Multi-language Concept Normalisation of Clinical Cohorts

The exploration of multiple cohorts allows researchers to answer new research questions using more substantial clinical data. However, this is only possible if the cohorts are interoperable, which implies the migration of the original cohort into a common data schema. The problem of this procedure is the effort necessary to map the original concepts into their standard definitions. While several automatic mapping solutions can help in this task, its complexity increases when dealing with multi-language cohorts, leading to a significant manual effort in translating and mapping. In this paper we propose a system that combines text mining with language detection techniques, aiming to optimise these migration pipelines. This system was designed to be integrated into already existing migration workflows, without the need of adapting them. The system was validated using Alzheimer's diseases cohorts, but it is enough general to be applied in other use cases.