FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196226391> ?p ?o ?g. }

• W3196226391 abstract "Abstract Background Early prediction of hospital mortality is crucial for ICU patients with sepsis. This study aimed to develop a novel blending machine learning (ML) model for hospital mortality prediction in ICU patients with sepsis. Methods Two ICU databases were employed: eICU Collaborative Research Database (eICU-CRD) and Medical Information Mart for Intensive Care III (MIMIC-III). All adult patients who fulfilled Sepsis-3 criteria were identified. Samples from eICU-CRD constituted training set and samples from MIMIC-III constituted test set. Stepwise logistic regression model was used for predictor selection. Blending ML model which integrated nine sorts of basic ML models was developed for hospital mortality prediction in ICU patients with sepsis. Model performance was evaluated by various measures related to discrimination or calibration. Results Twelve thousand five hundred fifty-eight patients from eICU-CRD were included as the training set, and 12,095 patients from MIMIC-III were included as the test set. Both the training set and the test set showed a hospital mortality of 17.9%. Maximum and minimum lactate, maximum and minimum albumin, minimum PaO2/FiO2 and age were important predictors identified by both random forest and extreme gradient boosting algorithm. Blending ML models based on corresponding set of predictors presented better discrimination than SAPS II (AUROC, 0.806 vs. 0.771; AUPRC 0.515 vs. 0.429) and SOFA (AUROC, 0.742 vs. 0.706; AUPRC 0.428 vs. 0.381) on the test set. In addition, calibration curves showed that blending ML models had better calibration than SAPS II. Conclusions The blending ML model is capable of integrating different sorts of basic ML models efficiently, and outperforms conventional severity scores in predicting hospital mortality among septic patients in ICU." @default.
• W3196226391 created "2021-08-30" @default.
• W3196226391 creator A5031114738 @default.
• W3196226391 creator A5036288356 @default.
• W3196226391 creator A5062314201 @default.
• W3196226391 creator A5063832031 @default.
• W3196226391 date "2021-08-16" @default.
• W3196226391 modified "2023-10-06" @default.
• W3196226391 title "Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis" @default.
• W3196226391 cites W1657774248 @default.
• W3196226391 cites W1970936458 @default.
• W3196226391 cites W2015329932 @default.
• W3196226391 cites W2027555966 @default.
• W3196226391 cites W2045010042 @default.
• W3196226391 cites W2049927822 @default.
• W3196226391 cites W2055571966 @default.
• W3196226391 cites W2096863518 @default.
• W3196226391 cites W2101082552 @default.
• W3196226391 cites W2103727400 @default.
• W3196226391 cites W2128349740 @default.
• W3196226391 cites W2142958578 @default.
• W3196226391 cites W2152154097 @default.
• W3196226391 cites W2160135708 @default.
• W3196226391 cites W2200122354 @default.
• W3196226391 cites W2280404143 @default.
• W3196226391 cites W2282181907 @default.
• W3196226391 cites W2328176404 @default.
• W3196226391 cites W2396881363 @default.
• W3196226391 cites W2524411259 @default.
• W3196226391 cites W2562278354 @default.
• W3196226391 cites W2580821343 @default.
• W3196226391 cites W2762658547 @default.
• W3196226391 cites W2782117851 @default.
• W3196226391 cites W2891400669 @default.
• W3196226391 cites W2896893468 @default.
• W3196226391 cites W2911572752 @default.
• W3196226391 cites W2912475038 @default.
• W3196226391 cites W2987952249 @default.
• W3196226391 cites W3048587623 @default.
• W3196226391 cites W3090266264 @default.
• W3196226391 cites W4233026002 @default.
• W3196226391 doi "https://doi.org/10.1186/s13040-021-00276-5" @default.
• W3196226391 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8365981" @default.
• W3196226391 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34399809" @default.
• W3196226391 hasPublicationYear "2021" @default.
• W3196226391 type Work @default.
• W3196226391 sameAs 3196226391 @default.
• W3196226391 citedByCount "11" @default.
• W3196226391 countsByYear W31962263912021 @default.
• W3196226391 countsByYear W31962263912022 @default.
• W3196226391 countsByYear W31962263912023 @default.
• W3196226391 crossrefType "journal-article" @default.
• W3196226391 hasAuthorship W3196226391A5031114738 @default.
• W3196226391 hasAuthorship W3196226391A5036288356 @default.
• W3196226391 hasAuthorship W3196226391A5062314201 @default.
• W3196226391 hasAuthorship W3196226391A5063832031 @default.
• W3196226391 hasBestOaLocation W31962263911 @default.
• W3196226391 hasConcept C105795698 @default.
• W3196226391 hasConcept C119857082 @default.
• W3196226391 hasConcept C126322002 @default.
• W3196226391 hasConcept C151956035 @default.
• W3196226391 hasConcept C154945302 @default.
• W3196226391 hasConcept C165838908 @default.
• W3196226391 hasConcept C169258074 @default.
• W3196226391 hasConcept C169903167 @default.
• W3196226391 hasConcept C170964787 @default.
• W3196226391 hasConcept C177264268 @default.
• W3196226391 hasConcept C177713679 @default.
• W3196226391 hasConcept C194828623 @default.
• W3196226391 hasConcept C199360897 @default.
• W3196226391 hasConcept C2776376669 @default.
• W3196226391 hasConcept C2777371824 @default.
• W3196226391 hasConcept C2778384902 @default.
• W3196226391 hasConcept C2780347030 @default.
• W3196226391 hasConcept C2987404301 @default.
• W3196226391 hasConcept C33923547 @default.
• W3196226391 hasConcept C41008148 @default.
• W3196226391 hasConcept C51632099 @default.
• W3196226391 hasConcept C58471807 @default.
• W3196226391 hasConcept C71924100 @default.
• W3196226391 hasConceptScore W3196226391C105795698 @default.
• W3196226391 hasConceptScore W3196226391C119857082 @default.
• W3196226391 hasConceptScore W3196226391C126322002 @default.
• W3196226391 hasConceptScore W3196226391C151956035 @default.
• W3196226391 hasConceptScore W3196226391C154945302 @default.
• W3196226391 hasConceptScore W3196226391C165838908 @default.
• W3196226391 hasConceptScore W3196226391C169258074 @default.
• W3196226391 hasConceptScore W3196226391C169903167 @default.
• W3196226391 hasConceptScore W3196226391C170964787 @default.
• W3196226391 hasConceptScore W3196226391C177264268 @default.
• W3196226391 hasConceptScore W3196226391C177713679 @default.
• W3196226391 hasConceptScore W3196226391C194828623 @default.
• W3196226391 hasConceptScore W3196226391C199360897 @default.
• W3196226391 hasConceptScore W3196226391C2776376669 @default.
• W3196226391 hasConceptScore W3196226391C2777371824 @default.
• W3196226391 hasConceptScore W3196226391C2778384902 @default.
• W3196226391 hasConceptScore W3196226391C2780347030 @default.
• W3196226391 hasConceptScore W3196226391C2987404301 @default.
• W3196226391 hasConceptScore W3196226391C33923547 @default.
• W3196226391 hasConceptScore W3196226391C41008148 @default.

• next