Mark S. Erlbaum

Publications (16)0 Total impact

• Article: Categorical information in pharmaceutical terminologies.

  John S Carter, Steven H Brown, Brent A Bauer, Peter L Elkin, Mark S Erlbaum, David A Froehling, Michael J Lincoln, S Trent Rosenbloom, Dietlind L Wahner-Roedler, Mark S Tuttle
  [show abstract] [hide abstract]
  ABSTRACT: Drug information sources use category labels to assist in navigating and organizing information. Some category labels describe drugs from multiple perspectives (e.g., both structure and function). The National Drug File - Reference Terminology (NDF RT) is a drug information source that augments a "legacy" categorization system with a formal reference model specifying Chemical Structure, Cellular or Sub-Cellular Mechanism of Action, Organ- or System-Level Physiological Effect, and Therapeutic Intent categories. We examined drug category names from three sources to better understand their information content and evaluate NDF RT's semantic coverage. On average, category names contain more than 1.5 attributes. NDF RT's reference model covers more than 76% of the information identified in drug category labels. A new NDF RT reference axis of drug formulations could improve NDF RT's coverage to 85%. The distinction between Physiological Effect and Therapeutic Intent, prompted many questions among category reviewers, suggesting that further clarification of these reference concepts is required. Careful review of existing categorization schemes may guide structured terminology and ontology development efforts toward greater fidelity to deployed information sources.
  AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 02/2006;
• Source

  Available from: ncbi.nlm.nih.gov

  Article: Adequacy of representation of the National Drug File Reference Terminology Physiologic Effects reference hierarchy for commonly prescribed medications.

  S Trent Rosenbloom, Joseph Awad, Ted Speroff, Peter L Elkin, Russell Rothman, Anderson Spickard, Josh Peterson, Brent A Bauer, Dietland L Wahner-Roedler, Mark Lee, William M Gregg, Kevin B Johnson, Jim Jirjis, Mark S Erlbaum, John S Carter, Michael J Lincoln, Steven H Brown
  [show abstract] [hide abstract]
  ABSTRACT: The National Drug File Reference Terminology contains a novel reference hierarchy to describe physiologic effects (PE) of drugs. The PE reference hierarchy contains 1697 concepts arranged into two broad categories; organ specific and generalized systemic effects. This investigation evaluated the appropriateness of the PE concepts for classifying a random selection of commonly prescribed medications. Ten physician reviewers classified the physiologic effects of ten drugs and rated the accuracy of the selected term. Inter reviewer agreement, overall confidence, and concept frequencies were assessed and were correlated with the complexity of the drug's known physiologic effects. In general, agreement between reviewers was fair to moderate (kappa 0.08-0.49). The physiologic effects modeled became more disperse with drugs having and inducing multiple physiologic processes. Complete modeling of all physiologic effects was limited by reviewers focusing on different physiologic processes. The reviewers were generally comfortable with the accuracy of the concepts selected. Overall, the PE reference hierarchy was useful for physician reviewers classifying the physiologic effects of drugs. Ongoing evolution of the PE reference hierarchy as it evolves should take into account the experiences of our reviewers.
  AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 02/2003;
• Source

  Available from: Mark Tuttle

  Article: A semantic normal form for clinical drugs in the UMLS: early experiences with the VANDF.

  Stuart J Nelson, Steven H Brown, Mark S Erlbaum, Nels Olson, Tammy Powell, Brian Carlsen, John Carter, Mark S Tuttle, William T Hole
  [show abstract] [hide abstract]
  ABSTRACT: A semantic normal form (SNF) for a clinical drug, designed to represent the meaning of an expression typically seen in a practitioner's medication order, has been developed and is being created in the UMLS Metathesaurus. The long term goal is to establish a relationship for every concept in the Metathesaurus with semantic type "clinical drug" with one or more of these semantic normal forms. First steps have been taken using the Veterans Administration National Drug File (VANDF). 70% of the entries in the VANDF could be parsed algorithmically into the SNF. Next steps include parsing other drug vocabularies included in the UMLS Metathesaurus and performing human review of the parsed vocabularies. After machine parsed forms have been merged in the Metathesaurus Information Database (MID), editors will be able to edit matched SNFs for accuracy and establish relationships and relationship attributes with other clinical drug concepts.
  Proceedings / AMIA ... Annual Symposium. AMIA Symposium 02/2002;
• Source

  Available from: Mark Tuttle

  Article: Initializing the VA medication reference terminology using UMLS metathesaurus co-occurrences.

  John S Carter, Steven H Brown, Mark S Erlbaum, William Gregg, Peter L Elkin, Ted Speroff, Mark S Tuttle
  [show abstract] [hide abstract]
  ABSTRACT: We developed and evaluated a UMLS Metathesaurus Co-occurrence mining algorithm to connect medications and diseases they may treat. Based on 16 years of co-occurrence data, we created 977 candidate drug-disease pairs for a sample of 100 ingredients (50 commonly prescribed and 50 selected at random). Our evaluation showed that more than 80% of the candidate drug-disease pairs were rated "APPROPRIATE" by physician raters. Additionally, there was a highly significant correlation between the overall frequency of citation and the likelihood that the connection was rated "APPROPRIATE." The drug-disease pairs were used to initialize term definitions in an ongoing effort to build a medication reference terminology for the Veterans Health Administration. Co-occurrence mining is a valuable technique for initializing term definitions in a large-scale reference terminology creation project.
  Proceedings / AMIA ... Annual Symposium. AMIA Symposium 02/2002;
• Source

  Available from: Mark Tuttle

  Article: Collaborative conversational interfaces

  Colleen E. Crangle, Lawrence M. Fagan, Robert W. Carlson, Mark S. Erlbaum, David D. Sherertz, Mark S. Tuttle
  [show abstract] [hide abstract]
  ABSTRACT: This paper proposes a method of designing human-computer speech interfaces based on principles of human conversation. It argues that conversation is the primary mode of language use and that it is fundamentally collaborative. Speech interfaces should therefore be designed to recreate the collaborative nature of natural conversations. The paper presents five strategies for designingcollaborative conversational interfaces, and it describes the principles of human-language use that underly these strategies. The paper also argues that collaborative conversational interfaces have a crucial advantage over other kinds of interfaces in that they are readily adaptive to different levels of experience and styles of use. The paper gives examples of collaborative conversational interfaces that we have developed, and discusses the ways in which these interfaces have been made adaptive.
  International Journal of Speech Technology 01/1998; 2(3):187-200.
• Article: Exploiting the Metathesaurus Update Model

  Nels E. Olson, Mark S. Erlbaum, Mark S. Tuttle, David D. Sherertz, Octavio Suarez-Munist, Stephanie S. Lipow, William G. Cole, Stuart J. Nelson
• Article: Suggesting Structural Enhancements to SNOMED International

  Stephanie S. Lipow, Lloyd F. Fuller, Kevin D. Keck, Nels E. Olson, Mark S. Erlbaum, Mark S. Tuttle, David D. Sheretz, Stuart J. Nelson
• Article: Browsing MIM, PDQ, CDD, and MEDLINE Using MetaCard*

  Stuart J. Nelson, David D. Sherertz, Mark S. Tuttle, Mark S. Erlbaum, Lawrence G. Smith
• Article: Mobile Access to Oncology Knowledge

  Richard D. Acuff, Robert W. Carlson, Lawrence M. Fagan, David D. Sherertz, Mark S. Erlbaum, Nels E. Olson, Mark S. Tuttle
  [show abstract] [hide abstract]
  ABSTRACT: Although considerable effort has been put into creating extensive on-line reference resources for oncology, this compiled knowledge is underutilized in clinical situations. The Mobile Access To Oncology Knowledge (MATOK) project facilitates access to a variety of knowledge sources by providing a system designed to be used at the point-of-care. The system's key characteristics are mobility, homogeneous access, concept-based searching, step-wise refinement, and integration with on-line patient data.
• Article: Using Metacard: A Hypercard Browser for Biomedical Knowledge Sources*

  Stuart J. Nelson, David D. Sherertz, Mark S. Tuttle, Mark S. Erlbaum
  [show abstract] [hide abstract]
  ABSTRACT: As part of the Unified Medical Language System (UMLS) project, a large metathesaurus (Meta-1) was built. We have adapted a Hypercard browser of Meta-1 (MetaCard) to enable a user to continue the browsing process, extending from the Metathesaurus to a variety of different knowledge sources. These knowledge sources include Current Disease Descriptions (CDD), Physicians Data Query (PDQ), and Mendelian Inheritance in Man (MIM). Metacard can also be linked to Grateful Med, the NLM program which is used to search MEDLINE. A user can, with minimal training, use MetaCard to access these four different knowledge sources. The links (how one goes from one knowledge source to another) have been built on the basis of disease names. In organizing these links, it was helpful to use CDD as an additional source of knowledge about how diseases are named in various sources. Further plans are to expand the use of the Metathesaurus in building links to the knowledge sources. The question with each method of linking used will be to what extent the method provides a robust linkage whose utility can be anticipated. While future refinements or developments of links may give additional functionality, the current linkages are sufficient to provide a useful browsing tool. We believe that this is so because much of the knowledge in each of these sources is organized around diseases. Navigation is easy because of the similarities of the Hypercard interfaces to each of the knowledge sources; a common set of conventions (e.g., point and click) helps make it work.
• Source

  Available from: Mark Tuttle

  Article: Representing Medical Knowledge in the Form of Structured Text: The Development of Current Disease Descriptions*

  Stuart J. Nelson, David D. Sherertz, Mark S. Erlbaum, Mark S. Tuttle
  [show abstract] [hide abstract]
  ABSTRACT: As part of the Unified Medical Language System (UMLS) initiative, some 900 diseases have been described using “structured text.” Structured text is words and short phrases entered under labelled contexts. Vocabulary is not controlled. The contexts comprise a template for the disease description. The structured text is both manipulable by machine and readable by humans. Use of the template was natural, and only a few problems arose in using the template. Instructions to disease description composers must be explicit in definitions of the contexts. Diseases to be described are chosen, after clustering related diseases, according to the distinctions that physicians practicing in the area under question believe are important. Limiting disease descriptions to primitive observations and to entities otherwise described within the corpus appears to be both feasible and desirable.
• Source

  Available from: Mark Tuttle

  Article: Toward a Bio-Medical Thesaurus: Building the Foundation of the UMLS

  Mark S. Tuttle, Marsden S. Blois, Mark S. Erlbaum, Stuart J. Nelson, David D. Sherertz
  [show abstract] [hide abstract]
  ABSTRACT: The Unified Medical Language System (UMLS) is being designed to provide a uniform user interface to heterogeneous machine-readable bio-medical information resources, such as bibliographic databases, genetic databases, expert systems and patient records.1 Such an interface will have to recognize different ways of saying the same thing, and provide links to ways of saying related things. One way to represent the necessary associations is via a domain thesaurus. As no such thesaurus exists, and because, once built, it will be both sizable and in need of continuous maintenance, its design should include a methodology for building and maintaining it. We propose a methodology, utilizing lexically expanded schema inversion, and a design, called T. Lex, which together form one approach to the problem of defining and building a bio-medical thesaurus. We argue that the semantic locality implicit in such a thesaurus will support model-based reasoning in bio-medicine.2
• Article: Formal Properties of the Metathesaurus: An Update*

  Stephanie S. Lipow, Keith E. Campbell, Nels E. Olson, Mark S. Tuttle, Mark S. Erlbaum, Lloyd F. Fuller, David D. Sherertz, Stuart J. Nelson, William G. Cole
• Article: Concept, Code, Term and Word: Preserving the Distinctions*

  Mark S. Tuttle, Keith E. Campbell, Nels E. Olson, Stuart J. Nelson, Octavio Suarez-Munist, Mark S. Erlbaum, Stephanie S. Lipow, Lloyd F. Fuller, David D. Sherertz, William G. Cole
• Article: Explaining Your Terminology to a Computer*

  Nels E. Olson, David D. Sherertz, Mark S. Erlbaum, Stephanie S. Lipow, Octavio Suarez-Munist, Lloyd F. Fuller, Keith E. Campbell, Mark S. Tuttle, Stuart J. Nelson, William G. Cole
• Article: MEME II: An Environment for Managing Meaning*

  Octavio Suarez-Munist, William T Hole, Robert J. Irons, Mark S. Erlbaum, Nels E. Olson, Stephanie S. Lipow, Lloyd F. Fuller, Mark S. Tuttle, David D. Sherertz, Anil K. Ganju, Stuart J. Nelson, William G. Cole