Semantic structuring of and information extraction from medical documents using the UMLS

This paper introduces SeReMeD (Semantic Representation of Medical Documents), a method for automatically generating knowledge representations from natural language documents. The suitability of the Unified Medical Language System (UMLS) as domain knowledge for this method is analyzed.

SeReMeD combines existing language engineering methods and semantic transformation rules for mapping syntactic information to semantic roles. In this way, the relevant content of medical documents is mapped to semantic structures. In order to extract specific data, these semantic structures are searched for concepts and semantic roles. A study is carried out that uses SeReMeD to detect specific data in medical narratives such as documented diagnoses or procedures.

The system is tested on chest X-ray reports. In first evaluations of the system's performance, the generation of semantic structures achieves a correctness of 80%, whereas the extraction of documented findings obtains values of 93% precision and 83% recall.

The results suggest that the methods described here can be used to accurately extract data from medical narratives, although there is also some potential for improving the results. The proposed methods provide two main benefits. By using existing language engineering methods, the effort required to construct a medical information extraction system is reduced. It is also possible to change the domain knowledge and therefore to create a more (or less) specialized system, capable of handling various medical sub-domains.