Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307379653> ?p ?o ?g. }
- W4307379653 abstract "Cluster randomized trials (CRTs) are becoming an increasingly important design. However, authors of CRTs do not always adhere to requirements to explicitly identify the design as cluster randomized in titles and abstracts, making retrieval from bibliographic databases difficult. Machine learning algorithms may improve their identification and retrieval. Therefore, we aimed to develop machine learning algorithms that accurately determine whether a bibliographic citation is a CRT report.We trained, internally validated, and externally validated two convolutional neural networks and one support vector machine (SVM) algorithm to predict whether a citation is a CRT report or not. We exclusively used the information in an article citation, including the title, abstract, keywords, and subject headings. The algorithms' output was a probability from 0 to 1. We assessed algorithm performance using the area under the receiver operating characteristic (AUC) curves. Each algorithm's performance was evaluated individually and together as an ensemble. We randomly selected 5000 from 87,633 citations to train and internally validate our algorithms. Of the 5000 selected citations, 589 (12%) were confirmed CRT reports. We then externally validated our algorithms on an independent set of 1916 randomized trial citations, with 665 (35%) confirmed CRT reports.In internal validation, the ensemble algorithm discriminated best for identifying CRT reports with an AUC of 98.6% (95% confidence interval: 97.8%, 99.4%), sensitivity of 97.7% (94.3%, 100%), and specificity of 85.0% (81.8%, 88.1%). In external validation, the ensemble algorithm had an AUC of 97.8% (97.0%, 98.5%), sensitivity of 97.6% (96.4%, 98.6%), and specificity of 78.2% (75.9%, 80.4%)). All three individual algorithms performed well, but less so than the ensemble.We successfully developed high-performance algorithms that identified whether a citation was a CRT report with high sensitivity and moderately high specificity. We provide open-source software to facilitate the use of our algorithms in practice." @default.
- W4307379653 created "2022-11-01" @default.
- W4307379653 creator A5001731019 @default.
- W4307379653 creator A5010873347 @default.
- W4307379653 creator A5024636525 @default.
- W4307379653 creator A5029801001 @default.
- W4307379653 creator A5040874215 @default.
- W4307379653 creator A5048981513 @default.
- W4307379653 creator A5052439686 @default.
- W4307379653 creator A5070564381 @default.
- W4307379653 date "2022-10-25" @default.
- W4307379653 modified "2023-09-25" @default.
- W4307379653 title "Machine learning algorithms to identify cluster randomized trials from MEDLINE and EMBASE" @default.
- W4307379653 cites W1015675232 @default.
- W4307379653 cites W1437335841 @default.
- W4307379653 cites W155390068 @default.
- W4307379653 cites W2006617902 @default.
- W4307379653 cites W2011301426 @default.
- W4307379653 cites W2051284664 @default.
- W4307379653 cites W2102330235 @default.
- W4307379653 cites W2122514515 @default.
- W4307379653 cites W2139279173 @default.
- W4307379653 cites W2140655809 @default.
- W4307379653 cites W2493916176 @default.
- W4307379653 cites W2497980412 @default.
- W4307379653 cites W2604568423 @default.
- W4307379653 cites W2618530766 @default.
- W4307379653 cites W2619694921 @default.
- W4307379653 cites W2767106145 @default.
- W4307379653 cites W2903236825 @default.
- W4307379653 cites W2963355221 @default.
- W4307379653 cites W3023732552 @default.
- W4307379653 cites W3024899947 @default.
- W4307379653 cites W3082234934 @default.
- W4307379653 cites W3120608097 @default.
- W4307379653 cites W3146722253 @default.
- W4307379653 cites W3152765990 @default.
- W4307379653 doi "https://doi.org/10.1186/s13643-022-02082-4" @default.
- W4307379653 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36284336" @default.
- W4307379653 hasPublicationYear "2022" @default.
- W4307379653 type Work @default.
- W4307379653 citedByCount "0" @default.
- W4307379653 crossrefType "journal-article" @default.
- W4307379653 hasAuthorship W4307379653A5001731019 @default.
- W4307379653 hasAuthorship W4307379653A5010873347 @default.
- W4307379653 hasAuthorship W4307379653A5024636525 @default.
- W4307379653 hasAuthorship W4307379653A5029801001 @default.
- W4307379653 hasAuthorship W4307379653A5040874215 @default.
- W4307379653 hasAuthorship W4307379653A5048981513 @default.
- W4307379653 hasAuthorship W4307379653A5052439686 @default.
- W4307379653 hasAuthorship W4307379653A5070564381 @default.
- W4307379653 hasBestOaLocation W43073796531 @default.
- W4307379653 hasConcept C11413529 @default.
- W4307379653 hasConcept C116834253 @default.
- W4307379653 hasConcept C119857082 @default.
- W4307379653 hasConcept C12267149 @default.
- W4307379653 hasConcept C124101348 @default.
- W4307379653 hasConcept C126322002 @default.
- W4307379653 hasConcept C141071460 @default.
- W4307379653 hasConcept C154945302 @default.
- W4307379653 hasConcept C168563851 @default.
- W4307379653 hasConcept C41008148 @default.
- W4307379653 hasConcept C44249647 @default.
- W4307379653 hasConcept C59822182 @default.
- W4307379653 hasConcept C71924100 @default.
- W4307379653 hasConcept C86803240 @default.
- W4307379653 hasConceptScore W4307379653C11413529 @default.
- W4307379653 hasConceptScore W4307379653C116834253 @default.
- W4307379653 hasConceptScore W4307379653C119857082 @default.
- W4307379653 hasConceptScore W4307379653C12267149 @default.
- W4307379653 hasConceptScore W4307379653C124101348 @default.
- W4307379653 hasConceptScore W4307379653C126322002 @default.
- W4307379653 hasConceptScore W4307379653C141071460 @default.
- W4307379653 hasConceptScore W4307379653C154945302 @default.
- W4307379653 hasConceptScore W4307379653C168563851 @default.
- W4307379653 hasConceptScore W4307379653C41008148 @default.
- W4307379653 hasConceptScore W4307379653C44249647 @default.
- W4307379653 hasConceptScore W4307379653C59822182 @default.
- W4307379653 hasConceptScore W4307379653C71924100 @default.
- W4307379653 hasConceptScore W4307379653C86803240 @default.
- W4307379653 hasIssue "1" @default.
- W4307379653 hasLocation W43073796531 @default.
- W4307379653 hasLocation W43073796532 @default.
- W4307379653 hasLocation W43073796533 @default.
- W4307379653 hasLocation W43073796534 @default.
- W4307379653 hasLocation W43073796535 @default.
- W4307379653 hasLocation W43073796536 @default.
- W4307379653 hasOpenAccess W4307379653 @default.
- W4307379653 hasPrimaryLocation W43073796531 @default.
- W4307379653 hasRelatedWork W1996541855 @default.
- W4307379653 hasRelatedWork W2355927362 @default.
- W4307379653 hasRelatedWork W2748952813 @default.
- W4307379653 hasRelatedWork W2899084033 @default.
- W4307379653 hasRelatedWork W2961085424 @default.
- W4307379653 hasRelatedWork W3159250744 @default.
- W4307379653 hasRelatedWork W3195168932 @default.
- W4307379653 hasRelatedWork W4256514411 @default.
- W4307379653 hasRelatedWork W4306674287 @default.
- W4307379653 hasRelatedWork W4316658362 @default.
- W4307379653 hasVolume "11" @default.