研究生: |
林冠翔 Guan-Siang Lin |
---|---|
論文名稱: |
基於放鬆及任務狀態腦波功能性連結之偏頭痛有無睡眠品質不佳分類研究 Classification of migraine with poor sleep quality based on resting-state and task EEG functional connectivity |
指導教授: |
劉益宏
Yi-Hung Liu |
口試委員: |
劉益宏
Yi-Hung Liu 楊富吉 Fu-Chi Yang 林鈺凱 Yu-Kai Lin 劉孟昆 Meng-Kun Liu |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2022 |
畢業學年度: | 110 |
語文別: | 中文 |
論文頁數: | 95 |
中文關鍵詞: | 偏頭痛 、睡眠品質不良 、腦電圖 、功能性連結 |
外文關鍵詞: | Migraine, Poor sleep quality, EEG, Functional connectivity |
相關次數: | 點閱:215 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
偏頭痛是常見且會嚴重影響生活品質的疾病,患者中約有30%-50%有睡眠障礙,若未及時治療偏頭痛及其共病,睡眠品質不佳容易惡化為失眠。過往使用腦電圖(Electroencephalography, EEG)訊號進行偏頭痛(Migraine)的研究中,主要為偏頭痛與健康受測者的比較、偏頭痛階段或有無預兆的比較,尚無使用EEG針對偏頭痛有無共病睡眠品質不佳的研究,因次本論文共收集19位有睡眠品質不佳的偏頭痛患者(MwPSQ)、17位無睡眠品質不佳的偏頭痛患者(MwoPSQ)和15位健康對照組(HC)在心算(mental arithmetic, MA)、心算前閉眼放鬆(eye-closed resting state before the MA task, Pre-resting)的EEG進行分析,並使用Pre-resting作為基準,得到校正(Basline correction)後的MA(校正)等三種狀態,希望藉由機器學習演算法找出可用於區分有無共病睡眠品質不佳之偏頭痛患者的獨特腦波生物標記。
由於偏頭痛患者與失眠患者皆有大腦功能性連結異常的狀況,故本論文使用連結性特徵作為EEG評估手段,分別採用相干性(Magnitude-squared coherence, Coh)、虛部相干性(Imaginary part of coherence, ImC)及相位延遲指數(Phase lag index, PLI)進行特徵抽取,並使用費雪準則進行特徵篩選,線性鑑別分析(Linear Discriminant Analysis, LDA)及非線性支持向量機(Nonliner Support Vector Machine,Nonlinear SVM)進行分類,最後整合分類結果最佳的特徵組並輸出腦波評估指標(EEG Assessment Index,EAI),再與匹茲堡睡眠品質量表(The Pittsburgh Sleep Quality Index, PSQI)進行相關性分析。研究結果顯示:一、使用PLI分類結果最佳;二、於MA及MA(校正)下分類表現優於Pre-resting;三、Nonlinear SVM分類表現優於LDA;四、使用PLI特徵可精準判斷偏頭痛患者有無睡眠品質不佳, MA下使用LDA:MwPSQ vs MwoPSQ可達97.4%分類率,於Pre-resting下使用SVM亦可達97.4%分類率;五、EAI可與PSQI總分及部分細項達到高度相關性,可幫助醫師快速評估患者病症嚴重程度及追蹤治療成效。
Migraine is a common disease that affect patients’s quality of life, and about 30%-50% of migraines are affected by sleep disorders. Both poor sleep quality and insomnia are sleep disorders. If not treated properly, poor sleep quality is likely to worsen and become insomnia.There have been many studies using EEG signals to conduct migrain research,but the main topics are about difference between migraineurs and healthy controls,difference between migraineurs with aura and without aura,or between each phase during migraine attack.We haven’t discover EEG research wich focus on the difference between migraineurs that with and without poor sleep quality.Therefore, in this study we collects the EEG of 19 migraineurs with poor sleep quality(MwPSQ), and 17 migraineurs without poor sleep quality(MwoPSQ), and 15 healthy controls(HC) during mental arithmetic(MA), eye-closed resting state before the MA task( Pre-resting), and using Pre-resting as baseline to obtain MA(baseline correction).This study aims to find the unique EEG biomarker of MwPSQ and MwoPSQ by machine learning algorithm.
This study use Magnitude-squared coherence(Coh), Imaginary part of coherence(ImC) and Phase lag index(PLI) as EEG feature.Feature selection was done by Fisher criterion, and classification was done by Linear Discriminant Analysis(LDA) and Nonlinear support vector machin(Nonlinear SVM).The features with best classification results will be intergrated to obtain the EEG Assessment Index(EAI).We use Pearson correlation coefficient to evaluate the correlation beween EAI and The Pittsburgh Sleep Quality Index(PSQI).Results show that 1.PLI outperforms ImC and Coh, 2. MA or MA(baseline correction) is better than just using resting-state, 3.Nonliner SVM outperforms LDA, 4.By using PLI in MA : MwPSQ vs MwoPSQ, LDA can achieve a Balance classification rate of 97.4% (B-CR).And in Pre-resting, SVM can achieve B-CR of 97.4%, 5.EAI is highly correlated with PSQI,it can be a new approach for doctors to evaluate patients, and it can also be used to track the therapeutic effect.
[1] S.-J. Wang, J.-L. Fuh, Y.-H. Young, S.-R. Lu, and B.-C. Shia, “Prevalence of migraine in Taipei, Taiwan: A population-based survey,” Cephalalgia, vol. 20, no. 6, pp. 566–572, 2000.
[2] S.-J. Wang, J.-L. Fuh, K.-D. Juang, and S.-R. Lu, “Rising prevalence of migraine in Taiwanese adolescents aged 13-15 years,” Cephalalgia, vol. 25, no. 6, pp. 433–438, 2005.
[3] S.-J. Wang, H.-C. Liu, J.-L. Fuh, C.-Y. Liu, K.-P. Lin, H.-M. Chen, C.-H. Lin, P.-N. Wang, L.-C. Hsu, H.-C. Wang, and K.-N. Lin, “Prevalence of headaches in a Chinese elderly population in Kinmen: Age and gender effect and cross-cultural comparisons,” Neurology, vol. 49, no. 1, pp. 195–200, 1997.
[4] M. Leonardi and A. Raggi, “Burden of migraine: International perspectives,” Neurological Sciences, vol. 34, no. S1, pp. 117–118, 2013.
[5] J. Zeitlhofer, A. Schmeiser-Rieder, G. Tribl, A. Rosenberger, J. Bolitschek, G. Kapfhammer, B. Saletu, H. Katschnig, B. Holzinger, R. Popovic, and M. Kunze, “Sleep and quality of life in the Austrian population,” Acta Neurologica Scandinavica, vol. 102, no. 4, pp. 249–257, 2000.
[6] L. Kelman and J. C. Rains, “Headache and sleep: Examination of sleep patterns and complaints in a large clinical sample of migraineurs,” Headache: The Journal of Head and Face Pain, vol. 45, no. 7, pp. 904–910, 2005.
[7] Y.-K. Lin, G.-Y. Lin, J.-T. Lee, M.-S. Lee, C.-K. Tsai, Y.-W. Hsu, Y.-Z. Lin, Y.-C. Tsai, and F.-C. Yang, “Associations between sleep quality and migraine frequency,” Medicine, vol. 95, no. 17, 2016.
[8] P. Sahota, “Morning headaches in patients with sleep disorders,” Sleep Medicine, vol. 4, no. 5, p. 377, 2003.
[9] S. S. Ødegård, T. Sand, M. Engstrøm, L. J. Stovner, J.-A. Zwart, and K. Hagen, “The long-term effect of insomnia on primary headaches: A prospective population-based cohort study (Hunt-2 and hunt-3),” Headache: The Journal of Head and Face Pain, vol. 51, no. 4, pp. 570–580, 2011.
[10] S. S. Ødegård, T. Sand, M. Engstrøm, L. J. Stovner, J.-A. Zwart, and K. Hagen, “The long-term effect of insomnia on primary headaches: A prospective population-based cohort study (Hunt-2 and hunt-3),” Headache: The Journal of Head and Face Pain, vol. 51, no. 4, pp. 570–580, 2011.
[11] S. S. Ødegård, T. Sand, M. Engstrøm, J.-A. Zwart, and K. Hagen, “The impact of headache and chronic musculoskeletal complaints on the risk of insomnia: Longitudinal data from the Nord-Trøndelag Health Study,” The Journal of Headache and Pain, vol. 14, no. 1, 2013.
[12] Y.-K. Lin, G.-Y. Lin, J.-T. Lee, M.-S. Lee, C.-K. Tsai, Y.-W. Hsu, Y.-Z. Lin, Y.-C. Tsai, and F.-C. Yang, “Associations between sleep quality and migraine frequency,” Medicine, vol. 95, no. 17, 2016.
[13] M. S. Mykland, M. H. Bjørk, M. Stjern, and T. Sand, “Alterations in post-movement beta event related synchronization throughout the migraine cycle: A controlled, Longitudinal Study,” Cephalalgia, vol. 38, no. 4, pp. 718–729, 2017.
[14] Y. Fogang, P. Gérard, V. De Pasqua, J. L. Pepin, M. Ndiaye, D. Magis, and J. Schoenen, “Analysis and clinical correlates of 20 Hz photic driving on routine EEG in Migraine,” Acta Neurologica Belgica, vol. 115, no. 1, pp. 39–45, 2014.
[15] M. S. Mykland, M. H. Bjørk, M. Stjern, P. M. Omland, M. Uglem, and T. Sand, “Fluctuations of sensorimotor processing in migraine: A Controlled Longitudinal Study of beta event related desynchronization,” The Journal of Headache and Pain, vol. 20, no. 1, 2019.
[16] G. Shahaf, P. Kuperman, Y. Bloch, S. Yariv, and Y. Granovsky, “Monitoring migraine cycle dynamics with an easy-to-use electrophysiological marker—a pilot study,” Sensors, vol. 18, no. 11, p. 3918, 2018.
[17] L. O’Hare, F. Menchinelli, and S. J. Durrant, “Resting-state alpha-band oscillations in Migraine,” Perception, vol. 47, no. 4, pp. 379–396, 2018.
[18] Z. Cao, C.-T. Lin, K.-L. Lai, L.-W. Ko, J.-T. King, K.-K. Liao, J.-L. Fuh, and S.-J. Wang, “Extraction of ssveps-based inherent fuzzy entropy using a wearable headband EEG in migraine patients,” IEEE Transactions on Fuzzy Systems, vol. 28, no. 1, pp. 14–27, 2020.
[19] A. Frid, M. Shor, A. Shifrin, D. Yarnitsky, and Y. Granovsky, “A biomarker for discriminating between migraine with and without aura: Machine learning on functional connectivity on resting-state eegs,” Annals of Biomedical Engineering, vol. 48, no. 1, pp. 403–412, 2019.
[20] Z. Cao, K.-L. Lai, C.-T. Lin, C.-H. Chuang, C.-C. Chou, and S.-J. Wang, “Exploring resting-state EEG complexity before migraine attacks,” Cephalalgia, vol. 38, no. 7, pp. 1296–1306, 2017.
[21] S. B. Akben, D. Tuncel, and A. Alkan, “ Classification of multi-channel EEG signals for migraine detection.”Biomedical Research-INDIA, vol. 27, no. 3,pp 743–748, 2016.
[22] Z. Cao, C.-T. Lin, C.-H. Chuang, K.-L. Lai, A. C. Yang, J.-L. Fuh, and S.-J. Wang, “Resting-state EEG power and coherence vary between migraine phases,” The Journal of Headache and Pain, vol. 17, no. 1, 2016.
[23] J. Mehnert, D. Bader, G. Nolte, and A. May, “Visual input drives increased occipital responsiveness and harmonized oscillations in multiple cortical areas in migraineurs,” NeuroImage: Clinical, vol. 23, p. 101815, 2019.
[24] A. Subasi, A. Ahmed, E. Aličković, and A. Rashik Hassan, “Effect of photic stimulation for migraine detection using random forest and discrete wavelet transform,” Biomedical Signal Processing and Control, vol. 49, pp. 231–239, 2019.
[25] M. de Tommaso, G. Trotta, E. Vecchio, K. Ricci, F. Van de Steen, A. Montemurno, M. Lorenzo, D. Marinazzo, R. Bellotti, and S. Stramaglia, “Functional connectivity of EEG signals under laser stimulation in Migraine,” Frontiers in Human Neuroscience, vol. 9, 2015.
[26] M. de Tommaso, S. Stramaglia, D. Marinazzo, G. Trotta, and M. Pellicoro, “Functional and effective connectivity in EEG alpha and beta bands during intermittent flash stimulation in migraine with and without aura,” Cephalalgia, vol. 33, no. 11, pp. 938–947, 2013.
[27] M. de Tommaso, G. Trotta, E. Vecchio, K. Ricci, R. Siugzdaite, and S. Stramaglia, “Brain networking analysis in migraine with and without aura,” The Journal of Headache and Pain, vol. 18, no. 1, 2017.
[28] J. Gomez-Pilar, D. García-Azorín, C. Gomez-Lopez-de-San-Roman, Á. L. Guerrero, and R. Hornero, “Exploring EEG spectral patterns in episodic and chronic migraine during the interictal state: Determining frequencies of interest in the resting state,” Pain Medicine, vol. 21, no. 12, pp. 3530–3538, 2020.
[29] A. Osama, A. Abo Hagar, M. Negm, and I. Hashish, “Peak power frequency changes in patients with migraine.” Egyptian Journal of Neurology, vol. 50 , no. 1,pp 67–72, 2013.
[30] M. H. Bjørk, L. J. Stovner, M. Engstrøm, M. Stjern, K. Hagen, and T. Sand, “Interictal quantitative EEG in Migraine: A Blinded Controlled Study,” The Journal of Headache and Pain, vol. 10, no. 5, pp. 331–339, 2009.
[31] Y. S. Koo, D. Ko, G.-T. Lee, K. Oh, M.-S. Kim, K. H. Kim, C.-H. Im, and K.-Y. Jung, “Reduced frontal P3A amplitude in migraine patients during the pain-free period,” Journal of Clinical Neurology, vol. 9, no. 1, p. 43, 2013.
[32] M. de Tommaso, D. Marinazzo, M. Guido, G. Libro, S. Stramaglia, L. Nitti, G. Lattanzi, L. Angelini, and M. Pellicoro, “Visually evoked phase synchronization changes of alpha rhythm in migraine: Correlations with clinical features,” International Journal of Psychophysiology, vol. 57, no. 3, pp. 203–210, 2005.
[33] T. Xue, K. Yuan, L. Zhao, D. Yu, L. Zhao, T. Dong, P. Cheng, K. M. von Deneen, W. Qin, and J. Tian, “Intrinsic brain network abnormalities in migraines without aura revealed in resting-state fmri,” PLoS ONE, vol. 7, no. 12, 2012.
[34] R. E. Challis and R. I. Kitney, “Biomedical Signal Processing (in four parts),” Medical & Biological Engineering & Computing, vol. 28, no. 6, pp. 509–524, 1990.
[35] R. Srinivasan, W. R. Winter, J. Ding, and P. L. Nunez, “EEG and Meg Coherence: Measures of functional connectivity at distinct spatial scales of neocortical dynamics,” Journal of Neuroscience Methods, vol. 166, no. 1, pp. 41–52, 2007.
[36] G. Nolte, O. Bai, L. Wheaton, Z. Mari, S. Vorbach, and M. Hallett, “Identifying true brain interaction from EEG data using the imaginary part of coherency,” Clinical Neurophysiology, vol. 115, no. 10, pp. 2292–2307, 2004.
[37] C. J. Stam, G. Nolte, and A. Daffertshofer, “Phase lag index: Assessment of functional connectivity from multi channel EEG and Meg with diminished bias from common sources,” Human Brain Mapping, vol. 28, no. 11, pp. 1178–1193, 2007.
[38] G.H. Klem and J.W. Lüders and H.H. Jasper and C. Elger. “The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology.” Electroencephalography and Clinical Neurophysiology, vol. 52, pp. 3–6, 1999.
[39] E. Fasiello, M. Gorgoni, S. Scarpelli, V. Alfonsi, L. Ferini Strambi, and L. De Gennaro, “Functional connectivity changes in insomnia disorder: A systematic review,” Sleep Medicine Reviews, vol. 61, p. 101569, 2022.
[40] B. Ratner, “The correlation coefficient: Its values range between +1/−1, or do they?,” Journal of Targeting, Measurement and Analysis for Marketing, vol. 17, no. 2, pp. 139–142, 2009.
[41] Y. Li, E. Wang, H. Zhang, S. Dou, L. Liu, L. Tong, Y. Lei, M. Wang, J. Xu, D. Shi, and Q. Zhang, “Functional connectivity changes between parietal and prefrontal cortices in primary insomnia patients: Evidence from resting-state fmri,” European Journal of Medical Research, vol. 19, no. 1, 2014.
[42] M. Yu, “Benchmarking metrics for inferring functional connectivity from multi-channel EEG and MEG: A simulation study,” Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 30, no. 12, p. 123124, 2020.
[43] J. J. González, S. Mañas, L. De Vera, L. D. Méndez, S. López, J. M. Garrido, and E. Pereda, “Assessment of electroencephalographic functional connectivity in term and preterm neonates,” Clinical Neurophysiology, vol. 122, no. 4, pp. 696–702, 2011.
[44] M. Vinck, R. Oostenveld, M. van Wingerden, F. Battaglia, and C. M. A. Pennartz, “An improved index of phase-synchronization for electrophysiological data in the presence of volume-conduction, noise and sample-size bias,” NeuroImage, vol. 55, no. 4, pp. 1548–1565, 2011.
[45] L. R. Peraza, A. U. R. Asghar, G. Green, and D. M. Halliday, “Volume conduction effects in brain network inference from electroencephalographic recordings using phase lag index,” Journal of Neuroscience Methods, vol. 207, no. 2, pp. 189–199, 2012.
[46] E. Ortiz, K. Stingl, J. Münßinger, C. Braun, H. Preissl, and P. Belardinelli, “Weighted phase lag index and Graph Analysis: Preliminary investigation of functional connectivity during resting state in children,” Computational and Mathematical Methods in Medicine, vol. 2012, pp. 1–8, 2012.
[47] S. Okuhata and T. Kobayashi, “Coherence and phase lag index analyses — a preliminary MEG/EEG sensor-level study on functional connectivities during the Sternberg memory task,” International Journal of Psychophysiology, vol. 94, no. 2, pp. 131–132, 2014.
[48] A. Khadem and G.-A. Hossein-Zadeh, “Quantification of the effects of volume conduction on the EEG/MEG Connectivity Estimates: An index of sensitivity to brain interactions,” Physiological Measurement, vol. 35, no. 10, pp. 2149–2164, 2014.
[49] L. S. Imperatori, M. Betta, L. Cecchetti, A. C. Johnson, E. Ricciardi, F. Siclari, P. Pietrini, S. Chennu, and G. Bernardi, “EEG functional connectivity metrics WPLI and WSMI account for D distinct types of brain functional interactions,” 2018.
[50] A. U. Patil, A. Dube, R. K. Jain, G. D. Jindal, and D. Madathil, “Classification and comparative analysis of control and migraine subjects using EEG signals,” Advances in Intelligent Systems and Computing, pp. 31–39, 2018.
[51] A. Subasi, A. Ahmed, and E. Alickovic, “Effect of flash stimulation for migraine detection using decision tree classifiers,” Procedia Computer Science, vol. 140, pp. 223–229, 2018.
[52] K. Jindal, R. Upadhyay, H. S. Singh, M. Vijay, A. Sharma, K. Gupta, J. Gupta, and A. Dube, “Migraine disease diagnosis from EEG signals using non-linear feature extraction technique,” 2018 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2018.
[53] B. Zhu, G. Coppola, and M. Shoaran, “Migraine classification using somatosensory evoked potentials,” Cephalalgia, vol. 39, no. 9, pp. 1143–1155, 2019.
[54] Z. Taufique, B. Zhu, G. Coppola, M. Shoaran, and M. A. Altaf, “A low power multi-class migraine detection processor based on somatosensory evoked potentials,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 5, pp. 1720–1724, 2021.
[55] Z. ASLAN, “Migraine detection from EEG signals using tunable Q-factor wavelet transform and Ensemble Learning Techniques,” 2021.
[56] C. T. Briels, D. N. Schoonhoven, C. J. Stam, H. de Waal, P. Scheltens, and A. A. Gouw, “Reproducibility of EEG functional connectivity in alzheimer’s disease,” Alzheimer's Research & Therapy, vol. 12, no. 1, 2020.
[57] Y. Fu Yu, “Classification of migraine with poor sleep quality based on resting and task EEG,” MSc Dissertation, Inst. of Mechatronic Engineering, Taipei Tech, Taipei, Taiwan, 2021.
[58] M. de Tommaso, E. Vecchio, S. G. Quitadamo, G. Coppola, A. Di Renzo, V. Parisi, M. Silvestro, A. Russo, and G. Tedeschi, “Pain-related brain connectivity changes in Migraine: A narrative review and proof of concept about possible novel treatments interference,” Brain Sciences, vol. 11, no. 2, p. 234, 2021.
[59] Q. Wang and O. Sourina, “Real-time mental arithmetic task recognition from EEG signals,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 21, no. 2, pp. 225–232, 2013.
[60] J. Owens, “Sleep disorders and attention-deficit/hyperactivity disorder,” Current Psychiatry Reports, vol. 10, pp. 439, 2008.