透過您的圖書館登入
IP:3.84.7.255
  • 學位論文

腦中風患者復健治療成效之研究 —以健保資料庫為例

指導教授 : 胡雅涵
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


腦中風已名列台灣十大死因多年,如何促進患者擁有較佳的預後,是一相當值得關注的議題。腦中風的再發為患者預後不佳的表現,代表患者無法進行有效的危險因子控制。因此,如何防範腦中風再發,持續成為臨床努力的方向。復健治療已被證實能夠有效改善腦中風患者的動作、認知功能,繼而減低患者的依賴程度;以慢性腦中風患者而言,透過各專業復健治療師的治療和指導,不但能夠協助患者維持一定的功能水平,亦能使患者強化健康管理意識,有效控制腦中風再發危險因子,降低腦中風的再發率。然而,腦中風病程相當長,患者經常面臨不知復健治療終點在何方的情況。因此,相關政府單位如何在有限的醫療資源條件下,提供合理、符合患者需求的復健治療給付便是一相當重要的公共衛生議題。 過去部分文獻曾針對單一醫院、單一機構之腦中風患者進行研究,探討復健治療資源使用情況對患者預後的影響。可惜的是,一旦患者更換就醫院所,便無法確實了解其復發狀況;再者,復健治療為一連續、長期的治療,相較於其他科別,復健科患者黏性較低,若未能精確掌握患者跨院、跨區間的復健治療資源利用情形,所得研究成果便容易出現偏頗。基於以上理由,本研究以2010年全民健保資料庫承保抽樣歸人檔中曾因腦中風入院的患者為資料來源,透過資料探勘技術中之決策樹與隨機林技術建立腦中風患者再發預測模型。 比較各分類器的平均預測正確率發現,以長期復健患者之住院復健治療紀錄為資料集,採用決策樹C4.5進行腦中風再發預測效能為最佳(72.04%),故本研究之實驗結果將以決策樹建立腦中風患者再發之預測模式。另一方面,透過重要因子排序分析顯示,住院期間所接受的物理治療、職能治療和語言治療強度及頻率是腦中風患者重要的再發影響因子。期能透過本研究結果,協助臨床人員提供合適的復健治療強度、頻率,協助患者防治腦中風再發之目的。  關鍵詞: 腦中風、腦中風再發、復健治療、全民健保資料庫、資料探勘

並列摘要


Stroke (Cerebral vascular accident, CVA) is a common and serious disease. Most of the survivals would be disabled after their illness recovery, causes serious burden on caregivers. It is said that rehabilitation could help functional recovery of stroke patients, regain independence after stroke . Due to the long course of stroke, how to prevent survivals from recurrence is an important issue. This study attempts to examine the relationship between stroke recurrence and strength of rehabilitation, and build a stroke recurrence prediction model utilizing a number of supervised learning techniques to assist physicians with making clinical decisions. In the past, most of the related work used the samples from a single hospital as a sample, but it cannot fully catch all the clinic information of the patients. Therefore, this study used the Longitudinal Health Insurance Database 2010 of the NHIRD as the data source, to examine the effectiveness of rehabilitation. In terms of accuracy rate of all classifiers, we get the best effectiveness (72.04%) while adopting the inpatient admission dataset and C4.5 to predict recurrence. We also find physical therapy, occupational therapy and speech therapy treatments during inpatient admission are the key factors to decrease the chance to recrudesce in the rehabilitation periods. The higher strength and frequency rehabilitation treatment is also the key influence variables in our high accuracy prediction model which means that is useful to lower the recurrence rate of stroke patients. Keyword:Cerebral vascular accident, stroke, rehabilitation, prognosis, classified technology

參考文獻


劉介宇, 洪永泰, 莊義利, 陳怡如, 翁文舜, 劉季鑫, et al. (2006). 台灣地區鄉鎮市區發展類型應用於大型健康調查抽樣設計之研究. 健康管理學刊, 4(1), 1-22.
Lin, J. H., Hsieh, C. L., Lo, S. K., Hsiao, S. F., & Huang, M. H. (2003). Prediction of functional outcomes in stroke inpatients receiving rehabilitation. Journal of the Formosan Medical Association, 102(10), 695-700.
Han, D. S., Pan, S. L., Chen, S. Y., Lie, S. K., Lien, I. N., & Wang, T. G. (2008). Predictors of long-term survival after stroke in Taiwan. Journal of Rehabilitation Medicine, 40(10), 844-849.
Appelros, P., Nydevik, I., Seiger, Å., & Terént, A. (2002). Predictors of severe stroke influence of preexisting dementia and cardiac disorders. Stroke, 33(10), 2357-2362.
Appelros, P., Nydevik, I., & Viitanen, M. (2003). Poor outcome after first-ever stroke predictors for death, dependency, and recurrent stroke within the first year. Stroke, 34(1), 122-126.

延伸閱讀