Semantic upgrade and normalization of existing EHR extracts.

We present the mapping and data transformation capabilities of LinkEHR-Ed, a visual tool to construct formal definitions of medical concepts in the form of archetypes which can be defined on the basis on multiple electronic health record architecture such as ISO 13606. With LinkEHR-Ed, users can enrich archetypes with mapping information which captures the relationship between relational or XML data sources and archetype structures. This mapping information is then analyzed and compiled into an XQuery expression that transforms source instances into an XML document. The target document satisfies the constraints imposed by the archetype and at the same time is compliant with the underlying electronic health record architecture.

Framework for clinical data standardization based on archetypes.

Standardization of data is a prerequisite to achieve semantic interoperability in any domain. This is even more important in the healthcare sector where the need for exchanging health related data among professional and institutions is not an exception but the rule. Currently, there are several international organizations working on the definition of electronic health record architectures, some of them based on a dual-model approach. We present both an archetype modeling framework and LinkEHR-ED, an archetype editor and mapping tool for transforming existing electronic healthcare data which do not conform to a particular electronic healthcare record architecture into compliant electronic health records extracts. In particular, archetypes in LinkEHR-ED are formal representations of clinical concepts built on a particular reference model but enriched with mapping information to data sources which define how to extract and transform existing data in order to generate standardized XML documents.

Archetype-based semantic integration and standardization of clinical data.

One of the basic needs for any healthcare professional is to be able to access to clinical information of patients in an understandable and normalized way. The lifelong clinical information of any person supported by electronic means configures his/her Electronic Health Record (EHR). This information is usually distributed among several independent and heterogeneous systems that may be syntactically or semantically incompatible. The Dual Model architecture has appeared as a new proposal for maintaining a homogeneous representation of the EHR with a clear separation between information and knowledge. Information is represented by a Reference Model which describes common data structures with minimal semantics. Knowledge is specified by archetypes, which are formal representations of clinical concepts built upon a particular Reference Model. This kind of architecture is originally thought for implantation of new clinical information systems, but archetypes can be also used for integrating data of existing and not normalized systems, adding at the same time a semantic meaning to the integrated data. In this paper we explain the possible use of a Dual Model approach for semantic integration and standardization of heterogeneous clinical data sources and present LinkEHR-Ed, a tool for developing archetypes as elements for integration purposes. LinkEHR-Ed has been designed to be easily used by the two main participants of the creation process of archetypes for clinical data integration: the Health domain expert and the Information Technologies domain expert.