臺灣博碩士論文加值系統

在台灣每年約有一萬七千人會因為腦中風而導致日常生活失能，不僅成為病患、家屬與照顧者沈重的負荷，也嚴重影響生活品質，因此腦中風急性期照護計畫的治療目標除了著重減少後續死亡率、預防再度中風之外，也著重於促進患者日常生活功能的恢復、改善生活品質並減少家庭與社會的負擔。在中風發作後的前幾個月，準確預測日常生活功能對於最佳化中風管理至關重要並有助於設定切實可行的目標，促使早期出院計劃的制定，為患者及其照顧者提供準確的信息。
本研究使用WEKA（Waikato Environment for Knowledge Analysis[WEKA]）作為分析及建構模型的工具軟體，以腦中風個案收案資訊與期初評估資訊來預測個案日常生活獨立能力的情形。
經資料篩選後共789位進行資料分析，研究結果發現以隨機森林（Random Forest）所建構的資料探勘模型有最佳的分類效能，能準確預測腦中風急性後期照護病患預後之日常生活獨立能力；預測住院PAC病患的日常生活獨立能力則以羅吉斯迴歸模型的分類效能最佳；BBS（Berg Balance Scale）是預測中最具影響力的關鍵特徵，其次是FMAmotor（Fugl-Meyer Assessment）。
本研究證實了基於資料探勘技術和多重評估量表的預測模型在腦中風日常生活獨立能力預測的可行性和有效性。這些模型不僅能夠提供精確的預測結果，還能夠幫助臨床醫師和家屬制定更為個性化的復健計劃，提高病患的生活品質和獨立能力。未來的研究應在此基礎上，進一步探索更多的影響因素和優化模型，從而為中風病患提供更加全面和精準的復健安排。


關鍵字：資料探勘、急性後期照護、腦中風、日常生活獨立能力、預測模型

In Taiwan, approximately 17,000 people suffer from stroke each year, leading to disabilities in daily living activities. This condition imposes a heavy burden on patients, families, and caregivers, significantly affecting their quality of life. Therefore, the goals of post-acute care (PAC) programs for stroke patients are not only to reduce subsequent mortality and prevent recurrent strokes but also to promote the recovery of daily living functions, improve quality of life, and reduce the burden on families and society. Accurately predicting daily living functions in the first few months after a stroke is crucial for optimizing stroke management and helps in setting achievable goals, facilitating the development of early discharge plans, and providing accurate information to patients and their caregivers.
This study uses WEKA (Waikato Environment for Knowledge Analysis) as the tool for analysis and model construction. The model predicts the daily living independence of stroke patients based on case information and initial assessment data.
After filtering the data, a total of 789 cases were analyzed. The research results revealed that the data mining model constructed with Random Forest had the best classification performance, accurately predicting the daily living independence of stroke patients in post-acute care. For predicting the daily living independence of hospitalized PAC patients, the Logistic Regression model had the best classification performance. The Berg Balance Scale (BBS) was identified as the most influential predictive feature, followed by the Fugl-Meyer Assessment (FMAmotor).
This study confirms the feasibility and effectiveness of predictive models based on data mining techniques and multiple assessment scales in predicting daily living independence for stroke patients. These models not only provide accurate predictive results but also assist clinicians and families in creating more personalized rehabilitation plans, enhancing patients' quality of life and independence. Future research should build on this foundation to explore more influencing factors and optimize the models, thereby providing more comprehensive and precise rehabilitation arrangements for stroke patients.


Keywords: Data Mining, Post-Acute Care, Stroke, Daily Living Independence, Predictive Model

目錄 i
圖目錄 iv
表目錄 v
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 4
1.3 研究目的 5
1.4 研究問題 6
第二章 文獻探討 7
2.1 腦中風介紹 7
2.1.1 流行病學 7
2.1.2 腦中風成因 7
2.1.3 造成腦中風危險因子 8
2.2 腦中風預後 10
2.3 腦中風急性後期照護計畫及評量量表相關研究 11
2.3.1 整體功能狀態評量 12
2.3.2 基本日常生活功能量表 13
2.3.3 工具性日常生活功能評量 14
2.3.4 姿勢控制與平衡功能評量 15
2.3.5 步行能力與整體行動功能評量 16
2.3.6 心肺耐力測試 16
2.3.7 感覺動作功能評量 17
2.3.8 認知、知覺功能評量 18
2.3.9 職能表現與重返社會能力評量 19
2.3.10 健康相關生活品質評量 19
2.3.11 吞嚥與進食功能評量 20
2.3.12 語言功能評估 20
2.3.13 營養評估 21
2.3.14 腦中風急性後期照護之成效 21
2.4 腦中風介入成效與資料探勘技術相關研究 22
第三章 研究方法 24
3.1 研究流程 24
3.2 資料來源 26
3.3 研究變項說明 27
3.4 研究工具 32
3.5 資料探勘技術 32
3.6 機器學習（machine learning）預測模型技術 33
3.6.1 邏輯斯廻歸（logistic regression[LR]） 34
3.6.2 順序最小優化算法（Sequential minimal optimization[SMO]） 34
3.6.3 隨機森林（Random forest[RF]） 35
3.6.4 決策樹（Decision Tree[DT]） 35
3.7 實驗設計 36
3.8 實驗驗證 37
3.8.1 訓練與測試 37
3.8.2 十摺交叉驗證 38
3.9 評估指標 38
第四章 實驗結果與分析 41
4.1 描述性資料分析 41
4.2 重要自變項及相關性 44
4.3 模型效能 49
4.3.1 資料探勘分析過程 49
4.3.2 資料探勘結果 49
第五章 研究結論與建議 51
5.1 研究結論 51
5.2 研究限制 53
5.3 未來研究方向與建議 53
參考文獻 55
中文文獻 55
英文文獻 56
網路文獻 63
附錄 人體試驗倫理委員會證明 65

中文文獻

李林富、林彣芷、周偉倪（2020）。以系統性回顧探討住院腦中風病人之出院安置地點. 台灣復健醫學雜誌，48（2），81-96。
杜建廣、白宜珊、李宥蓉、葉增邑、吳政哲、羅惠郁（2022）。〔論文摘要〕探討腦中風失能狀況改善程度之預測因子-急性後期計畫個案之初步分析。物理治療，47（4），319-319。
高玉馨（2018）。腦中風急性後期照護計畫-職能治療介入之成效分析。醫學與健康期刊，7（2），45-56。
張耿維、陳怡璇、林蓓宜、黃光聖（2016）。腦中風急性後期患者物理治療介入之成效。南臺灣醫學雜誌，12（2），61-68。
楊文英、李岩恆、吳淑娟、蘇希洵、陳美伶、孫天龍、黃建華（2017）。急性後期中風病患上肢動作缺損與日常生活功能之關聯分析。醫學與健康期刊，6（2），45-55。
董聖俐、許弘毅（2021）。探討急性後期照護對腦中風病人生活功能之影響。醫務管理期刊，22（3），187-201。
廖麗君、林昭宏、林瑞泰、劉景寬（1999）。缺血性腦中風患者功能預後之影響因素。中華民國物理治療學會雜誌，24（6），408-419。
https://doi-org.lib.chimei.org.tw:8443/10.29616/JPTAROC.199911.0005
賴慧貞、李淑芬、劉益坊、張崑敏、何清治、洪錦墩（2022）。臺灣腦中風病患類型與死亡之相關危險因子研究。醫學與健康期刊，11（1），1-12。
羅元廷、林彣芷、李林富、周偉倪（2022）。探討腦中風居家模式急性後期照護之成效及預測因子。台灣復健醫學雜誌，50（2），115-123。
竇文宏、馬上閔、陳啟忠、林碩琦、張喬俞、廖靖玲、郭雅玲（2019）。接受腦中風急性後期照護病患之物理治療成效探討：以南部某區域醫院為例。慈惠學報（15）， 53-62。

英文文獻

Alaka, S. A., Menon, B. K., Brobbey, A., Williamson, T., Goyal, M., Demchuk, A. M., Hill, M. D., & Sajobi, T. T.(2020. Functional outcome prediction in ischemic stroke: a comparison of machine learning algorithms and regression models.
Frontiers in Neurology, 11, 889. https://doi.org/10.3389/fneur.2020.00889
Aho, K., Harmsen, P., Hatano, S., Marquardsen, J., Smirnov, V. E., & Strasser, T.(1980). Cerebrovascular disease in the community: results of a WHO collaborative study. Bulletin of the World Health Organization, 58(1), 113-130.
Balzi, D., Lauretani, F., Barchielli, A., Ferrucci, L., Bandinelli, S., Buiatti, E., Milaneschi, Y., & Guralnik, J. M.(2010). Risk factors for disability in older persons over 3-year follow-up. Age and Ageing, 39(1), 92-98. https://doi.org/10.1093/ageing/afp209
Berg, K., Wood-Dauphine, S., Williams, J., & Gayton, D.(1989). Measuring balance in the elderly: preliminary development of an instrument. Physiotherapy Canada, 41(6), 304-311. https://doi.org/10.3138/ptc.41.6.304
Boser, B. E., Guyon, I. M., & Vapnik, V. N.(1992). A training algorithm for optimal margin classifiers. Proceedings of the Fifth Annual Workshop on Computational Learning Theory , 144-152. https://doi.org/10.1145/130385.130401
Boyd, C. R., Tolson, M. A., & Copes, W. S.(1987). Evaluating trauma care: the TRISS method. Journal of Trauma and Acute Care Surgery, 27(4), 370-378.
Breiman, L.(2001). Random forests. Machine Learning, 45, 5-32.
Brooks, R., & Group, E.(1996). EuroQol: the current state of play. Health Policy, 37(1), 53-72. https://doi.org/10.1016/0168-8510(96)00822-6
Chambers, B. R., Norris, J. W., Shurvell, B. L., & Hachinski, V. C.(1987). Prognosis of acute stroke. Neurology, 37(2), 221-221. https://doi.org/10.1212/WNL.37.2.221
Chang, F.-H., Lin, Y.-N., Liou, T.-H., Lin, J.-C., Yang, C.-H., & Cheng, H.-L.(2020). Predicting admission to post-acute inpatient rehabilitation in patients with acute stroke. Journal of Rehabilitation Medicine, 52(9), 1-6. https://doi.org/10.2340/16501977-2739
Chen, Y.-C., Chou, W., Hong, R.-B., Lee, J.-H., & Chang, J.-H.(2023). Home-based rehabilitation versus hospital-based rehabilitation for stroke patients in post-acute care stage: Comparison on the quality of life. Journal of the Formosan Medical Association, 122(9), 862-871. https://doi.org/10.1016/j.jfma.2023.05.007
Chen, Y.-W., Li, Y.-C., Huang, C.-Y., Lin, C.-J., Tien, C.-J., Chen, W.-S., Chen, C.-L., & Lin, K.-C. (2023). Predicting arm nonuse in individuals with good arm motor function after stroke rehabilitation: A machine learning study. International Journal of Environmental Research and Public Health, 20(5), 4123. https://doi.org/10.3390/ijerph20054123
Chong, D. K.-H.(1995). Measurement of instrumental activities of daily living in stroke. Stroke, 26(6), 1119-1122. https://doi.org/10.1161/01.str.26.6.1119
Desrosiers, J., Noreau, L., Rochette, A., Bravo, G., & Boutin, C.(2002). Predictors of handicap situations following post-stroke rehabilitation. Disability and Rehabilitation, 24(15), 774-785. https://doi.org/10.1080/09638280210125814
De Wit, L., Putman, K., Devos, H., Brinkmann, N., Dejaeger, E., De Weerdt, W., Jenni, W., Lincoln, N., Schuback, B., & Schupp, W.(2014). Long-term prediction of functional outcome after stroke using single items of the Barthel Index at discharge from rehabilitation centre. Disability and Rehabilitation, 36(5), 353-358. https://doi.org/10.3109/09638288.2013.793411
DeJong, G., & Branch, L. G.(1982). Predicting the stroke patient's ability to live independently. Stroke, 13(5), 648-655. https://doi.org/10.1161/01.str.13.5.648
Enright, P. L.(2003). The six-minute walk test. Respiratory Care, 48(8), 783-785.
Fritz, S.(2009). Lusardi M. White paper:“walking speed: the sixth vital sign”. Journal of Geriatric Physical Therapy, 32(2), 46-49.
Fugl-Meyer, A. R., Jääskö, L., Leyman, I., Olsson, S., & Steglind, S.(1975). A method for evaluation of physical performance. Scandinavian Journal of Rehabilitation Medicine, 7(1), 13-31.
Fulk, G. D., Reynolds, C., Mondal, S., & Deutsch, J. E.(2010). Predicting home and community walking activity in people with stroke. Archives of Physical Medicine and Rehabilitation, 91(10), 1582-1586. https://doi.org/10.1016/j.apmr.2010.07.005
Geyh, S., Cieza, A., Schouten, J., Dickson, H., Frommelt, P., Omar, Z., Kostanjsek, N., Ring, H., & Stucki, G.(2004). ICF Core Sets for stroke. Journal of Rehabilitation Medicine, 36(0), 135-141. https://doi.org/10.1080/16501960410016776
Ghaffari, A., Rostami, H. R., & Akbarfahimi, M.(2021). Predictors of instrumental activities of daily living performance in patients with stroke. Occupational Therapy International, 2021(1), 6675680. https://doi.org/10.1155/2021/6675680
Goldberg, R., Bernad, M., & Granger, C.(1980). Vocational status: prediction by the Barthel index and PULSES profile. Archives of Physical Medicine and Rehabilitation, 61(12), 580-583.
Granger, C. V., Albrecht, G., & Hamilton, B. B.(1979). Outcome of comprehensive medical rehabilitation: measurement by PULSES profile and the Barthel Index. Archives of Physical Medicine and Rehabilitation, 60(4), 145-154.
Granger, C. V., Dewis, L. S., Peters, N. C., Sherwood, C., & Barrett, J.(1979). Stroke rehabilitation: analysis of repeated Barthel index measures. Archives of Physical Medicine and Rehabilitation, 60(1), 14-17.
Grimby, G., Andrén, E., Daving, Y., & Wright, B.(1998). Dependence and perceived difficulty in daily activities in community-living stroke survivors 2 years after stroke: a study of instrumental structures. Stroke, 29(9), 1843-1849.
Hewer, R. L.(1990). Rehabilitation after stroke. QJM: An International Journal of Medicine, 76(1), 659-674. https://doi.org/10.1093/oxfordjournals.qjmed.a068473
Hartman-Maeir, A., Soroker, N., Ring, H., Avni, N., & Katz, N.(2007). Activities, participation and satisfaction one-year post stroke. Disability and Rehabilitation, 29(7), 559-566. https://doi.org/10.1080/09638280600924996
Hosmer Jr, D. W., Lemeshow, S., & Sturdivant, R. X.(2013). Applied Logistic Regression (Vol. 398). John Wiley & Sons.
Ivey, F. M., Macko, R., Ryan, A., & Hafer-Macko, C.(2005). Cardiovascular health and fitness after stroke. Topics in Stroke Rehabilitation, 12(1), 1-16. https://doi.org/10.1310/GEEU-YRUY-VJ72-LEAR
Johnson, W., Onuma, O., Owolabi, M., & Sachdev, S.(2016). Stroke: a global response is needed. Bulletin of the World Health Organization, 94(9), 634–634A. https://doi.org/10.2471/BLT.16.181636
Kuriakose, D., & Xiao, Z.(2020). Pathophysiology and treatment of stroke: present status and future perspectives. International Journal of Molecular Sciences, 21(20), 7609. https://doi.org/10.3390/ijms21207609
Kwon, S., Hartzema, A. G., Duncan, P. W., & Min-Lai, S.(2004). Disability measures in stroke: relationship among the Barthel Index, the Functional Independence Measure, and the Modified Rankin Scale. Stroke, 35(4), 918-923. https://doi.org/10.1161/01.STR.0000119385.56094.32
Lee, C. D., & Blair, S. N.(2002). Cardiorespiratory fitness and stroke mortality in men. Medicine and Science in Sports and Exercise, 34(4), 592-595. https://doi.org/10.1097/00005768-200204000-00005
Liao, W.-W., Hsieh, Y.-W., Lee, T.-H., Chen, C.-l., & Wu, C.-y.(2022). Machine learning predicts clinically significant health related quality of life improvement after sensorimotor rehabilitation interventions in chronic stroke. Scientific Reports, 12(1), 11235. https://doi.org/10.1038/s41598-022-14986-1
Lin, W. Y., Chen, C. H., Tseng, Y. J., Tsai, Y. T., Chang, C. Y., Wang, H. Y., & Chen, C. K. (2018). Predicting post-stroke activities of daily living through a machine learning-based approach on initiating rehabilitation. International Journal of Medical Informatics, 111, 159–164. https://doi.org/10.1016/j.ijmedinf.2018.01.002
Loewen, S. C., & Anderson, B. A.(1990). Predictors of stroke outcome using objective measurement scales. Stroke, 21(1), 78-81. https://doi.org/10.1161/01.str.21.1.78
Mahoney, F. I., & Barthel, D. W.(1965). Functional evaluation: the Barthel Index: a simple index of independence useful in scoring improvement in the rehabilitation of the chronically ill. Maryland State Medical Journal, 14 , 61–65.
Mehrholz, J., Pohl, M., Kugler, J., Burridge, J., Mückel, S., & Elsner, B.(2015). Physical rehabilitation for critical illness myopathy and neuropathy. The Cochrane Database of Systematic Reviews, 2015(3), CD010942. https://doi.org/10.1002/14651858.CD010942.pub2.
Mlinac, M. E., & Feng, M. C.(2016). Assessment of activities of daily living, self-care, and independence. Archives of Clinical Neuropsychology, 31(6), 506-516. https://doi.org/10.1093/arclin/acw049
Murphy, S. J., & Werring, D. J.(2020). Stroke: causes and clinical features. Medicine, 48(9), 561-566. https://doi.org/10.1016/j.mpmed.2020.06.002
Nakao, S., Takata, S., Uemura, H., Kashihara, M., Osawa, T., Komatsu, K., Masuda, Y., Okahisa, T., Nishikawa, K., & Kondo, S.(2010). Relationship between Barthel Index scores during the acute phase of rehabilitation and subsequent ADL in stroke patients. The Journal of Medical Investigation, 57(1-2), 81-88. https://doi.org/10.2152/jmi.57.81
Nishioka, S., Wakabayashi, H., Nishioka, E., Yoshida, T., Mori, N., & Watanabe, R.(2016). Nutritional improvement correlates with recovery of activities of daily living among malnourished elderly stroke patients in the convalescent stage: a cross-sectional study. Journal of the Academy of Nutrition and Dietetics, 116(5), 837-843. https://doi.org/10.1016/j.jand.2015.09.014
Patel, A. T., Duncan, P. W., Lai, S.-M., & Studenski, S.(2000). The relation between impairments and functional outcomes poststroke. Archives of Physical Medicine and Rehabilitation, 81(10), 1357-1363. https://doi.org/10.1053/apmr.2000.9397
Peel, N. M., Kuys, S. S., & Klein, K.(2013). Gait speed as a measure in geriatric assessment in clinical settings: a systematic review. Journals of Gerontology Series A: Biomedical Sciences and Medical Sciences, 68(1), 39-46. https://doi.org/10.1093/gerona/gls174
Peng, L.-N., Chen, L.-J., Lu, W.-H., Tsai, S.-L., Chen, L.-K., & Hsiao, F.-Y.(2019). Post-acute care regains quality of life among middle-aged and older stroke patients in Taiwan. Archives of Gerontology and Geriatrics, 83, 271-276. https://doi.org/10.1016/j.archger.2019.04.011
Pettersen, R., Dahl, T., & Wyller, T. B.(2002). Prediction of long-term functional outcome after stroke rehabilitation. Clinical Rehabilitation, 16(2), 149-159. https://doi.org/10.1191/0269215502cr482oa
Quinn, T. J., Langhorne, P., & Stott, D. J.(2011). Barthel index for stroke trials: development, properties, and application. Stroke, 42(4), 1146-1151. https://doi.org/10.1161/STROKEAHA.110.598540
Sangha, H., Lipson, D., Foley, N., Salter, K., Bhogal, S., Pohani, G., & Teasell, R. W.(2005). A comparison of the Barthel Index and the Functional Independence Measure as outcome measures in stroke rehabilitation: patterns of disability scale usage in clinical trials. International Journal of Rehabilitation Research, 28(2), 135-139. https://doi.org/10.1097/00004356-200506000-00006
Stinear, C. M., Smith, M.-C., & Byblow, W. D.(2019). Prediction tools for stroke rehabilitation. Stroke, 50(11), 3314-3322. https://doi.org/10.1161/STROKEAHA.119.025696
Studenski, S.(2009). Bradypedia: is gait speed ready for clinical use? The Journal of Nutrition, Health & Aging, 13(10), 878-880. https://doi.org/10.1007/s12603-009-0245-0
Sulter, G., Steen, C., & De Keyser, J.(1999). Use of the Barthel index and modified Rankin scale in acute stroke trials. Stroke, 30(8), 1538-1541. https://doi.org/10.1161/01.str.30.8.1538
Uswatte, G., Taub, E., Morris, D., Light, K., & Thompson, P.(2006). The Motor Activity Log-28: assessing daily use of the hemiparetic arm after stroke. Neurology, 67(7), 1189-1194. https://doi.org/10.1212/01.wnl.0000238164.90657.c2
Van der Putten, J., Hobart, J., Freeman, J., & Thompson, A.(1999). Measuring change in disability after inpatient rehabilitation: comparison of the responsiveness of the Barthel index and the Functional Independence Measure. Journal of Neurology, Neurosurgery & Psychiatry, 66(4), 480-484. https://doi.org/10.1136/jnnp.66.4.480
Wood-Dauphinee, S., Williams, J. I., & Shapiro, S.(1990). Examining outcome measures in a clinical study of stroke. Stroke, 21(5), 731-739. https://doi.org/10.1161/01.str.21.5.731

網路文獻

WHO.(2020). The top 10 causes of death. https://www.who.int/zh/news-room/fact-sheets/detail/the-top-10-causes-of-death
吳英黛、劉千綺、鄭建興（2018）。慢性中風病人的物理治療需求。 https://www.stroke.org.tw/GoWeb2/include/index.php?Page=5-1&paper02=19339206025bc969829f817
衛生福利部中央健康保險署（2020）。急性後期整合照護計畫。 https://www.nhi.gov.tw/Content_List.aspx?n=5A0BB383D955741C&topn=5FE8C9FEAE863B46
勞動部勞動力發展署（2023）。移工申辦工作申請作業流程-家庭看護工。移工事務 https://www.wda.gov.tw/NewsFAQ.aspx?n=8742DCE7A2A28761&sms=67AB43615F0F0CB2&_CSN=1548B29AE7A54B88
衛生福利部統計處（2022，6月12日）。111年國人死因統計結果。 https://www.mohw.gov.tw/cp-16-74869-1.html