臺灣博碩士論文加值系統

應用資料探勘(Data Mining)的技術，能夠找出隱藏在資料中潛藏的知識。但龐大雜亂的資料，不但使得資料探勘的困難度增加，不連貫的資訊也容易造成資料分析的錯誤。本研究將以臨床檢驗資料作為探勘之對象，這與傳統醫學上所採用的統計分析方法不同；為維持資料分類規則的準確性，因此結合類神經網路(Neural Network)與關聯法則(Association Rules)作為資料探勘分類及預測的工具，從大量資料中找出檢驗資訊與醫師診斷間的關聯性，以及檢驗資料中所隱藏的知識，以作為建立決策支援系統之依據，協助醫師臨床診斷參考，以及提供醫學資訊給醫師思考開立診斷相對應檢查項目，更提出警訊給檢驗人員於發送檢查報告時，能夠提早將檢驗異常通知主治醫師，以供作進一步醫療處理，能夠於第一時間搶救病患，使得醫院的醫療品質能更臻理想。

Lots of knowledge hidden in the data can be found out by using the technology of data mining. Regrets, huge disordered data causes big difficulity in data mining, and the inconsistent information is apt to cause many mistakes in data analysis. Compred to the methods of traditional medical statistic analysis, this research has big differences, due clinical information as a mining target has been used. In order to maintain the accuracy of the rules of data classification, BPN neural network and Association Rules are combined into this research as data mining classification and predictable instruments. To find out the connections from the huge data between the laboratory information and doctor’s diagnosis, and the hidden knowledge in the lab information can be used as a base of Decesion Support System, as a reference of beside clinical diagnosis, and providing medical message for the doctor’s to execute diagnosis exams. Furthermore, can remind the lab staffs to notice the doctors earlier as soon as they find a unusual or abnormal values while they fill the reports in order that the patients can be cared at the first time. Finally the medical care quality can be reached to a ideal situation.

摘 要 I
Abstract II
誌謝 III
目 錄 IV
圖 索 引 VI
表 索 引 VII
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 論文架構 4
第二章 文獻探討 5
2.1 醫療資訊系統 5
2.2 醫學檢驗 7
2.2.1 臨床檢驗分類 7
2.2.2 臨床診斷與檢驗的關係 8
2.2.3 目前檢驗發展挑戰 9
2.3 檢驗資訊系統 10
2.3.1 國內檢驗資訊系統現況 11
2.3.2 檢驗資訊系統發展方向 12
2.4 決策支援系統 12
2.4.1 決策支援系統 12
2.4.2 醫療決策支援系統 15
2.5 資料探勘 17
2.5.1 資料探勘之定義與目的 17
2.5.2 類神經網路 18
2.5.3 關聯法則(association rules) 22
2.5.4 Apriori 演算法 24
2.6 資料探勘技術之醫學應用 27
第三章 研究方法與步驟 29
3.1 研究方法與架構 29
3.2 系統建置步驟 31
3.2.1 前置作業 32
3.2.2 倒傳遞類神經網路(BPN) 34
3.2.3 關聯法則 42
第四章 系統實作 49
4.1 醫師診斷輔助系統 49
4.2 醫療檢驗支援系統 56
4.3 系統診斷結果評估 63
4.3.1 臨床資料蒐集 63
第五章 結論及未來研究方向 66
5.1 綜合結論 66
5.2 未來研究方向 67
參考文獻 68

中文部分
[1] 王景弘，設計一個具有學習能力的腦瘤診斷專家系統，國立交通大學資訊科學研究所碩士論文，1990。
[2] 台大醫院，(民81)，台大醫院全面整體醫院資訊系統簡介。
[3] 余儀呈，常見門診判讀之原則，台北榮民總醫院家庭醫學專題演講，2000。
[4] 吳坤祥，以個人電腦為基礎的醫用專家系統建構工具之設計與應用，國立成功大學電機工程研究所碩士論文，1990。
[5] 吳琮璠、謝清佳，資訊管理理論與實務，智勝，臺北市，2000。
[6] 李秉穎醫師，檢驗結果的不一致造成檢驗錯誤，台大醫院，1999.10。
[7] 李政宏，以知識庫為基礎之牙醫決策支援系統，國立屏東科技大學碩士論文，2004。
[8] 李彥良，Web-Based診間醫令系統之開發與建置，台北醫學大學醫療資訊研究所碩士論文，2001。
[9] 林等義，全方位的檢驗資訊系統.慈濟綜合醫院之發展與應用研討會，1999。
[10] 周義昌、蔡玉娟、劉榮宜、李素玲、戴敏倫，類神經網路的新架構：可塑性認知網路，電信研究季刊，第22卷第3期，6月，pp. 291-306。
[11] 孫漢屏，類神經網路為基礎之智慧型醫院網路掛號系統，中國醫藥學院醫務管理學研究所碩士論文，1992。
[12] 張顯洋，蔡俊榮，林俊龍：跨世紀新醫療資訊系統慈濟綜合醫院之發展與應用，1998。
[13] 梁定澎，決策支援系統與企業智慧，台北，智勝出版社，2002。
[14] 郭振邦，急性腹症診斷電腦諮詢系統，國立成功大學醫學工程研究所碩士論文，1994。
[15] 郭振宗，微生物類別診斷與抗生素用藥決策支援系統，國立屏東科技大學碩士論文，2000。
[16] 陳秋宏，神經網路專家系統之設計與製作，國立交通大學資訊科學研究所碩士論文，1988。
[17] 陳銘泉，醫院管理資訊系統規劃之研究.中國醫藥學院碩士論文，1988。
[18] 惠汝太，彰麟:名醫談百病-高血壓，南粵出版社，2000。
[19] 黃勝崇，資料探勘應用於醫療院所輔助病患看診指引之研究，南華大學資訊管理研究所碩士論文，2000。
[20] 葉怡成，應用類神經網路，儒林圖書公司，2001。
[21] 黎文琪，智慧型臨床醫囑輔助系統之開發，國立陽明大學公共衛生研究所碩士論文，2001。
[22] 賴燕賢，醫學診斷輔助護理過程支援系統，台北醫學院碩士論文，2000。
[23] 錢慶文，某醫學中心住院處方之分析研究：以DRG90為例，臺灣醫務管理雜誌，Vol.4 No.3，pp.98-113，2003。
[24] 檢驗醫學Merck Manual 默克診療手冊，第十五版，第268 節。
[25] 薛洪昇，皮膚病理非感染性全身性水泡診斷決策支援系統，台北醫學院碩士論文，2000。
[26] 謝逸中，以World Wide Web 為基礎之臨床資訊站對使用者之衝擊， 台北醫學院論文，1988。
[27] 顏志展，“醫院資訊系統專案管理-完全教戰手冊”，華騰文化股份有公司，1999。

英文部分
[1] Agrawal, R., Imielinski, T. and Swami, A., “Mining Association Rules between Sets of Items in Large Databases,” ACM SIGMOD, 5/93, Washington, DC, USA. 1993
[2] Brown and Company :Interpretation of Diagnostic Tests, 1992 Little,。
[3] Butter worth: Medical Decision Making. pp. 230-233 ,1998.
[4] Carlos Ordonez, Cesar A. Santana, Levien de Braal, "Discovering Interesting Association Rules in Medical Data", ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, pp.78-85, 2000
[5] Chen, M. S., Han, J., and Yu, P. S., 1997, "Data Mining: An Overview from Database Perspective," IEEE Transaction on Knowledge and Data Engineering, pp. 866-883.
[6] Crémilleux B., Ragel A., Bosson J. L. "An Interactive and Understandable Method to Treat Missing Values: Application to a Medical Data Set", 5th International Conference on Information Systems Analysis and Synthesis (ISAS / SCI 99), M. Torres, B. Sanchez & E. Wills (Eds.), pp. 137-144, Orlando, FL, August 1999.
[7] Fayyad, U. et al., “The KDD process for extracting useful knowledge from volumes of data”, Communication of ACM, Vol. 39, No. 11, 1996, pp. 27-34.
[8] Federspil G,Vettor R: Clinical and laboratory logic. Clinica Chimica Acta. 280(1-2):25-34,1999 Feb.
[9] George M. Marakas, 1998, “Decision Support Systems in the 21st Century”, Prentice Hall, Upper Saddle River, NJ, USA
[10] Gonzalez-Vallejo C,Sorum PC,Stewart TR,Chessare JB: Mumpower JL, Physicians' diagnostic judgments and treatment decisions for acute otitis media in children. Medical Decision Making.18(2):149-62,1998 Apr-Jun.
[11] Groselj, C., “Data mining problems in medicine,” Computer-Based Medical Systems, 2002. (CBMS 2002). Proceedings of the 15th IEEE Symposium on, 2002, Pages: 377 - 38
[12] Han, E. H., Boley, D., and Gini, M., 1998, "WebACE: A Web Agent for Documet Categorization and Exploration," proceddings of the Second International Conference on Autonomous Agents, pp. 408-415.
[13] Han, J. and Fu, Y., 1996, "Exploration of the Power of Attribute-Oriented Induction in Data Mining," Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy, R. (eds.), Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, pp. 399-421.
[14] Han, J. and Kamber, M., 2000, "Data Mining: Concepts and Techniques," Morgan Kaufmann Publishers.
[15] Han, J., 1999, "Characteristic Rules, ‘DBMiner, to appear in Kloesgen, W.and Zytkow, J. (eds.),’ Handbook of Data Mining and Knowledge Discovery," Oxford University Press.
[16] Han, J., Cai, Y., and Cercone, N., 1992, "Knowledge Discovery in Databases: An Attribute-Oriented Approach," Proc. of 1992 Int'l Conf. on Very Large Data Bases (VLDB'92), Vancouver, Canada, August, pp. 547-559.
[17] Heckerling PS,Verp MS. Albert N: Patient or physician preferences for decisionanalysis:the prenatal genetic testing decision. Medical Decision Making.19(1):66-77,1999.
[18] Helfer D, Marsh K, Sorensen M:Developing an integrated computer system for cardiac catheterization laboratories. Journal of Cardiovascular Management. 8(1):21-6, 1997 Jan-Feb.
[19] J. Ramirez, D. J. Cook, L. L. Peterson, and D. M. Peterson, "An Event Set Approach to Sequence Discovery in Medical Data", Intelligent Data Analysis, 4(6), pp. 513-530, 2000
[20] JAMA,280(15),October 21,1998.
[21] Jiawei Han and Micheline Kamber" Date Mining Comcepts and Techniques"Academic Press 2001
[22] Keri E,Pearlson:Managing AND Using Information Systems.250-252.1999.
[23] Kimble,Young,Kradjan,Gugllelmo：Handbook of Applied Therapeutics 應用治療學手冊.合記出版社.1994.
[24] Kokkotos S, Ioannidis EV,Spyropoulos CD：A system for efficient scheduling of patient tests in hospitals. Medical Informatics. 22(2):179-90, 1997 Apr-Jun.
[25] Liebowitz, J.(ed.), Knowledge Management Handbook, CRC Press, (1999).
[26] Markin RS：Recent trends in clinical laboratory automation. Clinical Laboratory Management Review.12(3);176-80,1998 May-Jun.
[27] Michael J.A.Berry,Gordon S.Linoff,Dr.彭文正：資料採礦顧客關係管理暨電子行銷之應用.樹博網資訊公股份有限公司.2000.
[28] Plebani M:The clinical importance of laboratory reasoning. Clinica Chimica Acta. 280(1-2):35-45, 1999 Feb.
[29] Rakesh Agrawal, Ramakrishnan Srikant, “Mining SequentialPatterns,” Proc. Of the Int’l Conference on Data Engineering(ICDE),Taipei, Taiwan, March 1995, Pages 2 -8
[30] Richardson H：Laboratory medicine in Ontario: its downsizing and the consequences on quality. Clinica Chimica Acta. 290(1):57-72, 1999 Dec.
[31] Simon Haykin, Neural Networks: A Comprehensive.1994
[32] Stair TO：Reduction of redundant laboratory orders by access to computerized patient records:Journal of Emergency Medicine. 16(6):895-7, 1998 Nov-Dec.
[33] Tafeit E,Reibnegger G：Artificial neural networks in laboratory medicine and medical outcome prediction. [Review] [35 refs]. Clinical Chemistry & Laboratory Medicine. 37(9):845-53, 1999 Sep.
[34] Tierny WM,McDonald CJ,Martin DK：Computerized display of past test results:effects on outpatient testing.Ann Intern Med .107:569-74.1987.
[35] Tierny WM,McDonald CJ,Martin DK：Computerized Predictions of abnormal test results:effects on outpatient testing. J Am Med Assoc.259:1194-8.1988.
[36] Tierny WM,Miller ME,Overhange Jm：Order-writing on microcomputer workstations:effects on resocurce utilization. J Am Med Assoc.269:379-83.1993.
[37] Turban Aronson：Decision Support System and Interllgent systems.269-274.1998.
[38] Waise A：Clinical audit and the contribution of the laboratory to clinical outcome. Clinica Chimica Acta. 280(1-2):47-57, 1999 Feb.
[39] Whiting-O’Keefe QE,Simbord DW,Epstein WV：A computerized summary medical record system can provide more in formation than the standard medical record. J Am Med Assoc.254：1185-92.1985.
[40] Wilkinson DS：The role of technology in the clinical laboratory of the future. Clinical Laboratory Management Review. 11(5):322-30, 1997 Sep-Oct.
[41] Wilkinson GA,McDonald CJ,McCabe GP：The effect of immediate access to acomputerizated medical record on physician test ordering a controlled clinical trial in emergency room.Am J Public Health.72：698-92.1982 .
[42] Wu AH：Improving the utilization of clinical laboratory tests. [Review] [43refs] Journal of Evaluation in Clinical Practice. 4(3):171-81,1998 Aug.
[43] Wynne Hsu, Mong Li Lee, Bing Liu, Tok Wang Ling, "Exploration mining in diabetic patients databases: findings and conclusions", Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, August 2000
[44] Zinder O：New directions in laboratory-clinician communications: Clinica Chimica Acta. 278(2):83-94, 1998 Dec.