Improved Identification of Noun Phrases in Clinical Radiology Reports Using a High-Performance Statistical Natural Language Parser Augmented with the UMLS Specialist Lexicon

Abstract

A b s t r a c t Objective: The aim of this study was to develop and evaluate a method of extracting noun phrases with full phrase structures from a set of clinical radiology reports using natural language processing (NLP) and to investigate the effects of using the UMLSÒ Specialist Lexicon to improve noun phrase identification within clinical radiology documents.Design: The noun phrase identification (NPI) module is composed of a sentence boundary detector, a statistical natural language parser trained on a nonmedical domain, and a noun phrase (NP) tagger. The NPI module processed a set of 100 XML-represented clinical radiology reports in Health Level 7 (HL7)Ò Clinical Document Architecture (CDA)-compatible format. Computed output was compared with manual markups made by four physicians and one author for maximal (longest) NP and those made by one author for base (simple) NP, respectively. An extended lexicon of biomedical terms was created from the UMLS Specialist Lexicon and used to improve NPI performance.Results: The test set was 50 randomly selected reports. The sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%. Conclusion:The sentence boundary detector performs excellently. After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.

Benchmarking natural-language parsers for biological applications using dependency graphs

“…The Stanford parser has been used to provide syntactic clues for identifying key clinical terms in the medical domain [34] and gene and protein names in the biological domain [35], although we disagree with the latter paper that unlexicalised parsers – those that represent words simply by their POS tags – are more suited to the biological domain than lexicalised parsers equipped with a general-English lexicon. While the relative positions of the lexicalised and unlexicalised versions of the Stanford parser in our study depend on which evaluation measure is used, both versions were consistently out-performed by the Bikel and Charniak-Lease parsers, both of whose parsing engines are lexicalised with a general-English vocabulary.…”

Annotating and recognising named entities in clinical notes

“…This can be done efficiently by using an appropriate data structure such as a hash table. Systems that use string matching techniques include SAPHIRE (Hersh and Hickam, 1995), IndexFinder (Zou et al, 2003), NIP (Huang et al, 2005) and MaxMatcher (Zhou et al, 2006). With a large lexicon, high precision and acceptable recall were achieved by this approach in their experiments.…”

A system for sharing routine surgical pathology specimens across institutions: the Shared Pathology Informatics Network

“…The autocoder tools search through (parse) the text of the report to find keywords or phrases representing the procedure, organ, and diagnosis terms (both assertion and negation of these terms) and assign codes to these based on the UMLS vocabulary [15][16][17][18][19][20][21][22]. Use of codes facilitates searching as discussed below.…”