Mapping of electronic health records in Spanish to the unified medical language system metathesaurus

Abstract

[EN] This work presents a preliminary approach to annotate Spanish electronic health records with concepts of the Unified Medical Language System Metathesaurus. The prototype uses Apache Lucene R to index the Metathesaurus and generate mapping candidates from input text. In addition, it relies on UKB to resolve ambiguities. The tool has been evaluated by measuring its agreement with MetaMap in two English-Spanish parallel corpora, one consisting of titles and abstracts of papers in the clinical domain, and the other of real electronic health record excerpts.

[EU] Lan honetan, espainieraz idatzitako mediku-txosten elektronikoak Unified Medical Languge System Metathesaurus deituriko terminologia biomedikoarekin etiketatzeko lehen urratsak eman dira. Prototipoak Apache Lucene R erabiltzen du Metathesaurus-a indexatu eta mapatze hautagaiak sortzeko. Horrez gain, anbiguotasunak UKB bidez ebazten ditu. Ebaluazioari dagokionez, prototipoaren eta MetaMap-en arteko adostasuna neurtu da bi ingelera-gaztelania corpus paralelotan. Corpusetako bat artikulu zientifikoetako izenburu eta laburpenez osatutako dago. Beste corpusa mediku-txosten pasarte batzuez dago osatuta.