FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296111641> ?p ?o ?g. }

• W4296111641 endingPage "5289" @default.
• W4296111641 startingPage "5289" @default.
• W4296111641 abstract "Background: General severity of illness scores are not well calibrated to predict mortality among patients receiving renal replacement therapy (RRT) for acute kidney injury (AKI). We developed machine learning models to make mortality prediction and compared their performance to that of the Sequential Organ Failure Assessment (SOFA) and HEpatic failure, LactatE, NorepInephrine, medical Condition, and Creatinine (HELENICC) scores. Methods: We extracted routinely collected clinical data for AKI patients requiring RRT in the MIMIC and eICU databases. The development models were trained in 80% of the pooled dataset and tested in the rest of the pooled dataset. We compared the area under the receiver operating characteristic curves (AUCs) of four machine learning models (multilayer perceptron [MLP], logistic regression, XGBoost, and random forest [RF]) to that of the SOFA, nonrenal SOFA, and HELENICC scores and assessed calibration, sensitivity, specificity, positive (PPV) and negative (NPV) predicted values, and accuracy. Results: The mortality AUC of machine learning models was highest for XGBoost (0.823; 95% confidence interval [CI], 0.791−0.854) in the testing dataset, and it had the highest accuracy (0.758). The XGBoost model showed no evidence of lack of fit with the Hosmer−Lemeshow test (p > 0.05). Conclusion: XGBoost provided the highest performance of mortality prediction for patients with AKI requiring RRT compared with previous scoring systems." @default.
• W4296111641 created "2022-09-17" @default.
• W4296111641 creator A5023660212 @default.
• W4296111641 creator A5025865647 @default.
• W4296111641 creator A5028164391 @default.
• W4296111641 creator A5029821404 @default.
• W4296111641 creator A5029887087 @default.
• W4296111641 creator A5030289143 @default.
• W4296111641 creator A5034692540 @default.
• W4296111641 creator A5039177822 @default.
• W4296111641 creator A5051036134 @default.
• W4296111641 creator A5060348832 @default.
• W4296111641 creator A5060907331 @default.
• W4296111641 creator A5082272833 @default.
• W4296111641 date "2022-09-08" @default.
• W4296111641 modified "2023-10-07" @default.
• W4296111641 title "Predicting Mortality Using Machine Learning Algorithms in Patients Who Require Renal Replacement Therapy in the Critical Care Unit" @default.
• W4296111641 cites W1590673512 @default.
• W4296111641 cites W1781481323 @default.
• W4296111641 cites W1898928487 @default.
• W4296111641 cites W1972828995 @default.
• W4296111641 cites W1994682257 @default.
• W4296111641 cites W2000566182 @default.
• W4296111641 cites W2017215287 @default.
• W4296111641 cites W2102132939 @default.
• W4296111641 cites W2110317531 @default.
• W4296111641 cites W2134568923 @default.
• W4296111641 cites W2141413316 @default.
• W4296111641 cites W2141559993 @default.
• W4296111641 cites W2149687213 @default.
• W4296111641 cites W2171953637 @default.
• W4296111641 cites W2395969030 @default.
• W4296111641 cites W2396881363 @default.
• W4296111641 cites W2586843379 @default.
• W4296111641 cites W2761181345 @default.
• W4296111641 cites W2767417386 @default.
• W4296111641 cites W2796004795 @default.
• W4296111641 cites W2891400669 @default.
• W4296111641 cites W2905322176 @default.
• W4296111641 cites W2911964244 @default.
• W4296111641 cites W2915106240 @default.
• W4296111641 cites W2944920235 @default.
• W4296111641 cites W2995877538 @default.
• W4296111641 cites W3005219125 @default.
• W4296111641 cites W3005410610 @default.
• W4296111641 cites W3007001459 @default.
• W4296111641 cites W3102476541 @default.
• W4296111641 doi "https://doi.org/10.3390/jcm11185289" @default.
• W4296111641 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36142936" @default.
• W4296111641 hasPublicationYear "2022" @default.
• W4296111641 type Work @default.
• W4296111641 citedByCount "3" @default.
• W4296111641 countsByYear W42961116412023 @default.
• W4296111641 crossrefType "journal-article" @default.
• W4296111641 hasAuthorship W4296111641A5023660212 @default.
• W4296111641 hasAuthorship W4296111641A5025865647 @default.
• W4296111641 hasAuthorship W4296111641A5028164391 @default.
• W4296111641 hasAuthorship W4296111641A5029821404 @default.
• W4296111641 hasAuthorship W4296111641A5029887087 @default.
• W4296111641 hasAuthorship W4296111641A5030289143 @default.
• W4296111641 hasAuthorship W4296111641A5034692540 @default.
• W4296111641 hasAuthorship W4296111641A5039177822 @default.
• W4296111641 hasAuthorship W4296111641A5051036134 @default.
• W4296111641 hasAuthorship W4296111641A5060348832 @default.
• W4296111641 hasAuthorship W4296111641A5060907331 @default.
• W4296111641 hasAuthorship W4296111641A5082272833 @default.
• W4296111641 hasBestOaLocation W42961116411 @default.
• W4296111641 hasConcept C119857082 @default.
• W4296111641 hasConcept C126322002 @default.
• W4296111641 hasConcept C151956035 @default.
• W4296111641 hasConcept C154945302 @default.
• W4296111641 hasConcept C177713679 @default.
• W4296111641 hasConcept C179717631 @default.
• W4296111641 hasConcept C194828623 @default.
• W4296111641 hasConcept C2776376669 @default.
• W4296111641 hasConcept C2779541074 @default.
• W4296111641 hasConcept C2779978075 @default.
• W4296111641 hasConcept C2780306776 @default.
• W4296111641 hasConcept C41008148 @default.
• W4296111641 hasConcept C44249647 @default.
• W4296111641 hasConcept C50644808 @default.
• W4296111641 hasConcept C58471807 @default.
• W4296111641 hasConcept C71924100 @default.
• W4296111641 hasConceptScore W4296111641C119857082 @default.
• W4296111641 hasConceptScore W4296111641C126322002 @default.
• W4296111641 hasConceptScore W4296111641C151956035 @default.
• W4296111641 hasConceptScore W4296111641C154945302 @default.
• W4296111641 hasConceptScore W4296111641C177713679 @default.
• W4296111641 hasConceptScore W4296111641C179717631 @default.
• W4296111641 hasConceptScore W4296111641C194828623 @default.
• W4296111641 hasConceptScore W4296111641C2776376669 @default.
• W4296111641 hasConceptScore W4296111641C2779541074 @default.
• W4296111641 hasConceptScore W4296111641C2779978075 @default.
• W4296111641 hasConceptScore W4296111641C2780306776 @default.
• W4296111641 hasConceptScore W4296111641C41008148 @default.
• W4296111641 hasConceptScore W4296111641C44249647 @default.
• W4296111641 hasConceptScore W4296111641C50644808 @default.
• W4296111641 hasConceptScore W4296111641C58471807 @default.

• next