Parsa Mirhaji, Min Zhu, Mattew Vagnoni, Elmer V bernstam, Jiajie Zhang and Jack W Smith
BMC Bioinformatics 2009, 10(Suppl 2):S2 doi:10.1186/1471-2105-10-S2-S2
This article is available from: http://www.biomedcentral.com/1471-2105/10/S2/S2
The authors present a semantic information integration platform which is conceptualized to use formal information and knowledge representation frameworks (semantic web) to construct an ontology-driven information system. All system resources and functions are defined explicitly and dynamically through a set of formal platform-independent reusable models。
Design of the system the authors presented
(1)The authors developed an algorithm to extract medical vocabularies from their source format and to translate to a SKOS ontology(current implementation of the method extracts source vocabularies included in the UMLS Knowledge Source.), employed a SKOS model to represent the UMLS Metathesaurus and the UMLS Semantic Network (UMLS-SN).
(2)A Web Service with methods to search and navigate the information space in order to identify correspondence of terms, codes, and names used to describe domain concepts, using underlying vocabulary systems.
(3)Also the authors developed a model that describes a typical questionnaire in terms of questions, answer options and some navigation rules to establish relationships between answers and questions
(4)To automate the integration process, the authors have developed an ontology-driven method to learn and produce an ontological representation, a “proto-ontology,” of any given XML message based on the system’s previous experience with the same or similar data sources, and inputs from human experts.
(5)The authors developed a patient-centric model to describe the syntactic and semantic representations found in a typical clinical text, as it appears in an electronic health record or a reporting system.
The authors are formalizing an objective and empirical evaluation plan to define, assess and report utility and validity of the methods and technologies developed and used in the system and extending the design with an analytical processing technique that enables traversing of large RDF graphs using an ontological representation of dimensions, dimension hierarchies and measures in order to construct multidimensional databases (similar to those of OLAP cubes) asynchronously.