建構以腦波評估疼痛程度之分析系統

疼痛在每個人的日常生活中是常見的主觀感受，當身體受到傷害性刺激時，大腦就會接收到疼痛的感覺，提醒我們對痛處趕緊處置。臨床上醫生為患者進行疼痛評估，主要是依據患者自身描述疼痛的感受且配合著數字等級刻度尺(NRS)等評估工具回答疼痛程度，才能針對疼痛進行有效的評估及管理，並依據世界衛生組織(WHO)施予疼痛緩解的治療方式，採用階梯原則(Analgesic Ladder)，以輕、中和重度疼痛之不同的疼痛程度，給予相應的治療劑量及的強度。然而，對於患有自主意識障礙(DOC)的患者或是因為自身因素而隱瞞自己的疼痛感受之患者，是無法提供確切的資訊，給予醫生對患者進行適切的疼痛緩解。因此針對此部分的患者，若是能將主觀的感覺以客觀的生理訊號進行數值的量化、分析和判斷疼痛程度，輔助臨床上現行的疼痛評估方式，以增加評估疼痛的精準度，減少誤判病情的機率，提升整體疼痛管理的品質。因此，本研究目的是透過腦波訊號的分析，分類出四種不同疼痛程度，藉以輔助醫生對於特殊患者，進行有效的評估級疼痛管理。本研究方法是使用自製熱刺激系統，對健康受試者誘發出四種不同疼痛程度的感受，分別是無、輕、中和重痛，透過NeuroScan腦電訊號擷取系統，將腦波取下來進行離線訊號分析。訊號分析前會先經過濾波和獨立成分分析(ICA)等預處理，再使用MATLAB軟體撰寫進行功率頻譜密度(PSD)和近似熵(ApEn)的演算分析，並依5個不同的腦區域和10個頻帶的組合後，得到不同區域和頻帶的特徵值，最後使用WEKA的平台對特徵值進行篩選，再以支持向量機(SVM)進行分類四種疼痛程度，結果所得到的分類準確率最高為67.19%。經由本實驗的結果，本研究之系統可分類出四種不同程度的疼痛，期望未來可藉由本雛形系統，提供研究分類疼痛程度的領域作為一個評估參考，建構一個完整的疼痛評估系統，以輔助醫生進行有效的疼痛管理。

關鍵字

腦波；疼痛程度；支持向量機

並列摘要

Pain is a common perception and subjective in everyone's daily life. when the body feel hurt, the brain will receive the perception of pain then to warn us to do pain relief. The clinician is depending on self-report (eg: NRS) to do the assessment of pain for patients, and give pain relief treatment based on the Analgesic Ladder by World Health Organization. The strength of painkiller administered is divided into three stages (none pain, mild pain, moderate pain and severe pain). However, doctors are not able to do accurate pain assessment when the patients have limited ability in expressing themselves, cognitive impairment or unwilling to give actual information. Therefore, to resolve this problem, physiological signals can be quantitative, analysis and evaluation of pain levels to reach the objective assessment of pain. And increase the accuracy of the assessment to support the current clinical assessment of pain, to improve the quality of the overall pain management. Therefore, the purpose of this study is developing the analysis system of four intensity of pain using EEG, to assist the doctors for special patients, with the effective assessment of pain management. This study used a self-made thermal contact-heat stimulator equipment, to induce four pain thresholds of heat pain potential for subjects. EEG signal was recorded using Neuroscan NuAmps system and to do filter and ICA by offline analysis. Following with power spectral density and approximate entropy were calculated using MATLAB, and according to 5 different brain regions and 10 different frequency bands to obtain the features. Finally, screen the features and SVM to classify the four intensity of pain using WEKA. The result provided up to 67.19% accuracy. In the study, the system can classify four intensity of pain, expected that can be used to provide a field of research for classification of pain as an evaluation reference by the prototype system, to construct a complete pain assessment system to assist the clinician in effective pain management.

並列關鍵字

EEG ； pain intensity ； SVM

參考文獻

[1] J. D. Loeser, and R.-D. Treede, “The Kyoto protocol of IASP Basic Pain Terminology,” Pain, vol. 137, no. 3, pp. 473-477, 2008.

[2] P. H. Berry, and J. L. Dahl, “The new JCAHO pain standards: implications for pain management nurses,” Pain Management Nursing, vol. 1, no. 1, pp. 3-12, 2000.

[4] W. H. Organization, Cancer pain relief and palliative care, World Health Organization, Geneva, 1990.

[6] G. A. Hawker, S. Mian, T. Kendzerska, and M. French, “Measures of adult pain: Visual analog scale for pain (vas pain), numeric rating scale for pain (nrs pain), mcgill pain questionnaire (mpq), short‐form mcgill pain questionnaire (sf‐mpq), chronic pain grade scale (cpgs), short form‐36 bodily pain scale (sf‐36 bps), and measure of intermittent and constant osteoarthritis pain (icoap),” Arthritis care & research, vol. 63, no. S11, pp. S240-S252, 2011.

[7] C. Schnakers, and N. D. Zasler, “Pain assessment and management in disorders of consciousness,” Current opinion in neurology, vol. 20, no. 6, pp. 620-626, 2007.

國際替代計量

建構以腦波評估疼痛程度之分析系統

全文下載

主題瀏覽