簡易檢索 / 詳目顯示

回結果列表
研究生： 林明煒
Lin, Ming-Wei
論文名稱： 運用資訊擷取技術進行醫學文獻評讀以建立臨床實證及搜尋系統
Automating the Process of Critical Appraisal with Information Retrieval Technology to Facilitate the Development of Evidence-Based Medicine and Clinical Search System
指導教授： 蔣榮先
Chiang, Jung-Hsien
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2010
畢業學年度： 98
語文別： 中文
論文頁數： 54
中文關鍵詞： 實證醫學 、資訊擷取 、臨床搜尋系統
外文關鍵詞： Evidence-Based Medicine(EBM), information retrieval, clinical search system
相關次數： 點閱：102  下載：2 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著實證醫學概念越來越普遍，以經驗來解決臨床問題的傳統方式已不再適合，取而代之的是落實實證醫學，透過網路搜尋最佳證據的方式，才能使病人得到最佳的照護。目前存在的生物醫學文獻資料庫以PubMed最為完整，但PubMed只提供原始的文獻資料，而未對其做有效的分類，使得臨床醫師仍需花費許多時間在搜尋想要的資料。因此本論文將透過自動化的方式進行文獻評讀，對醫學文獻評讀實證等級，幫助臨床醫師快速得到有用的資訊。
    本研究的目的為建構一個自動化的資訊擷取工具，其功能主要是將大型生物醫學文獻資料庫中與心血管疾病相關的文獻，透過語意分析、關鍵字比對、樣板比對等資訊擷取技術，擷取出與臨床實驗之資料收集、分析及解釋等相關的資訊，並使用決策支援系統進行文獻評讀，以判定醫學文獻的實證等級。並且提供一個結構化的實證醫學資料庫，並作為臨床搜尋系統的實證依據。
    經實驗證明，本系統評讀實證等級之查全率可達85.4%、查準率可達85.3%、查全率與查準率的調和平均數可達85.4%及Kappa統計量可達78.0%，相較於傳統方法，本系統可作為一快速且可靠之臨床搜尋系統。

    The popularity of Evidence-Based Medicine has led to the decline of empirical rule for solving clinical problems. Therefore, employing Evidence-Based Medicine by searching the best evidences via Internet can make the patients get a better health care. Among the existing biomedical literature databases, PubMed database is the most complete. Nevertheless, PubMed only provides original literature so that the clinicians consume much time to search the desired information. Hence, this thesis proposes an automatic system performing critical appraisal to assist the clinicians in searching the solutions for clinical problems more conveniently.
    This thesis focuses on building an automatic information retrieval platform. It mainly gathers the information of clinical experiments such as data collection, data analysis, and data interpretation using semantic analyzing, keywords matching, pattern matching, and other information retrieval techniques from cardiovascular-related literatures. Moreover, a decision support system is then applied to perform critical appraisal to determine the level of evidence of biomedical literatures. Finally, a conceptualized database for Evidence-Based Medicine is constructed and considered as the foundation of clinical problems.
    Experimental results for level of evidence reveal that this thesis obtains Recall of 85.4%, Precision of 85.3%, F-measure of 85.4%, and Kappa value of 78.0%. Compared to conventional means, this thesis is qualified to be a convenient and reliable clinical problems search system.

    摘要 I Abstract II 誌謝 IV 目錄 V 表目錄 VIII 圖目錄 IX 第一章 導論 1 1.1 前言 1 1.2 研究動機 2 1.3 解決方法 3 1.4 論文架構 3 第二章 文獻探討 5 2.1 實證醫學相關資源 5 2.1.1 實證等級 5 2.1.2 PICO架構 5 2.1.3 PubMed資料庫及E-Utilities 6 2.1.4 XML格式及LingPipe 7 2.1.5 影響係數及期刊引用報告資料庫 8 2.1.6 統一醫學語言系統 9 2.1.7 MetaMap及MMTx 11 2.1.8 Weka及分類器 12 2.2 相關研究 15 第三章 系統概述 17 3.1 系統架構 17 3.1.1 實證醫學資料庫之建立 18 3.1.2 臨床搜尋系統 19 3.2 實證醫學資料庫之建立 20 3.2.1 資料收集 20 3.2.2 實證樣板擷取 22 3.2.3 實證等級決策 30 3.2.4 資料庫建立 33 3.3 臨床搜尋系統 33 第四章 實驗設計與結果 34 4.1 實驗資料集介紹 34 4.2 準確度評估指標 35 4.3 各分類器對實證等級評讀正確性之實驗 36 4.3.1 各分類器對實證等級評讀正確性之實驗設計及結果 36 4.3.2 實驗結果討論 38 4.4 實證等級準確度評估之實驗 39 4.4.1 實證等級準確度評估實驗設計及結果 39 4.4.2 實驗結果討論 40 4.5 各特徵對實證等級之影響性實驗 41 4.5.1 各特徵對實證等級之影響性實驗設計及結果 41 4.5.2 實驗結果討論 42 第五章 結論與未來展望 43 5.1 結論 43 5.2 未來展望 44 參考文獻 46 附錄A 各分類器所使用參數 51

    1. Oxman AD, Sackett DL, Guyatt GH. Users' guides to the medical literature. I. How to get started. The Evidence-Based Medicine Working Group. JAMA. Nov 3 1993;270(17):2093-2095.
    2. Sackett DL, Rosenberg WM, Gray JA, Haynes RB, Richardson WS. Evidence based medicine: what it is and what it isn't. BMJ. Jan 13 1996;312(7023):71-72.
    3. Bradt P, Moyer V. How to teach evidence-based medicine. Clin Perinatol. Jun 2003;30(2):419-433.
    4. Eddy DM. Evidence-based medicine: a unified approach. Health Aff (Millwood). Jan-Feb 2005;24(1):9-17.
    5. Rosenberg W, Donald A. Evidence based medicine: an approach to clinical problem-solving. BMJ. Apr 29 1995;310(6987):1122-1126.
    6. PubMed. http://www.ncbi.nlm.nih.gov/pubmed. Accessed June 25.
    7. The Cochrane Library. http://www.update-software.com/cochrane/. Accessed June 25.
    8. Clinical Evidence. http://www.clinicalevidence.com/ceweb/conditions/. Accessed June 25.
    9. Ebell MH, Siwek J, Weiss BD, et al. Strength of recommendation taxonomy (SORT): a patient-centered approach to grading evidence in the medical literature. J Am Board Fam Pract. Jan-Feb 2004;17(1):59-67.
    10. Richardson WS, Wilson MC, Nishikawa J, Hayward RS. The well-built clinical question: a key to evidence-based decisions. ACP J Club. Nov-Dec 1995;123(3):A12-13.
    11. Entrez Programming Utilities. http://eutils.ncbi.nlm.nih.gov/entrez/query/static/eutils_help.html. Accessed June 25, 2010.
    12. LingPipe. http://alias-i.com/lingpipe/. Accessed June 25, 2010.
    13. Garfield E. Citation frequency as a measure of research activity and performance. Essays of an Information Scientist. 1973;1:406-408.
    14. Journal Citation Reports. http://admin-apps.isiknowledge.com/JCR/JCR?/. Accessed June 25.
    15. Bodenreider O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res. Jan 1 2004;32(Database issue):D267-270.
    16. Lindberg C. The Unified Medical Language System (UMLS) of the National Library of Medicine. J Am Med Rec Assoc. May 1990;61(5):40-42.
    17. Lindberg DA, Humphreys BL, McCray AT. The Unified Medical Language System. Methods Inf Med. Aug 1993;32(4):281-291.
    18. Bangalore A, Thorn KE, Tilley C, Peters L. The UMLS knowledge source server: an object model for delivering UMLS data. AMIA Annu Symp Proc. 2003:51-55.
    19. Thorn KE, Bangalore AK, Browne AC. The UMLS Knowledge Source Server: an experience in Web 2.0 technologies. AMIA Annu Symp Proc. 2007:721-725.
    20. Aronson AR. Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. Proc AMIA Symp. 2001:17-21.
    21. Divita G, Tse T, Roth L. Failure analysis of MetaMap Transfer (MMTx). Stud Health Technol Inform. 2004;107(Pt 2):763-767.
    22. Osborne JD, Lin S, Zhu L, Kibbe WA. Mining biomedical data using MetaMap Transfer (MMtx) and the Unified Medical Language System (UMLS). Methods Mol Biol. 2007;408:153-169.
    23. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The WEKA data mining software: an update. SIGKDD Explor. Newsl. 2009;11(1):10-18.
    24. Quinlan JR. C4.5: programs for machine learning: Morgan Kaufmann Publishers Inc.; 1993.
    25. Quinlan JR. Improved use of continuous attributes in C4.5. J. Artif. Int. Res. 1996;4(1):77-90.
    26. Zeidenberg M. Neural networks in artificial intelligence: Ellis Horwood; 1990.
    27. Joachims T. A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization. Proceedings of the 14th International Conference on Machine Learning, ICML-97. Nashville, Tennessee, USA: Morgan Kaufmann Publishers Inc.; 1997.
    28. Cover T, Hart P. Nearest neighbor pattern classification. Information Theory, IEEE Transactions on. 1967;13(1):21-27.
    29. Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. Proceedings of the 5th annual workshop on Computational learning theory, COLT-92. Pittsburgh, Pennsylvania, USA: ACM; 1992.
    30. ACP Journal Club. http://www.acpjc.org/. Accessed June 25.
    31. Evidence-Based Medicine. http://ebm.bmj.com/. Accessed June 25.
    32. The Cochrane Collaboration. http://www.cochrane.org/. Accessed June 25.
    33. Centre for Evidence-Based Medicine(CEBM). http://www.cebm.net/. Accessed June 25.
    34. Niu Y, Hirst G, McArthur G, Rodriguez-Gianolli P. Answering clinical questions with role identification. Proceedings of the 41st annual meeting of the Association for Computational Linguistics, ACL-03. Sapporo, Japan: Association for Computational Linguistics; 2003.
    35. Niu Y, Zhu X, Hirst G. Using outcome polarity in sentence extraction for medical question-answering. AMIA Annu Symp Proc. 2006:599-603.
    36. Aphinyanaphongs Y, Tsamardinos I, Statnikov A, Hardin D, Aliferis CF. Text categorization models for high-quality article retrieval in internal medicine. J Am Med Inform Assoc. Mar-Apr 2005;12(2):207-216.
    37. Salton G, Wong A, Yang CS. A vector space model for automatic indexing. Commun. ACM. 1975;18(11):613-620.
    38. Demner-Fushman D, Lin J. Knowledge extraction for clinical question answering: Preliminary results. Proceedings of the 20th National Conference on Artificial Intelligence, AAAI-05. Pittsburgh, Pennsylvania, USA: AAAI; 2005.
    39. Lin J, Demner-Fushman D. The role of knowledge in conceptual retrieval: a study in the domain of clinical medicine. Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR-06. Seattle, Washington, USA: ACM; 2006.
    40. Demner-Fushman D, Few B, Hauser SE, Thoma G. Automatically identifying health outcome information in MEDLINE records. J Am Med Inform Assoc. Jan-Feb 2006;13(1):52-60.
    41. Demner-Fushman D, Lin J. Answering Clinical Questions with Knowledge-Based and Statistical Techniques. Comput. Linguist. 2007;33(1):63-103.
    42. Huang X, Lin J, Demner-Fushman D. Evaluation of PICO as a knowledge representation for clinical questions. AMIA Annu Symp Proc. 2006:359-363.
    43. Lin J, Demner-Fushman D. "Bag of words" is not enough for strength of evidence classification. AMIA Annu Symp Proc. 2005:1031.
    44. EBM Solution. http://online.statref.com/Splash/Splash.aspx?SessionId=1285F7APNIJBQVJF/. Accessed June 25.
    45. Baeza-Yates RA, Ribeiro-Neto B. Modern Information Retrieval: Addison-Wesley Longman Publishing Co., Inc.; 1999.
    46. Fleiss JL. Measuring nominal scale agreement among many raters. Psychological Bulletin. 1971;76(5):378-382.
    47. Sim J, Wright CC. The kappa statistic in reliability studies: use, interpretation, and sample size requirements. Phys Ther. Mar 2005;85(3):257-268.
    48. Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. Mar 1977;33(1):159-174.

    下載圖示 校內：2012-08-10公開
    校外：2012-08-10公開
    QR CODE