Category : Various Text files
Archive   : NLM-INFO.ZIP
Filename : CSBRANCH.TXT

 
Output of file : CSBRANCH.TXT contained in archive : NLM-INFO.ZIP
National Library of Medicine
NOVEMBER 1990

Computer Science Branch

Lister Hill National Center for Biomedical Communications

Research projects of the Computer Science Branch (CSB) concentrate on the application of artificial intelligence techniques to problems in the representation, retrieval and manipulation of biomedical knowledge. CSB projects involve both basic and applied research in such areas as expert systems, natural language systems, machine learning and automated indexing for information classification and retrieval. Issues in knowledge representation, knowledge base structure and knowledge acquisition are important components of this research. Active projects are also exploring the validation of automated consultant systems, the human-machine interface for complex systems, the use of high-resolution graphics, interactive videodisc capability, multimedia expert systems and the linking of knowledge-based systems to large-scale mainframe databanks.

Branch staff members are actively involved in individual and team research projects; in the artificial intelligence, natural language and advanced database systems aspects of NLM projects such as the Unified Medical Language System initiative; and in the national and international medical informatics and information science research communities. Recognizing the importance of addressing the future of medical informatics by helping to train new researchers, Branch Chief Lawrence Kingsland directs the eight-week annual NIH-sponsored "Medical Informatics" elective for third-year and fourth-year medical students.

Expert Systems Program

Expert systems are computer programs that combine knowledge of a particular subject area with inferencing mechanisms enabling them to use this knowledge in problem-solving situations. An artificial intelligence research program concentrating in expert systems was established at LHNCBC in 1984. The objective of the Expert Systems Program is to facilitate computer-assisted access to knowledge. This knowledge may reside in different forms, in different places, on different media, with different structures and naming conventions.

Recent research projects of the Expert Systems Program have included the AI/RHEUM consultant system in rheumatology, the rheumatology videodisc image library, the CTX "criteria engine" shell and its family of Clipper-based tools, the medical expert systems evaluation project, the AI/COAG hemostasis consultant system, and the COACH expert searcher system. Additional Expert Systems Program efforts include developing interactive video exhibits on medical artificial intelligence and training medical students in medical informatics research.

Natural Language Systems Program

The Natural Language Systems (NLS) Program includes several research activities, all involving some aspect of natural language processing for improving access to biomedical information stored in computerized form. To that end, research efforts are directed toward the development of SPECIALIST, a prototype system for parsing, analyzing and accessing biomedical text. The system is implemented in Quintus Prolog with some supporting programs in C. It runs on Sun workstations.

Major NLS activities include the development of the parser, of an extensive lexicon of general English and biomedical terminology, of automated tools for enhancing the research process and of a language and information interface. NLS researchers are active participants in NLM's Unified Medical Language System' (UMLS') project. The current focus of the UMLS is the building, testing and evaluation of several new knowledge sources. Two of these knowledge sources, the Metathesaurus' of biomedical concepts and the Semantic Network, will be tested in the context of the SPECIALIST system over the coming months.

Machine Learning Project

A new research project began at LHNCBC in 1989 to investigate the subfield of artificial intelligence known as machine learning. The field encompasses a wide variety of mechanisms for creating computer programs that improve their performance with use. The objective of this project is to develop and apply methods by which programs can automatically acquire knowledge and put it to work.

The underlying motivation for this work arises from the explosion of available biomedical information and the less well-acknowledged explosion of the analytical tools and techniques applied to that information. The goal of the Machine Learning Project is to create computer programs that not only manipulate knowledge but also can acquire it themselves. An important component of the research is the development of a computationally tractable theory of how to select among and combine multiple sources of information and multiple analytical tools in pursuit of explicitly stated desires for knowledge. This approach is called knowledge acquisition planning. Ideally, a researcher or clinician with a question should be able to have a machine learning program identify where to find relevant information, retrieve that information and analyze and assemble the information into a complete, accurate and comprehensible response.

MedIndEx (Medical Indexing Expert) Project

The objective of the MedIndEx (Medical Indexing Expert) Project is to develop and test interactive knowledge-based systems for computer-assisted indexing of medical literature currently indexed in the MEDLINE" database using terms from the Medical Subject Headings (MeSH") thesaurus. Encoding the indexing scheme in a knowledge base (KB) and designing the system for indexers to use in a workstation environment is intended to facilitate "expert indexing" - indexing consistent with published indexing tools upon which indexers currently depend for declarative (factual) and procedural knowledge.

The KB is written in a frame language, a type of object-oriented language where objects, known as frames, are used for representing concepts and their interrelationships. Knowledge associated with higher-level frames is inherited by lower-level frames in explicit hierarchical paths. Indexers, with system help and guidance from the KB, create, for each document indexed, a set of indexing frames which are instances of KB frames. In addition, the system features a KB manager designed for use by knowledge engineers creating and editing the KB. These knowledge engineers need not be expert computer programmers. Employing menu and cut & paste interfaces, and utilizing inheritance, this software serves to ensure a consistent, compact, and syntactically correct KB.



For further information, contact:

Chief, Computer Science Branch
Lister Hill National Center
for Biomedical Communications
National Library of Medicine
Bethesda, Maryland 20894




  3 Responses to “Category : Various Text files
Archive   : NLM-INFO.ZIP
Filename : CSBRANCH.TXT

  1. Very nice! Thank you for this wonderful archive. I wonder why I found it only now. Long live the BBS file archives!

  2. This is so awesome! 😀 I’d be cool if you could download an entire archive of this at once, though.

  3. But one thing that puzzles me is the “mtswslnkmcjklsdlsbdmMICROSOFT” string. There is an article about it here. It is definitely worth a read: http://www.os2museum.com/wp/mtswslnk/