臺灣博碩士論文加值系統

摘要
建立功能完整、適用範圍廣泛的於醫療決策支援系統是一件高成本的事，尤其是建置過程中醫學專家扮演絕對關鍵性的角色，專家知識的取得與資訊系統間的轉換，是整體作業上最主要的重點。本文從輔助診療的角度提出一項醫療決策系統的快速建構模式，期能減少專家、知識工程人員的參與，降低開發時間與成本。我們試著將構想應用於染色體異常症候群的診療上，其目的就是協助醫師在遺傳門診中，配合此一工具的輔助而能更正確的初步判定其所可能罹患的病症，並藉以作為後續相關檢驗與遺傳諮詢的參考。我們採用web-based的多層架構作業平台本，以增加用戶端使用便利性，本文所提之建構模式同時採用rule-based以及機率推論的方式來處理確定與不確定性因素，除了具有臨床的輔助判斷外，也具有電子書的參考價值及臨床
教育訓練個案模擬功能。

Abstract
It is not a cost-effectiveness of establishing a full-wide function application which applies to computer-aided medical decision support system especially in terms of transforming expert tacit knowledge into explicit representation. This paper proposes a fast constructive mode to establish a medical diagnosis decision support system in order to reduce time cost but concern both knowledge representation and the practicability. We tried to present this concept in the diagnosis and examination of chromosomal abnormality syndrome, for which was the intention to provide an aid kit for the physician to make a more accurate determination preliminarily in their hereditary outpatient services, so as to further related examination of the diseases and to be as consultation information. We adopted a web-based n-tier platform to offer better conveniences for the end user. The constructive mode infered based on rules and probability to deal with complete and incomplete factors. This paper also illustrate the system we implemented that possesses the consultative function in clinical auxiliary judgment with feature of e-textbook and clinical educational training and case study.

摘要
英文摘要
目錄 i
表目錄 ii
圖目錄 iii
第一章、緒論
1.1 醫療決策支援系統之簡介 1
1.2 染色體異常疾病簡介 3
1.3 研究動機與目的 5
1.4 論文大綱 6
第二章、相關研究探討
2.1 醫療決策支援系統的使用與評估 8
2.2推論演算法 11
2.3專家知識的擷取與轉換 14
第三章、研究方法
3.1演算法的設計 16
3.2推論規則 21
第四章、系統實作
4.1.1 作業平台 23
4.1.2 資料庫選擇 26
4.1.3 色體異常知識庫的建立與管理 26
4.1.4 輸入介面設計 27
4.1.5 物件定義與推論 28
4.2 系統client端主要操作說明 30
4.3 系統功能與特色 32
第五章、實驗結果
5.1 實驗結果與討論 34
5.2 專家意見 35
第六章、結論 36
參考文獻 37


表 目 錄
表2.2.1：不同的演算法應用在電腦輔助診斷的結果 13
表3.1 : disease-findings計分表 17
附錄表一：OpenClinical機構公佈已發表的MDSS 41
附錄表二：MDSS使用狀況調查表(以HepatoConsult為例) 42
附錄表三：目前系統可分辨的 28 種染色體異常症候群 43
附錄表四：異常症候群病症所具有的病徵表述
(以Trisomy 21 Syndrome為例) 44
附錄表五：異常症候群病症所具有的病徵表述
(以Trisomy 18 Syndrome為例) 45
附錄表六：外觀病徵輸入項及其展開後的病徵敘述
(以Feature欄為例) 46
附錄表七：DiaseseDatabase 所列之
Chromosomal abnormalities種類 47
附錄表八：實驗結果與其他MDSS的比較表 49


圖 目 錄
圖2.3.1 專家系統的基本架構 14
圖3.1.1：diseases-findings對應圖 16
圖3.1.2：H. Yu等學者處理病徵條件相依方法 21
圖4.1.1.1 系統的3層架構 23
圖4.1.1.2：系統作業流程 25
附錄圖一A~E：系統操作畫面 50
附錄圖二A~B：演算推論規則程式片斷(pascal的語法) 51
附錄圖三：研究流程圖 52

參考文獻
[1]Stephen R. Yarnall, Richard A. Kronmal, “Computer aids to medical diagnosis—problems and progress”, P. of the 21st national conference, 1966.
[2]Lemaire JB et al., “Effectiveness of the Quick Medical Reference as a diagnostic tool”, CMAJ. Sep 21, 1999;161(6):725-8.
[3]Tommy S. Jaakkola, Michael I. Jordon, “Variational Probabilistic Inference and the QMR-DT Network”, J. of Artifical Intelligence Research 10, 1999, pp291-322.
[4]Reed M. Gardner, T. Allan Pryor, Homer R. Warner, “The HELP hospital information system”, International J.of Medical Informatics 54, 1999, pp169–182.
[5]DT Wong, WA Knaus,” Predicting outcome in critical care: the current status of the APACHE prognostic scoring system”, Can., J. of Anesthesia, Vol 38, 374-383, 1991.
[6]M. K. Goldstein et al., “Patient Safety in Guideline-Based Decision Support for Hypertension Management: ATHENA DSS”. AMIA Annual Symposium, 2001.
[7]R. D. Shankar et al., “Building an Explanation Function for a Hypertension Decision-Support System”, MedInfo2001, 2001.
[8]Mary K. Goldstein et al., “Translating Research Into Practice: SocioTechnical Integration of Automated Decision Support for Hypertension in Three Medical Centers”, J.of the American Medical Informatics Association 2004;11(5):368-376.
[9]Peter Szolovits et al., http://medg.lcs.mit.edu/projects/geninfer.html.
[10]E.H. Shortliffe and B.G. Buchanan. “A model of inexact reasoning in medicine in Rule-Based Expert Systems”, The MYCIN Experiments of the Stanford Heuristic Programming Project, Addison-Wesley, pp. 233- 262, 1984.
[11]Janice Aikins et al., http://www.openclinical.org/aisp_puff.html.
[12]Marko Suojanen, Steen Andreassen, Kristian G. Olesen, “A Method for Diagnosing Multiple Diseases in MUNIN”, IEEE Transactions on Biomedical Engineering , Vol.48 No.5 May 2001, pp.522-532.
[13]Perreault L, Metzger J., “A pragmatic framework for understanding clinical decision support”, J. of Healthcare Information Management. 1999;13(2):5-21.
[14]謝清佳、吳琮璠，<資訊管理>，台北：智勝文化，1998, pp17-31~34。
[15]Buscher HP et al., “HepatoConsult: a knowledge-based second opinion and documentation system”, Artifical Intelligence in Medicine 24(3), Mar. 2002, pp205-216..
[16]王作仁，<醫學遺傳學>，台北：聯經出版社，民八十，p31。
[17]顏兆熊、張嘉訓及尹長生，<產科遺傳學及產前診斷>，台中：欣林出版社，民八十。
[18]Kenneth Lyons Jones, “Smith’s Recognizable Patterns of Human malformation”, 5th Edition, W.B. Saunders Company, 1997.
[19]H.R. Warner et al.,.”A mathematical approach to medical diagnosis: application to congenital heart disease”, J. of the American Medical Association, vol. 177, 1961, pp.177-183.
[20]F.T. de Dombal et al., “Computer-aided diagnosis of acute abdominal pain”, British Medical Journal, vol. 2, 1972, pp.9-13.
[21]Lincoln MJ. et al., “Iliad training enhances medical students' diagnostic skills”, J. Med Syst. 1991 Feb;15(1):93-110.
[22]Barnett GO, Cimino JJ, Hupp JA, Hoffer EP. DXplain.” An evolving diagnostic decision-support system”. JAMA. 1987 Jul 3;258(1):67-74.
[23]Eta S. Berner et al., “Performance of Four Computer-Based Diagnostic Systems”, N Engl J Med. June 23, 1994 No 25, Vol. 330 pp1792-1796.
[24]Jane B. Lemaire et al., “Effectiveness of the Quick Medical Reference as a diagnostic tool”, CMAJ 1999;161(6):725-8.
[25]專家系統，江孟峰，2002[民91]，台北市，文魁資訊，p23。
[26]George-Peter K. Economou et al., “A new Concept Toward Computer-Aided Medical Diagnosis –A prototype Implementation Addressing Pulmonary diseases”, IEEE Transactions on Information Technology in Biomedicine, Vol. 5, No.1 Mar. 2001, pp55-66.
[27]Montgomery AA et al., “Evaluation of computer based clinical decision support system and risk chart for management of hypertension in primary care: randomised controlled trial”, British Medical Journal, 2000 March 11; 320(7236): 686–690.
[28]Tierney WM et al., “Effects of computerized guidelines for managing heart disease in primary care”, J Gen Intern Med. 2003 Dec;18(12):967-76.
[29]Rousseau N., “Practice based, longitudinal, qualitative interview study of computerised evidence based guidelines in primary care”, BMJ. 2003 Feb 8;326(7384):314.
[30]Carton M. et al., “Assessment of radiological referral practice and effect of computer-based guidelines on radiological requests in two emergency departments”, Clinical Radiology, Vol. 57, Issue 2 , Feb 2002, pp.123-128.
[31]Kononenko Igor. “Machine Learning for Medical Diagnosis:History, State of the Art and Perspective”, J. of Artificial Intelligence in Medicine, 2001, 23(1):89-109.
[32]Ramoni M, Riva A, Stefanelli M, Patel V. ,“An Ignorant Belief Network to Forecast Glucose Concentation from Clinical Databases”, J. of Artificial Intelligence in Medicine,1995,Vol.7, Issue 6, pp:541-559.
[33]E. Armengo et al., “Individual Prognosis of Diabetes Long-tem Risks:A CBR Approach”, J. of .Methods Inf Med., 2001 Mar.,40(1), pp:46-51.
[34]Hernando ME et al., “Evaluation of DIABNET, a decision support system for therapy planning in gestational diabetes”. Compute Methods Programs Biomed. 2000 Jul;62(3):235-48.
[35]Montani S, Bellazzi R. “Integrating case based and rule based reasoning in a decision support system: evaluation with simulated patients”. Proc AMIA Symp. 1999;:887-91.
[36]Aronsky D, Fiszman M, Chapman WW, Haug PJ.”Combining decision support methodologies to diagnose pneumonia”. Proc AMIA Symp. 2001;:12-6.
[37]P.R. Innocent, R.J. John, “Computer aided fuzzy medical diagnosis”, Information Science, vol. 162, pp 81-104, 2004.
[38]Anish Roychowdhury et al., “Diagnosis of the diseases──using a GA-fuzzy approach”, Information Sciences, vol. 162, pp105-120, 2004.
[39]G.-P.K. Economou, P.D. Goumas and K. Spiropoulos, “A novel medical decision support system”, Computing & Control Engineering Journal, Aug. 1996.
[40]George-Peter K. Economou, Dimitris Lymberopoulos, Evy Karavatselou, Costas Chassomeris, “A new Concept Toward Computer-Aided Medical Diagnosis –A prototype Implementation Addressing Pulmonary diseases”, IEEE Transactions on Information Technology in Biomedicine, Vol. 5, No.1 Mar. 2001, pp55-66.
[41]M. Brameier, W. Banzhaf, “A comparison of linear genetic programming and neural network in medical data mining”, Markus Brameier and Wolfgang Banzhaf, IEEE Transactions on Evolutionary Computation, Vol. 5, No. 1, 2001, pp.17-26.
[42]Marek W. Kurzynski, Edward Puchala, “Multiperspective Recognition Applied to The Computer-Aided Medical Diagnosis – A Comparative Study of Methods”, Proceedings of the 23rd Annual EMBS international Conference, Oct. 25-28, Istanbul, Turkey, 2001.
[43]Frank Puppe, “knowledge reuse among diagnostic problem-sloving methods in the Shell-Kit D3”, Int. J. Human-Computer Studies (1998) 49, pp 627-649.
[44]H.P. Buscher et al., “a knowledge-based second opinion and documentation system”, Artificial Intelligence in medicine 24 (2002) , pp205-216.
[45]J.D.F Habbema, J. Hilden, and B. Bjeregarrd, “The Measeurement of Performance in Probabilistic Diagnosis: I. The Problem, descriptive Tools, and Measures Based on Classification Matrices”, Methods of Information in Medicine, vol. 17, pp217-226.
[46]J.D.F Habbema, J. Hilden, and B. Bjeregarrd, “The Measeurement of Performance in Probabilistic Diagnosis: II. Trustworthiness of the Exact Values of the Diagnostic Probablities,” Methods of Information in Medicine, vol. 17, pp227-237.
[47]H.R. Warner, D.K. Sorenson, and O. Bouhaddou, Knowledge Eng., in Health Informatics. Berlin, New York: Springer Verlag, 1997.
[48]H. Yu et al., “Clustered Knowledge Representation: Increasing the Reliability of Computerized Expert System”, Proc. 12th Symp. Computer Application in Medical Care, 1998.
[49]于文貞，<五大資料庫管理系統之比較>，http://www.dbmaker.com.tw/reference/issue/dbmaiss11.html。