Using rule-based natural language processing to improve disease normalization in biomedical text

Abstract

Background and objectiveIn order for computers to extract useful information from unstructured text, a concept normalization system is needed to link relevant concepts in a text to sources that contain further information about the concept. Popular concept normalization tools in the biomedical field are dictionary-based. In this study we investigate the usefulness of natural language processing (NLP) as an adjunct to dictionary-based concept normalization.MethodsWe compared the performance of two biomedical concept normalization systems, MetaMap and Peregrine, on the Arizona Disease Corpus, with and without the use of a rule-based NLP module. Performance was assessed for exact and inexact boundary matching of the system annotations with those of the gold standard and for concept identifier matching.ResultsWithout the NLP module, MetaMap and Peregrine attained F-scores of 61.0% and 63.9%, respectively, for exact boundary matching, and 55.1% and 56.9% for concept identifier matching. With the aid of the NLP module, the F-scores of MetaMap and Peregrine improved to 73.3% and 78.0% for boundary matching, and to 66.2% and 69.8% for concept identifier matching. For inexact boundary matching, performances further increased to 85.5% and 85.4%, and to 73.6% and 73.3% for concept identifier matching.ConclusionsWe have shown the added value of NLP for the recognition and normalization of diseases with MetaMap and Peregrine. The NLP module is general and can be applied in combination with any concept normalization system. Whether its use for concept types other than disease is equally advantageous remains to be investigated.

Representation of complex terms in a vector space structured by an ontology for a normalization task

“…A lot of biomedical or biological knowledge is in a non-structured form, such as that expressed in scientific articles (Kang et al, 2013). For experts from these fields, the substantial increase in the specialized literature has created a significant need for automatic methods of information extraction (Ananiadou and McNaught, 2006).…”

Automated Disease Normalization with Low Rank Approximations

“…Similar methods have been applied to disease names (Doğan & Lu, 2012b;Kang et al, 2012;Névéol et al, 2009) and species names (Gerner et al, 2010;Wei et al, 2012b), and the MetaMap program is used to locate and identify concepts from the UMLS MetaThesaurus (Aronson, 2001;Bodenreider, 2004).…”

Text Classification Model Based on Document Matrix Convolutional Neural Networks

“…It is true that these rule-based approaches had very noticeable effects at the time [1,2]. But the inadequacies of these approaches are self-evident, and they are overly dependent on the subjective judgment of people (or domain experts) and can not be adapted to new areas.…”