An Empirical Evaluation of Resources for the Identification of Diseases and Adverse Effects in Biomedical Literature
Year: 2010
Type: conference-paper
Abstract: The mentions of human health perturbations such as the diseases and adverse effects denote a special entity class in the biomedical\nliterature. They help in understanding the underlying risk factors and develop a preventive rationale. The recognition of these named\nentities in texts through dictionary-based approaches relies on the availability of appropriate terminological resources. Although few\nresources are publicly available, not all are suitable for the text mining needs. Therefore, this work provides an overview of the well\nknown resources with respect to human diseases and adverse effects such as the MeSH, MedDRA, ICD-10, SNOMED CT, and UMLS.\nIndividual dictionaries are generated from these resources and their performance in recognizing the named entities is evaluated over a\nmanually annotated corpus. In addition, the steps for curating the dictionaries, rule-based acronym disambiguation and their impact\non the dictionary performance is discussed. The results show that the MedDRA and UMLS achieve the best recall. Besides this,\nMedDRA provides an additional benefit of achieving a higher precision. The combination of search results of all the dictionaries achieve\na considerably high recall. The corpus is available on http://www.scai.fraunhofer.de/disease-ae-corpus.html
Institutions: Fraunhofer-Gesellschaft, Center for Information Technology
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W39864132