跳到主要內容

臺灣博碩士論文加值系統

(44.192.95.161) 您好!臺灣時間:2024/10/10 09:28
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:劉宜佩
研究生(外文):Yi-pei Liu
論文名稱:發展一探勘模式於醫師用藥行為探討-以史蒂芬氏強生症候群為例
論文名稱(外文):Developing a Mining Approach to Investigate Physician Prescription Behavior-An Example of Stevens-Johnson Syndrome
指導教授:歐陽超歐陽超引用關係
指導教授(外文):Chao Ou-Yang
口試委員:歐陽超
口試日期:2011-06-28
學位類別:碩士
校院名稱:國立臺灣科技大學
系所名稱:工業管理系
學門:商業及管理學門
學類:其他商業及管理學類
論文種類:學術論文
論文出版年:2011
畢業學年度:99
語文別:中文
論文頁數:92
中文關鍵詞:資料探勘分類分群F-measure凝聚式的階層分群演算法序列性關聯用藥行為史蒂芬氏強生症候群
外文關鍵詞:ClassificationClusteringMatrix SimilarityF-measurePhysicians’ Prescription BehaviorsStevens-Johnson Syndrome
相關次數:
  • 被引用被引用:0
  • 點閱點閱:293
  • 評分評分:
  • 下載下載:35
  • 收藏至我的研究室書目清單書目收藏:1
隨著科技的日新月異,資料蒐集以及儲存方法的進步,因此能夠快速累積龐大的資料,然而如何能從大量的資料,萃取有用的資訊,甚至發現一些新奇以及有用的樣式,是一大課題。其中資料探勘即是一種能夠在大量資料自動化發現一些有用資訊的流程,且過去資料探勘的發展,已廣泛的被應用在各個知識領域中如醫療、工程、科學等。本研究希望發展一套有效的醫師用藥行為探勘模式,用以探討具有嚴重用藥併發症之疾病,會對醫師之用藥行為產生怎樣的變化。
本研究以全民健保資料庫,某一年份之史蒂芬氏強生症候群病人為例,希望以病人住院前、後用藥的觀點,藉由資料探勘的手法,透過以規則為基礎之分類的方法,將病人做分類,發現病人之用藥行為,除此之外,將病人之用藥以矩陣表示,透過F-measure相似度的計算,結合凝聚式的階層分群演算法,將用藥模式相似的病人做分群,再透過序列性關聯,發現各群的特徵用藥序列,做為醫生開藥的方針。其中病人用藥矩陣相似度的計算,可先將用藥相似病人歸為一群,如此可避免從大量資料中,透過序列性關聯,找出過多無意義之特徵用藥序列。
In clinical practice, a severe illness might be the result of an untoward reaction to the pharmacological treatment for another disease. For instance, Stevens-Johnson syndrome (SJS) can be caused by antibiotics; nonsteroidal anti-inflammatory drugs; antiepileptics; antugout agents; and cardiovascular drugs, as well as the drugs for local use in ophthalmology and dermatology. Since there are so many drugs covering various different medical fields, very few physicians are familiar with all the potential drugs that can cause SJS. Hence new cases or even recurrent cases of drug-induced SJS are still reported from time to time.
Currently in Taiwan, the causal relations between physicians’ prescription behaviors and the occurrence of SJS are not clear. Therefore, in this research, by applying the SJS cases data from National Health Insurance database, a pharmacological treatment mining approach is proposed to investigate physicians’ prescription behaviors before and after the occurrence of SJS.
This research will describe the behavior of pharmacological treatment by the rule-based classification method. A matrix will be used to specify the pharmacological record for each SJS case. Then, a modified F-measure will be used to measure the similarity between each pair of matrices. The measured data will be used to cluster the cases. For each group of cases, its frequent item sets will be mined and the behavior pattern of the pharmacological treatment will be identified.
摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vii
表目錄 viii
第一章、緒論 1
1.1研究背景 1
1.2研究動機 2
1.3研究目的 3
1.4論文架構 3
第二章、文獻探討 5
2.1流程相似度 6
2.2資料探勘 8
2.2.1分群演算法 9
2.2.2序列性關聯 9
2.3總結 10
第三章、研究方法 11
3.1概念階段 11
3.2設計階段 12
3.2.1資料前處理 12
3.2.2病人用藥行為分類 13
3.2.3建構個別病人住院前用藥矩陣 16
3.2.4以F-measure計算相似度 18
3.2.5利用凝聚式階層演算法將病人做分群 23
3.2.6依序列性關聯發現各群較常出現之特徵用藥序列 24
3.2.7研究限制 27
第四章、實作研究 28
4.1資料前處理 29
4.1.1專藥用藥取得 29
4.1.2專業用藥編碼 31
4.1.3刪除出現頻率低之專業用藥 33
4.2病人用藥行為分類 34
4.3病人用藥矩陣相似度計算 35
4.4具備相似用藥模式病人之分群 36
4.5依序列性關聯發現特徵用藥序列 43
4.6結果呈現 44
4.7驗證分析與結果討論 47
4.7.1驗證分析 47
4.7.2結果討論 48
第五章、結論與建議 52
5.1結論 52
5.2未來建議 54
參考文獻 56
附錄A-1、{f10,f01}類病人用藥相似度矩陣 59
附錄A-2、{f11}類病人用藥相似度矩陣 60
附錄A-3、{f10}類病人用藥相似度矩陣 61
附錄A-4、{f11,f10}類病人用藥相似度矩陣 62
附錄A-5、{f11,f10,f01}類病人用藥相似度矩陣 63
附錄B-1、{f10,f01}類病人分群樹狀圖 64
附錄B-2、{f11}類病人分群樹狀圖 64
附錄B-3、{f10}類病人分群樹狀圖 64
附錄B-4、{f11,f10}類病人分群樹狀圖 64
附錄B-5、{f11,f10,f01}類病人分群樹狀圖 64
附錄C-1.1、{f10,f01}類1.1群病人之用藥紀錄 65
附錄C-1.2、{f10,f01}類1.2群病人之用藥紀錄 66
附錄C-1.3、{f10,f01}類1.3群病人之用藥紀錄 69
附錄C-1.4、{f10,f01}類1.4群病人之用藥紀錄 70
附錄C-1.5、{f10,f01}類1.5群病人之用藥紀錄 71
附錄C-1.6、{f10,f01}類1.6群病人之用藥紀錄 72
附錄C-2.1、{f10}類2.1群病人之用藥紀錄 74
附錄C-2.2、{f10}類2.2群病人之用藥紀錄 75
附錄C-2.3、{f10}類2.3群病人之用藥紀錄 76
附錄C-2.4、{f10}類2.4群病人之用藥紀錄 77
附錄C-2.5、{f10}類2.5群病人之用藥紀錄 78
附錄C-3.1、{f11,f10,f01}類4.1群病人之用藥紀錄 79
附錄C-3.2、{f11,f10,f01}類4.2群病人之用藥紀錄 80
附錄C-3.3、{f11,f10,f01}類4.3群病人之用藥紀錄 80
附錄C-3.4、{f11,f10,f01}類4.4群病人之用藥紀錄(住院前) 81
附錄C-3.5、{f11,f10,f01}類4.4群病人之用藥紀錄(住院後) 82
附錄C-3.6、{f11,f10,f01}類4.5群病人之用藥紀錄(住院前) 83
附錄C-3.7、{f11,f10,f01}類4.5群病人之用藥紀錄(住院後) 84
附錄C-4.1、{f11}類5.1群病人之用藥紀錄 85
附錄C-4.2、{f11}類5.2群病人之用藥紀錄 86
附錄C-4.3、{f11}類5.3群病人之用藥紀錄 86
附錄C-4.4、{f11}類5.4群病人之用藥紀錄 87
附錄C-4.5、{f11}類5.5群病人之用藥紀錄 88
附錄C-5.1、{f11,f10}類6.1群病人之用藥紀錄 89
附錄C-5.2、{f11,f10}類6.2群病人之用藥紀錄 90
附錄C-5.3、{f11,f10}類6.3群病人之用藥紀錄 92
【Aalst 2006】W.M.P. van der Aalst, A.K. Alves de Medeiros and A.J.M.M.
Weijters,“ Process Equivalence: Comparing Two Process Models Based on Observed Behavior ”, In S. Dustdar, J.L. Fiadeiro, and A. Sheth, editors, BPM , 2006.
【Agrawal 1993】R. Agrawal , T. Imielinski and A. Swami, “ Mining Association Rules between Sets of Items in Large Database ”, Proceedings Of the ACM-SIGMOD Conference On the Management of Data, pp.207-216 , 1993.
【Agrawal 1994】R. Agrawal , R. Srikant, “ Mining Sequential patterns ”, Proceedings of the International Conference on Data Engineering , 1994.
【Chen 1996】M. S. Chen, J. W. Han, P. S. Yu, “ Data mining : An overview from a
database perspective ”, IEEE Transactions on Knowledge and DataEngineering,Vol.
8,No.6, December , 1996.
【Chung 2006】W.H. Chung ,S.I. Hung ,“Genetic susceptibility to carbamazepine- induced cutaneous adverse drug reactions ” , Pharmacogenetics and Genomics 16(4): 297-306 , 2006.
【Dimitriadoua 2004】E. Dimitriadoua ,M. Barthb ,C. Windischbergerc ,K. Hornika
and E. Moser , “A quantitative comparison of functional MRI cluster analysis”,
Artificial Intelligence in Medicine, 31, pp.57-71 , 2004.
【Dunham 2002】M.H. Dunham , “ Data Mining Introductory and AdvancedTopics ”,
Pearson Education, New Jersey , 2002.
【Frawley 1991】W. J. Frawley , G. Paitetsky-Shapiro, and C. J. Matheus,
“ Knowledge discovery in databases: An overview, knowledge discovery in
databases ” , AAAI/MIT Press , 1991.
【Gendy 1996】H. E. Gendy, “A New Theory for Equivalence Between Process
Specifications”, ICECS , 1996.
【Gendy 1998】H. E. Gendy, H. E. Sayed and A.W. Fayez, “Comparative Analysis of
the Notions of Equivalence for Process Specifications”, IEEE , 1998.
【Han 2001】J. Han, M. Kamber , “Data mining: Concepts and Techniques”, San
Francisco:Morgan Kaufmann Publishers , 2001.
【Hazin 2008】R. Hazin , O. A. Ibrahimi , “Stevens‐Johnson syndrome: Pathogenesis, diagnosis, and management ”, Annals of Medicine 40(2): 129-138 , 2008.
【Hennessy 1985】M. Hennessy and R. Milner, “Algebraic Laws for Nondeterminism
and Concurrency” , ACM J., Vol. 32, No. I, pp.137-161,Jan , 1985.
【Hoare 1981】C. Hoare, “ A Model for Communicating Sequential Processes ”,Tech.
Monograph Prg-22, Comp. Lab., Univ. of Oxford , 1981.
【Hoare 1981】C.A.R. Hoare, S. D. Brookes and A. W. Roscoe, “A Theory of
Communicating Sequential Processes ”, Technical Report PRG-16,Oxford University, Programming Research Group , 1981.
【Jung 2008】J. Jung , J. Bae and L. Liu, “ Hierarchical Business Process Clustering ”, IEEE International Conference on Services Computing, pp. 613‐616 , 2008.
【Ma 2005】Y. Ma ,Y. Liu , “ Chinese-English Quasi-equivalent Noun Phrase: Definition and Automatic Identification ”, Youth project of Asia research center, Tsinghua University , 2005.
【Milner 1981】R. Milner, “ A Calculs of Communicating Systems ”, Computer
Science, Springer Verlag, Vol. 92 , 1981.
【Mukhopadhyay 2009】A. Mukhopadhyay, U. Maulik, and S.Bandyopadhyay, “Refining Genetic Algorithm Based Fuzzy Clustering through Supervised Learning for Unsupervised Cancer Classification”, Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics Vol.5483, pp.191-202 , 2009.
【Nascimento 2009】A. Nascimento, R. Prudêncio, M. de Souto, and I. Costa,
“Mining Rules for the Automatic Selection Process of Clustering Methods Applied to
Cancer Gene Expression Data”, Artificial Neural Networks, ICANN, Vol.5769,
pp.20-29 , 2009.
【Nicola 1984】R.Nicola and M. C. B. Hennessy, “Testing Equivalences for
Processes”, heoretical Comp. SC. 34, N. Holland, pp.83-133 , 1984.
【Poelmans 2010】J. Poelmans, G. Dedene ,“Combining business process and data discovery techniques for analyzing and improving integrated care pathways ”,
Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects. Berlin, Germany, Springer-Verlag: 505-517, 2010.
【Thakur 2010】M. Thakur, S. Olafsson, J.S. Lee, and C.R. Hurburgh , “Data mining
for recognizing patterns in foodborne disease outbreaks”, Journal of Food Engineering, Vol.97, No.2, pp.213-227, 2010.
【Van Rijsbergen 1979】 C.J.Van Rijsbergen ,“ Information Retrieval ”,Butterworths , London , 1979.
【Yang 1999】Y. Yang, X. Liu , “A re-examination of text categorization methods”, In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval , 1999.
【李勝馥,2006】李勝馥,「STEVENS-JOHNSON SYNDROME」,耕莘藥訊,2006。
【洪乃勻,2006】洪乃勻,「藥物不良反應與皮膚疾病」,三總藥訊,2006。
【徐啟聖,2005】徐啟聖,「應用關聯法則分析不同科別高血壓處置的差異」,
元智大學資訊管理所,2005。
【陳世源,2000】陳世源,「資料採礦技術在病例與藥品關聯性之研究」,國立中山大學資訊管理所,2000。
【蘇芷凡,2004】蘇芷凡,「資料採礦之實務—心血管之交互作用與用藥分析」,
國立政治大學統計研究所,2004。
【TDRF,2011】 TDRF財團法人藥害救濟基金會,「歷年(1999年至2011年5月)藥害救濟統計資料」,取自http://www.tdrf.org.tw/ch/05knows/kno_07_main.
asp?bull_id=4199,2011。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top