Linking multiple disease-related resources through UMLS

Authors:
Aurélie Névéol;Jiao Li;Zhiyong Lu
Affiliations:
U.S. National Library of Medicine, NCBI, Bethesda, MD, USA;U.S. National Library of Medicine, NCBI, Bethesda, MD, USA;U.S. National Library of Medicine, NCBI, Bethesda, MD, USA
Venue:
Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium
Year:
2012

Citing 4
Cited 2

Compact representations by finite-state transducers

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Exploring two biomedical text genres for disease recognition

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
From indexing the biomedical literature to coding clinical text: experience with MTI and machine learning approaches

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Disease mention recognition with specific features

BioNLP '10 Proceedings of the 2010 Workshop on Biomedical Natural Language Processing

An improved corpus of disease mentions in PubMed citations

BioNLP '12 Proceedings of the 2012 Workshop on Biomedical Natural Language Processing
Special Report: NCBI disease corpus: A resource for disease name recognition and concept normalization

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.