FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310763014> ?p ?o ?g. }

• W4310763014 abstract "<sec> <title>BACKGROUND</title> Clinical electronic medical records (EMRs) contain important information on patients’ anatomy, symptoms, examinations, diagnoses, and medications. Large-scale mining of rich medical information from EMRs will provide notable reference value for medical research. With the complexity of Chinese grammar and blurred boundaries of Chinese words, Chinese clinical named entity recognition (CNER) remains a notable challenge. Follow-up tasks such as medical entity structuring, medical entity standardization, medical entity relationship extraction, and medical knowledge graph construction largely depend on medical named entity recognition effects. A promising CNER result would provide reliable support for building domain knowledge graphs, knowledge bases, and knowledge retrieval systems. Furthermore, it would provide research ideas for scientists and medical decision-making references for doctors and even guide patients on disease and health management. Therefore, obtaining excellent CNER results is essential. </sec> <sec> <title>OBJECTIVE</title> We aimed to propose a Chinese CNER method to learn semantics-enriched representations for comprehensively enhancing machines to understand deep semantic information of EMRs by using multisemantic features, which makes medical information more readable and understandable. </sec> <sec> <title>METHODS</title> First, we used Robustly Optimized Bidirectional Encoder Representation from Transformers Pretraining Approach Whole Word Masking (RoBERTa-wwm) with dynamic fusion and Chinese character features, including 5-stroke code, Zheng code, phonological code, and stroke code, extracted by 1-dimensional convolutional neural networks (CNNs) to obtain fine-grained semantic features of Chinese characters. Subsequently, we converted Chinese characters into square images to obtain Chinese character image features from another modality by using a 2-dimensional CNN. Finally, we input multisemantic features into Bidirectional Long Short-Term Memory with Conditional Random Fields to achieve Chinese CNER. The effectiveness of our model was compared with that of the baseline and existing research models, and the features involved in the model were ablated and analyzed to verify the model’s effectiveness. </sec> <sec> <title>RESULTS</title> We collected 1379 Yidu-S4K EMRs containing 23,655 entities in 6 categories and 2007 self-annotated EMRs containing 118,643 entities in 7 categories. The experiments showed that our model outperformed the comparison experiments, with <i>F</i>₁-scores of 89.28% and 84.61% on the Yidu-S4K and self-annotated data sets, respectively. The results of the ablation analysis demonstrated that each feature and method we used could improve the entity recognition ability. </sec> <sec> <title>CONCLUSIONS</title> Our proposed CNER method would mine the richer deep semantic information in EMRs by multisemantic embedding using RoBERTa-wwm and CNNs, enhancing the semantic recognition of characters at different granularity levels and improving the generalization capability of the method by achieving information complementarity among different semantic features, thus making the machine semantically understand EMRs and improving the CNER task accuracy. </sec>" @default.
• W4310763014 created "2022-12-17" @default.
• W4310763014 creator A5022968974 @default.
• W4310763014 creator A5026734857 @default.
• W4310763014 creator A5041208413 @default.
• W4310763014 creator A5051832001 @default.
• W4310763014 creator A5081062143 @default.
• W4310763014 date "2022-12-01" @default.
• W4310763014 modified "2023-10-17" @default.
• W4310763014 title "Chinese Clinical Named Entity Recognition in Electronic Medical Records: Using Multimodal Features With the Help of RoBERTa-wwm and CNN (Preprint)" @default.
• W4310763014 cites W1724588178 @default.
• W4310763014 cites W1981797826 @default.
• W4310763014 cites W1991983805 @default.
• W4310763014 cites W1993126589 @default.
• W4310763014 cites W2015079391 @default.
• W4310763014 cites W2076063813 @default.
• W4310763014 cites W2109711517 @default.
• W4310763014 cites W2114388055 @default.
• W4310763014 cites W2123512824 @default.
• W4310763014 cites W2128535227 @default.
• W4310763014 cites W2134429551 @default.
• W4310763014 cites W2159640576 @default.
• W4310763014 cites W2251131401 @default.
• W4310763014 cites W2402268235 @default.
• W4310763014 cites W2559281960 @default.
• W4310763014 cites W2590462354 @default.
• W4310763014 cites W2613831280 @default.
• W4310763014 cites W2752861104 @default.
• W4310763014 cites W2765816034 @default.
• W4310763014 cites W2888555238 @default.
• W4310763014 cites W2892525833 @default.
• W4310763014 cites W2905315292 @default.
• W4310763014 cites W2911489562 @default.
• W4310763014 cites W2912102336 @default.
• W4310763014 cites W2945018970 @default.
• W4310763014 cites W2948614377 @default.
• W4310763014 cites W2948947170 @default.
• W4310763014 cites W2949240244 @default.
• W4310763014 cites W2950021574 @default.
• W4310763014 cites W2955483668 @default.
• W4310763014 cites W2962739339 @default.
• W4310763014 cites W2963571188 @default.
• W4310763014 cites W2973965787 @default.
• W4310763014 cites W2974256357 @default.
• W4310763014 cites W2996350961 @default.
• W4310763014 cites W2997170098 @default.
• W4310763014 cites W3022975064 @default.
• W4310763014 cites W3023016026 @default.
• W4310763014 cites W3046929991 @default.
• W4310763014 cites W3064526859 @default.
• W4310763014 cites W3090138008 @default.
• W4310763014 cites W3091382176 @default.
• W4310763014 cites W3138408498 @default.
• W4310763014 cites W3199935730 @default.
• W4310763014 cites W3210120707 @default.
• W4310763014 doi "https://doi.org/10.2196/preprints.44597" @default.
• W4310763014 hasPublicationYear "2022" @default.
• W4310763014 type Work @default.
• W4310763014 citedByCount "0" @default.
• W4310763014 crossrefType "posted-content" @default.
• W4310763014 hasAuthorship W4310763014A5022968974 @default.
• W4310763014 hasAuthorship W4310763014A5026734857 @default.
• W4310763014 hasAuthorship W4310763014A5041208413 @default.
• W4310763014 hasAuthorship W4310763014A5051832001 @default.
• W4310763014 hasAuthorship W4310763014A5081062143 @default.
• W4310763014 hasConcept C142724271 @default.
• W4310763014 hasConcept C154945302 @default.
• W4310763014 hasConcept C162324750 @default.
• W4310763014 hasConcept C187736073 @default.
• W4310763014 hasConcept C204321447 @default.
• W4310763014 hasConcept C23123220 @default.
• W4310763014 hasConcept C2779135771 @default.
• W4310763014 hasConcept C2780451532 @default.
• W4310763014 hasConcept C41008148 @default.
• W4310763014 hasConcept C534262118 @default.
• W4310763014 hasConcept C71924100 @default.
• W4310763014 hasConcept C81363708 @default.
• W4310763014 hasConceptScore W4310763014C142724271 @default.
• W4310763014 hasConceptScore W4310763014C154945302 @default.
• W4310763014 hasConceptScore W4310763014C162324750 @default.
• W4310763014 hasConceptScore W4310763014C187736073 @default.
• W4310763014 hasConceptScore W4310763014C204321447 @default.
• W4310763014 hasConceptScore W4310763014C23123220 @default.
• W4310763014 hasConceptScore W4310763014C2779135771 @default.
• W4310763014 hasConceptScore W4310763014C2780451532 @default.
• W4310763014 hasConceptScore W4310763014C41008148 @default.
• W4310763014 hasConceptScore W4310763014C534262118 @default.
• W4310763014 hasConceptScore W4310763014C71924100 @default.
• W4310763014 hasConceptScore W4310763014C81363708 @default.
• W4310763014 hasLocation W43107630141 @default.
• W4310763014 hasOpenAccess W4310763014 @default.
• W4310763014 hasPrimaryLocation W43107630141 @default.
• W4310763014 hasRelatedWork W147166030 @default.
• W4310763014 hasRelatedWork W1541018942 @default.
• W4310763014 hasRelatedWork W1551179054 @default.
• W4310763014 hasRelatedWork W1593502373 @default.
• W4310763014 hasRelatedWork W2133753140 @default.
• W4310763014 hasRelatedWork W2405038964 @default.
• W4310763014 hasRelatedWork W2810280135 @default.
• W4310763014 hasRelatedWork W3002472320 @default.

• next