City Research Online

Abstract

Generation of entity coreference chains provides a means to extract linked narrative events from clinical notes, but despite being a well-researched topic in natural language processing, general- purpose coreference tools perform poorly on clinical texts. This paper presents a knowledge-centric and pattern-based approach to resolving coreference across a wide variety of clinical records comprising discharge summaries, progress notes, pathology, radiology and surgical reports from two corpora (Ontology Development and Information Extraction (ODIE) and i2b2/VA). In addition, a method for generating coreference chains using progressively pruned linked lists is demonstrated that reduces the search space and facilitates evaluation by a number of metrics. Independent evaluation results show an F-measure for each corpus of 79.2% and 87.5%, respectively, which offers performance at least as good as human annotators, greatly increased performance over general- purpose tools, and improvement on previously reported clinical coreference systems. The system uses a number of open-source components that are available to download.

Publication Type:	Article
Additional Information:	NOTICE: this is the author’s version of a work that was accepted for publication in Journal of Biomedical Informatics. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Journal of Biomedical Informatics, Volume 45, Issue 5, October 2012, Pages 901–912 http://dx.doi.org/10.1016/j.jbi.2012.02.012.
Subjects:	R Medicine Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Departments:	School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads