You are here
LAERTES: An open scalable architecture for linking pharmacovigilance evidence sources with clinical data.
Integrating multiple sources of pharmacovigilance evidence has the potential to advance the science of safety signal detection and evaluation. Consistent with these results, there has been a recent call for more research on how to integrate multiple disparate evidence sources while making the evidence computable from a knowledge representation perspective (i.e., semantic enrichment). Existing frameworks integrating various sources provide some of the input needed for combinatorial signal detection. However, none have been specifically designed to support both regulatory and clinical use cases, nor developed using an open architecture allowing interested scientists to easily add new sources. This paper discusses the architecture and functionality of a system called Large-scale Adverse Effects Related to Treatment Evidence Standardization (LAERTES). LAERTES provides an open and scalable architecture for linking evidence sources relevant to investigating the association of drugs with health outcomes of interest (HOIs). Standard terminologies/ontologies are used to represent different entities. For example, drugs and HOIs are represented respectively using RxNorm and SNOMED-CT. At the time of this writing, six evidence sources have been loaded into LAERTES. Also, a prototype evidence exploration user interface and set of Web API services are available. This system operates within a larger software environment provided by the OHDSI clinical research framework.