Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296886067> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4296886067 abstract "The Japanese Orthopaedic Association National Registry (JOANR) was recently launched in Japan and is expected to improve the quality of medical care. However, surgeons must register ten detailed features for total hip arthroplasty, which is labor intensive. One possible solution is to use a system that automatically extracts information about the surgeries. Although it is not easy to extract features from an operative record consisting of free-text data, natural language processing has been used to extract features from operative records. This study aimed to evaluate the best natural language processing method for building a system that automatically detects some elements in the JOANR from the operative records of total hip arthroplasty. We obtained operative records of total hip arthroplasty (n = 2574) in three hospitals and targeted two items: surgical approach and fixation technique. We compared the accuracy of three natural language processing methods: rule-based algorithms, machine learning, and bidirectional encoder representations from transformers (BERT). In the surgical approach task, the accuracy of BERT was superior to that of the rule-based algorithm (99.6% vs. 93.6%, p < 0.001), comparable to machine learning. In the fixation technique task, the accuracy of BERT was superior to the rule-based algorithm and machine learning (96% vs. 74%, p < 0.0001 and 94%, p = 0.0004). BERT is the most appropriate method for building a system that automatically detects the surgical approach and fixation technique." @default.
- W4296886067 created "2022-09-24" @default.
- W4296886067 creator A5000214180 @default.
- W4296886067 creator A5003213259 @default.
- W4296886067 creator A5012224052 @default.
- W4296886067 creator A5013823740 @default.
- W4296886067 creator A5027692193 @default.
- W4296886067 creator A5030896432 @default.
- W4296886067 creator A5034265751 @default.
- W4296886067 creator A5040927651 @default.
- W4296886067 creator A5049641043 @default.
- W4296886067 creator A5056150877 @default.
- W4296886067 creator A5061081732 @default.
- W4296886067 creator A5066382641 @default.
- W4296886067 creator A5074123400 @default.
- W4296886067 creator A5081622324 @default.
- W4296886067 date "2022-09-01" @default.
- W4296886067 modified "2023-09-29" @default.
- W4296886067 title "Use of artificial intelligence to identify data elements for The Japanese Orthopaedic Association National Registry from operative records" @default.
- W4296886067 cites W2030079148 @default.
- W4296886067 cites W2042416019 @default.
- W4296886067 cites W2118020653 @default.
- W4296886067 cites W2120017526 @default.
- W4296886067 cites W2323522479 @default.
- W4296886067 cites W2974146565 @default.
- W4296886067 cites W2996347561 @default.
- W4296886067 cites W3047431235 @default.
- W4296886067 cites W3091869825 @default.
- W4296886067 cites W3163158440 @default.
- W4296886067 cites W3169695576 @default.
- W4296886067 cites W3182884929 @default.
- W4296886067 cites W3186552329 @default.
- W4296886067 cites W3200849552 @default.
- W4296886067 cites W3213545440 @default.
- W4296886067 cites W4200205212 @default.
- W4296886067 doi "https://doi.org/10.1016/j.jos.2022.09.003" @default.
- W4296886067 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36163118" @default.
- W4296886067 hasPublicationYear "2022" @default.
- W4296886067 type Work @default.
- W4296886067 citedByCount "2" @default.
- W4296886067 countsByYear W42968860672023 @default.
- W4296886067 crossrefType "journal-article" @default.
- W4296886067 hasAuthorship W4296886067A5000214180 @default.
- W4296886067 hasAuthorship W4296886067A5003213259 @default.
- W4296886067 hasAuthorship W4296886067A5012224052 @default.
- W4296886067 hasAuthorship W4296886067A5013823740 @default.
- W4296886067 hasAuthorship W4296886067A5027692193 @default.
- W4296886067 hasAuthorship W4296886067A5030896432 @default.
- W4296886067 hasAuthorship W4296886067A5034265751 @default.
- W4296886067 hasAuthorship W4296886067A5040927651 @default.
- W4296886067 hasAuthorship W4296886067A5049641043 @default.
- W4296886067 hasAuthorship W4296886067A5056150877 @default.
- W4296886067 hasAuthorship W4296886067A5061081732 @default.
- W4296886067 hasAuthorship W4296886067A5066382641 @default.
- W4296886067 hasAuthorship W4296886067A5074123400 @default.
- W4296886067 hasAuthorship W4296886067A5081622324 @default.
- W4296886067 hasConcept C119857082 @default.
- W4296886067 hasConcept C124101348 @default.
- W4296886067 hasConcept C127413603 @default.
- W4296886067 hasConcept C141071460 @default.
- W4296886067 hasConcept C154945302 @default.
- W4296886067 hasConcept C195910791 @default.
- W4296886067 hasConcept C201995342 @default.
- W4296886067 hasConcept C204321447 @default.
- W4296886067 hasConcept C2778336525 @default.
- W4296886067 hasConcept C2780451532 @default.
- W4296886067 hasConcept C41008148 @default.
- W4296886067 hasConcept C71924100 @default.
- W4296886067 hasConceptScore W4296886067C119857082 @default.
- W4296886067 hasConceptScore W4296886067C124101348 @default.
- W4296886067 hasConceptScore W4296886067C127413603 @default.
- W4296886067 hasConceptScore W4296886067C141071460 @default.
- W4296886067 hasConceptScore W4296886067C154945302 @default.
- W4296886067 hasConceptScore W4296886067C195910791 @default.
- W4296886067 hasConceptScore W4296886067C201995342 @default.
- W4296886067 hasConceptScore W4296886067C204321447 @default.
- W4296886067 hasConceptScore W4296886067C2778336525 @default.
- W4296886067 hasConceptScore W4296886067C2780451532 @default.
- W4296886067 hasConceptScore W4296886067C41008148 @default.
- W4296886067 hasConceptScore W4296886067C71924100 @default.
- W4296886067 hasLocation W42968860671 @default.
- W4296886067 hasLocation W42968860672 @default.
- W4296886067 hasOpenAccess W4296886067 @default.
- W4296886067 hasPrimaryLocation W42968860671 @default.
- W4296886067 hasRelatedWork W2066257651 @default.
- W4296886067 hasRelatedWork W2748952813 @default.
- W4296886067 hasRelatedWork W2899084033 @default.
- W4296886067 hasRelatedWork W2961085424 @default.
- W4296886067 hasRelatedWork W3035032397 @default.
- W4296886067 hasRelatedWork W3044297557 @default.
- W4296886067 hasRelatedWork W3082127840 @default.
- W4296886067 hasRelatedWork W4286629047 @default.
- W4296886067 hasRelatedWork W4306674287 @default.
- W4296886067 hasRelatedWork W4224009465 @default.
- W4296886067 isParatext "false" @default.
- W4296886067 isRetracted "false" @default.
- W4296886067 workType "article" @default.