PEPS: a platform for supporting studies in pharmaco-epidemiology using medico-administrative databases

International audienceBackground:New approaches of pharmaco-epidemiology consist in using large EHR databases to investigate the effects and uses (or misuses) of drugs in real conditions. The objective is to benefit from nationwide available data to answer accurately and in a short time pharmaco-epidemiological queries for national public health institutions. Despite the potential availability of the data, their size and complexity make their analysis long and tremendous. The challenge we tackle is the conception of a generic digital toolbox to support the efficient design of a broad range of pharmaco-epidemiology studies from EHR databases.Methods:To be able to answer the broad range of pharmaco-epidemiological queries from national public health institutions, the PEPS platform exploits, in secondary use, the French health cross-schemes insurance system, called SNIIRAM. The SNIIRAM covers most of the French population with a sliding period of 3 past years. To tackle the volume and the diversity of the SNIIRAM data warehouse, a research program has been established to design an innovative toolbox. This research program is focused first on the modeling of care pathways from the SNIIRAM database and, second, on the design of tools supporting meaningful insights extraction about massive and complex care pathways by clinicians.Results:A data infrastructure has been set up to collect and to access the data securely. We proposed and developed a high level abstraction model to access and to visualize care pathways. We designed the principle of a toolbox to carry out generic pharmaco-epidemiological studies from the SNIIRAM data warehouse (see figure). This toolbox is oriented toward data analytics with data visualisation, domain specific query language, knowledge discovery and statistics modules.Conclusions:The preliminary results on the development of the PEPS platform show that our care pathways model is very expressive and that it allows to have a highly abstracted representation of the warehouse's complex data. Our modular architecture supports clinicians and epidemiologists all along their analysis process