Semantic indexing of biomedical publications and clinical text

National Library Of Medicine

Investigators

Linked publications & trials

Abstract

The Indexing Initiative project addresses both objectives by continually improving Named Entity Recognition algorithms and providing these algorithms to the public in a program called MetaMap. A recently developed MetaMap Lite, a faster and more accurate tool for Named Entity Recognition, gained popularity and was downloaded over 800 times in 2018-19. Both MetaMap and MetaMap Lite are widely used as NLM services for remote file processing and as downloadable tools. In FY2019, MetaMap , MetaMap Lite and related software were downloaded 5,088 times. In addition, the tools were accessed 76,685 times through its web and application program interface (API) facilities. The semantic indexing objective is addressed by the Medical Text Indexer (MTI) program that assigns most salient medical subject headings to medical text. Among other applications, MTI powers MeSH on Demand an online tool that helps authors find key terms for their publications, identifying MeSH Terms relevant to submitted text. In collaboration with the Index section, LHC researchers have developed a tool that will automatically exclude out-of-scope articles from the Indexers queue. The projected reduction in manual triage of these articles is 54%, which amounts to about 40,000 articles.