跳到主要內容

臺灣博碩士論文加值系統

(44.200.86.95) 您好!臺灣時間:2024/05/25 15:39
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:鄭軒智
研究生(外文):Syuan Jhih Jheng
論文名稱:應用文字探勘於電子病歷之腦中風影像報告資訊擷取
論文名稱(外文):Extraction of Stroke Image Reports from Electronic Medical Record Using Text Mining
指導教授:林詩偉林詩偉引用關係
指導教授(外文):S. W. Lin
學位類別:碩士
校院名稱:長庚大學
系所名稱:資訊管理學系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2018
畢業學年度:107
語文別:中文
論文頁數:51
中文關鍵詞:腦中風電子病歷影像報告文字探勘
外文關鍵詞:strokeelectronic medical recordsimage reporttext mining
相關次數:
  • 被引用被引用:1
  • 點閱點閱:191
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:3
衛服部於105年公布的國人十大死因,腦血管疾病高居第四,而腦血管疾病最為嚴重的是腦中風。腦中風患者因腦中風導致的障礙包括肢體麻痺無力、語言溝通障礙、吞嚥困難等後遺症,對日常生活影響甚鉅,而腦中風所需的醫療費用帶給患者家屬與社會沉重的負擔。記錄著腦中風病患的中風型態、療程、投藥、基本生理資料、照護資訊等個人就醫資訊的病歷,隨著科技的發展都逐漸的電子化,形成電子病歷。若能分析這些電子化的醫護資料,萃取出對於腦中風的治療值得探討的資訊,對於未來腦中風患者的療程與照護皆有提高效率的功用,腦中風的醫學研究也會有進一步的發現。
本研究使用直譯式程式語言Python開發文字探勘演算法,針對腦中風患者之電子病歷中的影像報告進行關鍵字萃取,對象為某醫學中心提供之腦中風患者的電子病歷,資料時間為2003年至2017年1月,總共有1,647,281筆資料,腦中風患者為47,107人。透過Python的正則表達式套件與關鍵字比對,萃取影像報告中目標血管明顯阻塞的敘述句,並計算該文字探勘軟體的萃取準確度,其萃取準確度可達98.85%。實務上,可提升醫護人員檢查該病患的血管狀況之效率與辨識度,對於日後相關醫學研究也可更有效率的使用該影像檢查報告。
In 2016, Ministry of Health and Welfare of Taiwan announced the top ten causes of death among Taiwanese people, and stroke ranked fourth. The physiological disorder caused by stroke include limb paralysis, language communication disorder, dysphagia and other sequelae, has a great impact on daily life. Also, the medical expenses required for stroke have a heavy burden on the stroke patients’ families and the whole society. With the development of science and technology, medical records which contain personal medical information such as basic physiological data and other personal receiving medical treatments are gradually formed as electronic medical records. If we can extract the information worthy about the treatment of stroke analyze contents from electronic medical records (EMR) and analyze them, more undiscovered results of stroke’s medical research would be found and the efficiency of the stroke treatment would be improved in the future.
This study uses one of the interpret language, Python, to develop an algorithm of text mining for keyword extraction of image reports in EMR of patients with stroke. The dataset to extract is an EMR of stroke patients provided by a medical center from 2003 to January, 2017. The dataset consists of 1,647,281 records of data in total, and 47,107 patients with stroke. Through Python's regular expression suite and keyword comparison, the narrative sentences of the target artery with obviously stenosis in the image report are extracted, and the extraction accuracy of the text mining algorithm was calculated. The accuracy of the extraction is up to 98.85%. The result shows the algorithm can help the medical staff to recognize the artery condition of the patient more efficiency in the future.
指導教授推薦書.........
口試委員會審定書.........
誌謝.........iii
中文摘要........iv
英文摘要........v
目錄........vi
圖目錄.........viii
表目錄.........ix
第一章 緒論........1
1.1研究背景與動機........1
1.2研究目的........2
1.3研究流程........3
1.4研究限制........5
第二章 文獻回顧........6
2.1.腦中風定義與分類........6
2.2 文字探勘之概述........6
2.3 電子病歷概述與定義........9
第三章 研究方法及進行步驟........12
3.1 資料來源與研究資料定義........12
3.2 資料描述........15
3.3 資料前處理........15
3.4 實驗方法........22
第四章 實驗研究結果........24
4.1 資料描述........24
4.2 實驗結果........26
第五章 結論........33
5.1 討論........33
5.2 未來研究方向........34
參考文獻........35
附錄一 全院彙總檔欄位說明........38
附錄二 檢查項目收費標準代碼之檢查項目對應表........39
1,台灣腦中風協會2008。Taiwan Guidelines for the Management of Stroke 2008。台灣腦中風協會。
2,行政院衛生福利部(2017)。2017年6月19日。105年國人死因統 計結果,取自https://www.mohw.gov.tw/cp-16-33598-1.html
3,陳楚杰(2001)。醫管辭彙-電子化病歷。醫院雜誌,34(2),14-15。
4,黃興進、余明玲、劉忠峰(2006)。醫療資訊管理。嘉義縣:台灣健 康資訊管理協會。
5,溫信財、鄭金英、范碧玉、簡文山、林玲珠(2007)。電子病歷時代 病歷管理人員的轉型與人才培育。台北醫學大學「醫務管理學 系暨研究所」期刊論文。
6,蔡昆元、劉見祥、劉建財(2009)。我國電子病歷發展現況與展望。 醫療品質雜誌,3(6),4-14。
7,劉建財、許明輝、楊沛墩、馮容莊(2012)。台灣醫療機構實施電子病歷之探討。領導護理,13(2),2-11。
8,Ayer, D. J., Menachemi, N., Ramamonjiarivelo, Z., Matthew, M., & Books, R.G. (2009). Adoption of electronic medical record : The role of network effects. Journal of Product and Brand Management, 18(2), 127-135.
9,Baeza-Yates, R., & Rebeiro-Neto, B. (1999). Modern information retrieval (Vol. 463). New York: ACM press.
10,Bronner, L.L., Kanter, D.S., & Manson, J.E. (1995). Primary Prevention of Stroke. The New England Journal of Medicine,333(21), 1392-1400.
11,Chawla, N. V. (2009). Data mining for imbalanced datasets: An overview. In Data mining and knowledge discovery handbook (pp.875-886). Springer, Boston, MA.
12,CPRI(1995). Description of the Computer-based Patient Record and Computer-based Patient Record System. Schaumburg, IL, CPRI Work Group on CPR Description.
13,Deogun, J. S., Sever, H & Rahgavan, V. V. (1998). Structural abstractions of hypertext documents for web-based retrieval. In dexa (p. 385). IEEE.
14,Detmer, D. E., Steen, E. B., & Dick, R. S (1997). The Computer- Based Patient Record: An Essential Technology for Health Care, Revised Edition. National Academies Press.
15,Feldman, R, & Dagan, I. (1995). Knowledge Discovery in Textual Databases (KDT). In KDD(Vol.95, pp. 112-117).
16,Hotho, A., Nürnberger, A., & Paaß, G. (2005). A brief survey of text mining. In Ldv Forum(Vol. 20, No. 1, pp. 19-62).
17,Institute of Medicine(1997). The computer-based Patient Record:An Essential Technology for Healthcare. Washington, DC:National Academy press.
18,Kleene, S. C., & Oliver, W. L. (1956). Sets, Logic, and Mathematical Foundations. Williams college.
19,Kouskouras, C., Charitanti, A., Giavroglou, C., Foroglou, N., Selviaridis, P., Kontopoulos, V., & Dimitriadis, A. S. (2004). Intracranial aneurysms: evaluation using CTA and MRA. Correlation with DSA and intraoperative findings. Neuroradiology, 46(10), 842-850.
20,Losiewicz, P., Oard, D. W., & Kostoff, R. N. (2000). Textual Data Mining to Support Science and Technology Management. Journal of Intelligent Information Systems, 15(2), 99-119.
21,Margert, A.(1993). Contributing Editor’s Note:What is the CPR. Journal of AHIMA, 64(2), 39-40.
22,Nahm, U. Y., & Mooney, R. J. (2000, July). A Mutually Beneficial Integration of Data Mining and Information Extraction. In AAAI/AAI(pp. 627-632).
23,Sullivan. D (2001). Document Warehousing and Text Mining: Techniques for Improving Business Operations, Marketing, and Sales. John Wiley & Sons, Inc..
24,Roque, F. S., Jensen, P. B., Schmock, H., Dalgaard, M., Andreatta, M., Hansen, T., Søeby, K., Bredkjær, S., Juul, A., Werge, T., Brunak, S., & Jensen, L. J. (2011). Using electronic patient records to discover disease correlations and stratify patient cohorts. PLoS computational biology, 7(8), e1002141.
25,Taylor, T. N., Davis P. H., Torner, J. C., Holmes, J., Meyer, J. W., & Jacobson, M. F. (1996). Lifetime Cost of Stroke in the United States. Stroke, 27(9), 1459-1466.
26,Thakkar, M., & Davis, D. C. (2006).Risks, barriers, and benefits of EHR systems: a comparative study based on size of hospital. Perspectives in Health Information Management/AHIMA, American Health Information Association, 3.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊