Fig. 2

Overview of the terminology development and information extraction setting. Based on default resources (dictionaries, templates, etc.) and supported by automatically inferred concept proposals, domain experts iteratively refine the domain knowledge and the high-level extraction knowledge of the terminology for each clinical subdomain (top left); technical experts adapt preexisting segmentation and filtering rules to the needs of specific subdomains (bottom left). The terminology and the segmentation module are integrated into a generic ontology-driven information extraction method that keeps the same across domains (mid right). It populates extracted attribute value pairs into a clinical data warehouse (top). $: input documents are (pre)processed by a de-identification module in order to ensure patient privacy