Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100221118> ?p ?o ?g. }
- W3100221118 endingPage "e19689" @default.
- W3100221118 startingPage "e19689" @default.
- W3100221118 abstract "Background Liver cancer is a substantial disease burden in China. As one of the primary diagnostic tools for detecting liver cancer, dynamic contrast-enhanced computed tomography provides detailed evidences for diagnosis that are recorded in free-text radiology reports. Objective The aim of our study was to apply a deep learning model and rule-based natural language processing (NLP) method to identify evidences for liver cancer diagnosis automatically. Methods We proposed a pretrained, fine-tuned BERT (Bidirectional Encoder Representations from Transformers)-based BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Field) model to recognize the phrases of APHE (hyperintense enhancement in the arterial phase) and PDPH (hypointense in the portal and delayed phases). To identify more essential diagnostic evidences, we used the traditional rule-based NLP methods for the extraction of radiological features. APHE, PDPH, and other extracted radiological features were used to design a computer-aided liver cancer diagnosis framework by random forest. Results The BERT-BiLSTM-CRF predicted the phrases of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using APHE and PDPH (84.88%) or other extracted radiological features (83.52%). APHE and PDPH were the top 2 essential features for liver cancer diagnosis. Conclusions This work was a comprehensive NLP study, wherein we identified evidences for the diagnosis of liver cancer from Chinese radiology reports, considering both clinical knowledge and radiology findings. The BERT-based deep learning method for the extraction of diagnostic evidence achieved state-of-the-art performance. The high performance proves the feasibility of the BERT-BiLSTM-CRF model in information extraction from Chinese radiology reports. The findings of our study suggest that the deep learning–based method for automatically identifying evidences for diagnosis can be extended to other types of Chinese clinical texts." @default.
- W3100221118 created "2020-11-23" @default.
- W3100221118 creator A5011702824 @default.
- W3100221118 creator A5013578258 @default.
- W3100221118 creator A5018805094 @default.
- W3100221118 creator A5056416945 @default.
- W3100221118 creator A5060832996 @default.
- W3100221118 creator A5066074514 @default.
- W3100221118 creator A5070749037 @default.
- W3100221118 creator A5078825783 @default.
- W3100221118 date "2021-01-12" @default.
- W3100221118 modified "2023-10-11" @default.
- W3100221118 title "Use of BERT (Bidirectional Encoder Representations from Transformers)-Based Deep Learning Method for Extracting Evidences in Chinese Radiology Reports: Development of a Computer-Aided Liver Cancer Diagnosis Framework" @default.
- W3100221118 cites W2056902052 @default.
- W3100221118 cites W2139054399 @default.
- W3100221118 cites W2250539671 @default.
- W3100221118 cites W2329011065 @default.
- W3100221118 cites W2558253459 @default.
- W3100221118 cites W2563364981 @default.
- W3100221118 cites W2750288184 @default.
- W3100221118 cites W2768488789 @default.
- W3100221118 cites W2897360548 @default.
- W3100221118 cites W2909707119 @default.
- W3100221118 cites W2911462778 @default.
- W3100221118 cites W2917157846 @default.
- W3100221118 cites W2943444949 @default.
- W3100221118 cites W2946766957 @default.
- W3100221118 cites W2952100895 @default.
- W3100221118 cites W2953196299 @default.
- W3100221118 cites W2963341956 @default.
- W3100221118 cites W2963571188 @default.
- W3100221118 cites W2966351171 @default.
- W3100221118 cites W2969542839 @default.
- W3100221118 cites W2978511610 @default.
- W3100221118 cites W2993873509 @default.
- W3100221118 cites W3007060302 @default.
- W3100221118 cites W3009459039 @default.
- W3100221118 cites W3023321484 @default.
- W3100221118 doi "https://doi.org/10.2196/19689" @default.
- W3100221118 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7837998" @default.
- W3100221118 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33433395" @default.
- W3100221118 hasPublicationYear "2021" @default.
- W3100221118 type Work @default.
- W3100221118 sameAs 3100221118 @default.
- W3100221118 citedByCount "29" @default.
- W3100221118 countsByYear W31002211182021 @default.
- W3100221118 countsByYear W31002211182022 @default.
- W3100221118 countsByYear W31002211182023 @default.
- W3100221118 crossrefType "journal-article" @default.
- W3100221118 hasAuthorship W3100221118A5011702824 @default.
- W3100221118 hasAuthorship W3100221118A5013578258 @default.
- W3100221118 hasAuthorship W3100221118A5018805094 @default.
- W3100221118 hasAuthorship W3100221118A5056416945 @default.
- W3100221118 hasAuthorship W3100221118A5060832996 @default.
- W3100221118 hasAuthorship W3100221118A5066074514 @default.
- W3100221118 hasAuthorship W3100221118A5070749037 @default.
- W3100221118 hasAuthorship W3100221118A5078825783 @default.
- W3100221118 hasBestOaLocation W31002211181 @default.
- W3100221118 hasConcept C108583219 @default.
- W3100221118 hasConcept C111919701 @default.
- W3100221118 hasConcept C118505674 @default.
- W3100221118 hasConcept C119857082 @default.
- W3100221118 hasConcept C121608353 @default.
- W3100221118 hasConcept C126322002 @default.
- W3100221118 hasConcept C126838900 @default.
- W3100221118 hasConcept C148524875 @default.
- W3100221118 hasConcept C152565575 @default.
- W3100221118 hasConcept C154945302 @default.
- W3100221118 hasConcept C169258074 @default.
- W3100221118 hasConcept C2776231280 @default.
- W3100221118 hasConcept C2776304256 @default.
- W3100221118 hasConcept C41008148 @default.
- W3100221118 hasConcept C71924100 @default.
- W3100221118 hasConceptScore W3100221118C108583219 @default.
- W3100221118 hasConceptScore W3100221118C111919701 @default.
- W3100221118 hasConceptScore W3100221118C118505674 @default.
- W3100221118 hasConceptScore W3100221118C119857082 @default.
- W3100221118 hasConceptScore W3100221118C121608353 @default.
- W3100221118 hasConceptScore W3100221118C126322002 @default.
- W3100221118 hasConceptScore W3100221118C126838900 @default.
- W3100221118 hasConceptScore W3100221118C148524875 @default.
- W3100221118 hasConceptScore W3100221118C152565575 @default.
- W3100221118 hasConceptScore W3100221118C154945302 @default.
- W3100221118 hasConceptScore W3100221118C169258074 @default.
- W3100221118 hasConceptScore W3100221118C2776231280 @default.
- W3100221118 hasConceptScore W3100221118C2776304256 @default.
- W3100221118 hasConceptScore W3100221118C41008148 @default.
- W3100221118 hasConceptScore W3100221118C71924100 @default.
- W3100221118 hasIssue "1" @default.
- W3100221118 hasLocation W31002211181 @default.
- W3100221118 hasLocation W31002211182 @default.
- W3100221118 hasOpenAccess W3100221118 @default.
- W3100221118 hasPrimaryLocation W31002211181 @default.
- W3100221118 hasRelatedWork W2947903144 @default.
- W3100221118 hasRelatedWork W2968586400 @default.
- W3100221118 hasRelatedWork W3100221118 @default.
- W3100221118 hasRelatedWork W3211546796 @default.
- W3100221118 hasRelatedWork W4223564025 @default.