Linking multiple disease-related resources through UMLS

A recent usage log analysis showed that disease information is frequently sought by PubMed users. Besides PubMed, many other resources provide valuable information on thousands of diseases for scientific professionals and health consumers. However, the lack of explicit links between resources limits the access to comprehensive information for a given disease. The objective of this work is to integrate a variety of disease-related resources in the public domain in order to enable integrated access to multiple disease resources. We applied automated methods for recognizing and mapping disease mentions in free text to disease concepts in UMLS. A total of 467 Gene Reviews and 1,581 A.D.A.M. disease records were mapped to UMLS concepts. These mappings complement manually curated associations and enable the automatic creation of relevant links between documents. With minimal human intervention, disease-related resources were mapped to UMLS and linked together, which is critical for providing integrated access to online disease information.

[1]  Dina Demner-Fushman,et al.  Methodology for Creating UMLS Content Views Appropriate for Biomedical Natural Language Processing , 2008, AMIA.

[2]  Dietrich Rebholz-Schuhmann,et al.  Assessment of disease named entity recognition on a corpus of annotated sentences , 2008, BMC Bioinformatics.

[3]  Zhiyong Lu,et al.  Extracting Rx information from clinical narrative , 2010, J. Am. Medical Informatics Assoc..

[4]  Olivier Bodenreider,et al.  From indexing the biomedical literature to coding clinical text: experience with MTI and machine learning approaches , 2007, BioNLP@ACL.

[5]  Olivier Bodenreider,et al.  Aggregating UMLS Semantic Types for Reducing Conceptual Complexity , 2001, MedInfo.

[6]  Xiaoyan Wang,et al.  Automated Terminology Networks for the Integration of Heterogeneous Databases , 2004, MedInfo.

[7]  Alan R. Aronson,et al.  An overview of MetaMap: historical perspective and recent advances , 2010, J. Am. Medical Informatics Assoc..

[8]  Zhiyong Lu,et al.  Understanding PubMed® user search behavior through log analysis , 2009, Database J. Biol. Databases Curation.

[9]  Zhiyong Lu,et al.  Exploring Two Biomedical Text Genres for Disease Recognition , 2009, BioNLP@HLT-NAACL.

[10]  James J Cimino,et al.  An integrated approach to computer-based decision support at the point of care. , 2007, Transactions of the American Clinical and Climatological Association.

[11]  Mehryar Mohri.  Compact Representations by Finite-State Transducers , 1994, ACL.

[12]  A Burgun,et al.  Accessing and Integrating Data and Knowledge for Biomedical Research , 2008, Yearbook of Medical Informatics.

[13]  Yves A Lussier,et al.  Automating terminological networks to link heterogeneous biomedical databases. , 2004, Studies in health technology and informatics.

[14]  Alberto Lavelli,et al.  Disease Mention Recognition with Specific Features , 2010, BioNLP@ACL.