FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283017730> ?p ?o ?g. }

• W4283017730 abstract "Abstract Background Metabolic predictors and potential mediators of survival in sepsis have been incompletely characterized. We examined whether machine learning (ML) tools applied to the human plasma metabolome could consistently identify and prioritize metabolites implicated in sepsis survivorship, and whether these methods improved upon conventional statistical approaches. Methods Plasma gas chromatography–liquid chromatography mass spectrometry quantified 411 metabolites measured ≤ 72 h of ICU admission in 60 patients with sepsis at a single center (Brigham and Women’s Hospital, Boston, USA). Seven ML approaches were trained to differentiate survivors from non-survivors. Model performance predicting 28 day mortality was assessed through internal cross-validation, and innate top-feature (metabolite) selection and rankings were compared across the 7 ML approaches and with conventional statistical methods (logistic regression). Metabolites were consensus ranked by a summary, ensemble ML ranking procedure weighing their contribution to mortality risk prediction across multiple ML models. Results Median (IQR) patient age was 58 (47, 62) years, 45% were women, and median (IQR) SOFA score was 9 (6, 12). Mortality at 28 days was 42%. The models’ specificity ranged from 0.619 to 0.821. Partial least squares regression-discriminant analysis and nearest shrunken centroids prioritized the greatest number of metabolites identified by at least one other method. Penalized logistic regression demonstrated top-feature results that were consistent with many ML methods. Across the plasma metabolome, the 13 metabolites with the strongest linkage to mortality defined through an ensemble ML importance score included lactate, bilirubin, kynurenine, glycochenodeoxycholate, phenylalanine, and others. Four of these top 13 metabolites (3-hydroxyisobutyrate, indoleacetate, fucose, and glycolithocholate sulfate) have not been previously associated with sepsis survival. Many of the prioritized metabolites are constituents of the tryptophan, pyruvate, phenylalanine, pentose phosphate, and bile acid pathways. Conclusions We identified metabolites linked with sepsis survival, some confirming prior observations, and others representing new associations. The application of ensemble ML feature-ranking tools to metabolomic data may represent a promising statistical platform to support biologic target discovery." @default.
• W4283017730 created "2022-06-18" @default.
• W4283017730 creator A5013249076 @default.
• W4283017730 creator A5020565341 @default.
• W4283017730 creator A5034441524 @default.
• W4283017730 creator A5042011412 @default.
• W4283017730 creator A5047332766 @default.
• W4283017730 creator A5052989862 @default.
• W4283017730 creator A5053213573 @default.
• W4283017730 creator A5056168495 @default.
• W4283017730 creator A5069347285 @default.
• W4283017730 creator A5079930622 @default.
• W4283017730 creator A5082214993 @default.
• W4283017730 creator A5085137537 @default.
• W4283017730 date "2022-06-17" @default.
• W4283017730 modified "2023-09-27" @default.
• W4283017730 title "Machine learning approaches to the human metabolome in sepsis identify metabolic links with survival" @default.
• W4283017730 cites W1505191356 @default.
• W4283017730 cites W1597115774 @default.
• W4283017730 cites W1966716734 @default.
• W4283017730 cites W1975117581 @default.
• W4283017730 cites W1977048165 @default.
• W4283017730 cites W1977868384 @default.
• W4283017730 cites W1991209345 @default.
• W4283017730 cites W1996203607 @default.
• W4283017730 cites W2003524197 @default.
• W4283017730 cites W2045596475 @default.
• W4283017730 cites W2051839360 @default.
• W4283017730 cites W2065076849 @default.
• W4283017730 cites W2068583747 @default.
• W4283017730 cites W2083320362 @default.
• W4283017730 cites W2083963821 @default.
• W4283017730 cites W2102942827 @default.
• W4283017730 cites W2107491903 @default.
• W4283017730 cites W2118136977 @default.
• W4283017730 cites W2125814863 @default.
• W4283017730 cites W2126310844 @default.
• W4283017730 cites W2131215891 @default.
• W4283017730 cites W2141151213 @default.
• W4283017730 cites W2155433658 @default.
• W4283017730 cites W2157501515 @default.
• W4283017730 cites W2214984488 @default.
• W4283017730 cites W2273661919 @default.
• W4283017730 cites W2274346642 @default.
• W4283017730 cites W2278752859 @default.
• W4283017730 cites W2295634666 @default.
• W4283017730 cites W2513955315 @default.
• W4283017730 cites W2586512179 @default.
• W4283017730 cites W2598111690 @default.
• W4283017730 cites W2599983619 @default.
• W4283017730 cites W2606454401 @default.
• W4283017730 cites W2689644554 @default.
• W4283017730 cites W2750720130 @default.
• W4283017730 cites W2756440951 @default.
• W4283017730 cites W2772308155 @default.
• W4283017730 cites W2783880833 @default.
• W4283017730 cites W2794903814 @default.
• W4283017730 cites W2810178364 @default.
• W4283017730 cites W2810324481 @default.
• W4283017730 cites W2883340375 @default.
• W4283017730 cites W2886027918 @default.
• W4283017730 cites W2901218091 @default.
• W4283017730 cites W2941198554 @default.
• W4283017730 cites W2944988359 @default.
• W4283017730 cites W2945103729 @default.
• W4283017730 cites W2945926895 @default.
• W4283017730 cites W2959053591 @default.
• W4283017730 cites W2964119475 @default.
• W4283017730 cites W2990218059 @default.
• W4283017730 cites W2998853022 @default.
• W4283017730 cites W3036255694 @default.
• W4283017730 cites W3037981659 @default.
• W4283017730 cites W3112250959 @default.
• W4283017730 doi "https://doi.org/10.1186/s40635-022-00445-8" @default.
• W4283017730 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35710638" @default.
• W4283017730 hasPublicationYear "2022" @default.
• W4283017730 type Work @default.
• W4283017730 citedByCount "6" @default.
• W4283017730 countsByYear W42830177302022 @default.
• W4283017730 countsByYear W42830177302023 @default.
• W4283017730 crossrefType "journal-article" @default.
• W4283017730 hasAuthorship W4283017730A5013249076 @default.
• W4283017730 hasAuthorship W4283017730A5020565341 @default.
• W4283017730 hasAuthorship W4283017730A5034441524 @default.
• W4283017730 hasAuthorship W4283017730A5042011412 @default.
• W4283017730 hasAuthorship W4283017730A5047332766 @default.
• W4283017730 hasAuthorship W4283017730A5052989862 @default.
• W4283017730 hasAuthorship W4283017730A5053213573 @default.
• W4283017730 hasAuthorship W4283017730A5056168495 @default.
• W4283017730 hasAuthorship W4283017730A5069347285 @default.
• W4283017730 hasAuthorship W4283017730A5079930622 @default.
• W4283017730 hasAuthorship W4283017730A5082214993 @default.
• W4283017730 hasAuthorship W4283017730A5085137537 @default.
• W4283017730 hasBestOaLocation W42830177301 @default.
• W4283017730 hasConcept C126322002 @default.
• W4283017730 hasConcept C135870905 @default.
• W4283017730 hasConcept C151956035 @default.
• W4283017730 hasConcept C21565614 @default.
• W4283017730 hasConcept C2777477808 @default.
• W4283017730 hasConcept C2778384902 @default.

• next