Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202269712> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3202269712 endingPage "2669" @default.
- W3202269712 startingPage "2661" @default.
- W3202269712 abstract "Neural network deidentification studies have focused on individual datasets. These studies assume the availability of a sufficient amount of human-annotated data to train models that can generalize to corresponding test data. In real-world situations, however, researchers often have limited or no in-house training data. Existing systems and external data can help jump-start deidentification on in-house data; however, the most efficient way of utilizing existing systems and external data is unclear. This article investigates the transferability of a state-of-the-art neural clinical deidentification system, NeuroNER, across a variety of datasets, when it is modified architecturally for domain generalization and when it is trained strategically for domain transfer.We conducted a comparative study of the transferability of NeuroNER using 4 clinical note corpora with multiple note types from 2 institutions. We modified NeuroNER architecturally to integrate 2 types of domain generalization approaches. We evaluated each architecture using 3 training strategies. We measured transferability from external sources; transferability across note types; the contribution of external source data when in-domain training data are available; and transferability across institutions.Transferability from a single external source gave inconsistent results. Using additional external sources consistently yielded an F1-score of approximately 80%. Fine-tuning emerged as a dominant transfer strategy, with or without domain generalization. We also found that external sources were useful even in cases where in-domain training data were available. Transferability across institutions differed by note type and annotation label but resulted in improved performance." @default.
- W3202269712 created "2021-10-11" @default.
- W3202269712 creator A5002548520 @default.
- W3202269712 creator A5021769068 @default.
- W3202269712 creator A5043896692 @default.
- W3202269712 creator A5070926324 @default.
- W3202269712 creator A5083901654 @default.
- W3202269712 date "2021-09-29" @default.
- W3202269712 modified "2023-10-10" @default.
- W3202269712 title "Transferability of neural network clinical deidentification systems" @default.
- W3202269712 cites W1034374084 @default.
- W3202269712 cites W1262131959 @default.
- W3202269712 cites W1685527554 @default.
- W3202269712 cites W1791866474 @default.
- W3202269712 cites W2015620729 @default.
- W3202269712 cites W2128004504 @default.
- W3202269712 cites W2156061936 @default.
- W3202269712 cites W2160987310 @default.
- W3202269712 cites W2250539671 @default.
- W3202269712 cites W2425617182 @default.
- W3202269712 cites W2619585391 @default.
- W3202269712 cites W2621075239 @default.
- W3202269712 cites W2622474949 @default.
- W3202269712 cites W2624380710 @default.
- W3202269712 cites W2772121968 @default.
- W3202269712 cites W2787267295 @default.
- W3202269712 cites W2963956191 @default.
- W3202269712 doi "https://doi.org/10.1093/jamia/ocab207" @default.
- W3202269712 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8633667" @default.
- W3202269712 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34586386" @default.
- W3202269712 hasPublicationYear "2021" @default.
- W3202269712 type Work @default.
- W3202269712 sameAs 3202269712 @default.
- W3202269712 citedByCount "2" @default.
- W3202269712 countsByYear W32022697122023 @default.
- W3202269712 crossrefType "journal-article" @default.
- W3202269712 hasAuthorship W3202269712A5002548520 @default.
- W3202269712 hasAuthorship W3202269712A5021769068 @default.
- W3202269712 hasAuthorship W3202269712A5043896692 @default.
- W3202269712 hasAuthorship W3202269712A5070926324 @default.
- W3202269712 hasAuthorship W3202269712A5083901654 @default.
- W3202269712 hasBestOaLocation W32022697122 @default.
- W3202269712 hasConcept C119857082 @default.
- W3202269712 hasConcept C124101348 @default.
- W3202269712 hasConcept C134306372 @default.
- W3202269712 hasConcept C136197465 @default.
- W3202269712 hasConcept C140331021 @default.
- W3202269712 hasConcept C150899416 @default.
- W3202269712 hasConcept C154945302 @default.
- W3202269712 hasConcept C177148314 @default.
- W3202269712 hasConcept C2522767166 @default.
- W3202269712 hasConcept C33923547 @default.
- W3202269712 hasConcept C36503486 @default.
- W3202269712 hasConcept C41008148 @default.
- W3202269712 hasConcept C50644808 @default.
- W3202269712 hasConcept C51632099 @default.
- W3202269712 hasConcept C61272859 @default.
- W3202269712 hasConceptScore W3202269712C119857082 @default.
- W3202269712 hasConceptScore W3202269712C124101348 @default.
- W3202269712 hasConceptScore W3202269712C134306372 @default.
- W3202269712 hasConceptScore W3202269712C136197465 @default.
- W3202269712 hasConceptScore W3202269712C140331021 @default.
- W3202269712 hasConceptScore W3202269712C150899416 @default.
- W3202269712 hasConceptScore W3202269712C154945302 @default.
- W3202269712 hasConceptScore W3202269712C177148314 @default.
- W3202269712 hasConceptScore W3202269712C2522767166 @default.
- W3202269712 hasConceptScore W3202269712C33923547 @default.
- W3202269712 hasConceptScore W3202269712C36503486 @default.
- W3202269712 hasConceptScore W3202269712C41008148 @default.
- W3202269712 hasConceptScore W3202269712C50644808 @default.
- W3202269712 hasConceptScore W3202269712C51632099 @default.
- W3202269712 hasConceptScore W3202269712C61272859 @default.
- W3202269712 hasFunder F4320337372 @default.
- W3202269712 hasIssue "12" @default.
- W3202269712 hasLocation W32022697121 @default.
- W3202269712 hasLocation W32022697122 @default.
- W3202269712 hasLocation W32022697123 @default.
- W3202269712 hasLocation W32022697124 @default.
- W3202269712 hasOpenAccess W3202269712 @default.
- W3202269712 hasPrimaryLocation W32022697121 @default.
- W3202269712 hasRelatedWork W3174891612 @default.
- W3202269712 hasRelatedWork W3176808018 @default.
- W3202269712 hasRelatedWork W3201453156 @default.
- W3202269712 hasRelatedWork W3202269712 @default.
- W3202269712 hasRelatedWork W3214552351 @default.
- W3202269712 hasRelatedWork W4221138378 @default.
- W3202269712 hasRelatedWork W4287116584 @default.
- W3202269712 hasRelatedWork W4287162726 @default.
- W3202269712 hasRelatedWork W4312665716 @default.
- W3202269712 hasRelatedWork W4313050734 @default.
- W3202269712 hasVolume "28" @default.
- W3202269712 isParatext "false" @default.
- W3202269712 isRetracted "false" @default.
- W3202269712 magId "3202269712" @default.
- W3202269712 workType "article" @default.