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

University of Utah, USA.
Proceedings / AMIA ... Annual Symposium. AMIA Symposium 02/2002; 2002:116-20.
Source: PubMed


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.

Download full-text


Available from: Mark Tuttle
  • Source
    • "However , current procedures for constructing such knowledge bases have significant limitations. The use of standard terminologies or commercially available resources comprises one method, though development of such resources is difficult and expensive, often requiring substantial maintenance [8] [9] [10]. Data mining methods are also common but can be hard to execute and may be biased to only include common links [11] [12] [13]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Correlation of data within electronic health records is necessary for implementation of various clinical decision support functions, including patient summarization. A key type of correlation is linking medications to clinical problems; while some databases of problem-medication links are available, they are not robust and depend on problems and medications being encoded in particular terminologies. Crowdsourcing represents one approach to generating robust knowledge bases across a variety of terminologies, but more sophisticated approaches are necessary to improve accuracy and reduce manual data review requirements.
    Full-text · Article · Dec 2013 · Journal of Biomedical Informatics
  • Source
    • "To date, the majority of this work has focused on discovering pairwise associations (e.g., [6] [7]). These measure the correlation between pairs of variables (e.g., diagnoses and treatments) using statistical tests (e.g., χ 2 or interestingness measures). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Although clinical decision support systems can reduce costs and improve care, the challenges associated with manually maintaining content has led to low utilization. Here we pilot an alternative, more automatic approach to decision support content generation. We use local order entry data and Bayesian networks to automatically find multivariate associations and suggest treatments. We evaluated this on 5044 hospitalizations of pregnant women, choosing 70 frequent order and treatment variables comprising 20 treatable conditions. The method produced treatment suggestion lists for 15 of these conditions. The lists captured accurate and non-trivial clinical knowledge, and all contained the key treatment for the condition, often as the first suggestion (71% overall, 90% non-labor-related). Additionally, when run on a test set of patient data, it very accurately predicted treatments (average AUC .873) and predicted pregnancy-specific treatments with even higher accuracy (AUC above .9). This method is a starting point for harnessing the wisdom-of-the-crowd for decision support.
    Full-text · Article · Jan 2010 · AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
  • Source
    • "Reference terminologies are being designed [9] [10] to meet specific needs and requirements. The prime customer for the ERT is the VA's Health Data Repository project. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The Veterans Health Affairs (VHA) branch of the Department of Veterans Affairs has undertaken an Enterprise Reference Terminology (ERT). VHA, arguably the largest integrated healthcare provider in the United States, has completely computerized virtually all clinical transactions, including physician orders and documentation. The VA is now integrating its clinical records across hundreds of sites of care by means of a Health Data Repository (HDR) project. ERT has been designed to provide a terminology development environment, terminology services, and maintenance services for the clinical and business content in HDR and other VHA applications. Drug, laboratory observations, and clinical document title files have been developed, and the ERT will encompass all HDR domains by 2008. Commercial tools are used to host the VHA's ERT terminology development and server environments. We will select and adopt both open-source and licensable terminology systems to provide ERT content, as well as reuse existing VA-specific terminology content.
    Full-text · Article · Feb 2004 · Studies in health technology and informatics
Show more