CONANN: An Online Biomedical Concept Annotator

Abstract

We describe our biomedical concept annotator designed for online environments, CONANN, which takes a biomedical source phrase and finds the best-matching biomedical concept from a domain resource. Domain concepts are defined in resources such as the United States National Library of Medicine’s Unified Medical Language System Metathesaurus. CONANN uses an incremental filtering approach to narrow down a list of candidate phrases before deciding on a best match. We show that this approach has the advantage of improving annotation speed over an existing state-of-the-art concept annotator, facilitating the use of concept annotation in online environments. Our main contributions are 1) the design of a phrase-unit concept annotator more readily usable in online environments than existing systems, 2) the introduction of a model which uses semantically focused words in a given ontology (e.g., UMLS) to measure coverage, called Inverse Phrase Frequency, and 3) the use of two different filters to measure coverage and coherence between a source phrase and a domain-specific candidate phrase. An intrinsic evaluation comparing CONANN’s concept output to a state-of-the-art concept annotator shows our system has an annotation precision ranging from 90% for exact match concept to 95% for relaxed concept matching while average phrase annotation time is eighteen times faster. In addition, an extrinsic evaluation using the generated concepts in a text summarization task shows no significant degradation when using CONANN.