FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224308809> ?p ?o ?g. }

• W4224308809 abstract "In the early stages of the COVID-19 pandemic our institution was interested in forecasting how long surgical patients receiving elective procedures would spend in the hospital. Initial examination of our models indicated that, due to the skewed nature of the length of stay, accurate prediction was challenging and we instead opted for a simpler classification model. In this work we perform a deeper examination of predicting in-hospital length of stay.We used electronic health record data on length of stay from 42,209 elective surgeries. We compare different loss-functions (mean squared error, mean absolute error, mean relative error), algorithms (LASSO, Random Forests, multilayer perceptron) and data transformations (log and truncation). We also assess the performance of two stage hybrid classification-regression approach.Our results show that while it is possible to accurately predict short length of stays, predicting longer length of stay is extremely challenging. As such, we opt for a two-stage model that first classifies patients into long versus short length of stays and then a second stage that fits a regresssor among those predicted to have a short length of stay.The results indicate both the challenges and considerations necessary to applying machine-learning methods to skewed outcomes.Two-stage models allow those developing clinical decision support tools to explicitly acknowledge where they can and cannot make accurate predictions." @default.
• W4224308809 created "2022-04-26" @default.
• W4224308809 creator A5005386609 @default.
• W4224308809 creator A5016986472 @default.
• W4224308809 creator A5024188537 @default.
• W4224308809 creator A5056639842 @default.
• W4224308809 creator A5067727757 @default.
• W4224308809 date "2022-04-24" @default.
• W4224308809 modified "2023-10-14" @default.
• W4224308809 title "Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data" @default.
• W4224308809 cites W1479680402 @default.
• W4224308809 cites W1919353527 @default.
• W4224308809 cites W1967021867 @default.
• W4224308809 cites W1990914666 @default.
• W4224308809 cites W2007281290 @default.
• W4224308809 cites W2012497503 @default.
• W4224308809 cites W2023942624 @default.
• W4224308809 cites W2036924892 @default.
• W4224308809 cites W2118523769 @default.
• W4224308809 cites W2121365500 @default.
• W4224308809 cites W2125475924 @default.
• W4224308809 cites W2133677532 @default.
• W4224308809 cites W2135046866 @default.
• W4224308809 cites W2149057497 @default.
• W4224308809 cites W2152742787 @default.
• W4224308809 cites W2153589240 @default.
• W4224308809 cites W2400385987 @default.
• W4224308809 cites W2601928458 @default.
• W4224308809 cites W2609847913 @default.
• W4224308809 cites W2793955735 @default.
• W4224308809 cites W2911964244 @default.
• W4224308809 cites W2979740388 @default.
• W4224308809 cites W3014965089 @default.
• W4224308809 cites W3024251604 @default.
• W4224308809 cites W3096153989 @default.
• W4224308809 cites W3149613179 @default.
• W4224308809 doi "https://doi.org/10.1186/s12911-022-01855-0" @default.
• W4224308809 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35462534" @default.
• W4224308809 hasPublicationYear "2022" @default.
• W4224308809 type Work @default.
• W4224308809 citedByCount "2" @default.
• W4224308809 countsByYear W42243088092023 @default.
• W4224308809 crossrefType "journal-article" @default.
• W4224308809 hasAuthorship W4224308809A5005386609 @default.
• W4224308809 hasAuthorship W4224308809A5016986472 @default.
• W4224308809 hasAuthorship W4224308809A5024188537 @default.
• W4224308809 hasAuthorship W4224308809A5056639842 @default.
• W4224308809 hasAuthorship W4224308809A5067727757 @default.
• W4224308809 hasBestOaLocation W42243088091 @default.
• W4224308809 hasConcept C105795698 @default.
• W4224308809 hasConcept C119857082 @default.
• W4224308809 hasConcept C138816342 @default.
• W4224308809 hasConcept C139945424 @default.
• W4224308809 hasConcept C145642194 @default.
• W4224308809 hasConcept C146357865 @default.
• W4224308809 hasConcept C151730666 @default.
• W4224308809 hasConcept C154945302 @default.
• W4224308809 hasConcept C159110408 @default.
• W4224308809 hasConcept C179717631 @default.
• W4224308809 hasConcept C33923547 @default.
• W4224308809 hasConcept C41008148 @default.
• W4224308809 hasConcept C50644808 @default.
• W4224308809 hasConcept C71924100 @default.
• W4224308809 hasConcept C83546350 @default.
• W4224308809 hasConcept C86803240 @default.
• W4224308809 hasConceptScore W4224308809C105795698 @default.
• W4224308809 hasConceptScore W4224308809C119857082 @default.
• W4224308809 hasConceptScore W4224308809C138816342 @default.
• W4224308809 hasConceptScore W4224308809C139945424 @default.
• W4224308809 hasConceptScore W4224308809C145642194 @default.
• W4224308809 hasConceptScore W4224308809C146357865 @default.
• W4224308809 hasConceptScore W4224308809C151730666 @default.
• W4224308809 hasConceptScore W4224308809C154945302 @default.
• W4224308809 hasConceptScore W4224308809C159110408 @default.
• W4224308809 hasConceptScore W4224308809C179717631 @default.
• W4224308809 hasConceptScore W4224308809C33923547 @default.
• W4224308809 hasConceptScore W4224308809C41008148 @default.
• W4224308809 hasConceptScore W4224308809C50644808 @default.
• W4224308809 hasConceptScore W4224308809C71924100 @default.
• W4224308809 hasConceptScore W4224308809C83546350 @default.
• W4224308809 hasConceptScore W4224308809C86803240 @default.
• W4224308809 hasIssue "1" @default.
• W4224308809 hasLocation W42243088091 @default.
• W4224308809 hasLocation W42243088092 @default.
• W4224308809 hasLocation W42243088093 @default.
• W4224308809 hasLocation W42243088094 @default.
• W4224308809 hasOpenAccess W4224308809 @default.
• W4224308809 hasPrimaryLocation W42243088091 @default.
• W4224308809 hasRelatedWork W2787191226 @default.
• W4224308809 hasRelatedWork W2995227436 @default.
• W4224308809 hasRelatedWork W3018959556 @default.
• W4224308809 hasRelatedWork W3211546796 @default.
• W4224308809 hasRelatedWork W4231994957 @default.
• W4224308809 hasRelatedWork W4285741730 @default.
• W4224308809 hasRelatedWork W4294067781 @default.
• W4224308809 hasRelatedWork W4320802194 @default.
• W4224308809 hasRelatedWork W4361795583 @default.
• W4224308809 hasRelatedWork W4385505619 @default.
• W4224308809 hasVolume "22" @default.
• W4224308809 isParatext "false" @default.

• next