FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382363687> ?p ?o ?g. }

• W4382363687 abstract "<sec> <title>BACKGROUND</title> There is an ongoing debate over whether a procedural specific (e.g. Society of Thoracic Surgeons (STS)) or universal model (e.g. EuroSCORE II (ES II)) should be used for patient selection in cardiac surgery. Recently, we showed that ES II suffers from severe performance drift across several important metrics and that ML approaches such as Xgboost and Random Forest are substantially more resistant to dataset drift. </sec> <sec> <title>OBJECTIVE</title> With the growing interest in big data and its leverage through the use of ML approaches that are not limited by linear statistical assumptions, the number of clinical variables can theoretically increase exponentially. In addition, the variations and residual confounding that historically hindered the usefulness of cardiac risk stratification scores can potentially be taken into account. Here, we assess these possibilities on a large United Kingdom (UK) database. </sec> <sec> <title>METHODS</title> A retrospective analysis of prospectively routinely gathered data on adult patients undergoing cardiac surgery in the UK between 2012-2019. We temporally split the data 70:30 into a training and validation subset. Two sets of seven ML mortality prediction models, with and without variable selection were assessed for consensus Clinical Effective Metric (CEM) overall performance and performance within each of CEM9s consistuent metrics. Confounding and potential causal relationships between covariates and outcomes were evaluated using bayesian network analysis. </sec> <sec> <title>RESULTS</title> A total of 227,087 adults underwent cardiac surgery during the study period with a mortality rate of 2.76%. For non-variable selected (NVS) risk scores with 102 variables, Xgboost with adjustment for hospital variation was superior to the Xgboost without adjustment (p < 2e-16). Both NVS and the 18 variables selected (VS) Xgboost with adjustment for hospital variation risk scores were superior to the Xgboost (ES II 18 variables) model (p < 6.3e-15), with NVS Xgboost with adjustment for hospital variation having the best performance, followed by the VS Xgboost with adjustment for hospital variation (CEM Difference: 0.0150 and 0.0023, respectively). </sec> <sec> <title>CONCLUSIONS</title> We have identified an ML adjusted risk score comprising 102 variables that increases risk stratification performance on hold out dataset, removing the need to perform variable selection and reduction. This paves the way for further research that utilises this new set of variables with hospital-based adjustments for the safer selection of patients undergoing cardiac surgery. </sec> <sec> <title>INTERNATIONAL REGISTERED REPORT</title> RR2-https://doi.org/10.1101/2023.06.08.23291129 </sec>" @default.
• W4382363687 created "2023-06-29" @default.
• W4382363687 creator A5010780140 @default.
• W4382363687 creator A5015199341 @default.
• W4382363687 creator A5016478380 @default.
• W4382363687 creator A5018195873 @default.
• W4382363687 creator A5019659335 @default.
• W4382363687 creator A5054764500 @default.
• W4382363687 creator A5058260579 @default.
• W4382363687 creator A5058622525 @default.
• W4382363687 creator A5061392978 @default.
• W4382363687 creator A5074185605 @default.
• W4382363687 creator A5092349164 @default.
• W4382363687 date "2023-06-13" @default.
• W4382363687 modified "2023-10-17" @default.
• W4382363687 title "Random effects adjustment in machine learning models for cardiac surgery risk prediction: a benchmarking study (Preprint)" @default.
• W4382363687 cites W2132331971 @default.
• W4382363687 cites W2534430069 @default.
• W4382363687 cites W2767329727 @default.
• W4382363687 cites W4206191195 @default.
• W4382363687 cites W4237660768 @default.
• W4382363687 cites W4241323460 @default.
• W4382363687 cites W4250299240 @default.
• W4382363687 doi "https://doi.org/10.2196/preprints.49914" @default.
• W4382363687 hasPublicationYear "2023" @default.
• W4382363687 type Work @default.
• W4382363687 citedByCount "0" @default.
• W4382363687 crossrefType "posted-content" @default.
• W4382363687 hasAuthorship W4382363687A5010780140 @default.
• W4382363687 hasAuthorship W4382363687A5015199341 @default.
• W4382363687 hasAuthorship W4382363687A5016478380 @default.
• W4382363687 hasAuthorship W4382363687A5018195873 @default.
• W4382363687 hasAuthorship W4382363687A5019659335 @default.
• W4382363687 hasAuthorship W4382363687A5054764500 @default.
• W4382363687 hasAuthorship W4382363687A5058260579 @default.
• W4382363687 hasAuthorship W4382363687A5058622525 @default.
• W4382363687 hasAuthorship W4382363687A5061392978 @default.
• W4382363687 hasAuthorship W4382363687A5074185605 @default.
• W4382363687 hasAuthorship W4382363687A5092349164 @default.
• W4382363687 hasConcept C105795698 @default.
• W4382363687 hasConcept C119857082 @default.
• W4382363687 hasConcept C126322002 @default.
• W4382363687 hasConcept C142724271 @default.
• W4382363687 hasConcept C153083717 @default.
• W4382363687 hasConcept C154945302 @default.
• W4382363687 hasConcept C168743327 @default.
• W4382363687 hasConcept C169258074 @default.
• W4382363687 hasConcept C2778789114 @default.
• W4382363687 hasConcept C33923547 @default.
• W4382363687 hasConcept C40423286 @default.
• W4382363687 hasConcept C41008148 @default.
• W4382363687 hasConcept C5274069 @default.
• W4382363687 hasConcept C71924100 @default.
• W4382363687 hasConcept C77350462 @default.
• W4382363687 hasConcept C95190672 @default.
• W4382363687 hasConceptScore W4382363687C105795698 @default.
• W4382363687 hasConceptScore W4382363687C119857082 @default.
• W4382363687 hasConceptScore W4382363687C126322002 @default.
• W4382363687 hasConceptScore W4382363687C142724271 @default.
• W4382363687 hasConceptScore W4382363687C153083717 @default.
• W4382363687 hasConceptScore W4382363687C154945302 @default.
• W4382363687 hasConceptScore W4382363687C168743327 @default.
• W4382363687 hasConceptScore W4382363687C169258074 @default.
• W4382363687 hasConceptScore W4382363687C2778789114 @default.
• W4382363687 hasConceptScore W4382363687C33923547 @default.
• W4382363687 hasConceptScore W4382363687C40423286 @default.
• W4382363687 hasConceptScore W4382363687C41008148 @default.
• W4382363687 hasConceptScore W4382363687C5274069 @default.
• W4382363687 hasConceptScore W4382363687C71924100 @default.
• W4382363687 hasConceptScore W4382363687C77350462 @default.
• W4382363687 hasConceptScore W4382363687C95190672 @default.
• W4382363687 hasLocation W43823636871 @default.
• W4382363687 hasOpenAccess W4382363687 @default.
• W4382363687 hasPrimaryLocation W43823636871 @default.
• W4382363687 hasRelatedWork W2089415104 @default.
• W4382363687 hasRelatedWork W2911455822 @default.
• W4382363687 hasRelatedWork W3174196512 @default.
• W4382363687 hasRelatedWork W3211546796 @default.
• W4382363687 hasRelatedWork W4281560664 @default.
• W4382363687 hasRelatedWork W4281616679 @default.
• W4382363687 hasRelatedWork W4293525103 @default.
• W4382363687 hasRelatedWork W4308191010 @default.
• W4382363687 hasRelatedWork W4318350883 @default.
• W4382363687 hasRelatedWork W4323021782 @default.
• W4382363687 isParatext "false" @default.
• W4382363687 isRetracted "false" @default.
• W4382363687 workType "article" @default.