FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320915294> ?p ?o ?g. }

• W4320915294 abstract "To assess whether transfer learning with a bidirectional encoder representations from transformers (BERT) model, pretrained on a clinical corpus, can perform sentence-level anatomic classification of free-text radiology reports, even for anatomic classes with few positive examples.This retrospective study included radiology reports of patients who underwent whole-body PET/CT imaging from December 2005 to December 2020. Each sentence in these reports (6272 sentences) was labeled by two annotators according to body part (brain, head & neck, chest, abdomen, limbs, spine, or others). The BERT-based transfer learning approach was compared with two baseline machine learning approaches: bidirectional long short-term memory (BiLSTM) and the count-based method. Area under the precision-recall curve (AUPRC) and area under the receiver operating characteristic curve (AUC) were computed for each approach, and AUCs were compared using the DeLong test.The BERT-based approach achieved a macro-averaged AUPRC of 0.88 for classification, outperforming the baselines. AUC results for BERT were significantly higher than those of BiLSTM for all classes and those of the count-based method for the brain, chest, abdomen, and others classes (P values < .025). AUPRC results for BERT were superior to those of baselines even for classes with few labeled training data (brain: BERT, 0.95, BiLSTM, 0.11, count based, 0.41; limbs: BERT, 0.74, BiLSTM, 0.28, count based, 0.46; spine: BERT, 0.82, BiLSTM, 0.53, count based, 0.69).The BERT-based transfer learning approach outperformed the BiLSTM and count-based approaches in sentence-level anatomic classification of free-text radiology reports, even for anatomic classes with few labeled training data.Keywords: Anatomy, Comparative Studies, Technology Assessment, Transfer Learning Supplemental material is available for this article. © RSNA, 2023." @default.
• W4320915294 created "2023-02-16" @default.
• W4320915294 creator A5012224052 @default.
• W4320915294 creator A5013823740 @default.
• W4320915294 creator A5027692193 @default.
• W4320915294 creator A5030896432 @default.
• W4320915294 creator A5034265751 @default.
• W4320915294 creator A5043822670 @default.
• W4320915294 creator A5049641043 @default.
• W4320915294 creator A5070168539 @default.
• W4320915294 date "2023-03-01" @default.
• W4320915294 modified "2023-10-16" @default.
• W4320915294 title "BERT-based Transfer Learning in Sentence-level Anatomic Classification of Free-Text Radiology Reports" @default.
• W4320915294 cites W1504212872 @default.
• W4320915294 cites W1745514781 @default.
• W4320915294 cites W1871067837 @default.
• W4320915294 cites W1976610063 @default.
• W4320915294 cites W1996582212 @default.
• W4320915294 cites W2006617902 @default.
• W4320915294 cites W2046971291 @default.
• W4320915294 cites W2057548436 @default.
• W4320915294 cites W2106419350 @default.
• W4320915294 cites W2114063639 @default.
• W4320915294 cites W2129367118 @default.
• W4320915294 cites W2139054399 @default.
• W4320915294 cites W2144211451 @default.
• W4320915294 cites W2148014577 @default.
• W4320915294 cites W2163670493 @default.
• W4320915294 cites W2342580795 @default.
• W4320915294 cites W2911489562 @default.
• W4320915294 cites W2964669888 @default.
• W4320915294 cites W2978511610 @default.
• W4320915294 cites W3035833355 @default.
• W4320915294 cites W3045332379 @default.
• W4320915294 cites W3138559567 @default.
• W4320915294 cites W3186552329 @default.
• W4320915294 cites W3213545440 @default.
• W4320915294 cites W3215985540 @default.
• W4320915294 doi "https://doi.org/10.1148/ryai.220097" @default.
• W4320915294 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37035437" @default.
• W4320915294 hasPublicationYear "2023" @default.
• W4320915294 type Work @default.
• W4320915294 citedByCount "2" @default.
• W4320915294 countsByYear W43209152942023 @default.
• W4320915294 crossrefType "journal-article" @default.
• W4320915294 hasAuthorship W4320915294A5012224052 @default.
• W4320915294 hasAuthorship W4320915294A5013823740 @default.
• W4320915294 hasAuthorship W4320915294A5027692193 @default.
• W4320915294 hasAuthorship W4320915294A5030896432 @default.
• W4320915294 hasAuthorship W4320915294A5034265751 @default.
• W4320915294 hasAuthorship W4320915294A5043822670 @default.
• W4320915294 hasAuthorship W4320915294A5049641043 @default.
• W4320915294 hasAuthorship W4320915294A5070168539 @default.
• W4320915294 hasBestOaLocation W43209152942 @default.
• W4320915294 hasConcept C108583219 @default.
• W4320915294 hasConcept C126322002 @default.
• W4320915294 hasConcept C126838900 @default.
• W4320915294 hasConcept C150899416 @default.
• W4320915294 hasConcept C154945302 @default.
• W4320915294 hasConcept C204321447 @default.
• W4320915294 hasConcept C2777530160 @default.
• W4320915294 hasConcept C41008148 @default.
• W4320915294 hasConcept C58471807 @default.
• W4320915294 hasConcept C71924100 @default.
• W4320915294 hasConceptScore W4320915294C108583219 @default.
• W4320915294 hasConceptScore W4320915294C126322002 @default.
• W4320915294 hasConceptScore W4320915294C126838900 @default.
• W4320915294 hasConceptScore W4320915294C150899416 @default.
• W4320915294 hasConceptScore W4320915294C154945302 @default.
• W4320915294 hasConceptScore W4320915294C204321447 @default.
• W4320915294 hasConceptScore W4320915294C2777530160 @default.
• W4320915294 hasConceptScore W4320915294C41008148 @default.
• W4320915294 hasConceptScore W4320915294C58471807 @default.
• W4320915294 hasConceptScore W4320915294C71924100 @default.
• W4320915294 hasFunder F4320334764 @default.
• W4320915294 hasIssue "2" @default.
• W4320915294 hasLocation W43209152941 @default.
• W4320915294 hasLocation W43209152942 @default.
• W4320915294 hasLocation W43209152943 @default.
• W4320915294 hasOpenAccess W4320915294 @default.
• W4320915294 hasPrimaryLocation W43209152941 @default.
• W4320915294 hasRelatedWork W2551012455 @default.
• W4320915294 hasRelatedWork W2889705046 @default.
• W4320915294 hasRelatedWork W3018421652 @default.
• W4320915294 hasRelatedWork W3091976719 @default.
• W4320915294 hasRelatedWork W3192840557 @default.
• W4320915294 hasRelatedWork W3195938642 @default.
• W4320915294 hasRelatedWork W4213299466 @default.
• W4320915294 hasRelatedWork W4292874285 @default.
• W4320915294 hasRelatedWork W4312200629 @default.
• W4320915294 hasRelatedWork W4382286161 @default.
• W4320915294 hasVolume "5" @default.
• W4320915294 isParatext "false" @default.
• W4320915294 isRetracted "false" @default.
• W4320915294 workType "article" @default.