Matches in SemOpenAlex for { <https://semopenalex.org/work/W4231752746> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4231752746 abstract "<sec> <title>BACKGROUND</title> Deidentification of clinical records is a critical step before their publication. This is usually treated as a type of sequence labeling task, and ensemble learning is one of the best performing solutions. Under the framework of multi-learner ensemble, the significance of a candidate rule-based learner remains an open issue. </sec> <sec> <title>OBJECTIVE</title> The aim of this study is to investigate whether a rule-based learner is useful in a hybrid deidentification system and offer suggestions on how to build and integrate a rule-based learner. </sec> <sec> <title>METHODS</title> We chose a data-driven rule-learner named transformation-based error-driven learning (TBED) and integrated it into the best performing hybrid system in this task. </sec> <sec> <title>RESULTS</title> On the popular Informatics for Integrating Biology and the Bedside (i2b2) deidentification data set, experiments showed that TBED can offer high performance with its generated rules, and integrating the rule-based model into an ensemble framework, which reached an F1 score of 96.76%, achieved the best performance reported in the community. </sec> <sec> <title>CONCLUSIONS</title> We proved the rule-based method offers an effective contribution to the current ensemble learning approach for the deidentification of clinical records. Such a rule system could be automatically learned by TBED, avoiding the high cost and low reliability of manual rule composition. In particular, we boosted the ensemble model with rules to create the best performance of the deidentification of clinical records. </sec>" @default.
- W4231752746 created "2022-05-12" @default.
- W4231752746 creator A5013444954 @default.
- W4231752746 creator A5014238603 @default.
- W4231752746 creator A5032806825 @default.
- W4231752746 creator A5038560914 @default.
- W4231752746 date "2019-12-30" @default.
- W4231752746 modified "2023-09-29" @default.
- W4231752746 title "Re-examination of Rule-Based Methods in Deidentification of Electronic Health Records: Algorithm Development and Validation (Preprint)" @default.
- W4231752746 cites W1034374084 @default.
- W4231752746 cites W2111063183 @default.
- W4231752746 cites W2123442489 @default.
- W4231752746 cites W2133362931 @default.
- W4231752746 cites W2140663467 @default.
- W4231752746 cites W2153635508 @default.
- W4231752746 cites W2160987310 @default.
- W4231752746 cites W2183114698 @default.
- W4231752746 cites W2190333735 @default.
- W4231752746 cites W2610743175 @default.
- W4231752746 cites W2621075239 @default.
- W4231752746 cites W2622474949 @default.
- W4231752746 cites W2623375817 @default.
- W4231752746 cites W2767419415 @default.
- W4231752746 cites W28412257 @default.
- W4231752746 cites W2951820126 @default.
- W4231752746 cites W2962902328 @default.
- W4231752746 cites W2963956191 @default.
- W4231752746 cites W2972578755 @default.
- W4231752746 cites W3103594582 @default.
- W4231752746 cites W4252608096 @default.
- W4231752746 cites W2250822364 @default.
- W4231752746 doi "https://doi.org/10.2196/preprints.17622" @default.
- W4231752746 hasPublicationYear "2019" @default.
- W4231752746 type Work @default.
- W4231752746 citedByCount "0" @default.
- W4231752746 crossrefType "posted-content" @default.
- W4231752746 hasAuthorship W4231752746A5013444954 @default.
- W4231752746 hasAuthorship W4231752746A5014238603 @default.
- W4231752746 hasAuthorship W4231752746A5032806825 @default.
- W4231752746 hasAuthorship W4231752746A5038560914 @default.
- W4231752746 hasBestOaLocation W42317527462 @default.
- W4231752746 hasConcept C11413529 @default.
- W4231752746 hasConcept C119857082 @default.
- W4231752746 hasConcept C124101348 @default.
- W4231752746 hasConcept C127413603 @default.
- W4231752746 hasConcept C136764020 @default.
- W4231752746 hasConcept C148524875 @default.
- W4231752746 hasConcept C149271511 @default.
- W4231752746 hasConcept C154945302 @default.
- W4231752746 hasConcept C160735492 @default.
- W4231752746 hasConcept C162324750 @default.
- W4231752746 hasConcept C177264268 @default.
- W4231752746 hasConcept C199360897 @default.
- W4231752746 hasConcept C201995342 @default.
- W4231752746 hasConcept C23123220 @default.
- W4231752746 hasConcept C2780451532 @default.
- W4231752746 hasConcept C3019952477 @default.
- W4231752746 hasConcept C41008148 @default.
- W4231752746 hasConcept C43169469 @default.
- W4231752746 hasConcept C45942800 @default.
- W4231752746 hasConcept C50522688 @default.
- W4231752746 hasConceptScore W4231752746C11413529 @default.
- W4231752746 hasConceptScore W4231752746C119857082 @default.
- W4231752746 hasConceptScore W4231752746C124101348 @default.
- W4231752746 hasConceptScore W4231752746C127413603 @default.
- W4231752746 hasConceptScore W4231752746C136764020 @default.
- W4231752746 hasConceptScore W4231752746C148524875 @default.
- W4231752746 hasConceptScore W4231752746C149271511 @default.
- W4231752746 hasConceptScore W4231752746C154945302 @default.
- W4231752746 hasConceptScore W4231752746C160735492 @default.
- W4231752746 hasConceptScore W4231752746C162324750 @default.
- W4231752746 hasConceptScore W4231752746C177264268 @default.
- W4231752746 hasConceptScore W4231752746C199360897 @default.
- W4231752746 hasConceptScore W4231752746C201995342 @default.
- W4231752746 hasConceptScore W4231752746C23123220 @default.
- W4231752746 hasConceptScore W4231752746C2780451532 @default.
- W4231752746 hasConceptScore W4231752746C3019952477 @default.
- W4231752746 hasConceptScore W4231752746C41008148 @default.
- W4231752746 hasConceptScore W4231752746C43169469 @default.
- W4231752746 hasConceptScore W4231752746C45942800 @default.
- W4231752746 hasConceptScore W4231752746C50522688 @default.
- W4231752746 hasLocation W42317527461 @default.
- W4231752746 hasLocation W42317527462 @default.
- W4231752746 hasOpenAccess W4231752746 @default.
- W4231752746 hasPrimaryLocation W42317527461 @default.
- W4231752746 hasRelatedWork W11244355 @default.
- W4231752746 hasRelatedWork W11991885 @default.
- W4231752746 hasRelatedWork W13978995 @default.
- W4231752746 hasRelatedWork W14854443 @default.
- W4231752746 hasRelatedWork W193554 @default.
- W4231752746 hasRelatedWork W2804300 @default.
- W4231752746 hasRelatedWork W5447123 @default.
- W4231752746 hasRelatedWork W6264993 @default.
- W4231752746 hasRelatedWork W8432713 @default.
- W4231752746 hasRelatedWork W881173 @default.
- W4231752746 isParatext "false" @default.
- W4231752746 isRetracted "false" @default.
- W4231752746 workType "article" @default.