Combining ontologies and rules with clinical archetypes

Abstract

Like many other fields that heavily rely on the capabilities of information and communication technologies, healthcare and biomedical environments are rapidly increasing the demand for widely accepted agreements on data, information and knowledge exchange. Such needs for compatibility or interoperability go beyond syntactical and structural issues as semantic interoperability is also required. Semantic interoperability is essential to facilitate the computerized support for alerts, workflow management and evidence-based healthcare across heterogeneous Electronic Health Record (EHR) systems. The model of clinical archetypes supported by the CEN/ISO EN13606 standard and the openEHR foundation provides a mechanism to express data structures in a shared and interoperable way. It has acquired considerable acceptance in the last years by allowing the definition of clinical concepts based on a common Reference Model while low level storage implementation can keep its heterogeneity across EHR systems. However, archetype languages do not provide direct support neither for clinical rules nor mappings to formal ontologies, which are both key elements of full semantic interoperability as they allow exploiting reasoning on clinical knowledge. It has been acknowledged that the World Wide Web demands analogous capabilities to those mentioned above, leading to the development of the Semantic Web extension. The progress made in that field, regarding reasoning and knowledge representation, is combined in this thesis with EHR models in order to enhance the archetype approach and to support features that correspond to a richer level of semantic interoperability. Concretely, this research presents and evaluates an approach to translate definitions expressed in openEHR Archetype Definition Language (ADL) to a formal representation using ontology languages. The approach is implemented in the ArchOnt framework, which is also described. The integration of those formal representations with clinical rules is then studied, providing an approach to reuse reasoning on concrete instances of clinical data. Sharing the knowledge expressed in the form of rules is coherent with the philosophy of open sharing underlying archetypes, and it also extends reuse to propositions of declarative knowledge as those encoded for example in clinical guidelines. Thus, this thesis describes the techniques to map archetypes to formal ontologies and how rules can be attached to the resulting representation. In addition, the translation allows specifying logical bindings to equivalent clinical concepts from other knowledge sources. Such bindings encourage reuse as well as ontology reasoning and navigability across different ontologies. Another significant contribution of the thesis is the application of the presented approach as part of two research projects in collaboration with teaching hospitals in Madrid. Examples taken from those cases, such as the development of alerting systems aimed at improving patient safety, are here explained. Besides the direct applications described, the automatic translation of archetypes to an ontology language fosters a wide range of semantic and reasoning activities to be designed and implemented on top of a common representation instead of taking an ad-hoc approach.