Send to

Choose Destination
Proc AMIA Symp. 2001:642-6.

MeSHmap: a text mining tool for MEDLINE.

Author information

School of Library & Information Science, University of Iowa, Iowa City, IA 52242, USA.


Our research goal is to explore text mining from the metadata included in MEDLINE documents. We present MeSHmap our prototype text mining system that exploits the MeSH indexing accompanying MEDLINE records. MeSHmap supports searches via PubMed followed by user driven exploration of the MeSH terms and subheadings in the retrieved set. The potential of the system goes beyond text retrieval. It may also be used to compare entities of the same type such as pairs of drugs or pairs of procedures etc. In addition there is the potential to generate maps of entities (drugs or diseases etc.) such that the strength of the link between two entities in the map represents their similarity as expressed in the MeSH metadata of the MEDLINE documents. Higher level operators have been proposed to support these comparison and mapping functions. This paper motivates and describes MeSHmap. Future work will include user evaluations of the system.

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for PubMed Central
Loading ...
Support Center