Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308552803> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4308552803 endingPage "4620" @default.
- W4308552803 startingPage "4612" @default.
- W4308552803 abstract "Introduction In patients undergoing high-risk cardiac surgery, the uncertainty of outcome may complicate the decision process to intervene. To augment decision-making, a machine learning approach was used to determine weighted personalized factors contributing to mortality. Methods American College of Surgeons National Surgical Quality Improvement Program was queried for cardiac surgery patients with predicted mortality ≥10% between 2012 and 2019. Multiple machine learning models were investigated, with significant predictors ultimately used in gradient boosting machine (GBM) modeling. GBM-trained data were then used for local interpretable model-agnostic explanations (LIME) modeling to provide individual patient-specific mortality prediction. Results A total of 194 patient deaths among 1291 high-risk cardiac surgeries were included. GBM performance was superior to other model approaches. The top five factors contributing to mortality in LIME modeling were preoperative dialysis, emergent cases, Hispanic ethnicity, steroid use, and ventilator dependence. LIME results individualized patient factors with model probability and explanation of fit. Conclusions The application of machine learning techniques provides individualized predicted mortality and identifies contributing factors in high-risk cardiac surgery. Employment of this modeling to the Society of Thoracic Surgeons database may provide individualized risk factors contributing to mortality." @default.
- W4308552803 created "2022-11-12" @default.
- W4308552803 creator A5016777555 @default.
- W4308552803 creator A5021245608 @default.
- W4308552803 creator A5033156221 @default.
- W4308552803 creator A5039969814 @default.
- W4308552803 creator A5040119864 @default.
- W4308552803 creator A5045005612 @default.
- W4308552803 creator A5067083734 @default.
- W4308552803 creator A5071373628 @default.
- W4308552803 creator A5077810174 @default.
- W4308552803 creator A5086932309 @default.
- W4308552803 creator A5089412814 @default.
- W4308552803 date "2022-11-08" @default.
- W4308552803 modified "2023-10-17" @default.
- W4308552803 title "A machine learning approach to high‐risk cardiac surgery risk scoring" @default.
- W4308552803 cites W2007941691 @default.
- W4308552803 cites W2021613300 @default.
- W4308552803 cites W2035066672 @default.
- W4308552803 cites W2048301249 @default.
- W4308552803 cites W2098026442 @default.
- W4308552803 cites W2282821441 @default.
- W4308552803 cites W2727650337 @default.
- W4308552803 cites W2762836337 @default.
- W4308552803 cites W2790952035 @default.
- W4308552803 cites W2888528836 @default.
- W4308552803 cites W2980665503 @default.
- W4308552803 cites W2986424528 @default.
- W4308552803 cites W3042882333 @default.
- W4308552803 cites W3092494313 @default.
- W4308552803 cites W3126587432 @default.
- W4308552803 cites W3148629439 @default.
- W4308552803 cites W3205476205 @default.
- W4308552803 cites W3206146265 @default.
- W4308552803 cites W3206554013 @default.
- W4308552803 cites W4200035054 @default.
- W4308552803 cites W4225329299 @default.
- W4308552803 doi "https://doi.org/10.1111/jocs.17110" @default.
- W4308552803 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36345692" @default.
- W4308552803 hasPublicationYear "2022" @default.
- W4308552803 type Work @default.
- W4308552803 citedByCount "4" @default.
- W4308552803 countsByYear W43085528032023 @default.
- W4308552803 crossrefType "journal-article" @default.
- W4308552803 hasAuthorship W4308552803A5016777555 @default.
- W4308552803 hasAuthorship W4308552803A5021245608 @default.
- W4308552803 hasAuthorship W4308552803A5033156221 @default.
- W4308552803 hasAuthorship W4308552803A5039969814 @default.
- W4308552803 hasAuthorship W4308552803A5040119864 @default.
- W4308552803 hasAuthorship W4308552803A5045005612 @default.
- W4308552803 hasAuthorship W4308552803A5067083734 @default.
- W4308552803 hasAuthorship W4308552803A5071373628 @default.
- W4308552803 hasAuthorship W4308552803A5077810174 @default.
- W4308552803 hasAuthorship W4308552803A5086932309 @default.
- W4308552803 hasAuthorship W4308552803A5089412814 @default.
- W4308552803 hasBestOaLocation W43085528031 @default.
- W4308552803 hasConcept C119857082 @default.
- W4308552803 hasConcept C126322002 @default.
- W4308552803 hasConcept C136764020 @default.
- W4308552803 hasConcept C141071460 @default.
- W4308552803 hasConcept C154945302 @default.
- W4308552803 hasConcept C177713679 @default.
- W4308552803 hasConcept C2777984932 @default.
- W4308552803 hasConcept C2778789114 @default.
- W4308552803 hasConcept C37616216 @default.
- W4308552803 hasConcept C41008148 @default.
- W4308552803 hasConcept C71924100 @default.
- W4308552803 hasConceptScore W4308552803C119857082 @default.
- W4308552803 hasConceptScore W4308552803C126322002 @default.
- W4308552803 hasConceptScore W4308552803C136764020 @default.
- W4308552803 hasConceptScore W4308552803C141071460 @default.
- W4308552803 hasConceptScore W4308552803C154945302 @default.
- W4308552803 hasConceptScore W4308552803C177713679 @default.
- W4308552803 hasConceptScore W4308552803C2777984932 @default.
- W4308552803 hasConceptScore W4308552803C2778789114 @default.
- W4308552803 hasConceptScore W4308552803C37616216 @default.
- W4308552803 hasConceptScore W4308552803C41008148 @default.
- W4308552803 hasConceptScore W4308552803C71924100 @default.
- W4308552803 hasIssue "12" @default.
- W4308552803 hasLocation W43085528031 @default.
- W4308552803 hasLocation W43085528032 @default.
- W4308552803 hasOpenAccess W4308552803 @default.
- W4308552803 hasPrimaryLocation W43085528031 @default.
- W4308552803 hasRelatedWork W2002120878 @default.
- W4308552803 hasRelatedWork W2003938723 @default.
- W4308552803 hasRelatedWork W2047967234 @default.
- W4308552803 hasRelatedWork W2118496982 @default.
- W4308552803 hasRelatedWork W2439875401 @default.
- W4308552803 hasRelatedWork W3129804828 @default.
- W4308552803 hasRelatedWork W3174196512 @default.
- W4308552803 hasRelatedWork W4283697347 @default.
- W4308552803 hasRelatedWork W4298144215 @default.
- W4308552803 hasRelatedWork W4318350883 @default.
- W4308552803 hasVolume "37" @default.
- W4308552803 isParatext "false" @default.
- W4308552803 isRetracted "false" @default.
- W4308552803 workType "article" @default.