How knowledge drives understandingmatching medical ontologies with the needs of medical language processing

In this article, we introduce a knowledge-based approach to medical text understanding. From an in-depth consideration of deep sentence and text understanding we distill basic requirements for an adequate knowledge representation framework. These requirements are then matched with currently available medical ontologies (thesauri, terminologies, etc.). A fundamental trade-off is recognized between large-scale conceptual coverage on the one hand, and formal mechanisms for integrity preservation and conceptual expressiveness on the other hand. We discuss various shortcomings of the most wide-spread ontologies to capture medical knowledge in-the-large. As a result, we argue for the need of a formally sound and expressive model along the lines of KL-ONE-style terminological representation systems in the format of description logics. These provide an adequate methodology for designing more sophisticated, flexible medical ontologies serving the needs of 'deep' knowledge applications which are by no means restricted to medical language processing.

[1]  Elpida T. Keravnou,et al.  Temporal diagnostic reasoning based on time-objects , 1996, Artif. Intell. Medicine.

[2]  A L Rector,et al.  The GALEN project. , 1994, Computer methods and programs in biomedicine.

[3]  Stanley M. Huff,et al.  Position Paper: Toward a Medical-concept Representation Language , 1994, J. Am. Medical Informatics Assoc..

[4]  Jon Sticklen,et al.  'Deep' models and their relation to diagnosis , 1989, Artif. Intell. Medicine.

[5]  S Shiffman,et al.  A free-text processing system to capture physical findings: Canonical Phrase Identification System (CAPIS). , 1991, Proceedings. Symposium on Computer Applications in Medical Care.

[6]  Peter Szolovits,et al.  Categorical and Probabilistic Reasoning in Medical Diagnosis , 1990, Artif. Intell..

[7]  Rüdiger Klar,et al.  Conceptual Classifications and Nomenclatures in Medicine , 1996 .

[8]  M. Roux,et al.  Medical Knowledge Representation for Medical Report Analysis , 1995, AIME.

[9]  Udo Hahn,et al.  A qualitative growth model for real world text knowledge bases , 1997, RIAO.

[10]  Martin Romacker,et al.  Text structures in medical text processing: empirical evidence and a text understanding prototype , 1997, AMIA.

[11]  Nicoletta Calzolari,et al.  Review of Medical language processing: computer management of narrative data by Naomi Sager, Carol Friedman, and Margaret S. Lyman. Addison-Wesley 1987. , 1989 .

[12]  Steffen Staab,et al.  "Tall", "Good", "High" - Compared to What? , 1997, IJCAI.

[13]  Scott Weinstein,et al.  Centering: A Framework for Modeling the Local Coherence of Discourse , 1995, CL.

[14]  P Carpenter,et al.  Phase II evaluation of clinical coding schemes: completeness, taxonomy, mapping, definitions, and clarity. CPRI Work Group on Codes and Structures. , 1997, Journal of the American Medical Informatics Association : JAMIA.

[15]  Udo Hahn,et al.  A Conceptual Reasoning Approach to Textual Ellipsis , 1996, ECAI.

[16]  Ted Briscoe,et al.  Book Reviews: Computational Lexicography for Natural Language Processing , 1990, CL.

[17]  J. Ingenerf.  On the Relationship between Description Logics and Conceptual Graphs with some References to the Medical Domain , 1996 .

[18]  Victor Sadler,et al.  Review of Lexical acquisition: exploiting on-line resources to build a lexicon by Uri Zernik. Lawrence Erlbaum Associates 1991. , 1993 .

[19]  U Hahn,et al.  Automatic knowledge acquisition from medical texts. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[20]  Peter Szolovits,et al.  Representing Medical Knowledge in a Terminological Language is Difficult , 1988 .

[21]  Udo Hahn,et al.  Concurrent, object-oriented natural language parsing: the ParseTalk model , 1994, Int. J. Hum. Comput. Stud..

[22]  J. D. Moore,et al.  Using the UMLS Semantic Network as a basis for constructing a terminological knowledge base: a preliminary report. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.

[23]  L M Lau,et al.  A natural language understanding system combining syntactic and semantic techniques. , 1994, Proceedings. Symposium on Computer Applications in Medical Care.

[24]  A T McCray,et al.  The Representation of Meaning in the UMLS , 1995, Methods of Information in Medicine.

[25]  Udo Hahn,et al.  Functional Centering , 1996, ACL.

[26]  Ian Horrocks,et al.  A Description Logic Based Schema for the Classification of Medical Data , 1996, KRDB.

[27]  Brian R. Gaines,et al.  Current Trends in Knowledge Acquisition , 1990 .

[28]  Ramesh S. Patil,et al.  Systematic knowledge base design for medical , 1989, Appl. Artif. Intell..

[29]  Bernhard Nebel,et al.  An Empirical Analysis of Terminological Representation Systems , 1992, Artif. Intell..

[30]  Thomas Diedrich,et al.  Notwendigkeit und Funktionalität eines Terminologieservers in der Medizin , 1997, Künstliche Intell..

[31]  José L. V. Mejino,et al.  Research Paper: Motivation and Organizational Principles for Anatomical Knowledge Representation: The Digital Anatomist Symbolic Knowledge Base , 1998, J. Am. Medical Informatics Assoc..

[32]  C Lovis,et al.  Representing Clinical Narratives Using Conceptual Graphs , 1995, Methods of Information in Medicine.

[33]  Udo Hahn,et al.  Text condensation as knowledge base abstraction , 1988, [1988] Proceedings. The Fourth Conference on Artificial Intelligence Applications.

[34]  J J Cimino,et al.  Coding Systems in Health Care , 1995, Yearbook of Medical Informatics.

[35]  M. Stefanelli,et al.  Ontology and Terminology Servers in Agent-based Health-care Information Systems , 1997, Methods of Information in Medicine.

[36]  Ian Horrocks,et al.  The GRAIL concept modelling language for medical terminology , 1997, Artif. Intell. Medicine.

[37]  Douglas Herrmann,et al.  A Taxonomy of Part-Whole Relations , 1987, Cogn. Sci..

[38]  A T McCray,et al.  The UMLS Knowledge Source server. , 1995, Medinfo. MEDINFO.

[39]  Alan L. Rector,et al.  Medical Knowledge Representation and Predictive Data Entry , 1991, AIME.

[40]  James G. Schmolze,et al.  The KL-ONE family , 1992 .

[41]  Ray Bareiss,et al.  Concept Learning and Heuristic Classification in WeakTtheory Domains , 1990, Artif. Intell..

[42]  Harold L. Somers,et al.  New Methods in Language Processing , 1997 .

[43]  Olivier Bodenreider,et al.  Application of Information Technology: A Web Terminology Server Using UMLS for the Description of Medical Procedures , 1997, J. Am. Medical Informatics Assoc..

[44]  D A Evans,et al.  Automating concept identification in the electronic medical record: an experiment in extracting dosage information. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[45]  Carol Friedman,et al.  Research Paper: A General Natural-language Text Processor for Clinical Radiology , 1994, J. Am. Medical Informatics Assoc..

[46]  M Fieschi,et al.  Structuration and acquisition of medical knowledge. Using UMLS in the conceptual graph formalism. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.

[47]  Marc Cavazza,et al.  Extracting implicit information from free text technical reports , 1991, RIAO.

[48]  Hans-Hermann Bock,et al.  Data Analysis and Information Systems , 1996 .

[49]  A. Rector,et al.  A Terminology Server for Medical Language and Medical Information Systems , 1995, Methods of Information in Medicine.

[50]  Brigitte Biebow,et al.  A Comparison between Conceptual Graphs and KL-ONE , 1993, ICCS.

[51]  C Lovis,et al.  Analysis of medical texts based on a sound medical model. , 1995, Proceedings. Symposium on Computer Applications in Medical Care.

[52]  F B ROGERS,et al.  Medical Subject Headings , 1948, Nature.