FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285471437> ?p ?o ?g. }

• W4285471437 abstract "<sec> <title>BACKGROUND</title> Although machine learning (ML) algorithms have been applied to point-of-care sepsis prognostication, ML has not been used to predict sepsis mortality in an administrative database. Therefore, we examined the performance of common ML algorithms in predicting sepsis mortality in adult patients with sepsis and compared it with that of the conventional context knowledge–based logistic regression approach. </sec> <sec> <title>OBJECTIVE</title> The aim of this study is to examine the performance of common ML algorithms in predicting sepsis mortality in adult patients with sepsis and compare it with that of the conventional context knowledge–based logistic regression approach. </sec> <sec> <title>METHODS</title> We examined inpatient admissions for sepsis in the US National Inpatient Sample using hospitalizations in 2010-2013 as the training data set. We developed four ML models to predict in-hospital mortality: logistic regression with least absolute shrinkage and selection operator regularization, random forest, gradient-boosted decision tree, and deep neural network. To estimate their performance, we compared our models with the Super Learner model. Using hospitalizations in 2014 as the testing data set, we examined the models’ area under the receiver operating characteristic curve (AUC), confusion matrix results, and net reclassification improvement. </sec> <sec> <title>RESULTS</title> Hospitalizations of 923,759 adults were included in the analysis. Compared with the reference logistic regression (AUC: 0.786, 95% CI 0.783-0.788), all ML models showed superior discriminative ability (<i>P</i>&lt;.001), including logistic regression with least absolute shrinkage and selection operator regularization (AUC: 0.878, 95% CI 0.876-0.879), random forest (AUC: 0.878, 95% CI 0.877-0.880), xgboost (AUC: 0.888, 95% CI 0.886-0.889), and neural network (AUC: 0.893, 95% CI 0.891-0.895). All 4 ML models showed higher sensitivity, specificity, positive predictive value, and negative predictive value compared with the reference logistic regression model (<i>P</i>&lt;.001). We obtained similar results from the Super Learner model (AUC: 0.883, 95% CI 0.881-0.885). </sec> <sec> <title>CONCLUSIONS</title> ML approaches can improve sensitivity, specificity, positive predictive value, negative predictive value, discrimination, and calibration in predicting in-hospital mortality in patients hospitalized with sepsis in the United States. These models need further validation and could be applied to develop more accurate models to compare risk-standardized mortality rates across hospitals and geographic regions, paving the way for research and policy initiatives studying disparities in sepsis care. </sec> <sec> <title>CLINICALTRIAL</title> <p /> </sec>" @default.
• W4285471437 created "2022-07-15" @default.
• W4285471437 creator A5006775367 @default.
• W4285471437 creator A5034096265 @default.
• W4285471437 creator A5036636130 @default.
• W4285471437 creator A5050613037 @default.
• W4285471437 creator A5051298255 @default.
• W4285471437 creator A5072282992 @default.
• W4285471437 creator A5083986639 @default.
• W4285471437 creator A5089640419 @default.
• W4285471437 date "2021-04-28" @default.
• W4285471437 modified "2023-09-30" @default.
• W4285471437 title "Predicting Sepsis Mortality in a Population-Based National Database: Machine Learning Approach (Preprint)" @default.
• W4285471437 cites W1678356000 @default.
• W4285471437 cites W1869842011 @default.
• W4285471437 cites W1970936458 @default.
• W4285471437 cites W1971217338 @default.
• W4285471437 cites W1971954188 @default.
• W4285471437 cites W1974873560 @default.
• W4285471437 cites W1985372952 @default.
• W4285471437 cites W2000658385 @default.
• W4285471437 cites W2015334590 @default.
• W4285471437 cites W2024436502 @default.
• W4285471437 cites W2034705773 @default.
• W4285471437 cites W2035038290 @default.
• W4285471437 cites W2057367182 @default.
• W4285471437 cites W2067747050 @default.
• W4285471437 cites W2078968344 @default.
• W4285471437 cites W2090470999 @default.
• W4285471437 cites W2091288994 @default.
• W4285471437 cites W2145577370 @default.
• W4285471437 cites W2186520609 @default.
• W4285471437 cites W2187885137 @default.
• W4285471437 cites W2200122354 @default.
• W4285471437 cites W2323525554 @default.
• W4285471437 cites W2331591468 @default.
• W4285471437 cites W2337695428 @default.
• W4285471437 cites W2503109850 @default.
• W4285471437 cites W2639510502 @default.
• W4285471437 cites W2772836084 @default.
• W4285471437 cites W2789512708 @default.
• W4285471437 cites W2883566781 @default.
• W4285471437 cites W2897667116 @default.
• W4285471437 cites W2901312569 @default.
• W4285471437 cites W2912071375 @default.
• W4285471437 cites W2915292867 @default.
• W4285471437 cites W2922753330 @default.
• W4285471437 cites W2955053048 @default.
• W4285471437 cites W2979638097 @default.
• W4285471437 cites W2981116786 @default.
• W4285471437 cites W2987952249 @default.
• W4285471437 cites W3012828280 @default.
• W4285471437 cites W3121048980 @default.
• W4285471437 cites W4212883601 @default.
• W4285471437 cites W4232037120 @default.
• W4285471437 cites W4233056867 @default.
• W4285471437 cites W4238355959 @default.
• W4285471437 cites W4294541781 @default.
• W4285471437 doi "https://doi.org/10.2196/preprints.29982" @default.
• W4285471437 hasPublicationYear "2021" @default.
• W4285471437 type Work @default.
• W4285471437 citedByCount "0" @default.
• W4285471437 crossrefType "posted-content" @default.
• W4285471437 hasAuthorship W4285471437A5006775367 @default.
• W4285471437 hasAuthorship W4285471437A5034096265 @default.
• W4285471437 hasAuthorship W4285471437A5036636130 @default.
• W4285471437 hasAuthorship W4285471437A5050613037 @default.
• W4285471437 hasAuthorship W4285471437A5051298255 @default.
• W4285471437 hasAuthorship W4285471437A5072282992 @default.
• W4285471437 hasAuthorship W4285471437A5083986639 @default.
• W4285471437 hasAuthorship W4285471437A5089640419 @default.
• W4285471437 hasBestOaLocation W42854714372 @default.
• W4285471437 hasConcept C105795698 @default.
• W4285471437 hasConcept C119857082 @default.
• W4285471437 hasConcept C126322002 @default.
• W4285471437 hasConcept C151956035 @default.
• W4285471437 hasConcept C154945302 @default.
• W4285471437 hasConcept C166957645 @default.
• W4285471437 hasConcept C169258074 @default.
• W4285471437 hasConcept C205649164 @default.
• W4285471437 hasConcept C2778384902 @default.
• W4285471437 hasConcept C2779343474 @default.
• W4285471437 hasConcept C33923547 @default.
• W4285471437 hasConcept C41008148 @default.
• W4285471437 hasConcept C58471807 @default.
• W4285471437 hasConcept C71924100 @default.
• W4285471437 hasConcept C84525736 @default.
• W4285471437 hasConceptScore W4285471437C105795698 @default.
• W4285471437 hasConceptScore W4285471437C119857082 @default.
• W4285471437 hasConceptScore W4285471437C126322002 @default.
• W4285471437 hasConceptScore W4285471437C151956035 @default.
• W4285471437 hasConceptScore W4285471437C154945302 @default.
• W4285471437 hasConceptScore W4285471437C166957645 @default.
• W4285471437 hasConceptScore W4285471437C169258074 @default.
• W4285471437 hasConceptScore W4285471437C205649164 @default.
• W4285471437 hasConceptScore W4285471437C2778384902 @default.
• W4285471437 hasConceptScore W4285471437C2779343474 @default.
• W4285471437 hasConceptScore W4285471437C33923547 @default.
• W4285471437 hasConceptScore W4285471437C41008148 @default.
• W4285471437 hasConceptScore W4285471437C58471807 @default.

• next