腦中風是台灣重大疾病之一，而中風後的復健十分重要，有效率的復健策略可以提高中風病人痊癒的可能性，因此對於中風後的預測與判斷更是重要的一環。許多關於個體差異的神經影像學研究都注重於在建立大腦測量值與特徵（例如智力，記憶力，注意力或疾病症狀）之間的相關關係。藉由科技的進步及大量收集的數據資料能夠建立一個能從神經影像取得的大腦關聯性來預測中風病人復健狀況的模型。本論文利用聯結體來建立模型，這個方法主要分成四個部分，特徵選取、特徵總結、建立模型及評估預測效果。本論文運用中風病人的靜息態腦功能性磁振造影及復健量表參數來完成聯結體模型的建立，以利於往後復健策略的改善與調整。

Stroke is one of the major diseases in Taiwan, and rehabilitation after a stroke is very important. Effective rehabilitation strategies can increase the possibility of stroke patients' recovery. Therefore, it is important to predict and judge after stroke. Many neuroimaging studies of individual differences have focused on establishing correlational relationships between brain measurements and traits such as intelligence, memory, and attention, or disease symptoms. Through the advancement of technology and a large amount of collected data, a model can be established to predict the rehabilitation status of stroke patients by brain correlation obtained from neuroimaging. We will present Connectome-based predictive modeling in this case. This method is mainly divided into four parts, feature selection, feature summarization, model building and assessment of prediction significance. We use fMRI and rehabilitation scale parameters of stroke patients to complete the establishment of the CPM model, in order to facilitate the improvement and adjustment of rehabilitation strategies in the future.

〔1〕 吳孟潔, 腦中風怎麼復健？如何快速辨別腦中風，後遺症與復健歷程, 2019, https://drbao.org/stroke3/
〔2〕 朱芷君, 6觀念，中風復健不再難, 康健雜誌 第187期, 2014,https://www.commonhealth.com.tw/article/article.action?nid=68459
〔3〕 魏大森, 腦中風患者的復健治療, 2010, https://www1.cch.org.tw/knowledge/knowledge_1_1_det ail.aspx?oid=785&no=1&pID=57&sNO=145

〔4〕 Quinn TJ, Dawson J, Walters M . "Dr John Rankin; his life, legacy, and the 50th anniversary of the Rankin Stroke Scale". Scott Med J. 53 (1): 44–7, 2008
〔5〕 Farrell B, Godwin J, Richards S, Warlow C, et al. European ". J Neurol Neurosurg Psychiatry. 54 (12): 1044–1054, 1991
〔6〕 Pang, M.Y., J.E. Harris, and J.J. Eng, A community-based upper-extremity group exercise program improves motor function and performance of functional activities in chronic stroke: a randomized controlled trial. Arch Phys Med Rehabil. 87(1): 1-9,2006
〔7〕 Ogawa, S., Lee, T.M., Nayak, A.S., and Glynn, P. Oxygenation-sensitive contrast in magnetic resonance image of rodent brain at high magnetic fields. Magn Reson Med 14, 68-78,1990
〔8〕 Rorden, C., & Brett, M. Stereotaxic Display of Brain Lesions. Behavioural Neurology, 12(4), 191–200, 2000
〔9〕 Chao-Gan, Y. and Z. Yu-Feng, DPARSF: A MATLAB Toolbox for "Pipeline" Data Analysis of Resting-State fMRI. Front Syst Neurosci. 4: p. 13, 2010
〔10〕 William D. Penny, K.J.F., John T. Ashburner, Stefan J. Kiebel, Thomas E. Nichols, Statistical Parametric Mapping: The Analysis of Functional Brain Images. 2011: Elsevier.
〔11〕 Tzourio-Mazoyer, N., et al., Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage. 15(1): p. 273-89, 2002
〔12〕 Song, X.W., et al., REST: a toolkit for resting-state functional magnetic resonance imaging data processing. PLoS One6(9): p. e25031, 2011.
〔13〕 Xilin Shen, et al., Using connectome-based predictive modeling to predict individual behavior from brain connectivity, Nature protocols ,vol.12(3),p.506-508,2017
〔14〕 Stephanie Fountain-Zaragoza ,et al, Connectome-based models predict attentional control in aging adults, NeuroImage,186,1-13, 2019
〔15〕 Emily S. Finn, et al., Functional connectome fingerprinting: Identifying individuals based on patterns of brain connectivity, Nat Neurosci. , 18(11): 1664–1671, 2015
〔16〕 Chunliang Feng, Connectome-based individualized prediction of loneliness, Social Cognitive and Affective Neuroscience, 353–365, 2019
〔17〕 Monlca D.Rosenberg , et al ,Connectome-based Models Predict Separable Components of Attention in Novel Individuals, Journal of Cognitive Neuroscience,2017
〔18〕 Gibbons, J.D. & Chakraborti, S. Nonparametric Statistical Inference, Springer, 2011
〔19〕 Holland, P.W. & Welsch, R.E. Robust regression using iteratively reweighted least-squares. Commun. Stat.-Theory Methods 6, 813–827, 1977
〔20〕 Sarah W. Yip, Ph.D., Connectome-Based Prediction of Cocaine Abstinence, Am J Psychiatry 176:2, 2019
〔21〕 N Ramnani, Nature Reviews Neuroscience, 7: 511-522, 2006
〔22〕 Martijn et al., European Neuropsychopharmacology, 20: 519-534, 2010
〔23〕 J. L. Rodgers and W. A. Nicewander , Thirteen ways to look at the correlation coefficient. The American Statistician, 42(1):59–66, February ,1988
〔24〕 Wikipedia, Partial correlation, https://en.wikipedia.org/wiki/Partial_correlation
〔25〕 Taghreed Al-Said et al, The Logistic Regression Models and the Accuracy Measures in Analyzing Medical Data, IJSBAR, Vol 38 No2, 2018
〔26〕 M. Xia, J. Wang, and Y. He, “BrainNet Viewer: A Network Visualization Tool for Human Brain Connectomics,” Public Library of Science, vol. 8, no. 7, p. 068910, 4 July ,2013.
〔27〕 Kwakkel G, Kollen B, Twisk J. Impact of time on improvement of outcome after stroke. Stroke. 37:2348–53 , 2006
〔28〕 Öneş K., Yalçinkaya E.Y., Toklu B.Ç., Cağlar N. Effects of age, gender, and cognitive, functional and motor status on functional outcomes of stroke rehabilitation. NeuroRehabilitation.;25:241–249. ,2009
〔29〕 Mohmoud E., Mohammed A. Saud M., Effect of risk factors on functional outcome after stroke rehabilitation. Neurosciences: Vol 11 (1): 15- 20, 2006
〔30〕 Jiang T, He Y, Zang Y, Weng X. Modulation of functional connectivity during the resting state and the motor task. Hum Brain Mapp; 22: 63–71, 2004
〔31〕 Wang, L., et al., Dynamic functional reorganization of the motor execution network after stroke. Brain. 133(Pt 4): p. 1224-38, 2010
〔32〕 王馨世, 如何維持較佳的腦力與認知功能?, 康健雜誌 2019, https://www.commonhealth.com.tw/blog/3391
〔33〕 Zhu, Y., et al., Disrupted brain connectivity networks in acute ischemic stroke patients. Brain Imaging Behav. 11(2): p. 444-453 , 2017
〔34〕 Bournonville, C., et al., Identification of a specific functional network altered in poststroke cognitive impairment. Neurology. 90(21): p. e1879-e1888 , 2018
〔35〕 Dacosta-Aguayo R, Graña M, Savio A, Fernández-Andújar M, Millán M, et al. Prognostic value of changes in resting-state functional connectivity patterns in cognitive recovery after stroke: A 3T fMRI pilot study. Human Brain Mapping 35:3819–31. ,2014
〔36〕 Greicius MD, Srivastava G, Reiss AL, Menon V. Default-mode network activity distinguishes Alzheimer’s disease from healthy aging: evidence from functional MRI. Proc Natl Acad Sci USA101(13):4637-42, 2004
〔37〕 GAO, Siyuan, et al. Combining multiple connectomes improves predictive modeling of phenotypic measures. Neuroimage, 2019, 201: 116038.
〔38〕 Hardoon, David R.; Szedmak, Sandor; Shawe-Taylor, John. Canonical correlation analysis: An overview with application to learning methods. Neural computation, 2004, 16.12: 2639-2664.
〔39〕 Marquardt, D. W., & Snee, R. D. (1975). Ridge regression in practice. The American Statistician, 29(1), 3-20.
〔40〕 Rosenberg, M. D., Finn, E. S., Scheinost, D., Papademetris, X., Shen, X., Constable, R. T., & Chun, M. M. (2016). A neuromarker of sustained attention from whole-brain functional connectivity. Nature neuroscience, 19(1), 165-171.
〔41〕 Jang, S. H. (2010). Prediction of motor outcome for hemiparetic stroke patients using diffusion tensor imaging: a review. NeuroRehabilitation, 27(4), 367-372.
〔42〕 Kusano, Y., Seguchi, T., Horiuchi, T., Kakizawa, Y., Kobayashi, T., Tanaka, Y., ... & Hongo, K. (2009). Prediction of functional outcome in acute cerebral hemorrhage using diffusion tensor imaging at 3T: a prospective study. American Journal of Neuroradiology, 30(8), 1561-1565.
〔43〕 維基百科：額葉，取自https://zh.wikipedia.org/wiki/%E9%A1%8D%E8%91%89