FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387338911> ?p ?o ?g. }

• W4387338911 abstract "Abstract Data extraction is a crucial, yet labor-intensive and error-prone part of evidence synthesis. To date, efforts to harness machine learning for enhancing efficiency of the data extraction process have fallen short of achieving sufficient accuracy and usability. With the advent of Large Language Models (LLMs), new possibilities have emerged to increase efficiency and accuracy of data extraction for evidence synthesis. The objective of this proof-of-concept study was to assess the performance of an LLM (Claude 2) in extracting data elements from published studies, compared with human data extraction as employed in systematic reviews. Our analysis utilized a convenience sample of 10 English-language, open-access publications of randomized controlled trials included in a single systematic review. We selected 16 distinct types of data, posing varying degrees of difficulty (160 data elements across 10 studies). We used the browser version of Claude 2 to upload the portable document format of each publication and then prompted the model for each data element. Across 160 data elements, Claude 2 demonstrated an overall accuracy of 96.3% with a high test-retest reliability (replication 1: 96.9%; replication 2: 95.0% accuracy). Overall, Claude 2 made 6 errors on 160 data items. The most common errors (n=4) were missed data items. Importantly, Claude 2’s ease of use was high; it required no technical expertise or training data for effective operation. Based on findings of our proof-of-concept study, leveraging LLMs has the potential to substantially enhance the efficiency and accuracy of data extraction for evidence syntheses." @default.
• W4387338911 created "2023-10-05" @default.
• W4387338911 creator A5005728741 @default.
• W4387338911 creator A5006395550 @default.
• W4387338911 creator A5013031059 @default.
• W4387338911 creator A5014098617 @default.
• W4387338911 creator A5021630385 @default.
• W4387338911 creator A5031031174 @default.
• W4387338911 creator A5039893367 @default.
• W4387338911 creator A5042088170 @default.
• W4387338911 creator A5047858317 @default.
• W4387338911 creator A5078175691 @default.
• W4387338911 creator A5078399314 @default.
• W4387338911 creator A5080463323 @default.
• W4387338911 date "2023-10-03" @default.
• W4387338911 modified "2023-10-18" @default.
• W4387338911 title "Data Extraction for Evidence Synthesis Using a Large Language Model: A Proof-of-Concept Study" @default.
• W4387338911 cites W1629765770 @default.
• W4387338911 cites W1957267795 @default.
• W4387338911 cites W2004500024 @default.
• W4387338911 cites W2011753281 @default.
• W4387338911 cites W2532238474 @default.
• W4387338911 cites W2550814440 @default.
• W4387338911 cites W2570140560 @default.
• W4387338911 cites W2620306249 @default.
• W4387338911 cites W2770117783 @default.
• W4387338911 cites W2794845062 @default.
• W4387338911 cites W2797238574 @default.
• W4387338911 cites W2896987528 @default.
• W4387338911 cites W2961552777 @default.
• W4387338911 cites W2997875868 @default.
• W4387338911 cites W3037060742 @default.
• W4387338911 cites W3163124033 @default.
• W4387338911 cites W3169933308 @default.
• W4387338911 cites W3185341429 @default.
• W4387338911 cites W4213127247 @default.
• W4387338911 doi "https://doi.org/10.1101/2023.10.02.23296415" @default.
• W4387338911 hasPublicationYear "2023" @default.
• W4387338911 type Work @default.
• W4387338911 citedByCount "0" @default.
• W4387338911 crossrefType "posted-content" @default.
• W4387338911 hasAuthorship W4387338911A5005728741 @default.
• W4387338911 hasAuthorship W4387338911A5006395550 @default.
• W4387338911 hasAuthorship W4387338911A5013031059 @default.
• W4387338911 hasAuthorship W4387338911A5014098617 @default.
• W4387338911 hasAuthorship W4387338911A5021630385 @default.
• W4387338911 hasAuthorship W4387338911A5031031174 @default.
• W4387338911 hasAuthorship W4387338911A5039893367 @default.
• W4387338911 hasAuthorship W4387338911A5042088170 @default.
• W4387338911 hasAuthorship W4387338911A5047858317 @default.
• W4387338911 hasAuthorship W4387338911A5078175691 @default.
• W4387338911 hasAuthorship W4387338911A5078399314 @default.
• W4387338911 hasAuthorship W4387338911A5080463323 @default.
• W4387338911 hasConcept C105795698 @default.
• W4387338911 hasConcept C107457646 @default.
• W4387338911 hasConcept C111919701 @default.
• W4387338911 hasConcept C119857082 @default.
• W4387338911 hasConcept C121332964 @default.
• W4387338911 hasConcept C124101348 @default.
• W4387338911 hasConcept C124978682 @default.
• W4387338911 hasConcept C12590798 @default.
• W4387338911 hasConcept C136764020 @default.
• W4387338911 hasConcept C154945302 @default.
• W4387338911 hasConcept C163258240 @default.
• W4387338911 hasConcept C170130773 @default.
• W4387338911 hasConcept C17744445 @default.
• W4387338911 hasConcept C199360897 @default.
• W4387338911 hasConcept C199539241 @default.
• W4387338911 hasConcept C204321447 @default.
• W4387338911 hasConcept C23123220 @default.
• W4387338911 hasConcept C2522767166 @default.
• W4387338911 hasConcept C2777466982 @default.
• W4387338911 hasConcept C2779473830 @default.
• W4387338911 hasConcept C33923547 @default.
• W4387338911 hasConcept C41008148 @default.
• W4387338911 hasConcept C43214815 @default.
• W4387338911 hasConcept C62520636 @default.
• W4387338911 hasConcept C71901391 @default.
• W4387338911 hasConcept C98045186 @default.
• W4387338911 hasConceptScore W4387338911C105795698 @default.
• W4387338911 hasConceptScore W4387338911C107457646 @default.
• W4387338911 hasConceptScore W4387338911C111919701 @default.
• W4387338911 hasConceptScore W4387338911C119857082 @default.
• W4387338911 hasConceptScore W4387338911C121332964 @default.
• W4387338911 hasConceptScore W4387338911C124101348 @default.
• W4387338911 hasConceptScore W4387338911C124978682 @default.
• W4387338911 hasConceptScore W4387338911C12590798 @default.
• W4387338911 hasConceptScore W4387338911C136764020 @default.
• W4387338911 hasConceptScore W4387338911C154945302 @default.
• W4387338911 hasConceptScore W4387338911C163258240 @default.
• W4387338911 hasConceptScore W4387338911C170130773 @default.
• W4387338911 hasConceptScore W4387338911C17744445 @default.
• W4387338911 hasConceptScore W4387338911C199360897 @default.
• W4387338911 hasConceptScore W4387338911C199539241 @default.
• W4387338911 hasConceptScore W4387338911C204321447 @default.
• W4387338911 hasConceptScore W4387338911C23123220 @default.
• W4387338911 hasConceptScore W4387338911C2522767166 @default.
• W4387338911 hasConceptScore W4387338911C2777466982 @default.
• W4387338911 hasConceptScore W4387338911C2779473830 @default.
• W4387338911 hasConceptScore W4387338911C33923547 @default.

• next