Context Related Extraction of Conceptual Information from Electronic Health Records

Abstract. This paper discusses some language technologies applied for the automatic processing of Electronic Health Records in Bulgarian, in order to extract multi-layer conceptual chunks from medical texts. We consider an Information Extraction view to text processing, where se-mantic information is extracted using predefined templates. At the first step the templates are filled in with information about the patient sta-tus. Afterwards the system excerpts or infers temporal relations between the events, described in the EHR text. Then cause-effect relations are explicated and at last, implicit knowledge is derived from the medical records after reasoning. Thus we propose a cascade approach for the ex-traction of multi-layer knowledge representation statements because the subject is too complex. In this article we present laboratory prototypes for the first two tasks and discuss typical examples of conceptual struc-tures, which cover the most challenging tasks in the extraction scenario- the recognition of cause-effect relations and temporal structures. The present work in progress is part of the research project EVTIMA (2009-2011) that aims at the design and implementation of technologies for efficient search of conceptual patterns in medical information.