Mark S. Tuttle

VA national drug file reference terminology: A cross-institutional content coverage study

BACKGROUND Content coverage studies provide valuable information to potential users of terminologies. We detail the VA National Drug File Reference Terminologys (NDF-RT) ability to represent dictated medication list phrases from the Mayo Clinic. NDF-RT is a description logic-based resource created to support clinical operations at one of the largest healthcare providers in the US. METHODS Medication list phrases were extracted from dictated patient notes from the Mayo Clinic. Algorithmic mappings to NDF-RT using the SmartAccess Vocabulary Server (SAVS) were presented to two non-VA physicians. The physicians used a terminology browser to determine the accuracy of the algorithmic mapping and the content coverage of NDF-RT. RESULTS The 509 extracted documents on 300 patients contained 847 medication concepts in medication lists. NDF-RT covered 97.8% of concepts. Of the 18 phrases that NDF-RT did not represent, 10 were for OTCs and food supplements, 5 were for prescription medications, and 3 were missing synonyms. The SAVS engine properly mapped 773 of 810 phrases with an overall sensitivity (precision) was 95.4% and positive predictive value (recall) of 99.9%. CONCLUSIONS This study demonstrates that NDF-RT has more general utility than its initial design parameters dictated

Evaluating RECONSIDER: a computer program for diagnostic prompting

RECONSIDER, a computer program designed to perform as a diagnostic prompting aid, was evaluated for its ability to include the correct diagnosis in an ordered computed list of candidate diseases. The study was performed using 100 consecutive first admissions to the medical service of a university hospital, where the individuals entering the data into the program were blind to all but a limited set of findings known at time of admission. Each person entering the data created one or more lists of diagnostic possibilities (versions) using the program. The program suggested the correct diagnosis within the first 40 on its list 61% (498/797) of the time; the correct diagnosis was present with the first 40 in at least one version 93% (98/105) of the time. Performance was found to be best with cases having a single diagnosis and when more terms were entered into the program.

The role of compositionality in standardized problem list generation

Compositionality is the ability of a Vocabulary System to record non-atomic strings. In this manuscript we define the types of composition, which can occur. We will then propose methods for both server based and client-based composition. We will differentiate the terms Pre-Coordination, Post-Coordination, and User-Directed Coordination. A simple grammar for the recording of terms with concept level identification will be presented, with examples from the Unified Medical Language Systems (UMLS) Metathesaurus. We present an implementation of a Windows NT based client application and a remote Internet Based Vocabulary Server, which makes use of this method of compositionality. Finally we will suggest a research agenda which we believe is necessary to move forward toward a more complete understanding of compositionality. This work has the promise of paving the way toward a robust and complete Problem List Entry Tool.

Collaborative conversational interfaces

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.

The role of context in the integration of heterogeneous health care databases

The valid assimilation of data from heterogeneous databases is a critical informatics issue with implications for both clinical and population research. Heterogeneous databases have representational and semantic differences whose resolution requires mapping the intended meanings of local data structures to standard reference models. We argue that the representation and use of contextual information enhances this mapping process, and may indeed be a necessary part of this process to maintain meaning. A database integration project to assimilate presenting complaint data from heterogeneous emergency department databases afforded the opportunity to characterize multiple levels of context that were important in identifying and resolving representational and semantic differences. Consideration and representation of context at multiple levels can preserve granularity and intended meaning of local data at the aggregate level, and increase the quality and utility of the data for secondary analyses. We propose five aspects of context (data instance context, context of database schema, context of data collection process, context of data collection quality, and domain context) which are necessary to understand the merging of heterogeneous data. Ideal representations for each aspect of context vary by purpose and domain.

Medical Informatics Challenges of the 1990s: Acknowledging Secular Change

Medical informatics is in the midst of deep secular changes. In hindsight, these changes have been operating throughout the 1990s; they show no signs of abating. A simple exercise will demonstrate that these changes are not yet widely acknowledged in our field. Before you read further, please free associate in response to the following phrases, and then compare your associations with those below: My associations when I hear “Software in the 1990s” are as follows: The first thing I think of is SCALE. Prior to the 1990s, it was not at all clear how anything in computing was going to scale—e.g., how it was going to be accessed by the majority of computer users. As of 1997, we are starting to take the Internet, Web browsers, and Web search engines for granted. Web search engines are particularly dramatic; whatever their shortcomings, the fact that several systems independently index the World Wide Web (WWW) on a more or less daily basis was not anticipated. After scale, my next association with “Software in the 1990s” is GLOBALIZATION. One can now buy software that is used productively around the world by users who know only their native languages. The economic incentives are clear. If a software product can be used worldwide, it is easier to justify investing in its development, maintenance, and enhancement than if that same product could only be used by one country or by users of one language. My third “Software in the 1990s” association was easier to foresee: namely, it is TOUGH TO SURVIVE AS A NICHE. Microeconomic theory predicts that new markets can support many suppliers of …

Bioprospecting the Bibleome: Adding Evidence to Support the Inflammatory Basis of Cancer

BACKGROUND CANCER SIGNIFICANCE AND QUESTION BioProspecting is a novel approach that enabled our team to mine genetic marker related data from the New England Journal of Medicine (NEJM) utilizing Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) and the Human Gene Ontology (HUGO). Genes associated with disorders using the Multi-threaded Clinical Vocabulary Server (MCVS) Natural Language Processing (NLP) engine, whose output was represented as an ontology-network incorporating the semantic encodings of the literature. Metabolic functions were used to identify potentially novel relationships between (genes or proteins) and (diseases or drugs). In an effort to identify genes important to transformation of normal tissue into a malignancy, we went on to identify the genes linked to multiple cancers and then mapped those genes to metabolic and signaling pathways. FINDINGS Ten Genes were related to 30 or more cancers, 72 genes were related to 20 or more cancers and 191 genes were related to 10 or more cancers. The three pathways most often associated with the top 200 novel cancer markers were the Acute Phase Response Signaling, the Glucocorticoid Receptor Signaling and the Hepatic Fibrosis/Hepatic Stellate Cell Activation pathway. MEANING AND IMPLICATIONS OF THE ADVANCE This association highlights the role of inflammation in the induction and perhaps transformation of mortal cells into cancers. MAJOR FINDINGS BioProspecting can speed our identification and understanding of synergies between articles in the biomedical literature. In this case we found considerable synergy between the Oncology literature and the Sepsis literature. By mapping these associations to known metabolic, regulatory and signaling pathways we were able to identify further evidence for the inflammatory basis of cancer.