臺灣博碩士論文加值系統

史蒂芬強生症是一種罕見且嚴重的疾病，其特徵為表皮的細胞死亡、真皮與表皮分離，是一種可致命的皮膚疾病。引起史蒂芬強生症的因素很多種，其中大多數病例為不當使用藥物所導致。會引起史蒂芬強生症藥物廣泛分佈於各種不同的醫療用途，然而只有極少數的醫師熟悉這些藥物，導致時常有使用SJS 用藥而導致得病的案例。
本研究使用台灣全民健保資料庫，以某一年份之史蒂芬強生症病患為例。藉由資料探勘分析病患資料，把病患的就醫與用藥記錄，透過關聯法則找出資料間的相關關係。根據關聯法則中的序列模式，把病患就醫與用藥記錄以序列模式呈現，並運用GSP、PrefixSpan 演算法找出高頻率的就醫與用藥序列，所得結果可作為醫療上的參考。

Stevens-Johnson syndrome (SJS), a form of toxic epidermal necrolysis, is a lifethreatening skin condition, in which cell death causes the epidermis to separate from the dermis. There are many factors cause SJS, most of SJS cases are caused by using improper drugs. The drugs which cause SJS are used in various medical fields. However, very few physician are familiar with all these drugs, so there are many cases when physician is not aware about the drugs causing SJS.
This study uses 1-year data of Taiwan’s NHIRD (National Health Insurance Research Database) to find the sequential pattern of medical specialties and their prescription for SJS patients. Two sequential patterns mining algorithms, GSP and PrefixSpan are used to find patterns. The research results could be use as medical reference.

摘要 I
Abstract II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VII
第一章 緒論 1
1.1 研究背景 1
1.2 研究目的 2
1.3 論文架構 2
第二章 文獻探討 4
2.1 運用健保資料庫研究史蒂芬強生症 4
2.2 資料探勘 5
2.3 Apriori 關聯規則 6
2.4 序列性關聯演算法 6
2.5 應用 8
第三章 研究方法 9
3.1 研究流程與架構 9
3.2 資料前處理 11
3.2.1 類別檔整理與合併 11
3.2.2 篩選SJS 病患資料 13
3.2.3 用藥分類及篩選 14
3.3 序列性關聯-就醫科別與用藥之關聯 16
3.3.1 序列關聯之定義 17
3.3.2 主要族群的序列關聯 18
3.3.3 高頻就醫序列之用藥序列 20
3.4 用藥序列關聯 21
3.4.1 用藥序列關聯之定義 21
3.4.2 SJS 用藥的序列關聯 22
3.5 研究限制 23
第四章 實作研究 25
4.1 資料介紹 26
4.2 資料前處理 26
4.2.1 類別檔整理與合併實作 27
4.2.2 就醫科別之取得與整併 28
4.2.3 就醫科別編碼 29
4.2.4 SJS 用藥分類及篩選 31
4.2.5 篩選SJS 病患資料 31
4.3 就醫科別與用藥之關聯分析 31
4.3.1 就醫序列關聯分析 32
4.3.2 各組的用藥序列關聯分析 34
4.4 用藥序列關聯分析 37
4.5 討論與分析 39
第五章 結論與建議 41
5.1 結論 41
5.2 未來建議 42
參考文獻 4.3
附錄 A SJS 病患就醫與SJS 用藥序列(就醫1 次) 47
附錄 B1 SJS 病患就醫與SJS 用藥序列(就醫2 次) 48
附錄 B2 SJS 病患就醫與SJS 用藥序列(就醫2 次) 49
附錄 C1 SJS 病患就醫與SJS 用藥序列(就醫3 次) 50
附錄 C2 SJS 病患就醫與SJS 用藥序列(就醫3 次) 51
附錄 D1 SJS 病患就醫與SJS 用藥序列(就醫4 次) 52
附錄 D2 SJS 病患就醫與SJS 用藥序列(就醫4 次) 53
附錄 E1 SJS 病患就醫與SJS 用藥序列(就醫5 次) 54
附錄 E2 SJS 病患就醫與SJS 用藥序列(就醫5 次) 55
附錄 F1 SJS 病患就醫與SJS 用藥序列(就醫6~8 次) 56
附錄 F2 SJS 病患就醫與SJS 用藥序列(就醫6~8 次) 57
附錄 F3 SJS 病患就醫與SJS 用藥序列(就醫6~8 次) 58
附錄 G1 SJS 病患就醫與SJS 用藥序列(就醫9 次以上) 59
附錄 G2 SJS 病患就醫與SJS 用藥序列(就醫9 次以上) 60
附錄 G3 SJS 病患就醫與SJS 用藥序列(就醫9 次以上) 61

Agrawal, Rakesh, Tomasz Imieliński, and Arun Swami. "Mining association rules between sets of items in large databases." Acm sigmod record. Vol. 22. No. 2. ACM, 1993.
Agrawal, Rakesh, and Ramakrishnan Srikant. "Mining sequential patterns." Data Engineering, 1995. Proceedings of the Eleventh International Conference on. IEEE, 1995.
Ayres, Jay, et al. "Sequential pattern mining using a bitmap representation." Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2002.
Cabena, Peter, et al. Discovering data mining: from concept to implementation. Prentice-Hall, Inc., 1998.
Cios, Krzysztof J., and G. William Moore. "Uniqueness of medical data mining." Artificial intelligence in medicine 26.1 (2002): 1-24.
Dunham, Margaret H. Data mining: Introductory and advanced topics. Pearson Education India, 2006.
Ellenhorn, Matthew J., and F. A. Sternad. "Problems of drug interactions." Journal of the American Pharmaceutical Association 6.2 (1966): 62.
Fayyad, Usama, Gregory Piatetsky-Shapiro, and Padhraic Smyth. "From data mining to knowledge discovery in databases." AI magazine 17.3 (1996): 37.
Frawley, William J., Gregory Piatetsky-Shapiro, and Christopher J. Matheus. "Knowledge discovery in databases: An overview." AI magazine 13.3 (1992): 57.
Hartshorn, E. A., and D. S. Tatro. "Principles of drug interactions." Drug Interaction Facts, 5th edn. St. Louis: Facts and Comparisons (1996): b4.
Han, Jiawei, et al. "FreeSpan: frequent pattern-projected sequential pattern mining." Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2000.
Hazin, Ribhi, et al. "Stevens‐Johnson syndrome: Pathogenesis, diagnosis, and management." Annals of medicine 40.2 (2008): 129-138.
Lee, Ting-Ting, et al. "Application of data mining to the identification of critical factors in patient falls using a web-based reporting system." international journal of medical informatics 80.2 (2011): 141-150.
Linoff, Gordon S., and Michael JA Berry. Data mining techniques: for marketing, sales, and customer relationship management. John Wiley & Sons, 2011.
Mukhopadhyay, Anirban, Ujjwal Maulik, and Sanghamitra Bandyopadhyay. "Refining genetic algorithm based fuzzy clustering through supervised learning for unsupervised cancer classification." Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics. Springer Berlin Heidelberg, 2009. 191-202.
Nascimento, André CA, et al. "Mining rules for the automatic selection process of clustering methods applied to cancer gene expression data." Artificial Neural Networks–ICANN 2009. Springer Berlin Heidelberg, 2009. 20-29.
Palaniappan, Sellappan, and Rafiah Awang. "Intelligent heart disease prediction system using data mining techniques." 2008 IEEE/ACS International Conference on Computer Systems and Applications. IEEE, 2008.
Pecchia, Leandro, Paolo Melillo, and Marcello Bracale. "Remote health monitoring of heart failure with data mining via CART method on HRV features." IEEE Transactions on Biomedical Engineering 58.3 (2011): 800-804.
Pei, Jian, et al. "Prefixspan: Mining sequential patterns efficiently by prefix-projected pattern growth." icccn. IEEE, 2001.
Poelmans, Jonas, et al. "Combining business process and data discovery techniques for analyzing and improving integrated care pathways." Advances in Data Mining. Applications and Theoretical Aspects. Springer Berlin Heidelberg, 2010. 505-517.
Srikant, Ramakrishnan, and Rakesh Agrawal. Mining sequential patterns: Generalizations and performance improvements. Springer Berlin Heidelberg, 1996.
Srikant, Ramakrishnan, and Rakesh Agrawal. "Mining quantitative association rules in large relational tables." Acm Sigmod Record. Vol. 25. No. 2. ACM, 1996.
Thakur, Maitri, et al. "Data mining for recognizing patterns in foodborne disease outbreaks." Journal of food engineering 97.2 (2010): 213-227.
Trifiro, Gianluca, et al. "Data mining on electronic health record databases for signal detection in pharmacovigilance: which events to monitor?." Pharmacoepidemiology and drug safety 18.12 (2009): 1176-1184.
Zaki, Mohammed J. "SPADE: An efficient algorithm for mining frequent sequences."
Machine learning 42.1-2 (2001): 31-60.
李勝馥. (2016). STEVENS-JOHNSON SYNDROME. 耕莘藥訊.
江政家、蔡國卿、邱瑞科、蘇景傑. (2007). 以服務導向架構建立院際間醫令資料查詢系統之研究. 天主教輔仁大學資訊管理研究所.
呂宗學. (2012). 健康與醫療資料的加值應用. 2012健康與醫療資料加值應用論壇.
林政緯, 許仲瑤, & 張雅菁. (2011). 臨床常見的藥物過敏反應. 長庚醫訊32卷9期.
徐啟聖. (2005). 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.
陳世源. (2000). 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.
蘇芷凡. (2004). 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.
鍾欣蓓. (2010). 史蒂芬強生症候群 多是藥物引起. 擷取自自由時報. http://news.ltn.com.tw/news/life/paper/429169.