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
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
Journal of Biomedical Informatics
Hi-index | 0.00 |
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.