远程临床诊断专家系统的设计与实现
摘要
随着计算机与网络的发展与普及,数字技术正在改变人类赖以生存的社会环境,并因此使人类的生活和工作环境具备了更多的数字化。数字化技术在医学中的应用也取得了很大的进展,能够代表其发展水平的就是专家系统。
专家系统出现于20世纪60年代中期,是人工智能领域的重要分支,专家系统是一个智能计算机程序系统,其内部含有大量的某个领域专家水平的知识与经验,能够利用人类专家的知识和解决问题的方法来处理该领域的问题。远程临床诊断专家系统拥有医生的专业知识,能够对某些疾病进行分析和推理,得出诊断结果,并给出相应的解决方法。
远程临床诊断专家系统开发的目的就是为了提高临床医生在诊断过程中的诊断准确率和抢救成功率,此外,远程界面的开发为远程用户自我诊断提供了有效接口。系统的建立对于辅助医生治疗和远程用户就诊有着广泛和现实的意义。
文章首先从经典的专家系统实例MYCIN出发,介绍了专家系统的组成、特点和开发工具,为下文的进一步研究提供理论基础;紧接其后从现实角度,分析了专家系统在各个领域发展现状,笔者结合目前医院传统的就诊模式和专家系统的特点,构建了系统的框架,解决了系统难点,为系统的建立提供现实依据。
系统由知识库、推理机和用户界面三大主要部分组成。本文的重点是知识库的构造和推理机的设计。系统知识库的设计主要通过知识工程师来获取临床诊断的相关知识:一是经验知识——主要是与临床领域专家进行交流,做到了解实验方面的经验、思考问题的思路以及对各种具体问题的分析、解决方法。二是书本知识——主要是查阅文献以及上网浏览该领域专家的相关著作与研究成果。并选用产生式表示法来表示知识,建立完成了八种疾病的知识库。推理机的设计是本系统的难点,文章通过分析完成了基于逆向、正向、和双向三种推理方法的推理策略,对三种推理算法进行了详细的文字表述和公式推理,并给出了推理核心代码。用户界面采用专家系统外壳E2gLit,通过外壳设计出了基于网络的用户接口,编写了完整的html代码。此外本文对不确定推理进行了深入研究,为系统的改进和优化指明了方向。
With the development and popularization of computer and network, digital technology is changing the social environment of human being, and this has led to more digitalization in the life and work environments. Digital Technology Application in Medicine has also made a lot of progress, and on behalf of this development is the Remote Clinical Diagnosis Expert System.
Emerged in the mid-1960s, Expert System is an important branch of artificial intelligence, which contains abundant knowledge and experience of experts level in every specific field, and is capable of dealing with problems in some area with the knowledge and problem-solving methods of human experts. Remote Clinical Diagnosis Expert System has the human doctor expertise in analysis, reasoning and diagnosis of certain diseases, and is capable to give the final corresponding solution.
Remote diagnosis expert system is designed to improve the diagnosis accuracy and successful rescue rate in clinical treatment, in addition, the development of remote interface provides effective ports for remote users' self-diagnosis. The establishment of Expert System has extensive and realistic significance in medical treatment assistance and remote users' attendance.
Starting from the classic examples MYCIN expert system, the article introduces the composition, characteristics, and development tools of the system, which lays the theoretical foundation for further research; immediately followed the analysis of the present development of the system in different areas from the realistic perspective. Combining the current traditional hospital treatment mode and characteristics of expert system, the author constructs the framework of the system, overcomes system difficulties, and provides the realistic basis for the establishment.
The system includes three main components: knowledge base, inference engine and user interface. This paper focuses on the knowledge base structure and reasoning machine design. Knowledge Base of the system is constructed mainly of the clinical diagnosis of knowledge obtained by the design engineers: firstly, experience knowledge - through communication with clinical experts, to obtain experimental experience, thoughts of dealing with cases and methods of analyzing and solving specific problems. Secondly, book knowledge - by consulting literature and as well as Internet browsing, we can find related works and research results of experts in some fields. Then by employing production representation to represent knowledge, we can build a knowledge base for eight diseases. Inference Engine design is the difficult part of the system, the article has accomplished the reasoning strategy based on the analysis of the reverse, forward, and two-way reasoning methods, in which a detailed formula written expression and inference algorithm of the three methods have been carried out, and the Reasoning core code has been given. User interface uses expert system shell E2gLit, through which Web-based user's port is designed, and the complete html code is written. In addition, in-depth research in uncertainty reasoning has been carried out, and sheds a bright light on the path to improve and optimize the system.
专家系统出现于20世纪60年代中期,是人工智能领域的重要分支,专家系统是一个智能计算机程序系统,其内部含有大量的某个领域专家水平的知识与经验,能够利用人类专家的知识和解决问题的方法来处理该领域的问题。远程临床诊断专家系统拥有医生的专业知识,能够对某些疾病进行分析和推理,得出诊断结果,并给出相应的解决方法。
远程临床诊断专家系统开发的目的就是为了提高临床医生在诊断过程中的诊断准确率和抢救成功率,此外,远程界面的开发为远程用户自我诊断提供了有效接口。系统的建立对于辅助医生治疗和远程用户就诊有着广泛和现实的意义。
文章首先从经典的专家系统实例MYCIN出发,介绍了专家系统的组成、特点和开发工具,为下文的进一步研究提供理论基础;紧接其后从现实角度,分析了专家系统在各个领域发展现状,笔者结合目前医院传统的就诊模式和专家系统的特点,构建了系统的框架,解决了系统难点,为系统的建立提供现实依据。
系统由知识库、推理机和用户界面三大主要部分组成。本文的重点是知识库的构造和推理机的设计。系统知识库的设计主要通过知识工程师来获取临床诊断的相关知识:一是经验知识——主要是与临床领域专家进行交流,做到了解实验方面的经验、思考问题的思路以及对各种具体问题的分析、解决方法。二是书本知识——主要是查阅文献以及上网浏览该领域专家的相关著作与研究成果。并选用产生式表示法来表示知识,建立完成了八种疾病的知识库。推理机的设计是本系统的难点,文章通过分析完成了基于逆向、正向、和双向三种推理方法的推理策略,对三种推理算法进行了详细的文字表述和公式推理,并给出了推理核心代码。用户界面采用专家系统外壳E2gLit,通过外壳设计出了基于网络的用户接口,编写了完整的html代码。此外本文对不确定推理进行了深入研究,为系统的改进和优化指明了方向。
With the development and popularization of computer and network, digital technology is changing the social environment of human being, and this has led to more digitalization in the life and work environments. Digital Technology Application in Medicine has also made a lot of progress, and on behalf of this development is the Remote Clinical Diagnosis Expert System.
Emerged in the mid-1960s, Expert System is an important branch of artificial intelligence, which contains abundant knowledge and experience of experts level in every specific field, and is capable of dealing with problems in some area with the knowledge and problem-solving methods of human experts. Remote Clinical Diagnosis Expert System has the human doctor expertise in analysis, reasoning and diagnosis of certain diseases, and is capable to give the final corresponding solution.
Remote diagnosis expert system is designed to improve the diagnosis accuracy and successful rescue rate in clinical treatment, in addition, the development of remote interface provides effective ports for remote users' self-diagnosis. The establishment of Expert System has extensive and realistic significance in medical treatment assistance and remote users' attendance.
Starting from the classic examples MYCIN expert system, the article introduces the composition, characteristics, and development tools of the system, which lays the theoretical foundation for further research; immediately followed the analysis of the present development of the system in different areas from the realistic perspective. Combining the current traditional hospital treatment mode and characteristics of expert system, the author constructs the framework of the system, overcomes system difficulties, and provides the realistic basis for the establishment.
The system includes three main components: knowledge base, inference engine and user interface. This paper focuses on the knowledge base structure and reasoning machine design. Knowledge Base of the system is constructed mainly of the clinical diagnosis of knowledge obtained by the design engineers: firstly, experience knowledge - through communication with clinical experts, to obtain experimental experience, thoughts of dealing with cases and methods of analyzing and solving specific problems. Secondly, book knowledge - by consulting literature and as well as Internet browsing, we can find related works and research results of experts in some fields. Then by employing production representation to represent knowledge, we can build a knowledge base for eight diseases. Inference Engine design is the difficult part of the system, the article has accomplished the reasoning strategy based on the analysis of the reverse, forward, and two-way reasoning methods, in which a detailed formula written expression and inference algorithm of the three methods have been carried out, and the Reasoning core code has been given. User interface uses expert system shell E2gLit, through which Web-based user's port is designed, and the complete html code is written. In addition, in-depth research in uncertainty reasoning has been carried out, and sheds a bright light on the path to improve and optimize the system.
引文
[1]蔡自兴,徐光佑 人工智能及其应用第二版 北京:清华大学出版社,2003.1-3
[2]陈京民,杜冬军等 据仓库与数据挖掘技术 北京:电子工业出版社,2002,259-260
[3]万家华,刘冰,江早 知识发现中的可视化技术 计算机科学,2000,27:131-152
[4]Neena Buck Eureka Knowledge discovery Software Magazine,2001,20(6):24-29
[5]黄解军,潘和平,万幼川 数据挖掘技术的应用研究 计算机工程与应用,2003,2:43-57
[6]吉根林,孙志挥 数据挖掘技术 中国图象图形学报,2001,6(8):715-721
[7]邓锋,符云清等 OCDES 口腔癌医疗诊断专家系统设计与实现
[8]张惠康,钱宗才等 专家系统及其在医疗诊断中的应用 第四军医大学学报,2002,23:73-76
[9]曹立明,陈石麟,周强 知识工程原理 徐州:中国矿业大学出版社,1995.1-3
[10]童须,沈一栋,知识工程 北京:科学出版社,1992.20-22
[11]徐良贤,蒋智平,王士同 知识工程 北京:电子工业出版社,1991.5-8
[12]Jay M.Lightfoot.Expert knowledge acquisition and the unwilling expert:a kno,ledge engineering perspective.Expert syste,1999,16:141-147
[13]杨开英,胡迎久 基于框架与规则相结合的棉纺工艺专家系统知识库的设计微型计算机应用,2004,25:735-738
[14]Kyung-Ho Lee,Dongkon Lee and Soon-Hung Han.object-oriented approach to a knowledge-based structural design system[J].Expert System,ith Applcations,1996,10[2]:223-231
[18]Yiu-Wng Chan,iang-Kok 510.A knowledge-based expert system for gearng design application usingPrologandC[J],AdvancedinEngineering
[15]A. Cerpa, J. Elson, D. Estrin, L. Girod, M. Hamilton, and J. Zhao. Habitat monitoring: Application driver for wireless communications technology. In Proceedings of the 2001 ACM SIGCOMM Workshop on Data Communications in Latin America and the Caribbean, April 2001.
[16]Alan Mainwaring, Joseph Polastre, Robert Szewczyk, David Culler, and John Anderson. Wireless sensor networks for habitat monitoring. In ACM International Workshop on Wireless Sensor Networks and Applications (WSNA'02), Atlanta, GA, September 2002.
[17]Edoardo Biagioni and Kent Bridges. The application of remote sensor technology to assist the recovery of rare and endangered species. In Special issue on Distributed Sensor Networks for the International Journal of High Performance Computing Applications, Vol. 16, N. 3,August 2002.
[18]J. Ca_rey, R. Govindan, E. Johnson, B. Krishnamachari, S. Masri, and G. Sukhatme. Networked Sensing for Structural Health Monitoring. In Proceedings of the Fourth International Workshop on Structural Monitoring and Control, June 2004.
[19]Loren Schwiebert, Sandeep K. S. Gupta, and Jennifer Weinmann. Research challenges in wireless networks of biomedical sensors. In Mobile Computing and Networking, pages 151-165, 2001.
[20]University of California, Los Angeles. Center for Embedded Networked Sensing. http://lecs. cs. ucla. edu/"estrin/. June,2005.
[21] Hanbiao Wang, Jeremy Elson, Lewis Girod, Deborah Estrin, and Kung Yao.Target classification and localization in habitat monitoring. In Proceedings of the IEEE ICASSP 2003, Hong Kong, April 2003.
[22] Y. Yao and J. Gehrke. Query processing in sensor networks. In Conference on Innovative Data Systems Research (CIDR), 2003.
[2]陈京民,杜冬军等 据仓库与数据挖掘技术 北京:电子工业出版社,2002,259-260
[3]万家华,刘冰,江早 知识发现中的可视化技术 计算机科学,2000,27:131-152
[4]Neena Buck Eureka Knowledge discovery Software Magazine,2001,20(6):24-29
[5]黄解军,潘和平,万幼川 数据挖掘技术的应用研究 计算机工程与应用,2003,2:43-57
[6]吉根林,孙志挥 数据挖掘技术 中国图象图形学报,2001,6(8):715-721
[7]邓锋,符云清等 OCDES 口腔癌医疗诊断专家系统设计与实现
[8]张惠康,钱宗才等 专家系统及其在医疗诊断中的应用 第四军医大学学报,2002,23:73-76
[9]曹立明,陈石麟,周强 知识工程原理 徐州:中国矿业大学出版社,1995.1-3
[10]童须,沈一栋,知识工程 北京:科学出版社,1992.20-22
[11]徐良贤,蒋智平,王士同 知识工程 北京:电子工业出版社,1991.5-8
[12]Jay M.Lightfoot.Expert knowledge acquisition and the unwilling expert:a kno,ledge engineering perspective.Expert syste,1999,16:141-147
[13]杨开英,胡迎久 基于框架与规则相结合的棉纺工艺专家系统知识库的设计微型计算机应用,2004,25:735-738
[14]Kyung-Ho Lee,Dongkon Lee and Soon-Hung Han.object-oriented approach to a knowledge-based structural design system[J].Expert System,ith Applcations,1996,10[2]:223-231
[18]Yiu-Wng Chan,iang-Kok 510.A knowledge-based expert system for gearng design application usingPrologandC[J],AdvancedinEngineering
[15]A. Cerpa, J. Elson, D. Estrin, L. Girod, M. Hamilton, and J. Zhao. Habitat monitoring: Application driver for wireless communications technology. In Proceedings of the 2001 ACM SIGCOMM Workshop on Data Communications in Latin America and the Caribbean, April 2001.
[16]Alan Mainwaring, Joseph Polastre, Robert Szewczyk, David Culler, and John Anderson. Wireless sensor networks for habitat monitoring. In ACM International Workshop on Wireless Sensor Networks and Applications (WSNA'02), Atlanta, GA, September 2002.
[17]Edoardo Biagioni and Kent Bridges. The application of remote sensor technology to assist the recovery of rare and endangered species. In Special issue on Distributed Sensor Networks for the International Journal of High Performance Computing Applications, Vol. 16, N. 3,August 2002.
[18]J. Ca_rey, R. Govindan, E. Johnson, B. Krishnamachari, S. Masri, and G. Sukhatme. Networked Sensing for Structural Health Monitoring. In Proceedings of the Fourth International Workshop on Structural Monitoring and Control, June 2004.
[19]Loren Schwiebert, Sandeep K. S. Gupta, and Jennifer Weinmann. Research challenges in wireless networks of biomedical sensors. In Mobile Computing and Networking, pages 151-165, 2001.
[20]University of California, Los Angeles. Center for Embedded Networked Sensing. http://lecs. cs. ucla. edu/"estrin/. June,2005.
[21] Hanbiao Wang, Jeremy Elson, Lewis Girod, Deborah Estrin, and Kung Yao.Target classification and localization in habitat monitoring. In Proceedings of the IEEE ICASSP 2003, Hong Kong, April 2003.
[22] Y. Yao and J. Gehrke. Query processing in sensor networks. In Conference on Innovative Data Systems Research (CIDR), 2003.