¹（北京大学医学图书馆 北京 100083）
²（中国科学院国家科学图书馆 北京10080）  

选择基于Medline的医学数据挖掘系统中应用效果较好，具有普遍特性的3个系统进行分析，探讨系统的研究背景，在具体实现上所采取的技术思路和方法，总结其在设计和实现中普遍性和规律性的特点，供实践参考。

¹ (Peking University Health Science Library,Beijing 100083,China) 
² (National Science Library,Chinese Academy of Sciences,Beijing 100080,China)

This paper analyzes several systems and selects three of them which have common characteristics of medical data mining systems from the Medline.Then,discusses about the origin and implementation of these systems,and also investigates the technical methods and consideration on system design and implementation.At last,the paper summarizes the common and regular characteristics in system design and implementation,and provides useful references for future development.

G250.73

*本文系国家社科基金项目“从数字信息资源中实现知识抽取的理论和方法研究”(项目编号：05BTQ006)的研究成果之一。

1Swanson D R.Fishv oil. Raynaud’s Syndrome, and Undiscovered Public Knowledge. Perspectives Biolog Med,1986,30(1):18-22
2尚彤，国强华，景霞. 常用医学生物信息学数据库.北京：北京大学医学出版社，2003
3Database and Tools Menu .http://www.ncbi.nlm.nih.gov/About/tools/index.html (Accessed Dec. 19,2006)
4Medstract.http://www.medstract.org/(Accessed Dec. 19,2006)
5Joyce Peng . Life Sciences Integrated Demo. http://www.oracle.com/technology/industries/life_sciences/presentations/lsday903_2a_Peng_IntegratedDemo.ppt  (Accessed Dec. 19,2006)
6PubGene. http://www.pubgene.com/  (Accessed Dec. 19,2006)
7MedMiner. http://discover.nci.nih.gov/textmining/main.jsp (Accessed Dec. 19,2006)
8Bruce Schatz. Automatically Extracting Signaling Pathways from Biomedical Knowledge.http://www.canis.uiuc.edu/~schatz/NCBC-Proposal-Final.doc (Accessed Dec. 19,2006)
9Tor-Kristian Jenssen,et al. A Literature Network of Human Genes for High-Throughput Analysis of Gene Expression .http://www.pubgene.com/PDF/Nature-May.pdf  (Accessed Dec. 19,2006)
10Yang S T. A Literature Network of Human Genes for High-throughput Analysis of Gene Expression.http://binfo.ym.edu.tw/edu/seminars/111601/111601.PPT (Accessed Dec. 19,2006)
11Pustejovsky J, et al. Medstract: Creating Large-scale Information Servers for Biomedical Libraries. http://medstract.org/papers/acl2002-4.pdf  (Accessed Dec. 19,2006)
12Olivier Bodenreider. The Unified Medical Language System (UMLS):Integrating Biomedical Terminology.http://nar.oxfordjournals.org/cgi/reprint/32/suppl_1/D267(Accessed Dec.19,2006)
13Jiang J, Zhai C. Exploiting Domain Structure for Named Entity Recognition. Proceedings of HLT/NAACL.2006 (6): 74-81
14Hu Z Z, et al. Literature Mining and Database Annotation of Protein Phosphorylation Using a Rule-based System . BIOINFORMATIC. 2005,21(11):2759-2765
15Narayanaswamy M, Ravikumar K E，Shanker K V. Beyond the Clause: Extraction of Phosphorylation Information from Medline Abstracts. BIOINFORMATIC. 2005,21(Suppl.) : i319-i327
16Tanabe L, et al . MedMiner: An Internet Text-Mining Tool for Biomedical Information, with Application to Gene Expression Profiling. BioTechniques . 1999(27):1210-1217
17Cios K J, Moore G W. Uniqueness of Medical Data Mining. http://isl.cudenver.edu/Publications/Papers/UniquenessOfMedicalDataMining.pdf (Accessed Feb. 1,2007)
18Becker K G, et al. PubMatrix: A Tool for Multiplex Literature Mining . BMC Bioinformatics.2003. http://www.biomedcentral.com/1471-2105/4/61 (Accessed Dec. 19,2006)
19Mudunuri U, et al. BotXminer: Mining Biomedical Literature with a New Web-based Application. http://nar.oxfordjournals.org/cgi/content/full/34/suppl_2/W748 (Accessed Dec. 19,2006)
20Uramoto N, et al. A Text-mining System for Knowledge Discovery from Biomedical Documents. http://www.research.ibm.com/journal/sj/433/uramoto.pdf  (Accessed Dec. 19,2006)