(3.236.118.225) 您好!臺灣時間:2021/05/16 13:37
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:::

: 
twitterline
研究生:邱曉莉
研究生(外文):Hsiao-Li Chiu
論文名稱:相關查詢詞自動建議應用於心血管疾病資訊檢索之研究
論文名稱(外文):Automatic Relevant Term Suggestion in Cardiovascular Disease Information Retrieval
指導教授:林紋正林紋正引用關係
指導教授(外文):Wen-Cheng Lin
學位類別:碩士
校院名稱:慈濟大學
系所名稱:醫學資訊研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
畢業學年度:96
語文別:中文
論文頁數:47
中文關鍵詞:健康資訊檢索心血管疾病查詢詞推薦查詢擴展機器學習統一醫學語言系統
外文關鍵詞:Health information retrievalCardiovascular disease(CVD)Query term suggestionMachine learningQuery expansionUnified Medical Language System (UMLS)
相關次數:
  • 被引用被引用:7
  • 點閱點閱:474
  • 評分評分:
  • 下載下載:71
  • 收藏至我的研究室書目清單書目收藏:5
網際網路的普及使民眾方便在網路上搜尋醫療健康資訊,而心血管疾病每年皆列國內十大死因之ㄧ,且有罹病人口遽增、年齡層下降之趨勢,因此民眾利用網際網路搜尋心血管疾病相關資訊之需求倍增。不過礙於民眾對醫學詞彙的認知極為有限,常常使用不精確的查詢,使得搜尋結果所涵蓋的範圍太廣,或是使用的查詢詞和欲搜尋的文件內的用語不相符合,以致降低檢索效能。因此本研究希望建置「心血管疾病相關查詢詞推薦系統」,自動推薦相關詞予使用者選擇,協助使用者建立更精確的查詢,以便能更快速找到所需求的心血管疾病相關資訊。本研究分別從語料庫及語言知識庫(Unified Medical Language System, UMLS)中擷取出相關詞,並結合常見查詢詞推薦給使用者。當使用者在查詢心血管疾病相關資訊時,鍵入查詢詞,系統會自動推薦相關查詢詞給使用者選擇,建立更精確的查詢之後,再送至搜尋引擎搜尋,如此有利使用者更快速及正確地找到所需要的醫療健康資訊。實驗結果發現使用從語料庫中自動擷取出的相關詞時,系統推薦的前10個詞中約有77%是與原查詢詞很相關的。使用相關查詢詞推薦系統能使檢索效能提高,搜尋結果前10篇網頁的查準率(precision)約0.83,較一般民眾自訂查詢語句的檢索效能提高約38%。使用者認為使用本系統能協助他們建立有用的查詢語句,搜尋到更多相關網頁。
The availability of internet has brought convenience for consumers to search for health information. Cardiovascular disease is one of the top ten deaths in Taiwan. Its prevalence has increased and the age of affected population has decreased. Therefore, there is an increased demand for searching information about cardiovascular disease. However, the lay people have limit knowledge of medical terminologies. Moreover, they often use imprecise queries which have broader meanings or can’t match the terms in documents. That would make retrieval effectiveness decreased.
In this study, we develop a “Relevant Term Suggestion System for Cardiovascular Disease” that would automatically recommend related terms for users to help them constructing a more precise query and increasing search performance. The related terms are extracted from a corpus of cardiovascular disease and UMLS which is a medical language knowledge base. When a user key in a query term, the system will automatically recommend terms related to the original query term. After user selecting appropriate terms, the new query is submitted to a searching engine. This would make users to search for the needed health information more effectively.
Experimental results showed that for the terms extracted from the cardiovascular disease corpus, 77% of the top ten recommended terms are related to the original query term. Using the query term suggestion system would increase the search effectiveness. The precision of the top 10 returned web pages is about 0.83 and is 38% better than that of constructing queries by themselves. Users think that the query term suggestion system could help them to build a more useful query and to find more related web pages.
中文摘要 I
英文摘要 II
致謝 III
目錄 IV
表目錄 VI
圖目錄 VII
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 3
第二章 文獻探討 4
2.1 心血管疾病 4
2.2 資訊檢索 5
2.3 查詢擴展 7
2.3.1 自動查詢擴展 8
2.3.2 半自動查詢擴展 9
2.4 UMLS 10
第三章 相關查詢詞推薦 14
3.1 系統架構 14
3.2 由心血管疾病語料庫自動訓練相關詞 15
3.2.1 心血管疾病語料庫 15
3.2.2 自動訓練相關詞 17
3.3 由語言知識庫擷取相關詞 18
3.4 推薦不同來源之相關詞 20
3.5 相關查詢詞推薦系統 22
第四章 實驗設計及評估 25
4.1 實驗設計 25
4.2 實驗評估及結果分析 27
4.2.1 自動擷取之相關詞與原始查詢詞之相關程度 27
4.2.2 相關查詢詞推薦對檢索效能之影響 29
4.2.3 使用者滿意度評估 34
第五章 結論及未來工作 36
5.1 結論 36
5.2 未來發展 37
參考文獻 38
附錄A 43
附錄B 44
參考文獻
[1]Aronson, A.R. and Rindflesch, T.C. (1997). “Query Expansion Using the UMLS Metathesaurus.” In Proceedings of the 1997 AMIA Annual Fall Symposium, 485-489.
[2]Baeza-Yates, R. and Ribeiro-Neto, B. (1999). Modern Information Retrieval. Addison Wesley, 1999.
[3]Bodenreider, O. (2001). “Circular hierarchical relationships in the UMLS: etiology, diagnosis, treatment, complications and prevention.” In Proceedings of the AMIA Symposium 2001, 57–61.
[4]Bodenreider, O. (2004) “The Unified Medical Language System (UMLS): integrating biomedical terminology.” Nucleic Acids Research, 32, D267-D270.
[5]Chen, H. (2000). “UMLS and Linguistics Enhanced Medical Information Retrieval.” In Proceedings of NHRI (National Health Research Institute) Research Resources, Taipei, Taiwan, April 27, 2000.
[6]Church, K.W. and Hanks, P. (1990). “Word Association Norms, Mutual Information, and Lexicography.” Computational Linguistics, 16(1), 22-29.
[7]Fox, S. (2005). “Health Information Online: Eight in ten internet users have looked for health information online, with increased interest in diet, fitness, drugs, health insurance, experimental treatments, and particular doctors and hospitals.” [On-line] Pew Internet & American Life Project, May 17, 2005.
http://www.pewinternet.org/pdfs/PIP_Healthtopics_May05.pdf
[8]Gedzelman, S., Simonet, M., Bernhard, D., Diallo, G., and Palmer, P. (2005). “Building an ontology of Cardio-Vascular diseases for Concept-Based Information Retrieval.” [On-line].
http://www.noesis-eu.org/Disemination/Cinc%20%20presentation%20SIMONET/Simonet_352.pdf
[9]Gene Ontology (GO). http://www.geneontology.org/
[10 ]Gobel, G., Andreatta, S., Masser, J., and Pfeiffer, K.P.(2001). “A MeSH based intelligent search intermediary for Consumer Health Information Systems.” International Journal of Medical Informatics, 64, 241–51.
[11]Health On the Net Foundation (2002). “Excerpt of the 8th HON's survey of health and medical internet users.” [On-line].
http://www.hon.ch/Survey/8th_HON_results.html
[12]Hersh, W., Price, S., and Donohoe, L.(2000). “Assessing thesaurus-based query expansion using the UMLS Metathesaurus.” In Proceedings AMIA Symposium 2000, 344–8.
[13 ]Joubert, M., Fieschi, M., Robert, J.J., Volot, F, and Fieschi, D. (1998). “UMLS-based conceptual queries to biomedical information databases: an overview of the project ARIANE.” Journal of the American Medical Informatics Association, 5, 52–61.
[14]Kakade, V. and Sharangpani, M. (2004). “Improving the Precision of Web Search for Medical Domain using Automatic Query Expansion.” [On-line]. http://www.stanford.edu/class/archive/cs/cs276a/cs276a.1032/projects/reports/vkakade-smadhura.pdf
[15]Li, J.-F., Guo, M.-Z., and Tian, S.-H. (2005). “A new approach to query expansion.” In Proceedings of the Fourth International Conference on Machine Learning and Cybernetics (ICMLC2005), 2302-2306.
[16]McCray, A.T., Ide, N.C., Loane, R.R., and Tse, T. (2004). “Strategies for supporting consumer health information seeking.” Medinfo, 11(2), 1152-1156.
[17]Medical Subject Heading (MeSH). http://www.nlm.nih.gov/mesh/
[18]OVID MEDLINE. http://ovid.digilib.nctu.edu.tw
[19]Owais, S.S.J., Kromer, P., Snasel, V., Maleki-Dizaji, S., and Nyongesa, H.O. (2007). “Upgrading Web Search Queries.” In Proceedings of Database and Expert Systems Applications, 2007, 18th International Conference on, 128-132.
[20]Qing, T., Robert, M., Ngo, L., and Dibble, E. (2006). “Assisting consumer health information retrieval with query recommendations.” Journal of the American Medical Informatics Association, 13, 80-90.
[21]Silverstein, C., Marais, H., Henzinger, M., and Moricz, M. (1999). “Analysis of a very large web search engine query log.” ACM SIGIR Forum, 33(3), 6-12.
[22]Soergel, D., Tse, T., and Slaughter, L. (2004). “Helping Healthcare Consumers Understand: An "Interpretive Layer" for Finding and Making Sense of Medical Information.” Medinfo, 11(2), 931-935.
[23]Su, L.T. (2003). “A comprehensive and systematic model of user evaluation of web search engines: I. theory and background.” Journal of the American Society for Information Science and Technology, 54(13), 1175-1192.
[24]Tseng, Y.-H. (1998). “Solving Vocabulary Problems with Interactive Query Expansion.” Journal of Library Information Science, 24(1), 1-18.
[25]Unified Medical Language System Knowledge Source Server.
http://umlsks.nlm.nih.gov
[26]Xu, J. and Croft, W. (1996). “Query Expansion Using Local and Global Document Analysis.” In Proceedings of the Nineteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 4-11.
[27]Zeng, Q., Kogan, S., Ash, N., Greenes, R.A., and Boxwala, A.A. (2002). “Characteristics of consumer terminology for health information retrieval.” Methods of Information in Medicine, 41(4), 289-98.
[28]台北市政府衛生局新聞稿 (2007). 臺北市民心血管疾病死亡知多少?
[Online]. http://www.health.gov.tw/Default.aspx?tabid=36&mid=442&itemid=17479
[29]行政院交通部統計處, “台灣地區民眾使用網際網路狀況調查報告”.
[30]行政院衛生署國民健康局. http://www.bhp.doh.gov.tw
[31]行政院衛生署衛生統計資訊網. http://www.doh.gov.tw/statistic/index.htm
[32]朱怡霖 (2002), “中文斷詞及專有名詞辨識之研究”, 國立台灣大學資訊工程研究所碩士論文.
[33]李滿梅 (2006), “冠狀動脈疾病病患對疾病認知、態度及自我照顧行為之探討-以中部某教學醫院為例”, 弘光科技大學護理研究所碩士論文.
[34]林敏玲、邱艷芬 (2001), “花蓮地區心臟衰竭病患對疾病認知、態度及自我照顧行為相關性之探討”, 慈濟醫學雜誌, 13(1), 57-64.
[35]卓玉聰、林千鈺 (2001), “消費者健康資訊網路資源之探討”, 圖書資訊學刊, 2(2) , 57-85.
[36]林俊龍 (2005). 吃好心臟病. 天下文化出版社.
[37]林吟映、林瑞興 (2006), “運動對預防中老年人心血管疾病的效果探討”, 中華體育, 20(3), 11-17.
[38]翁心植、胡亞美(主編) (2001). 英漢/漢英醫學分科辭典, 台北: 旺文社.
[39]張順全 (2003), ”從疾病負擔研究談健康測量之發展”, 台北:行政院衛生署.
[40]張慧銖 (1995), “統一醫學語言系統簡介”, 國立臺灣大學醫學院圖書分館館訊, 27, 1-4.
[41]陳光華、莊雅蓁 (2001), “資訊檢索之中文詞彙擴展”, 資訊傳播與圖書館學, 8(1), 59-75.
[42]陳光華 (2004), “資訊檢索之績效評估”, 2004年現代資訊組織與檢索研討會論文集, 125-139.
[43]張淳茜 (2000), “病患健康資訊來源及其相關因素之研究”, 中國醫藥學院醫務管理研究所碩士論文.
[44]許麗齡 (2002), “健康/醫療網站之需求與功能”, 臺灣醫學雜誌, 6(4), 585-589.
[45]黃慕萱 (1996). 資訊檢索中「相關」概念之研究. 學生書局.
[46]黃翠媛、黃秀梨 (1995), “冠狀動脈疾病病人的疾病認知、態度及自我照顧行為之探討”, 護理研究, 3(3), 225-233.
[47]錢美�� (2004), “台灣地區老人飲食與心血管疾病危險因子之討探”, 國防大學公共衛生所碩士論文.
[48]戴再松 (2005), “運動與心血管疾病的預防”, 嘉基院訊, 110期.
[49]魏美珠、楊美雪、吳聰慧 (1995), “南市老人預防腦血管疾病的認知、態度與行為調查”, 中華衛誌, 14 (1), 62-77.
[50]簡仁宗、楊敦淇 (2003), “相關資訊回饋於被式混合是機率檢索模型”, 國立成功大學資訊工程學系碩士論文.
[51]顏永泰 (2004), “整合資訊檢索與醫學本體論之SARS知識管理系統”, 台北醫學大學醫學資訊研究所碩士論文.
[52]蘇純閨 (2000). 哈里遜內科學手冊 13版, 台北:合記圖書.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top