI-based model with chaotic swarm intelligence optimization and recurrent long short-term memory. Fractal Fract 7:598 Özcelik YB, Altan A (2023) Classification of diabetic retinopathy by machine learning algorithm using entorpy-based features Peterson LE (2009) K-nearest neighbor. Scholarpedia 4:1883 Powers DM (2020) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061 Sah DWY, Ossipo MH, Porreca F (2003) Neurotrophic factors as novel therapeutics for neuropathic pain. Nat Rev Drug Discov 2:460–472 Salvi M, Loh HW, Seoni S, Barua PD, García S, Molinari F, Acharya UR (2023) Multi-modality approaches for medical support systems: a systematic review of the last decade. Inf Fusion 103:102134 Scholz J et al (2019) The IASP classification of chronic pain for ICD-11: chronic neuropathic pain. Pain 160:53 Selesnick IW (2011) Wavelet transform with tunable Q-factor. IEEE Trans Sig Process 59:3560–3575 Seoni S, Jahmunah V, Salvi M, Barua PD, Molinari F, Acharya UR (2023) Application of uncertainty quantification to artificial intelligence in healthcare: a review of last decade (2013–2023). Comput Biol Med 165:107441 Sheldon BL, Olmsted ZT, Sabourin S, Heydari E, Harland TA, Pilitsis JG (2022) Review of the Treatments for Central Neuropathic Pain. Brain Sci 12:1727 Shinu P et al (2022) Novel therapies for the treatment of neuropathic pain: potential and pitfalls. J Clin Med 11:3002 Szczudlik A et al (2014) Diagnosis and management of neuropathic pain: review of literature and recommendations of the Polish Association for the Study of Pain and the Polish Neurological Society–part two. Neurol Neurochir. Polska 48:423–435 Tuncer T, Dogan S, Özyurt F, Belhaouari SB, Bensmail H (2020a) Novel multi center and threshold ternary pattern based method for disease detection method using voice. IEEE Access 8:84532–84540 Tuncer T, Dogan S, Subasi A (2020b) Surface EMG signal classification using ternary pattern and discrete wavelet transform based feature extraction for hand movement recognition. Biomed Sig Process Control 58:101872 Vorobeychik Y, Gordin V, Mao J, Chen L (2011) Combination therapy for neuropathic pain: a review of current evidence. CNS Drugs 25:1023–1034 Yang S, Chang MC (2019) Chronic pain: structural and functional changes in brain structures and associated negative affective states. Int J Mol Sci 20:3130 Zolezzi DM, Alonso-Valerdi LM, Ibarra-Zarate DI (2023a) EEG frequency band analysis in chronic neuropathic pain: a linear and nonlinear approach to classify pain severity. Comput Methods Program Biomed 230:107349 Zolezzi DM, Naal-Ruiz NE, Alonso-Valerdi LM, Ibarra-Zarate DI (2023b) Chronic neuropathic pain: EEG data in eyes open and eyes closed with painDETECT and brief pain inventory reports. Data Brief 48:109060