Abstract

BackgroundStructured data acquisition is a common task that is widely performed in biomedicine. However, current solutions for this task are far from providing a means to structure data in such a way that it can be automatically employed in decision making (e.g., in our example application domain of clinical functional assessment, for determining eligibility for disability benefits) based on conclusions derived from acquired data (e.g., assessment of impaired motor function). To use data in these settings, we need it structured in a way that can be exploited by automated reasoning systems, for instance, in the Web Ontology Language (OWL); the de facto ontology language for the Web.ResultsWe tackle the problem of generating Web-based assessment forms from OWL ontologies, and aggregating input gathered through these forms as an ontology of “semantically-enriched” form data that can be queried using an RDF query language, such as SPARQL. We developed an ontology-based structured data acquisition system, which we present through its specific application to the clinical functional assessment domain. We found that data gathered through our system is highly amenable to automatic analysis using queries.ConclusionsWe demonstrated how ontologies can be used to help structuring Web-based forms and to semantically enrich the data elements of the acquired structured data. The ontologies associated with the enriched data elements enable automated inferences and provide a rich vocabulary for performing queries.

Highlights

  • Structured data acquisition is a common task that is widely performed in biomedicine

  • The resulting data individuals are structured in Web ontology language (OWL) to how the form is structured in the configuration, that is, if question Q is configured as having two sub-questions, the Observation individual generated by Q will have two outgoing hasComponent relations to the instances of Observation generated by the two sub-questions of Q

  • The output ontology is modeled according to the datamodel ontology presented in the Modeling Section, which is a resource of the overall system distribution

Read more

Summary

Introduction

Structured data acquisition is a common task that is widely performed in biomedicine. The rise of the Web Ontology Language (OWL) [3, 4], standardized by the World Wide Web Consortium (W3C) in 2004, caused a paradigm shift in knowledge representation from frame-based to axiom-based. With OWL as the preferred modeling language for ontologies, class definitions are collections of description logic (DL) axioms, and can no longer be seen as templates for forms [5]. Template-based knowledge representation systems use closed-world reasoning and have local constraints (e.g., cardinality of a slot for a particular class) that can be validated while in an axiom-based system with the open-world assumption such local constraint checking is much more problematic. Items in the instruments have potentially complex descriptions of information to be collected, such as the severity of pain with a particular quality, and at a specific anatomical

Objectives
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call