The Journal of Medical Systems has recently published an article that describes a method to trace semantic connections between clinical archetypes, based on the Unified Medical Language System:
Associating clinical archetypes through UMLS Metathesaurus term clusters
Clinical archetypes are modular definitions of clinical data, expressed using standard or open constraint-based data models as the CEN EN13606 and openEHR. There is an increasing archetype specification activity that raises the need for techniques to associate archetypes to support better management and user navigation in archetype repositories. This paper reports on a computational technique to generate tentative archetype associations by mapping them through term clusters obtained from the UMLS Metathesaurus. The terms are used to build a bipartite graph model and graph connectivity measures can be used for deriving associations.
Bipartite graph between clinical archetypes (blue nodes) and UMLS terms (green nodes)
The thicker the edge, the stronger the relationship between the associated archetypes.
