Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327582012> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4327582012 abstract "Abstract Background : De-identification of clinical notes is essential to utilize the rich information in unstructured text data in medical research. However, only limited work has been done in removing personal information from clinical notes in Korea. Objective : In this study, we aimed to perform de-identifying of radiology reports in Seoul National University, Bundang Hospital, a tertiary university hospital in South Korea. Methods : We used two de-identification strategies to improve performance with limited and few annotated data. First, a rule-based approach is used to construct regular expressions on the 1,112 notes annotated by domain experts. Second, by using the regular expressions as label-er, we applied a semi-supervised approach to fine-tune a pre-trained Korean BERT model with pseudo-labeled notes. Results : Our rule-based approach achieved 97.2% precision, 93.7% recall, and 96.2% F1 score from the department of radiology notes. For machine learning approach,KoBERT-NER that is fine-tuned with 32,000 automatically pseudo-labeled notes achieved 96.5% precision, 97.6% recall, and 97.1% F1 score. Conclusion : By combining a rule-based approach and machine learning in a semi-supervised way, our results show that the performance of de-identification can be improved." @default.
- W4327582012 created "2023-03-17" @default.
- W4327582012 creator A5004841618 @default.
- W4327582012 creator A5015725420 @default.
- W4327582012 creator A5038598245 @default.
- W4327582012 creator A5049355350 @default.
- W4327582012 creator A5058961028 @default.
- W4327582012 creator A5068195598 @default.
- W4327582012 date "2023-03-16" @default.
- W4327582012 modified "2023-09-26" @default.
- W4327582012 title "De-Identification of Clinical Notes with Pseudo-labeling using Regular Expression Rules and Pre-trained BERT" @default.
- W4327582012 cites W2012326946 @default.
- W4327582012 cites W2068402150 @default.
- W4327582012 cites W2105578014 @default.
- W4327582012 cites W2160987310 @default.
- W4327582012 cites W2396881363 @default.
- W4327582012 cites W2911489562 @default.
- W4327582012 cites W3017330637 @default.
- W4327582012 doi "https://doi.org/10.21203/rs.3.rs-2672115/v1" @default.
- W4327582012 hasPublicationYear "2023" @default.
- W4327582012 type Work @default.
- W4327582012 citedByCount "0" @default.
- W4327582012 crossrefType "posted-content" @default.
- W4327582012 hasAuthorship W4327582012A5004841618 @default.
- W4327582012 hasAuthorship W4327582012A5015725420 @default.
- W4327582012 hasAuthorship W4327582012A5038598245 @default.
- W4327582012 hasAuthorship W4327582012A5049355350 @default.
- W4327582012 hasAuthorship W4327582012A5058961028 @default.
- W4327582012 hasAuthorship W4327582012A5068195598 @default.
- W4327582012 hasBestOaLocation W43275820121 @default.
- W4327582012 hasConcept C100660578 @default.
- W4327582012 hasConcept C116834253 @default.
- W4327582012 hasConcept C119857082 @default.
- W4327582012 hasConcept C134306372 @default.
- W4327582012 hasConcept C148524875 @default.
- W4327582012 hasConcept C154945302 @default.
- W4327582012 hasConcept C15744967 @default.
- W4327582012 hasConcept C162324750 @default.
- W4327582012 hasConcept C180747234 @default.
- W4327582012 hasConcept C187736073 @default.
- W4327582012 hasConcept C199360897 @default.
- W4327582012 hasConcept C204321447 @default.
- W4327582012 hasConcept C23123220 @default.
- W4327582012 hasConcept C2779135771 @default.
- W4327582012 hasConcept C2780451532 @default.
- W4327582012 hasConcept C2780801425 @default.
- W4327582012 hasConcept C33923547 @default.
- W4327582012 hasConcept C36503486 @default.
- W4327582012 hasConcept C41008148 @default.
- W4327582012 hasConcept C59822182 @default.
- W4327582012 hasConcept C81669768 @default.
- W4327582012 hasConcept C86803240 @default.
- W4327582012 hasConceptScore W4327582012C100660578 @default.
- W4327582012 hasConceptScore W4327582012C116834253 @default.
- W4327582012 hasConceptScore W4327582012C119857082 @default.
- W4327582012 hasConceptScore W4327582012C134306372 @default.
- W4327582012 hasConceptScore W4327582012C148524875 @default.
- W4327582012 hasConceptScore W4327582012C154945302 @default.
- W4327582012 hasConceptScore W4327582012C15744967 @default.
- W4327582012 hasConceptScore W4327582012C162324750 @default.
- W4327582012 hasConceptScore W4327582012C180747234 @default.
- W4327582012 hasConceptScore W4327582012C187736073 @default.
- W4327582012 hasConceptScore W4327582012C199360897 @default.
- W4327582012 hasConceptScore W4327582012C204321447 @default.
- W4327582012 hasConceptScore W4327582012C23123220 @default.
- W4327582012 hasConceptScore W4327582012C2779135771 @default.
- W4327582012 hasConceptScore W4327582012C2780451532 @default.
- W4327582012 hasConceptScore W4327582012C2780801425 @default.
- W4327582012 hasConceptScore W4327582012C33923547 @default.
- W4327582012 hasConceptScore W4327582012C36503486 @default.
- W4327582012 hasConceptScore W4327582012C41008148 @default.
- W4327582012 hasConceptScore W4327582012C59822182 @default.
- W4327582012 hasConceptScore W4327582012C81669768 @default.
- W4327582012 hasConceptScore W4327582012C86803240 @default.
- W4327582012 hasLocation W43275820121 @default.
- W4327582012 hasOpenAccess W4327582012 @default.
- W4327582012 hasPrimaryLocation W43275820121 @default.
- W4327582012 hasRelatedWork W147166030 @default.
- W4327582012 hasRelatedWork W2114945967 @default.
- W4327582012 hasRelatedWork W2947903144 @default.
- W4327582012 hasRelatedWork W2995950854 @default.
- W4327582012 hasRelatedWork W3026298482 @default.
- W4327582012 hasRelatedWork W3096378489 @default.
- W4327582012 hasRelatedWork W3136886378 @default.
- W4327582012 hasRelatedWork W3154941836 @default.
- W4327582012 hasRelatedWork W3164477379 @default.
- W4327582012 hasRelatedWork W3217585508 @default.
- W4327582012 isParatext "false" @default.
- W4327582012 isRetracted "false" @default.
- W4327582012 workType "article" @default.