FontoXML in Life Sciences
Together with our partners we enable pharma companies to improve data governance and to better integrate text authoring processes in regulatory operations. We offer a platform for managing reference data sets in the pharmacological domain and an extractor that takes a Summary of Product Characteristics (SmPC) in the form of a textual document as input and a dataset as output. It recognizes elements in the text and traces these back to codes in the reference datasets.
Of course we offer tooling for structured authoring. An author is guided through the authoring process whereby the document structure is predefined and content is controlled. Importantly, when entering the name of, say, a substance, the substance name has to be selected from a drop down list. This list is populated from a reference data set. What gets inserted is both the selected lexical form (as the author sees it) and the underlying identifying code (which computers use for unambiguous reference).