FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387083351> ?p ?o ?g. }

• W4387083351 endingPage "111272" @default.
• W4387083351 startingPage "111272" @default.
• W4387083351 abstract "To develop an algorithm to predict intraoperative Red Blood Cell (RBC) transfusion from preoperative variables contained in the electronic medical record of our institution, with the goal of guiding type and screen ordering.Machine Learning model development on retrospective single-center hospital data.Preoperative period and operating room.The study included patients ≥18 years old who underwent surgery during 2019-2022 and excluded those who refused transfusion, underwent emergency surgery, or surgery for organ donation after cardiac or brain death.Prediction of intraoperative transfusion vs. no intraoperative transfusion.The outcome variable was intraoperative transfusion of RBCs. Predictive variables were surgery, surgeon, anesthesiologist, age, sex, body mass index, race or ethnicity, preoperative hemoglobin (g/dL), partial thromboplastin time (s), platelet count x 109 per liter, and prothrombin time. We compared the performances of seven machine learning algorithms. After training and optimization on the 2019-2021 dataset, model thresholds were set to the current institutional performance level of sensitivity (93%). To qualify for comparison, models had to maintain clinically relevant sensitivity (>90%) when predicting on 2022 data; overall accuracy was the comparative metric.Out of 100,813 cases that met study criteria from 2019 to 2021, intraoperative transfusion occurred in 5488 (5.4%) of cases. The LightGBM model was the highest performing algorithm in external temporal validity experiments, with overall accuracy of (76.1%) [95% confidence interval (CI), 75.6-76.5], while maintaining clinically relevant sensitivity of (91.2%) [95% CI, 89.8-92.5]. If type and screens were ordered based upon the LightGBM model, the predicted type and screen to transfusion ratio would improve from 8.4 to 5.1.Machine learning approaches are feasible in predicting intraoperative transfusion from preoperative variables and may improve preoperative type and screen ordering practices when incorporated into the electronic health record." @default.
• W4387083351 created "2023-09-28" @default.
• W4387083351 creator A5024124240 @default.
• W4387083351 creator A5024436230 @default.
• W4387083351 creator A5029954233 @default.
• W4387083351 creator A5033034338 @default.
• W4387083351 creator A5035367076 @default.
• W4387083351 creator A5073290483 @default.
• W4387083351 creator A5092221816 @default.
• W4387083351 date "2023-12-01" @default.
• W4387083351 modified "2023-10-17" @default.
• W4387083351 title "Development of a machine learning model to predict intraoperative transfusion and guide type and screen ordering" @default.
• W4387083351 cites W1146608908 @default.
• W4387083351 cites W2019694480 @default.
• W4387083351 cites W2031233186 @default.
• W4387083351 cites W2041174332 @default.
• W4387083351 cites W2043128333 @default.
• W4387083351 cites W2059960804 @default.
• W4387083351 cites W2066330427 @default.
• W4387083351 cites W2087313741 @default.
• W4387083351 cites W2106407512 @default.
• W4387083351 cites W2112316706 @default.
• W4387083351 cites W2125847307 @default.
• W4387083351 cites W2148143831 @default.
• W4387083351 cites W2336262108 @default.
• W4387083351 cites W2370697120 @default.
• W4387083351 cites W2608446414 @default.
• W4387083351 cites W2760537253 @default.
• W4387083351 cites W2765837713 @default.
• W4387083351 cites W2789970635 @default.
• W4387083351 cites W2896902100 @default.
• W4387083351 cites W2954312269 @default.
• W4387083351 cites W3008200287 @default.
• W4387083351 cites W3012413426 @default.
• W4387083351 cites W3012804303 @default.
• W4387083351 cites W3047907463 @default.
• W4387083351 cites W3150635270 @default.
• W4387083351 cites W4211087433 @default.
• W4387083351 cites W4309926015 @default.
• W4387083351 cites W73156971 @default.
• W4387083351 doi "https://doi.org/10.1016/j.jclinane.2023.111272" @default.
• W4387083351 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37774648" @default.
• W4387083351 hasPublicationYear "2023" @default.
• W4387083351 type Work @default.
• W4387083351 citedByCount "0" @default.
• W4387083351 crossrefType "journal-article" @default.
• W4387083351 hasAuthorship W4387083351A5024124240 @default.
• W4387083351 hasAuthorship W4387083351A5024436230 @default.
• W4387083351 hasAuthorship W4387083351A5029954233 @default.
• W4387083351 hasAuthorship W4387083351A5033034338 @default.
• W4387083351 hasAuthorship W4387083351A5035367076 @default.
• W4387083351 hasAuthorship W4387083351A5073290483 @default.
• W4387083351 hasAuthorship W4387083351A5092221816 @default.
• W4387083351 hasConcept C126322002 @default.
• W4387083351 hasConcept C141071460 @default.
• W4387083351 hasConcept C2778261982 @default.
• W4387083351 hasConcept C2780434524 @default.
• W4387083351 hasConcept C42219234 @default.
• W4387083351 hasConcept C44249647 @default.
• W4387083351 hasConcept C71924100 @default.
• W4387083351 hasConcept C89560881 @default.
• W4387083351 hasConceptScore W4387083351C126322002 @default.
• W4387083351 hasConceptScore W4387083351C141071460 @default.
• W4387083351 hasConceptScore W4387083351C2778261982 @default.
• W4387083351 hasConceptScore W4387083351C2780434524 @default.
• W4387083351 hasConceptScore W4387083351C42219234 @default.
• W4387083351 hasConceptScore W4387083351C44249647 @default.
• W4387083351 hasConceptScore W4387083351C71924100 @default.
• W4387083351 hasConceptScore W4387083351C89560881 @default.
• W4387083351 hasFunder F4320332161 @default.
• W4387083351 hasFunder F4320337338 @default.
• W4387083351 hasLocation W43870833511 @default.
• W4387083351 hasLocation W43870833512 @default.
• W4387083351 hasOpenAccess W4387083351 @default.
• W4387083351 hasPrimaryLocation W43870833511 @default.
• W4387083351 hasRelatedWork W1857288271 @default.
• W4387083351 hasRelatedWork W1972266366 @default.
• W4387083351 hasRelatedWork W2029341269 @default.
• W4387083351 hasRelatedWork W2035952571 @default.
• W4387083351 hasRelatedWork W2110223924 @default.
• W4387083351 hasRelatedWork W2128846056 @default.
• W4387083351 hasRelatedWork W2326821580 @default.
• W4387083351 hasRelatedWork W2359135438 @default.
• W4387083351 hasRelatedWork W2811413127 @default.
• W4387083351 hasRelatedWork W4211117411 @default.
• W4387083351 hasVolume "91" @default.
• W4387083351 isParatext "false" @default.
• W4387083351 isRetracted "false" @default.
• W4387083351 workType "article" @default.