Article

An RDF/OWL Knowledge Base for Query Answering and Decision Support in Clinical Pharmacogenetics

Medical University of Vienna, Vienna, Austria.
Studies in health technology and informatics 08/2013; 192(1):539-42. DOI: 10.3233/978-1-61499-289-9-539
Source: PubMed

ABSTRACT

Genetic testing for personalizing pharmacotherapy is bound to become an important part of clinical routine. To address associated issues with data management and quality, we are creating a semantic knowledge base for clinical pharmacogenetics. The knowledge base is made up of three components: an expressive ontology formalized in the Web Ontology Language (OWL 2 DL), a Resource Description Framework (RDF) model for capturing detailed results of manual annotation of pharmacogenomic information in drug product labels, and an RDF conversion of relevant biomedical datasets. Our work goes beyond the state of the art in that it makes both automated reasoning as well as query answering as simple as possible, and the reasoning capabilities go beyond the capabilities of previously described ontologies.

0 Followers
 · 
17 Reads
  • Source
    • "In summary, there is considerable interest in data mining of health records to support clinical decision making, but there are also obstacles. In addition to concerns about privacy, there is a need for techniques that can support decision-making in real-time, and that do not require large, and costly efforts to develop associated knowledge bases or ontologies (e.g., [23]). Thus our focus on this paper will be on a relatively assumption-free form of lightweight data mining and generalized prediction that could ultimately be conducted in real time as a Web service. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We previously described a methodology for converting a large set of confidential data records into a set of summaries of similar patients. They claimed that the resulting patient types could "capture important trends and patterns in the data set without disclosing the information in any of the individual data records." In this paper we examine the predictive validity of an initial set of patient types developed in our earlier research. We ask the following question: To what extent can the summarized data derived from each cluster (patient type) be as informative as the original case level data (individuals) from which the clusters were inferred? We address this question by assessing how well predictions made with summarized data matched predictions made with original data. After reviewing relevant literature, and explaining how data is summarized in each cluster of similar patients, we compare the results of predicting death in the ICU 1 using both summarized (regression analysis) and original case data (discriminant analysis and logistic regression analysis). When multiple clusters were used, prediction based on regression analysis of the summarized data was found to be better than prediction using either logistic regression or discriminant analysis on the raw data. We hypothesize that this result is due to segmentation of a heterogenous multivariate space into more homogeneous subregions. We see the present results as an important step towards the development of generalized health data search engines that can utilize non-confidential summarized data passed through health data repository firewalls.
    Full-text · Technical Report · Jul 2014
    • "In summary, there is considerable interest in data mining of health records to support clinical decision making, but there are also obstacles. In addition to concerns about privacy, there is a need for techniques that can support decision-making in real-time, and that do not require large, and costly efforts to develop associated knowledge bases or ontologies (e.g., [23]). Thus our focus on this paper will be on a relatively assumption-free form of lightweight data mining and generalized prediction that could ultimately be conducted in real time as a Web service. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Chignell et al. [1] previously described a methodology for converting a large set of confidential data records into a set of summaries of similar patients. They claimed that the resulting patient types could "capture important trends and patterns in the data set without disclosing the information in any of the individual data records." In this paper we examine the predictive validity of an initial set of patient types developed by [1]. We ask the following question: To what extent can the summarized data derived from each cluster (patient type) be as informative as the original case level data (individuals) from which the clusters were inferred? We address this question by assessing how well predictions made with summarized data matched predictions made with original data. After reviewing relevant literature, and explaining how data is summarized in each cluster of similar patients, we compare the results of predicting death in the ICU 1 using both summarized (regression analysis) and original case data (discriminant analysis and logistic regression analysis). When multiple clusters were used, prediction based on regression analysis of the summarized data was found to be better than prediction using either logistic regression or discriminant analysis on the raw data. We hypothesize that this result is due to segmentation of a heterogenous multivariate space into more homogeneous subregions. We see the present results as an important step towards the development of generalized health data search engines that can utilize non-confidential summarized data passed through health data repository firewalls.
    No preview · Technical Report · Jun 2014
  • Source
    • "The Reasoning Engine module was implemented using Semantic Web technologies and based on the Genomic CDS ontology we developed recently [23], [24]. The Genomic CDS ontology is an OWL 2 DL ontology containing pharmacogenomic domain knowledge such as definitions of polymorphisms, alleles, phenotypes and treatment recommendations. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The development of genotyping and genetic sequencing techniques and their evolution towards low costs and quick turnaround have encouraged a wide range of applications. One of the most promising applications is pharmacogenomics, where genetic profiles are used to predict the most suitable drugs and drug dosages for the individual patient. This approach aims to ensure appropriate medical treatment and avoid, or properly manage, undesired side effects. We developed the Medicine Safety Code (MSC) service, a novel pharmacogenomics decision support system, to provide physicians and patients with the ability to represent pharmacogenomic data in computable form and to provide pharmacogenomic guidance at the point-of-care. Pharmacogenomic data of individual patients are encoded as Quick Response (QR) codes and can be decoded and interpreted with common mobile devices without requiring a centralized repository for storing genetic patient data. In this paper, we present the first fully functional release of this system and describe its architecture, which utilizes Web Ontology Language 2 (OWL 2) ontologies to formalize pharmacogenomic knowledge and to provide clinical decision support functionalities. The MSC system provides a novel approach for enabling the implementation of personalized medicine in clinical routine.
    Full-text · Article · May 2014 · PLoS ONE
Show more