Automatic Extraction of semantic relations between medical entities: Application to the treatment relation

Information extraction is a complex task which is necessary to develop highprecision information retrieval tools. In this paper, we present MeTAE, a platform to extract medical entities and the medical relations linking them. The proposed approach relies on linguistic patterns and domain knowledge and consists in two steps: (i) recognition of medical entities and (ii) identification of the correct semantic relation between each pair of entities. The first step is achieved by an enhanced use of MetaMap which improves the precision obtained by MetaMap by 19.59% in our evaluation. The second step relies on linguistic patterns which are built semiautomatically from a corpus selected according to semantic criteria. We evaluate our system’s ability to identify medical entities of 16 types. We also evaluate the extraction of treatment relations between a treatment (e.g., medication) and a problem (e.g., disease): we obtain 75.72% of precision and 60.46% of recall. We achieve encouraging results w.r.t similar research works in the literature.