FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900627007> ?p ?o ?g. }

• W2900627007 endingPage "e0206862" @default.
• W2900627007 startingPage "e0206862" @default.
• W2900627007 abstract "Background Prognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission. Methods and findings This study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission improved the maximum AUC to 0.895 (σ = 0.008). Beyond the second day, predictive ability declined. Conclusion This has implications for decision making in intensive care and provides a justification for time-limited trials of ICU therapy; the assessment of prognosis over more than one day may be a valuable strategy as new information on the second day helps to differentiate outcomes. New ML models based on trend data beyond the first day could greatly improve upon current risk stratification tools." @default.
• W2900627007 created "2018-11-29" @default.
• W2900627007 creator A5013117957 @default.
• W2900627007 creator A5027793258 @default.
• W2900627007 creator A5032741507 @default.
• W2900627007 creator A5046351592 @default.
• W2900627007 creator A5048777602 @default.
• W2900627007 creator A5057363437 @default.
• W2900627007 creator A5060830413 @default.
• W2900627007 creator A5067694107 @default.
• W2900627007 creator A5068199165 @default.
• W2900627007 creator A5082629342 @default.
• W2900627007 creator A5083283614 @default.
• W2900627007 creator A5086478476 @default.
• W2900627007 date "2018-11-14" @default.
• W2900627007 modified "2023-10-05" @default.
• W2900627007 title "Optimal intensive care outcome prediction over time using machine learning" @default.
• W2900627007 cites W1493241108 @default.
• W2900627007 cites W1966890293 @default.
• W2900627007 cites W1994224528 @default.
• W2900627007 cites W1997103919 @default.
• W2900627007 cites W2003135043 @default.
• W2900627007 cites W2006617902 @default.
• W2900627007 cites W2012700815 @default.
• W2900627007 cites W2016555683 @default.
• W2900627007 cites W2020586758 @default.
• W2900627007 cites W2033925475 @default.
• W2900627007 cites W2060970919 @default.
• W2900627007 cites W2071637551 @default.
• W2900627007 cites W2074546317 @default.
• W2900627007 cites W2082137964 @default.
• W2900627007 cites W2085208748 @default.
• W2900627007 cites W2091678224 @default.
• W2900627007 cites W2110317531 @default.
• W2900627007 cites W2111547563 @default.
• W2900627007 cites W2112831158 @default.
• W2900627007 cites W2128349740 @default.
• W2900627007 cites W2131807433 @default.
• W2900627007 cites W2141220041 @default.
• W2900627007 cites W2146255968 @default.
• W2900627007 cites W2150469511 @default.
• W2900627007 cites W2151172952 @default.
• W2900627007 cites W2166639881 @default.
• W2900627007 cites W2169685811 @default.
• W2900627007 cites W2171685483 @default.
• W2900627007 cites W2177870565 @default.
• W2900627007 cites W2278600110 @default.
• W2900627007 cites W2346435289 @default.
• W2900627007 cites W2372800617 @default.
• W2900627007 cites W2396881363 @default.
• W2900627007 cites W2518269322 @default.
• W2900627007 cites W2523834880 @default.
• W2900627007 cites W2624697962 @default.
• W2900627007 cites W2755492370 @default.
• W2900627007 cites W2778067226 @default.
• W2900627007 cites W2785641136 @default.
• W2900627007 cites W2888723514 @default.
• W2900627007 cites W3098949126 @default.
• W2900627007 cites W4247943214 @default.
• W2900627007 cites W4293242440 @default.
• W2900627007 doi "https://doi.org/10.1371/journal.pone.0206862" @default.
• W2900627007 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6241126" @default.
• W2900627007 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30427913" @default.
• W2900627007 hasPublicationYear "2018" @default.
• W2900627007 type Work @default.
• W2900627007 sameAs 2900627007 @default.
• W2900627007 citedByCount "63" @default.
• W2900627007 countsByYear W29006270072019 @default.
• W2900627007 countsByYear W29006270072020 @default.
• W2900627007 countsByYear W29006270072021 @default.
• W2900627007 countsByYear W29006270072022 @default.
• W2900627007 countsByYear W29006270072023 @default.
• W2900627007 crossrefType "journal-article" @default.
• W2900627007 hasAuthorship W2900627007A5013117957 @default.
• W2900627007 hasAuthorship W2900627007A5027793258 @default.
• W2900627007 hasAuthorship W2900627007A5032741507 @default.
• W2900627007 hasAuthorship W2900627007A5046351592 @default.
• W2900627007 hasAuthorship W2900627007A5048777602 @default.
• W2900627007 hasAuthorship W2900627007A5057363437 @default.
• W2900627007 hasAuthorship W2900627007A5060830413 @default.
• W2900627007 hasAuthorship W2900627007A5067694107 @default.
• W2900627007 hasAuthorship W2900627007A5068199165 @default.
• W2900627007 hasAuthorship W2900627007A5082629342 @default.
• W2900627007 hasAuthorship W2900627007A5083283614 @default.
• W2900627007 hasAuthorship W2900627007A5086478476 @default.
• W2900627007 hasBestOaLocation W29006270071 @default.
• W2900627007 hasConcept C105795698 @default.
• W2900627007 hasConcept C111472728 @default.
• W2900627007 hasConcept C119857082 @default.
• W2900627007 hasConcept C138885662 @default.
• W2900627007 hasConcept C151956035 @default.
• W2900627007 hasConcept C154945302 @default.
• W2900627007 hasConcept C177713679 @default.
• W2900627007 hasConcept C194828623 @default.
• W2900627007 hasConcept C197640229 @default.
• W2900627007 hasConcept C2776376669 @default.
• W2900627007 hasConcept C2777371824 @default.
• W2900627007 hasConcept C2778136018 @default.

• next