FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044693911> ?p ?o ?g. }

• W3044693911 endingPage "224" @default.
• W3044693911 startingPage "203" @default.
• W3044693911 abstract "Abstract Using natural language processing, it is possible to extract structured information from raw text in the electronic health record (EHR) at reasonably high accuracy. However, the accurate distinction between negated and non-negated mentions of clinical terms remains a challenge. EHR text includes cases where diseases are stated not to be present or only hypothesised, meaning a disease can be mentioned in a report when it is not being reported as present. This makes tasks such as document classification and summarisation more difficult. We have developed the rule-based EdIE-R-Neg, part of an existing text mining pipeline called EdIE-R (Edinburgh Information Extraction for Radiology reports), developed to process brain imaging reports, ( https://www.ltg.ed.ac.uk/software/edie-r/ ) and two machine learning approaches; one using a bidirectional long short-term memory network and another using a feedforward neural network. These were developed on data from the Edinburgh Stroke Study (ESS) and tested on data from routine reports from NHS Tayside (Tayside). Both datasets consist of written reports from medical scans. These models are compared with two existing rule-based models: pyConText (Harkema et al . 2009. Journal of Biomedical Informatics 42 (5), 839–851), a python implementation of a generalisation of NegEx, and NegBio (Peng et al . 2017. NegBio: A high-performance tool for negation and uncertainty detection in radiology reports. arXiv e-prints, p. arXiv:1712.05898 ), which identifies negation scopes through patterns applied to a syntactic representation of the sentence. On both the test set of the dataset from which our models were developed, as well as the largely similar Tayside test set, the neural network models and our custom-built rule-based system outperformed the existing methods. EdIE-R-Neg scored highest on F1 score, particularly on the test set of the Tayside dataset, from which no development data were used in these experiments, showing the power of custom-built rule-based systems for negation detection on datasets of this size. The performance gap of the machine learning models to EdIE-R-Neg on the Tayside test set was reduced through adding development Tayside data into the ESS training set, demonstrating the adaptability of the neural network models." @default.
• W3044693911 created "2020-07-29" @default.
• W3044693911 creator A5004978342 @default.
• W3044693911 creator A5007623614 @default.
• W3044693911 creator A5021489611 @default.
• W3044693911 creator A5031469343 @default.
• W3044693911 creator A5036399769 @default.
• W3044693911 creator A5043179000 @default.
• W3044693911 creator A5073041438 @default.
• W3044693911 creator A5083770055 @default.
• W3044693911 creator A5089456652 @default.
• W3044693911 date "2020-11-18" @default.
• W3044693911 modified "2023-10-16" @default.
• W3044693911 title "Comparison of rule-based and neural network models for negation detection in radiology reports" @default.
• W3044693911 cites W1961993270 @default.
• W3044693911 cites W1964625659 @default.
• W3044693911 cites W2053154970 @default.
• W3044693911 cites W2064362294 @default.
• W3044693911 cites W2064675550 @default.
• W3044693911 cites W2079735306 @default.
• W3044693911 cites W2101891738 @default.
• W3044693911 cites W2107878631 @default.
• W3044693911 cites W2116446440 @default.
• W3044693911 cites W2123442489 @default.
• W3044693911 cites W2139865360 @default.
• W3044693911 cites W2142786899 @default.
• W3044693911 cites W2150721991 @default.
• W3044693911 cites W2167917621 @default.
• W3044693911 cites W2168041406 @default.
• W3044693911 cites W2338526423 @default.
• W3044693911 cites W2508309896 @default.
• W3044693911 cites W2604972438 @default.
• W3044693911 cites W2915429162 @default.
• W3044693911 cites W2939054980 @default.
• W3044693911 cites W2963441585 @default.
• W3044693911 cites W2963716420 @default.
• W3044693911 cites W2964352358 @default.
• W3044693911 cites W2990505288 @default.
• W3044693911 cites W3099982175 @default.
• W3044693911 cites W3101156210 @default.
• W3044693911 cites W79139011 @default.
• W3044693911 doi "https://doi.org/10.1017/s1351324920000509" @default.
• W3044693911 hasPublicationYear "2020" @default.
• W3044693911 type Work @default.
• W3044693911 sameAs 3044693911 @default.
• W3044693911 citedByCount "17" @default.
• W3044693911 countsByYear W30446939112020 @default.
• W3044693911 countsByYear W30446939112021 @default.
• W3044693911 countsByYear W30446939112022 @default.
• W3044693911 countsByYear W30446939112023 @default.
• W3044693911 crossrefType "journal-article" @default.
• W3044693911 hasAuthorship W3044693911A5004978342 @default.
• W3044693911 hasAuthorship W3044693911A5007623614 @default.
• W3044693911 hasAuthorship W3044693911A5021489611 @default.
• W3044693911 hasAuthorship W3044693911A5031469343 @default.
• W3044693911 hasAuthorship W3044693911A5036399769 @default.
• W3044693911 hasAuthorship W3044693911A5043179000 @default.
• W3044693911 hasAuthorship W3044693911A5073041438 @default.
• W3044693911 hasAuthorship W3044693911A5083770055 @default.
• W3044693911 hasAuthorship W3044693911A5089456652 @default.
• W3044693911 hasBestOaLocation W30446939112 @default.
• W3044693911 hasConcept C119857082 @default.
• W3044693911 hasConcept C154945302 @default.
• W3044693911 hasConcept C195807954 @default.
• W3044693911 hasConcept C199360897 @default.
• W3044693911 hasConcept C204321447 @default.
• W3044693911 hasConcept C2185349 @default.
• W3044693911 hasConcept C23123220 @default.
• W3044693911 hasConcept C2777530160 @default.
• W3044693911 hasConcept C41008148 @default.
• W3044693911 hasConcept C43521106 @default.
• W3044693911 hasConcept C50644808 @default.
• W3044693911 hasConcept C519991488 @default.
• W3044693911 hasConcept C60048249 @default.
• W3044693911 hasConceptScore W3044693911C119857082 @default.
• W3044693911 hasConceptScore W3044693911C154945302 @default.
• W3044693911 hasConceptScore W3044693911C195807954 @default.
• W3044693911 hasConceptScore W3044693911C199360897 @default.
• W3044693911 hasConceptScore W3044693911C204321447 @default.
• W3044693911 hasConceptScore W3044693911C2185349 @default.
• W3044693911 hasConceptScore W3044693911C23123220 @default.
• W3044693911 hasConceptScore W3044693911C2777530160 @default.
• W3044693911 hasConceptScore W3044693911C41008148 @default.
• W3044693911 hasConceptScore W3044693911C43521106 @default.
• W3044693911 hasConceptScore W3044693911C50644808 @default.
• W3044693911 hasConceptScore W3044693911C519991488 @default.
• W3044693911 hasConceptScore W3044693911C60048249 @default.
• W3044693911 hasIssue "2" @default.
• W3044693911 hasLocation W30446939111 @default.
• W3044693911 hasLocation W30446939112 @default.
• W3044693911 hasOpenAccess W3044693911 @default.
• W3044693911 hasPrimaryLocation W30446939111 @default.
• W3044693911 hasRelatedWork W159132833 @default.
• W3044693911 hasRelatedWork W1788528807 @default.
• W3044693911 hasRelatedWork W2020540721 @default.
• W3044693911 hasRelatedWork W2140548485 @default.
• W3044693911 hasRelatedWork W2351555819 @default.
• W3044693911 hasRelatedWork W2375211870 @default.

• next