Esta web utiliza cookies. Si continúas navegando consideramos que aceptas su uso.
Más información
Aceptar
I Jornadas Científicas del IMIB-Arrixaca
Acceso Personal
Contacto
Aviso Legal
Inicio
Bienvenida
Comités
Ponencias
Comunicaciones
Programa
Fechas clave
Inscripciones
Selección comunicaciones
Enviar comunicación
Patrocinadores
Sede
Imprimir
A SEMANTIC WEB BASED FRAMEWORK FOR THE INTEROPERABILITY AND EXPLOITATION OF CLINICAL MODELS AND EHR DATA
Autores:
MARÍA DEL CARMEN LEGAZ GARCÍA
,
CATALINA MARTINEZ COSTA
,
MARCOS MENARGUEZ TORTOSA
,
JESUALDO TOMÁS FERNÁNDEZ BREIS
,
Grupos de investigación:
[GI/IMIB/E170/2011] TECNOLOGÍAS DE MODELADO, PROCESAMIENTO Y GESTIÓN DEL CONOCIMIENTO
Comunicación:
Antecedentes:
The semantic interoperability of clinical information, that is, its meaningful communication across Electronic Health Record (EHR) systems, is required to effectively use and exploit patient’s health data that are spread across different systems. The joint use of EHR standards and semantic resources has been identified as key for semantic interoperability. International efforts have focused on development and use of EHR standards based on the dual model architecture, such as openEHR and ISO 13606, that distinguishes the information model, used to structure the EHR information and the clinical models (archetypes), used to specify clinical recording scenarios by constraining the information model structures. Semantic Web technologies, such as ontologies and its de facto implementation standard, OWL, enables the precise description of data meaning, allowing machines to understand the meaning of heterogeneous distributed content. Existing tools focused on EHR standards permit to create, search, explore clinical models and to map data sources to clinical models, but do not provide an appropriate support and integration of semantic resources or permit the secondary use of EHR data.
Métodos:
We describe an OWL-based framework that uses EHR and Semantic Web technologies for the interoperability and exploitation of archetypes and EHR data, and the secondary use of clinical data. The framework works with openEHR and ISO 13606 standards, managing ADL archetypes and XML EHR data extracts. ADL archetypes are transformed into OWL representation for checking its consistency; transforming archetypes and EHR data between different standards and calculating the semantic similarity between archetypes to identify archetypes representing the same concept. Archetypes are enriched with additional meaning by annotating them with recommended resources obtained from BioPortal, a repository of biomedical ontologies. The transformation of XML EHR data into OWL is guided by mappings defined between the ADL archetypes and domain OWL ontologies. The OWL representation is exploited together with OWL-DL rules and reasoning for classifying patients attending to different criteria.
Resultados:
This framework has been implemented in the Archetype Management System (ArchMS). ArchMS has been used in a real study in the colorectal cancer domain. Using the methods provided by ArchMS we have been able to reuse and exploit the content from existing archetypes and ontologies to represent and enrich the clinical data in this domain. The representation of patient data, annotations about archetypes and classifications rules in the same formalism allow the joint exploitation by means of automated reasoning that have been used for classifying patients according to their risk of developing colorectal cancer using European and American protocols. After comparing our classification with the one done by the physicians, the results showed 63% of agreement. The physicians confirmed that our classification was correct and that they were sometimes recording a level of risk different from the one suggested by the protocols due to restrictions related to the assignation of treatments of the patients.
Conclusiones:
Our results show the potential of Semantic Web technologies for the management and exploitation of archetypes and EHR data, and we think that our approach could be applied to other dual model standards. Further work will focus on integrating new standards and improving the transformation and recommendation methods.
Instituto de Investigación Sanitaria Acreditado
Inicio
Grupo de Investigación
Miembros
Proyectos
Colaboraciones
Servicios
Recursos formativos
Producción Científica
Publicaciones
Tesis
Novedades
Noticias
Eventos
Convocatorias
Agenda