Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384382793> ?p ?o ?g. }
- W4384382793 endingPage "102625" @default.
- W4384382793 startingPage "102625" @default.
- W4384382793 abstract "The wide adoption of electronic health records (EHRs) offers immense potential as a source of support for clinical research. However, previous studies focused on extracting only a limited set of medical concepts to support information extraction in the cancer domain for the Spanish language. Building on the success of deep learning for processing natural language texts, this paper proposes a transformer-based approach to extract named entities from breast cancer clinical notes written in Spanish and compares several language models. To facilitate this approach, a schema for annotating clinical notes with breast cancer concepts is presented, and a corpus for breast cancer is developed. Results indicate that both BERT-based and RoBERTa-based language models demonstrate competitive performance in clinical Named Entity Recognition (NER). Specifically, BETO and multilingual BERT achieve F-scores of 93.71% and 94.63%, respectively. Additionally, RoBERTa Biomedical attains an F-score of 95.01%, while RoBERTa BNE achieves an F-score of 94.54%. The findings suggest that transformers can feasibly extract information in the clinical domain in the Spanish language, with the use of models trained on biomedical texts contributing to enhanced results. The proposed approach takes advantage of transfer learning techniques by fine-tuning language models to automatically represent text features and avoiding the time-consuming feature engineering process." @default.
- W4384382793 created "2023-07-15" @default.
- W4384382793 creator A5008927068 @default.
- W4384382793 creator A5023776074 @default.
- W4384382793 creator A5048944936 @default.
- W4384382793 creator A5055766625 @default.
- W4384382793 creator A5085499011 @default.
- W4384382793 creator A5089110514 @default.
- W4384382793 creator A5089559663 @default.
- W4384382793 date "2023-09-01" @default.
- W4384382793 modified "2023-09-30" @default.
- W4384382793 title "Transformers for extracting breast cancer information from Spanish clinical narratives" @default.
- W4384382793 cites W1922167300 @default.
- W4384382793 cites W1984910136 @default.
- W4384382793 cites W2025100889 @default.
- W4384382793 cites W2087347434 @default.
- W4384382793 cites W2125117006 @default.
- W4384382793 cites W2145522203 @default.
- W4384382793 cites W2197312909 @default.
- W4384382793 cites W2236169403 @default.
- W4384382793 cites W2260982265 @default.
- W4384382793 cites W2262790950 @default.
- W4384382793 cites W2345195116 @default.
- W4384382793 cites W2531939526 @default.
- W4384382793 cites W2586254558 @default.
- W4384382793 cites W2594685110 @default.
- W4384382793 cites W2783114168 @default.
- W4384382793 cites W2787969497 @default.
- W4384382793 cites W2805211535 @default.
- W4384382793 cites W2808129629 @default.
- W4384382793 cites W2897687848 @default.
- W4384382793 cites W2927032858 @default.
- W4384382793 cites W2966232305 @default.
- W4384382793 cites W2997394673 @default.
- W4384382793 cites W3001466087 @default.
- W4384382793 cites W3047190783 @default.
- W4384382793 cites W3048179169 @default.
- W4384382793 cites W3094215866 @default.
- W4384382793 cites W3102144021 @default.
- W4384382793 cites W3118721495 @default.
- W4384382793 cites W3156308192 @default.
- W4384382793 cites W3156333129 @default.
- W4384382793 cites W4224299761 @default.
- W4384382793 cites W4292560523 @default.
- W4384382793 cites W79139011 @default.
- W4384382793 doi "https://doi.org/10.1016/j.artmed.2023.102625" @default.
- W4384382793 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37673566" @default.
- W4384382793 hasPublicationYear "2023" @default.
- W4384382793 type Work @default.
- W4384382793 citedByCount "0" @default.
- W4384382793 crossrefType "journal-article" @default.
- W4384382793 hasAuthorship W4384382793A5008927068 @default.
- W4384382793 hasAuthorship W4384382793A5023776074 @default.
- W4384382793 hasAuthorship W4384382793A5048944936 @default.
- W4384382793 hasAuthorship W4384382793A5055766625 @default.
- W4384382793 hasAuthorship W4384382793A5085499011 @default.
- W4384382793 hasAuthorship W4384382793A5089110514 @default.
- W4384382793 hasAuthorship W4384382793A5089559663 @default.
- W4384382793 hasBestOaLocation W43843827931 @default.
- W4384382793 hasConcept C119857082 @default.
- W4384382793 hasConcept C121332964 @default.
- W4384382793 hasConcept C121608353 @default.
- W4384382793 hasConcept C126322002 @default.
- W4384382793 hasConcept C137293760 @default.
- W4384382793 hasConcept C138885662 @default.
- W4384382793 hasConcept C154945302 @default.
- W4384382793 hasConcept C162324750 @default.
- W4384382793 hasConcept C165801399 @default.
- W4384382793 hasConcept C187736073 @default.
- W4384382793 hasConcept C195324797 @default.
- W4384382793 hasConcept C195807954 @default.
- W4384382793 hasConcept C199033989 @default.
- W4384382793 hasConcept C204321447 @default.
- W4384382793 hasConcept C23123220 @default.
- W4384382793 hasConcept C2779135771 @default.
- W4384382793 hasConcept C2780451532 @default.
- W4384382793 hasConcept C41008148 @default.
- W4384382793 hasConcept C41895202 @default.
- W4384382793 hasConcept C52146309 @default.
- W4384382793 hasConcept C530470458 @default.
- W4384382793 hasConcept C62520636 @default.
- W4384382793 hasConcept C66322947 @default.
- W4384382793 hasConcept C71924100 @default.
- W4384382793 hasConceptScore W4384382793C119857082 @default.
- W4384382793 hasConceptScore W4384382793C121332964 @default.
- W4384382793 hasConceptScore W4384382793C121608353 @default.
- W4384382793 hasConceptScore W4384382793C126322002 @default.
- W4384382793 hasConceptScore W4384382793C137293760 @default.
- W4384382793 hasConceptScore W4384382793C138885662 @default.
- W4384382793 hasConceptScore W4384382793C154945302 @default.
- W4384382793 hasConceptScore W4384382793C162324750 @default.
- W4384382793 hasConceptScore W4384382793C165801399 @default.
- W4384382793 hasConceptScore W4384382793C187736073 @default.
- W4384382793 hasConceptScore W4384382793C195324797 @default.
- W4384382793 hasConceptScore W4384382793C195807954 @default.
- W4384382793 hasConceptScore W4384382793C199033989 @default.
- W4384382793 hasConceptScore W4384382793C204321447 @default.
- W4384382793 hasConceptScore W4384382793C23123220 @default.