FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379469178> ?p ?o ?g. }

• W4379469178 abstract "The COVID-19 pandemic has led to an unprecedented amount of scientific publications, growing at a pace never seen before. Multiple living systematic reviews have been developed to assist professionals with up-to-date and trustworthy health information, but it is increasingly challenging for systematic reviewers to keep up with the evidence in electronic databases. We aimed to investigate deep learning-based machine learning algorithms to classify COVID-19-related publications to help scale up the epidemiological curation process.In this retrospective study, five different pre-trained deep learning-based language models were fine-tuned on a dataset of 6365 publications manually classified into two classes, three subclasses, and 22 sub-subclasses relevant for epidemiological triage purposes. In a k-fold cross-validation setting, each standalone model was assessed on a classification task and compared against an ensemble, which takes the standalone model predictions as input and uses different strategies to infer the optimal article class. A ranking task was also considered, in which the model outputs a ranked list of sub-subclasses associated with the article.The ensemble model significantly outperformed the standalone classifiers, achieving a F1-score of 89.2 at the class level of the classification task. The difference between the standalone and ensemble models increases at the sub-subclass level, where the ensemble reaches a micro F1-score of 70% against 67% for the best-performing standalone model. For the ranking task, the ensemble obtained the highest recall@3, with a performance of 89%. Using an unanimity voting rule, the ensemble can provide predictions with higher confidence on a subset of the data, achieving detection of original papers with a F1-score up to 97% on a subset of 80% of the collection instead of 93% on the whole dataset.This study shows the potential of using deep learning language models to perform triage of COVID-19 references efficiently and support epidemiological curation and review. The ensemble consistently and significantly outperforms any standalone model. Fine-tuning the voting strategy thresholds is an interesting alternative to annotate a subset with higher predictive confidence." @default.
• W4379469178 created "2023-06-07" @default.
• W4379469178 creator A5007692232 @default.
• W4379469178 creator A5009975749 @default.
• W4379469178 creator A5017706396 @default.
• W4379469178 creator A5021497669 @default.
• W4379469178 creator A5040055230 @default.
• W4379469178 creator A5041439282 @default.
• W4379469178 creator A5042070839 @default.
• W4379469178 creator A5064868401 @default.
• W4379469178 creator A5080408994 @default.
• W4379469178 creator A5083967421 @default.
• W4379469178 creator A5090870583 @default.
• W4379469178 date "2023-06-05" @default.
• W4379469178 modified "2023-09-27" @default.
• W4379469178 title "Ensemble of deep learning language models to support the creation of living systematic reviews for the COVID-19 literature" @default.
• W4379469178 cites W1480287196 @default.
• W4379469178 cites W2014453502 @default.
• W4379469178 cites W2084413241 @default.
• W4379469178 cites W2094726706 @default.
• W4379469178 cites W2118020653 @default.
• W4379469178 cites W2121879602 @default.
• W4379469178 cites W2147469877 @default.
• W4379469178 cites W2148130205 @default.
• W4379469178 cites W2150850055 @default.
• W4379469178 cites W2171895522 @default.
• W4379469178 cites W2787894218 @default.
• W4379469178 cites W2789889445 @default.
• W4379469178 cites W2887377515 @default.
• W4379469178 cites W2911489562 @default.
• W4379469178 cites W2913428185 @default.
• W4379469178 cites W2946690328 @default.
• W4379469178 cites W2963563735 @default.
• W4379469178 cites W3023417367 @default.
• W4379469178 cites W3023596762 @default.
• W4379469178 cites W3046375318 @default.
• W4379469178 cites W3090612586 @default.
• W4379469178 cites W3101381894 @default.
• W4379469178 cites W3102369639 @default.
• W4379469178 cites W3105753785 @default.
• W4379469178 cites W3106825982 @default.
• W4379469178 cites W3111096384 @default.
• W4379469178 cites W3143985904 @default.
• W4379469178 cites W3208587672 @default.
• W4379469178 cites W3217155045 @default.
• W4379469178 cites W4220821700 @default.
• W4379469178 cites W4281566145 @default.
• W4379469178 cites W4313371821 @default.
• W4379469178 cites W4324148013 @default.
• W4379469178 doi "https://doi.org/10.1186/s13643-023-02247-9" @default.
• W4379469178 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37277872" @default.
• W4379469178 hasPublicationYear "2023" @default.
• W4379469178 type Work @default.
• W4379469178 citedByCount "0" @default.
• W4379469178 crossrefType "journal-article" @default.
• W4379469178 hasAuthorship W4379469178A5007692232 @default.
• W4379469178 hasAuthorship W4379469178A5009975749 @default.
• W4379469178 hasAuthorship W4379469178A5017706396 @default.
• W4379469178 hasAuthorship W4379469178A5021497669 @default.
• W4379469178 hasAuthorship W4379469178A5040055230 @default.
• W4379469178 hasAuthorship W4379469178A5041439282 @default.
• W4379469178 hasAuthorship W4379469178A5042070839 @default.
• W4379469178 hasAuthorship W4379469178A5064868401 @default.
• W4379469178 hasAuthorship W4379469178A5080408994 @default.
• W4379469178 hasAuthorship W4379469178A5083967421 @default.
• W4379469178 hasAuthorship W4379469178A5090870583 @default.
• W4379469178 hasBestOaLocation W43794691781 @default.
• W4379469178 hasConcept C119857082 @default.
• W4379469178 hasConcept C119898033 @default.
• W4379469178 hasConcept C153668964 @default.
• W4379469178 hasConcept C154945302 @default.
• W4379469178 hasConcept C162324750 @default.
• W4379469178 hasConcept C187736073 @default.
• W4379469178 hasConcept C189430467 @default.
• W4379469178 hasConcept C194828623 @default.
• W4379469178 hasConcept C204321447 @default.
• W4379469178 hasConcept C2522767166 @default.
• W4379469178 hasConcept C2777120189 @default.
• W4379469178 hasConcept C2777212361 @default.
• W4379469178 hasConcept C2780451532 @default.
• W4379469178 hasConcept C41008148 @default.
• W4379469178 hasConcept C45942800 @default.
• W4379469178 hasConcept C71924100 @default.
• W4379469178 hasConceptScore W4379469178C119857082 @default.
• W4379469178 hasConceptScore W4379469178C119898033 @default.
• W4379469178 hasConceptScore W4379469178C153668964 @default.
• W4379469178 hasConceptScore W4379469178C154945302 @default.
• W4379469178 hasConceptScore W4379469178C162324750 @default.
• W4379469178 hasConceptScore W4379469178C187736073 @default.
• W4379469178 hasConceptScore W4379469178C189430467 @default.
• W4379469178 hasConceptScore W4379469178C194828623 @default.
• W4379469178 hasConceptScore W4379469178C204321447 @default.
• W4379469178 hasConceptScore W4379469178C2522767166 @default.
• W4379469178 hasConceptScore W4379469178C2777120189 @default.
• W4379469178 hasConceptScore W4379469178C2777212361 @default.
• W4379469178 hasConceptScore W4379469178C2780451532 @default.
• W4379469178 hasConceptScore W4379469178C41008148 @default.
• W4379469178 hasConceptScore W4379469178C45942800 @default.
• W4379469178 hasConceptScore W4379469178C71924100 @default.
• W4379469178 hasFunder F4320320924 @default.

• next