Abstract

A large amount of free text is available as a source of knowledge in the biomedical field. MetaMap is a widely used tool that identifies concepts within the UMLS in English text. In this study, we study the performance of MetaMap. Performance is measured in retrieval speed, precision of results and recall of results. This automated MetaMap indexing is compared with manual indexing of the same text. Results shows that MetaMap by default was able to identify 98.19% of the biomedical concepts occurred in the sample set. MetaMap by default identified 78.79% of the concepts that manually were not identified. MetaMap is tested under four scenarios; the default output, displaying the mapping list, restricting the candidates’ score within the candidate list and restricting the candidates’ score within the mapping list. This study describes the limitations of the MetaMap tool and ways to improve the performance of the tool and increase its recall and precision.

Keywords:

Biomedical, MetaMap, performance, UMLS,

References

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.